[PATCH 6/7] btrfs: remove unnecessary check_parent_dirs_for_sync()

[fdmanana@kernel.org]

From: Filipe Manana <fdmanana@suse.com>

Whenever we fsync an inode, if it is a directory, a regular file that was
created in the current transaction or has last_unlink_trans set to the
generation of the current transaction, we check if any of its ancestor
inodes (and the inode itself if it is a directory) can not be logged and
need a fallback to a full transaction commit - if so, we return with a
value of 1 in order to fallback to a transaction commit.

However we often do not need to fallback to a transaction commit because:

1) The ancestor inode is not an immediate parent, and therefore there is
   not an explicit request to log it and it is not needed neither to
   guarantee the consistency of the inode originally asked to be logged
   (fsynced) nor its immediate parent;

2) The ancestor inode was already logged before, in which case any link,
   unlink or rename operation updates the log as needed.

So for these two cases we can avoid an unnecessary transaction commit.
Therefore remove check_parent_dirs_for_sync() and add a check at the top
of btrfs_log_inode() to make us fallback immediately to a transaction
commit when we are logging a directory inode that can not be logged and
needs a full transaction commit. All we need to protect is the case where
after renaming a file someone fsyncs only the old directory, which would
result is losing the renamed file after a log replay.

This patch is part of a patchset comprised of the following patches:

  btrfs: remove unnecessary directory inode item update when deleting dir entry
  btrfs: stop setting nbytes when filling inode item for logging
  btrfs: avoid logging new ancestor inodes when logging new inode
  btrfs: skip logging directories already logged when logging all parents
  btrfs: skip logging inodes already logged when logging new entries
  btrfs: remove unnecessary check_parent_dirs_for_sync()
  btrfs: make concurrent fsyncs wait less when waiting for a transaction commit

Performance results, after applying all patches, are mentioned in the
change log of the last patch.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
---
 fs/btrfs/tree-log.c | 121 ++++++--------------------------------------
 1 file changed, 15 insertions(+), 106 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 6dc376a16cf2..4c7b283ed2b2 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -5265,6 +5265,21 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		mutex_lock(&inode->log_mutex);
 	}
 
+	/*
+	 * This is for cases where logging a directory could result in losing a
+	 * a file after replaying the log. For example, if we move a file from a
+	 * directory A to a directory B, then fsync directory A, we have no way
+	 * to known the file was moved from A to B, so logging just A would
+	 * result in losing the file after a log replay.
+	 */
+	if (S_ISDIR(inode->vfs_inode.i_mode) &&
+	    inode_only == LOG_INODE_ALL &&
+	    inode->last_unlink_trans >= trans->transid) {
+		btrfs_set_log_full_commit(trans);
+		err = 1;
+		goto out_unlock;
+	}
+
 	/*
 	 * a brute force approach to making sure we get the most uptodate
 	 * copies of everything.
@@ -5428,99 +5443,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	return err;
 }
 
-/*
- * Check if we must fallback to a transaction commit when logging an inode.
- * This must be called after logging the inode and is used only in the context
- * when fsyncing an inode requires the need to log some other inode - in which
- * case we can't lock the i_mutex of each other inode we need to log as that
- * can lead to deadlocks with concurrent fsync against other inodes (as we can
- * log inodes up or down in the hierarchy) or rename operations for example. So
- * we take the log_mutex of the inode after we have logged it and then check for
- * its last_unlink_trans value - this is safe because any task setting
- * last_unlink_trans must take the log_mutex and it must do this before it does
- * the actual unlink operation, so if we do this check before a concurrent task
- * sets last_unlink_trans it means we've logged a consistent version/state of
- * all the inode items, otherwise we are not sure and must do a transaction
- * commit (the concurrent task might have only updated last_unlink_trans before
- * we logged the inode or it might have also done the unlink).
- */
-static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
-					  struct btrfs_inode *inode)
-{
-	bool ret = false;
-
-	mutex_lock(&inode->log_mutex);
-	if (inode->last_unlink_trans >= trans->transid) {
-		/*
-		 * Make sure any commits to the log are forced to be full
-		 * commits.
-		 */
-		btrfs_set_log_full_commit(trans);
-		ret = true;
-	}
-	mutex_unlock(&inode->log_mutex);
-
-	return ret;
-}
-
-/*
- * follow the dentry parent pointers up the chain and see if any
- * of the directories in it require a full commit before they can
- * be logged.  Returns zero if nothing special needs to be done or 1 if
- * a full commit is required.
- */
-static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
-					       struct btrfs_inode *inode,
-					       struct dentry *parent,
-					       struct super_block *sb)
-{
-	int ret = 0;
-	struct dentry *old_parent = NULL;
-
-	/*
-	 * for regular files, if its inode is already on disk, we don't
-	 * have to worry about the parents at all.  This is because
-	 * we can use the last_unlink_trans field to record renames
-	 * and other fun in this file.
-	 */
-	if (S_ISREG(inode->vfs_inode.i_mode) &&
-	    inode->generation < trans->transid &&
-	    inode->last_unlink_trans < trans->transid)
-		goto out;
-
-	if (!S_ISDIR(inode->vfs_inode.i_mode)) {
-		if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
-			goto out;
-		inode = BTRFS_I(d_inode(parent));
-	}
-
-	while (1) {
-		if (btrfs_must_commit_transaction(trans, inode)) {
-			ret = 1;
-			break;
-		}
-
-		if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
-			break;
-
-		if (IS_ROOT(parent)) {
-			inode = BTRFS_I(d_inode(parent));
-			if (btrfs_must_commit_transaction(trans, inode))
-				ret = 1;
-			break;
-		}
-
-		parent = dget_parent(parent);
-		dput(old_parent);
-		old_parent = parent;
-		inode = BTRFS_I(d_inode(parent));
-
-	}
-	dput(old_parent);
-out:
-	return ret;
-}
-
 /*
  * Check if we need to log an inode. This is used in contexts where while
  * logging an inode we need to log another inode (either that it exists or in
@@ -5686,9 +5608,6 @@ static int log_new_dir_dentries(struct btrfs_trans_handle *trans,
 				log_mode = LOG_INODE_ALL;
 			ret = btrfs_log_inode(trans, root, BTRFS_I(di_inode),
 					      log_mode, ctx);
-			if (!ret &&
-			    btrfs_must_commit_transaction(trans, BTRFS_I(di_inode)))
-				ret = 1;
 			btrfs_add_delayed_iput(di_inode);
 			if (ret)
 				goto next_dir_inode;
@@ -5835,9 +5754,6 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 				ctx->log_new_dentries = false;
 			ret = btrfs_log_inode(trans, root, BTRFS_I(dir_inode),
 					      LOG_INODE_ALL, ctx);
-			if (!ret &&
-			    btrfs_must_commit_transaction(trans, BTRFS_I(dir_inode)))
-				ret = 1;
 			if (!ret && ctx && ctx->log_new_dentries)
 				ret = log_new_dir_dentries(trans, root,
 						   BTRFS_I(dir_inode), ctx);
@@ -6053,12 +5969,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct super_block *sb;
 	int ret = 0;
 	bool log_dentries = false;
 
-	sb = inode->vfs_inode.i_sb;
-
 	if (btrfs_test_opt(fs_info, NOTREELOG)) {
 		ret = 1;
 		goto end_no_trans;
@@ -6069,10 +5982,6 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		goto end_no_trans;
 	}
 
-	ret = check_parent_dirs_for_sync(trans, inode, parent, sb);
-	if (ret)
-		goto end_no_trans;
-
 	/*
 	 * Skip already logged inodes or inodes corresponding to tmpfiles
 	 * (since logging them is pointless, a link count of 0 means they
-- 
2.28.0