1 files changed, 61 insertions, 30 deletions

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index cf306351b148..0bf42dccb041 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -56,12 +56,17 @@ static struct kmem_cache *btrfs_trans_handle_cachep;
  * |  Call btrfs_commit_transaction() on any trans handle attached to
  * |  transaction N
  * V
- * Transaction N [[TRANS_STATE_COMMIT_START]]
+ * Transaction N [[TRANS_STATE_COMMIT_PREP]]
+ * |
+ * | If there are simultaneous calls to btrfs_commit_transaction() one will win
+ * | the race and the rest will wait for the winner to commit the transaction.
+ * |
+ * | The winner will wait for previous running transaction to completely finish
+ * | if there is one.
  * |
- * | Will wait for previous running transaction to completely finish if there
- * | is one
+ * Transaction N [[TRANS_STATE_COMMIT_START]]
  * |
- * | Then one of the following happes:
+ * | Then one of the following happens:
  * | - Wait for all other trans handle holders to release.
  * |   The btrfs_commit_transaction() caller will do the commit work.
  * | - Wait for current transaction to be committed by others.
@@ -112,6 +117,7 @@ static struct kmem_cache *btrfs_trans_handle_cachep;
  */
 static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = {
 	[TRANS_STATE_RUNNING]		= 0U,
+	[TRANS_STATE_COMMIT_PREP]	= 0U,
 	[TRANS_STATE_COMMIT_START]	= (__TRANS_START | __TRANS_ATTACH),
 	[TRANS_STATE_COMMIT_DOING]	= (__TRANS_START |
 					   __TRANS_ATTACH |
@@ -292,10 +298,11 @@ loop:
 	spin_unlock(&fs_info->trans_lock);
 
 	/*
-	 * If we are ATTACH, we just want to catch the current transaction,
-	 * and commit it. If there is no transaction, just return ENOENT.
+	 * If we are ATTACH or TRANS_JOIN_NOSTART, we just want to catch the
+	 * current transaction, and commit it. If there is no transaction, just
+	 * return ENOENT.
 	 */
-	if (type == TRANS_ATTACH)
+	if (type == TRANS_ATTACH || type == TRANS_JOIN_NOSTART)
 		return -ENOENT;
 
 	/*
@@ -591,8 +598,13 @@ start_transaction(struct btrfs_root *root, unsigned int num_items,
 		u64 delayed_refs_bytes = 0;
 
 		qgroup_reserved = num_items * fs_info->nodesize;
-		ret = btrfs_qgroup_reserve_meta_pertrans(root, qgroup_reserved,
-				enforce_qgroups);
+		/*
+		 * Use prealloc for now, as there might be a currently running
+		 * transaction that could free this reserved space prematurely
+		 * by committing.
+		 */
+		ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserved,
+							 enforce_qgroups, false);
 		if (ret)
 			return ERR_PTR(ret);
 
@@ -705,6 +717,14 @@ again:
 		h->reloc_reserved = reloc_reserved;
 	}
 
+	/*
+	 * Now that we have found a transaction to be a part of, convert the
+	 * qgroup reservation from prealloc to pertrans. A different transaction
+	 * can't race in and free our pertrans out from under us.
+	 */
+	if (qgroup_reserved)
+		btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+
 got_it:
 	if (!current->journal_info)
 		current->journal_info = h;
@@ -752,7 +772,7 @@ alloc_fail:
 		btrfs_block_rsv_release(fs_info, &fs_info->trans_block_rsv,
 					num_bytes, NULL);
 reserve_fail:
-	btrfs_qgroup_free_meta_pertrans(root, qgroup_reserved);
+	btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
 	return ERR_PTR(ret);
 }
 
@@ -785,7 +805,10 @@ struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *
 
 /*
  * Similar to regular join but it never starts a transaction when none is
- * running or after waiting for the current one to finish.
+ * running or when there's a running one at a state >= TRANS_STATE_UNBLOCKED.
+ * This is similar to btrfs_attach_transaction() but it allows the join to
+ * happen if the transaction commit already started but it's not yet in the
+ * "doing" phase (the state is < TRANS_STATE_COMMIT_DOING).
  */
 struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root)
 {
@@ -826,8 +849,13 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root)
 
 	trans = start_transaction(root, 0, TRANS_ATTACH,
 				  BTRFS_RESERVE_NO_FLUSH, true);
-	if (trans == ERR_PTR(-ENOENT))
-		btrfs_wait_for_commit(root->fs_info, 0);
+	if (trans == ERR_PTR(-ENOENT)) {
+		int ret;
+
+		ret = btrfs_wait_for_commit(root->fs_info, 0);
+		if (ret)
+			return ERR_PTR(ret);
+	}
 
 	return trans;
 }
@@ -931,6 +959,7 @@ int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid)
 	}
 
 	wait_for_commit(cur_trans, TRANS_STATE_COMPLETED);
+	ret = cur_trans->aborted;
 	btrfs_put_transaction(cur_trans);
 out:
 	return ret;
@@ -1054,8 +1083,8 @@ int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
 	u64 start = 0;
 	u64 end;
 
-	while (!find_first_extent_bit(dirty_pages, start, &start, &end,
-				      mark, &cached_state)) {
+	while (find_first_extent_bit(dirty_pages, start, &start, &end,
+				     mark, &cached_state)) {
 		bool wait_writeback = false;
 
 		err = convert_extent_bit(dirty_pages, start, end,
@@ -1108,8 +1137,8 @@ static int __btrfs_wait_marked_extents(struct btrfs_fs_info *fs_info,
 	u64 start = 0;
 	u64 end;
 
-	while (!find_first_extent_bit(dirty_pages, start, &start, &end,
-				      EXTENT_NEED_WAIT, &cached_state)) {
+	while (find_first_extent_bit(dirty_pages, start, &start, &end,
+				     EXTENT_NEED_WAIT, &cached_state)) {
 		/*
 		 * Ignore -ENOMEM errors returned by clear_extent_bit().
 		 * When committing the transaction, we'll remove any entries
@@ -1831,8 +1860,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 
 	btrfs_i_size_write(BTRFS_I(parent_inode), parent_inode->i_size +
 						  fname.disk_name.len * 2);
-	parent_inode->i_mtime = current_time(parent_inode);
-	parent_inode->i_ctime = parent_inode->i_mtime;
+	parent_inode->i_mtime = inode_set_ctime_current(parent_inode);
 	ret = btrfs_update_inode_fallback(trans, parent_root, BTRFS_I(parent_inode));
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
@@ -1960,7 +1988,7 @@ void btrfs_commit_transaction_async(struct btrfs_trans_handle *trans)
 	 * Wait for the current transaction commit to start and block
 	 * subsequent transaction joins
 	 */
-	btrfs_might_wait_for_state(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_START);
+	btrfs_might_wait_for_state(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_PREP);
 	wait_event(fs_info->transaction_blocked_wait,
 		   cur_trans->state >= TRANS_STATE_COMMIT_START ||
 		   TRANS_ABORTED(cur_trans));
@@ -2107,7 +2135,7 @@ static void add_pending_snapshot(struct btrfs_trans_handle *trans)
 		return;
 
 	lockdep_assert_held(&trans->fs_info->trans_lock);
-	ASSERT(cur_trans->state >= TRANS_STATE_COMMIT_START);
+	ASSERT(cur_trans->state >= TRANS_STATE_COMMIT_PREP);
 
 	list_add(&trans->pending_snapshot->list, &cur_trans->pending_snapshots);
 }
@@ -2131,7 +2159,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	ktime_t interval;
 
 	ASSERT(refcount_read(&trans->use_count) == 1);
-	btrfs_trans_state_lockdep_acquire(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_START);
+	btrfs_trans_state_lockdep_acquire(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_PREP);
 
 	clear_bit(BTRFS_FS_NEED_TRANS_COMMIT, &fs_info->flags);
 
@@ -2191,7 +2219,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	}
 
 	spin_lock(&fs_info->trans_lock);
-	if (cur_trans->state >= TRANS_STATE_COMMIT_START) {
+	if (cur_trans->state >= TRANS_STATE_COMMIT_PREP) {
 		enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED;
 
 		add_pending_snapshot(trans);
@@ -2203,7 +2231,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 			want_state = TRANS_STATE_SUPER_COMMITTED;
 
 		btrfs_trans_state_lockdep_release(fs_info,
-						  BTRFS_LOCKDEP_TRANS_COMMIT_START);
+						  BTRFS_LOCKDEP_TRANS_COMMIT_PREP);
 		ret = btrfs_end_transaction(trans);
 		wait_for_commit(cur_trans, want_state);
 
@@ -2215,9 +2243,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		return ret;
 	}
 
-	cur_trans->state = TRANS_STATE_COMMIT_START;
+	cur_trans->state = TRANS_STATE_COMMIT_PREP;
 	wake_up(&fs_info->transaction_blocked_wait);
-	btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_START);
+	btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_PREP);
 
 	if (cur_trans->list.prev != &fs_info->trans_list) {
 		enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED;
@@ -2238,11 +2266,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 			btrfs_put_transaction(prev_trans);
 			if (ret)
 				goto lockdep_release;
-		} else {
-			spin_unlock(&fs_info->trans_lock);
+			spin_lock(&fs_info->trans_lock);
 		}
 	} else {
-		spin_unlock(&fs_info->trans_lock);
 		/*
 		 * The previous transaction was aborted and was already removed
 		 * from the list of transactions at fs_info->trans_list. So we
@@ -2250,11 +2276,16 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		 * corrupt state (pointing to trees with unwritten nodes/leafs).
 		 */
 		if (BTRFS_FS_ERROR(fs_info)) {
+			spin_unlock(&fs_info->trans_lock);
 			ret = -EROFS;
 			goto lockdep_release;
 		}
 	}
 
+	cur_trans->state = TRANS_STATE_COMMIT_START;
+	wake_up(&fs_info->transaction_blocked_wait);
+	spin_unlock(&fs_info->trans_lock);
+
 	/*
 	 * Get the time spent on the work done by the commit thread and not
 	 * the time spent waiting on a previous commit
@@ -2564,7 +2595,7 @@ lockdep_release:
 	goto cleanup_transaction;
 
 lockdep_trans_commit_start_release:
-	btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_START);
+	btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_PREP);
 	btrfs_end_transaction(trans);
 	return ret;
 }