1 files changed, 117 insertions, 39 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 54bcf639d1cf..a85c23dfcddb 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1530,10 +1530,45 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page,
 static void btrfs_split_extent_hook(struct inode *inode,
 				    struct extent_state *orig, u64 split)
 {
+	u64 size;
+
 	/* not delalloc, ignore it */
 	if (!(orig->state & EXTENT_DELALLOC))
 		return;
 
+	size = orig->end - orig->start + 1;
+	if (size > BTRFS_MAX_EXTENT_SIZE) {
+		u64 num_extents;
+		u64 new_size;
+
+		/*
+		 * We need the largest size of the remaining extent to see if we
+		 * need to add a new outstanding extent.  Think of the following
+		 * case
+		 *
+		 * [MEAX_EXTENT_SIZEx2 - 4k][4k]
+		 *
+		 * The new_size would just be 4k and we'd think we had enough
+		 * outstanding extents for this if we only took one side of the
+		 * split, same goes for the other direction.  We need to see if
+		 * the larger size still is the same amount of extents as the
+		 * original size, because if it is we need to add a new
+		 * outstanding extent.  But if we split up and the larger size
+		 * is less than the original then we are good to go since we've
+		 * already accounted for the extra extent in our original
+		 * accounting.
+		 */
+		new_size = orig->end - split + 1;
+		if ((split - orig->start) > new_size)
+			new_size = split - orig->start;
+
+		num_extents = div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+					BTRFS_MAX_EXTENT_SIZE);
+		if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
+			      BTRFS_MAX_EXTENT_SIZE) < num_extents)
+			return;
+	}
+
 	spin_lock(&BTRFS_I(inode)->lock);
 	BTRFS_I(inode)->outstanding_extents++;
 	spin_unlock(&BTRFS_I(inode)->lock);
@@ -1549,10 +1584,34 @@ static void btrfs_merge_extent_hook(struct inode *inode,
 				    struct extent_state *new,
 				    struct extent_state *other)
 {
+	u64 new_size, old_size;
+	u64 num_extents;
+
 	/* not delalloc, ignore it */
 	if (!(other->state & EXTENT_DELALLOC))
 		return;
 
+	old_size = other->end - other->start + 1;
+	new_size = old_size + (new->end - new->start + 1);
+
+	/* we're not bigger than the max, unreserve the space and go */
+	if (new_size <= BTRFS_MAX_EXTENT_SIZE) {
+		spin_lock(&BTRFS_I(inode)->lock);
+		BTRFS_I(inode)->outstanding_extents--;
+		spin_unlock(&BTRFS_I(inode)->lock);
+		return;
+	}
+
+	/*
+	 * If we grew by another max_extent, just return, we want to keep that
+	 * reserved amount.
+	 */
+	num_extents = div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
+				BTRFS_MAX_EXTENT_SIZE);
+	if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
+		      BTRFS_MAX_EXTENT_SIZE) > num_extents)
+		return;
+
 	spin_lock(&BTRFS_I(inode)->lock);
 	BTRFS_I(inode)->outstanding_extents--;
 	spin_unlock(&BTRFS_I(inode)->lock);
@@ -1604,7 +1663,7 @@ static void btrfs_del_delalloc_inode(struct btrfs_root *root,
  * have pending delalloc work to be done.
  */
 static void btrfs_set_bit_hook(struct inode *inode,
-			       struct extent_state *state, unsigned long *bits)
+			       struct extent_state *state, unsigned *bits)
 {
 
 	if ((*bits & EXTENT_DEFRAG) && !(*bits & EXTENT_DELALLOC))
@@ -1645,9 +1704,11 @@ static void btrfs_set_bit_hook(struct inode *inode,
  */
 static void btrfs_clear_bit_hook(struct inode *inode,
 				 struct extent_state *state,
-				 unsigned long *bits)
+				 unsigned *bits)
 {
 	u64 len = state->end + 1 - state->start;
+	u64 num_extents = div64_u64(len + BTRFS_MAX_EXTENT_SIZE -1,
+				    BTRFS_MAX_EXTENT_SIZE);
 
 	spin_lock(&BTRFS_I(inode)->lock);
 	if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG))
@@ -1667,7 +1728,7 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 			*bits &= ~EXTENT_FIRST_DELALLOC;
 		} else if (!(*bits & EXTENT_DO_ACCOUNTING)) {
 			spin_lock(&BTRFS_I(inode)->lock);
-			BTRFS_I(inode)->outstanding_extents--;
+			BTRFS_I(inode)->outstanding_extents -= num_extents;
 			spin_unlock(&BTRFS_I(inode)->lock);
 		}
 
@@ -2945,7 +3006,7 @@ static int __readpage_endio_check(struct inode *inode,
 	return 0;
 zeroit:
 	if (__ratelimit(&_rs))
-		btrfs_info(BTRFS_I(inode)->root->fs_info,
+		btrfs_warn(BTRFS_I(inode)->root->fs_info,
 			   "csum failed ino %llu off %llu csum %u expected csum %u",
 			   btrfs_ino(inode), start, csum, csum_expected);
 	memset(kaddr + pgoff, 1, len);
@@ -3407,7 +3468,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 
 out:
 	if (ret)
-		btrfs_crit(root->fs_info,
+		btrfs_err(root->fs_info,
 			"could not do orphan cleanup %d", ret);
 	btrfs_free_path(path);
 	return ret;
@@ -3490,7 +3551,6 @@ static void btrfs_read_locked_inode(struct inode *inode)
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_inode_item *inode_item;
-	struct btrfs_timespec *tspec;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_key location;
 	unsigned long ptr;
@@ -3527,17 +3587,19 @@ static void btrfs_read_locked_inode(struct inode *inode)
 	i_gid_write(inode, btrfs_inode_gid(leaf, inode_item));
 	btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item));
 
-	tspec = btrfs_inode_atime(inode_item);
-	inode->i_atime.tv_sec = btrfs_timespec_sec(leaf, tspec);
-	inode->i_atime.tv_nsec = btrfs_timespec_nsec(leaf, tspec);
+	inode->i_atime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->atime);
+	inode->i_atime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->atime);
+
+	inode->i_mtime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->mtime);
+	inode->i_mtime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->mtime);
 
-	tspec = btrfs_inode_mtime(inode_item);
-	inode->i_mtime.tv_sec = btrfs_timespec_sec(leaf, tspec);
-	inode->i_mtime.tv_nsec = btrfs_timespec_nsec(leaf, tspec);
+	inode->i_ctime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->ctime);
+	inode->i_ctime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->ctime);
 
-	tspec = btrfs_inode_ctime(inode_item);
-	inode->i_ctime.tv_sec = btrfs_timespec_sec(leaf, tspec);
-	inode->i_ctime.tv_nsec = btrfs_timespec_nsec(leaf, tspec);
+	BTRFS_I(inode)->i_otime.tv_sec =
+		btrfs_timespec_sec(leaf, &inode_item->otime);
+	BTRFS_I(inode)->i_otime.tv_nsec =
+		btrfs_timespec_nsec(leaf, &inode_item->otime);
 
 	inode_set_bytes(inode, btrfs_inode_nbytes(leaf, inode_item));
 	BTRFS_I(inode)->generation = btrfs_inode_generation(leaf, inode_item);
@@ -3656,21 +3718,26 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 	btrfs_set_token_inode_mode(leaf, item, inode->i_mode, &token);
 	btrfs_set_token_inode_nlink(leaf, item, inode->i_nlink, &token);
 
-	btrfs_set_token_timespec_sec(leaf, btrfs_inode_atime(item),
+	btrfs_set_token_timespec_sec(leaf, &item->atime,
 				     inode->i_atime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_atime(item),
+	btrfs_set_token_timespec_nsec(leaf, &item->atime,
 				      inode->i_atime.tv_nsec, &token);
 
-	btrfs_set_token_timespec_sec(leaf, btrfs_inode_mtime(item),
+	btrfs_set_token_timespec_sec(leaf, &item->mtime,
 				     inode->i_mtime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_mtime(item),
+	btrfs_set_token_timespec_nsec(leaf, &item->mtime,
 				      inode->i_mtime.tv_nsec, &token);
 
-	btrfs_set_token_timespec_sec(leaf, btrfs_inode_ctime(item),
+	btrfs_set_token_timespec_sec(leaf, &item->ctime,
 				     inode->i_ctime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_ctime(item),
+	btrfs_set_token_timespec_nsec(leaf, &item->ctime,
 				      inode->i_ctime.tv_nsec, &token);
 
+	btrfs_set_token_timespec_sec(leaf, &item->otime,
+				     BTRFS_I(inode)->i_otime.tv_sec, &token);
+	btrfs_set_token_timespec_nsec(leaf, &item->otime,
+				      BTRFS_I(inode)->i_otime.tv_nsec, &token);
+
 	btrfs_set_token_inode_nbytes(leaf, item, inode_get_bytes(inode),
 				     &token);
 	btrfs_set_token_inode_generation(leaf, item, BTRFS_I(inode)->generation,
@@ -5007,6 +5074,7 @@ static int fixup_tree_root_location(struct btrfs_root *root,
 	struct btrfs_root *new_root;
 	struct btrfs_root_ref *ref;
 	struct extent_buffer *leaf;
+	struct btrfs_key key;
 	int ret;
 	int err = 0;
 
@@ -5017,9 +5085,12 @@ static int fixup_tree_root_location(struct btrfs_root *root,
 	}
 
 	err = -ENOENT;
-	ret = btrfs_find_item(root->fs_info->tree_root, path,
-				BTRFS_I(dir)->root->root_key.objectid,
-				location->objectid, BTRFS_ROOT_REF_KEY, NULL);
+	key.objectid = BTRFS_I(dir)->root->root_key.objectid;
+	key.type = BTRFS_ROOT_REF_KEY;
+	key.offset = location->objectid;
+
+	ret = btrfs_search_slot(NULL, root->fs_info->tree_root, &key, path,
+				0, 0);
 	if (ret) {
 		if (ret < 0)
 			err = ret;
@@ -5258,7 +5329,10 @@ static struct inode *new_simple_dir(struct super_block *s,
 	inode->i_op = &btrfs_dir_ro_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 	inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;
-	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	inode->i_mtime = CURRENT_TIME;
+	inode->i_atime = inode->i_mtime;
+	inode->i_ctime = inode->i_mtime;
+	BTRFS_I(inode)->i_otime = inode->i_mtime;
 
 	return inode;
 }
@@ -5826,7 +5900,12 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 
 	inode_init_owner(inode, dir, mode);
 	inode_set_bytes(inode, 0);
-	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+
+	inode->i_mtime = CURRENT_TIME;
+	inode->i_atime = inode->i_mtime;
+	inode->i_ctime = inode->i_mtime;
+	BTRFS_I(inode)->i_otime = inode->i_mtime;
+
 	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				  struct btrfs_inode_item);
 	memset_extent_buffer(path->nodes[0], 0, (unsigned long)inode_item,
@@ -7134,11 +7213,12 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	u64 start = iblock << inode->i_blkbits;
 	u64 lockstart, lockend;
 	u64 len = bh_result->b_size;
+	u64 orig_len = len;
 	int unlock_bits = EXTENT_LOCKED;
 	int ret = 0;
 
 	if (create)
-		unlock_bits |= EXTENT_DELALLOC | EXTENT_DIRTY;
+		unlock_bits |= EXTENT_DIRTY;
 	else
 		len = min_t(u64, len, root->sectorsize);
 
@@ -7269,14 +7349,12 @@ unlock:
 		if (start + len > i_size_read(inode))
 			i_size_write(inode, start + len);
 
-		spin_lock(&BTRFS_I(inode)->lock);
-		BTRFS_I(inode)->outstanding_extents++;
-		spin_unlock(&BTRFS_I(inode)->lock);
-
-		ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
-				     lockstart + len - 1, EXTENT_DELALLOC, NULL,
-				     &cached_state, GFP_NOFS);
-		BUG_ON(ret);
+		if (len < orig_len) {
+			spin_lock(&BTRFS_I(inode)->lock);
+			BTRFS_I(inode)->outstanding_extents++;
+			spin_unlock(&BTRFS_I(inode)->lock);
+		}
+		btrfs_free_reserved_data_space(inode, len);
 	}
 
 	/*
@@ -7805,8 +7883,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	}
 
 	/* async crcs make it difficult to collect full stripe writes. */
-	if (btrfs_get_alloc_profile(root, 1) &
-	    (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6))
+	if (btrfs_get_alloc_profile(root, 1) & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		async_submit = 0;
 	else
 		async_submit = 1;
@@ -8053,8 +8130,6 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 		else if (ret >= 0 && (size_t)ret < count)
 			btrfs_delalloc_release_space(inode,
 						     count - (size_t)ret);
-		else
-			btrfs_delalloc_release_metadata(inode, 0);
 	}
 out:
 	if (wakeup)
@@ -8575,6 +8650,9 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 
 	ei->delayed_node = NULL;
 
+	ei->i_otime.tv_sec = 0;
+	ei->i_otime.tv_nsec = 0;
+
 	inode = &ei->vfs_inode;
 	extent_map_tree_init(&ei->extent_tree);
 	extent_io_tree_init(&ei->io_tree, &inode->i_data);