Merge branch 'for-linus-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs updates from Chris Mason:
 "This pull is dedicated to Josef's enospc rework, which we've been
  testing for a few releases now.  It fixes some early enospc problems
  and is dramatically faster.

  This also includes an updated fix for the delalloc accounting that
  happens after a fault in copy_from_user.  My patch in v4.7 was almost
  but not quite enough"

* 'for-linus-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  Btrfs: fix delalloc accounting after copy_from_user faults
  Btrfs: avoid deadlocks during reservations in btrfs_truncate_block
  Btrfs: use FLUSH_LIMIT for relocation in reserve_metadata_bytes
  Btrfs: fill relocation block rsv after allocation
  Btrfs: always use trans->block_rsv for orphans
  Btrfs: change how we calculate the global block rsv
  Btrfs: use root when checking need_async_flush
  Btrfs: don't bother kicking async if there's nothing to reclaim
  Btrfs: fix release reserved extents trace points
  Btrfs: add fsid to some tracepoints
  Btrfs: add tracepoints for flush events
  Btrfs: fix delalloc reservation amount tracepoint
  Btrfs: trace pinned extents
  Btrfs: introduce ticketed enospc infrastructure
  Btrfs: add tracepoint for adding block groups
  Btrfs: warn_on for unaccounted spaces
  Btrfs: change delayed reservation fallback behavior
  Btrfs: always reserve metadata for delalloc extents
  Btrfs: fix callers of btrfs_block_rsv_migrate
  Btrfs: add bytes_readonly to the spaceinfo at once

1 files changed, 25 insertions, 43 deletions

diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index d3aaabbfada0..dd3c040139a2 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -553,7 +553,7 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans,
 	dst_rsv = &root->fs_info->delayed_block_rsv;
 
 	num_bytes = btrfs_calc_trans_metadata_size(root, 1);
-	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
+	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
 	if (!ret) {
 		trace_btrfs_space_reservation(root->fs_info, "delayed_item",
 					      item->key.objectid,
@@ -598,6 +598,29 @@ static int btrfs_delayed_inode_reserve_metadata(
 	num_bytes = btrfs_calc_trans_metadata_size(root, 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(&BTRFS_I(inode)->lock);
+		if (test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
+				       &BTRFS_I(inode)->runtime_flags))
+			release = true;
+		else
+			src_rsv = NULL;
+		spin_unlock(&BTRFS_I(inode)->lock);
+	}
+
+	/*
 	 * btrfs_dirty_inode will update the inode under btrfs_join_transaction
 	 * which doesn't reserve space for speed.  This is a problem since we
 	 * still need to reserve space for this update, so try to reserve the
@@ -626,51 +649,10 @@ static int btrfs_delayed_inode_reserve_metadata(
 						      num_bytes, 1);
 		}
 		return ret;
-	} else if (src_rsv->type == BTRFS_BLOCK_RSV_DELALLOC) {
-		spin_lock(&BTRFS_I(inode)->lock);
-		if (test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-				       &BTRFS_I(inode)->runtime_flags)) {
-			spin_unlock(&BTRFS_I(inode)->lock);
-			release = true;
-			goto migrate;
-		}
-		spin_unlock(&BTRFS_I(inode)->lock);
-
-		/* Ok we didn't have space pre-reserved.  This shouldn't happen
-		 * too often but it can happen if we do delalloc to an existing
-		 * inode which gets dirtied because of the time update, and then
-		 * isn't touched again until after the transaction commits and
-		 * then we try to write out the data.  First try to be nice and
-		 * reserve something strictly for us.  If not be a pain and try
-		 * to steal from the delalloc block rsv.
-		 */
-		ret = btrfs_block_rsv_add(root, dst_rsv, num_bytes,
-					  BTRFS_RESERVE_NO_FLUSH);
-		if (!ret)
-			goto out;
-
-		ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
-		if (!ret)
-			goto out;
-
-		if (btrfs_test_opt(root, ENOSPC_DEBUG)) {
-			btrfs_debug(root->fs_info,
-				    "block rsv migrate returned %d", ret);
-			WARN_ON(1);
-		}
-		/*
-		 * Ok this is a problem, let's just steal from the global rsv
-		 * since this really shouldn't happen that often.
-		 */
-		ret = btrfs_block_rsv_migrate(&root->fs_info->global_block_rsv,
-					      dst_rsv, num_bytes);
-		goto out;
 	}
 
-migrate:
-	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
+	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
 
-out:
 	/*
 	 * 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