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

Pull btrfs updates from Chris Mason:
 "The biggest change here is Josef's rework of the btrfs quota
  accounting, which improves the in-memory tracking of delayed extent
  operations.

  I had been working on Btrfs stack usage for a while, mostly because it
  had become impossible to do long stress runs with slab, lockdep and
  pagealloc debugging turned on without blowing the stack.  Even though
  you upgraded us to a nice king sized stack, I kept most of the
  patches.

  We also have some very hard to find corruption fixes, an awesome sysfs
  use after free, and the usual assortment of optimizations, cleanups
  and other fixes"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (80 commits)
  Btrfs: convert smp_mb__{before,after}_clear_bit
  Btrfs: fix scrub_print_warning to handle skinny metadata extents
  Btrfs: make fsync work after cloning into a file
  Btrfs: use right type to get real comparison
  Btrfs: don't check nodes for extent items
  Btrfs: don't release invalid page in btrfs_page_exists_in_range()
  Btrfs: make sure we retry if page is a retriable exception
  Btrfs: make sure we retry if we couldn't get the page
  btrfs: replace EINVAL with EOPNOTSUPP for dev_replace raid56
  trivial: fs/btrfs/ioctl.c: fix typo s/substract/subtract/
  Btrfs: fix leaf corruption after __btrfs_drop_extents
  Btrfs: ensure btrfs_prev_leaf doesn't miss 1 item
  Btrfs: fix clone to deal with holes when NO_HOLES feature is enabled
  btrfs: free delayed node outside of root->inode_lock
  btrfs: replace EINVAL with ERANGE for resize when ULLONG_MAX
  Btrfs: fix transaction leak during fsync call
  btrfs: Avoid trucating page or punching hole in a already existed hole.
  Btrfs: update commit root on snapshot creation after orphan cleanup
  Btrfs: ioctl, don't re-lock extent range when not necessary
  Btrfs: avoid visiting all extent items when cloning a range
  ...

1 files changed, 204 insertions, 89 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5a3b8371772e..7fa5f7fd7bc7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -125,7 +125,7 @@ static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
  * the btree.  The caller should have done a btrfs_drop_extents so that
  * no overlapping inline items exist in the btree
  */
-static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
+static int insert_inline_extent(struct btrfs_trans_handle *trans,
 				struct btrfs_path *path, int extent_inserted,
 				struct btrfs_root *root, struct inode *inode,
 				u64 start, size_t size, size_t compressed_size,
@@ -2678,6 +2678,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		trans = NULL;
 		goto out_unlock;
 	}
+
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
@@ -2947,14 +2948,15 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
 	root->orphan_block_rsv = NULL;
 	spin_unlock(&root->orphan_lock);
 
-	if (root->orphan_item_inserted &&
+	if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state) &&
 	    btrfs_root_refs(&root->root_item) > 0) {
 		ret = btrfs_del_orphan_item(trans, root->fs_info->tree_root,
 					    root->root_key.objectid);
 		if (ret)
 			btrfs_abort_transaction(trans, root, ret);
 		else
-			root->orphan_item_inserted = 0;
+			clear_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
+				  &root->state);
 	}
 
 	if (block_rsv) {
@@ -3271,7 +3273,8 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 		btrfs_block_rsv_release(root, root->orphan_block_rsv,
 					(u64)-1);
 
-	if (root->orphan_block_rsv || root->orphan_item_inserted) {
+	if (root->orphan_block_rsv ||
+	    test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) {
 		trans = btrfs_join_transaction(root);
 		if (!IS_ERR(trans))
 			btrfs_end_transaction(trans, root);
@@ -3473,7 +3476,7 @@ cache_acl:
 		ret = btrfs_load_inode_props(inode, path);
 		if (ret)
 			btrfs_err(root->fs_info,
-				  "error loading props for ino %llu (root %llu): %d\n",
+				  "error loading props for ino %llu (root %llu): %d",
 				  btrfs_ino(inode),
 				  root->root_key.objectid, ret);
 	}
@@ -3998,7 +4001,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	 * not block aligned since we will be keeping the last block of the
 	 * extent just the way it is.
 	 */
-	if (root->ref_cows || root == root->fs_info->tree_root)
+	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+	    root == root->fs_info->tree_root)
 		btrfs_drop_extent_cache(inode, ALIGN(new_size,
 					root->sectorsize), (u64)-1, 0);
 
@@ -4091,7 +4095,9 @@ search_again:
 							 extent_num_bytes);
 				num_dec = (orig_num_bytes -
 					   extent_num_bytes);
-				if (root->ref_cows && extent_start != 0)
+				if (test_bit(BTRFS_ROOT_REF_COWS,
+					     &root->state) &&
+				    extent_start != 0)
 					inode_sub_bytes(inode, num_dec);
 				btrfs_mark_buffer_dirty(leaf);
 			} else {
@@ -4105,7 +4111,8 @@ search_again:
 				num_dec = btrfs_file_extent_num_bytes(leaf, fi);
 				if (extent_start != 0) {
 					found_extent = 1;
-					if (root->ref_cows)
+					if (test_bit(BTRFS_ROOT_REF_COWS,
+						     &root->state))
 						inode_sub_bytes(inode, num_dec);
 				}
 			}
@@ -4120,10 +4127,9 @@ search_again:
 			    btrfs_file_extent_other_encoding(leaf, fi) == 0) {
 				u32 size = new_size - found_key.offset;
 
-				if (root->ref_cows) {
+				if (test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 					inode_sub_bytes(inode, item_end + 1 -
 							new_size);
-				}
 
 				/*
 				 * update the ram bytes to properly reflect
@@ -4133,7 +4139,8 @@ search_again:
 				size =
 				    btrfs_file_extent_calc_inline_size(size);
 				btrfs_truncate_item(root, path, size, 1);
-			} else if (root->ref_cows) {
+			} else if (test_bit(BTRFS_ROOT_REF_COWS,
+					    &root->state)) {
 				inode_sub_bytes(inode, item_end + 1 -
 						found_key.offset);
 			}
@@ -4155,8 +4162,9 @@ delete:
 		} else {
 			break;
 		}
-		if (found_extent && (root->ref_cows ||
-				     root == root->fs_info->tree_root)) {
+		if (found_extent &&
+		    (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+		     root == root->fs_info->tree_root)) {
 			btrfs_set_path_blocking(path);
 			ret = btrfs_free_extent(trans, root, extent_start,
 						extent_num_bytes, 0,
@@ -5168,8 +5176,7 @@ static int btrfs_dentry_delete(const struct dentry *dentry)
 
 static void btrfs_dentry_release(struct dentry *dentry)
 {
-	if (dentry->d_fsdata)
-		kfree(dentry->d_fsdata);
+	kfree(dentry->d_fsdata);
 }
 
 static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
@@ -5553,6 +5560,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_inode_ref *ref;
 	struct btrfs_key key[2];
 	u32 sizes[2];
+	int nitems = name ? 2 : 1;
 	unsigned long ptr;
 	int ret;
 
@@ -5572,7 +5580,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	 */
 	inode->i_ino = objectid;
 
-	if (dir) {
+	if (dir && name) {
 		trace_btrfs_inode_request(dir);
 
 		ret = btrfs_set_inode_index(dir, index);
@@ -5581,6 +5589,8 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 			iput(inode);
 			return ERR_PTR(ret);
 		}
+	} else if (dir) {
+		*index = 0;
 	}
 	/*
 	 * index_cnt is ignored for everything but a dir,
@@ -5605,21 +5615,24 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
 	key[0].offset = 0;
 
-	/*
-	 * Start new inodes with an inode_ref. This is slightly more
-	 * efficient for small numbers of hard links since they will
-	 * be packed into one item. Extended refs will kick in if we
-	 * add more hard links than can fit in the ref item.
-	 */
-	key[1].objectid = objectid;
-	btrfs_set_key_type(&key[1], BTRFS_INODE_REF_KEY);
-	key[1].offset = ref_objectid;
-
 	sizes[0] = sizeof(struct btrfs_inode_item);
-	sizes[1] = name_len + sizeof(*ref);
+
+	if (name) {
+		/*
+		 * Start new inodes with an inode_ref. This is slightly more
+		 * efficient for small numbers of hard links since they will
+		 * be packed into one item. Extended refs will kick in if we
+		 * add more hard links than can fit in the ref item.
+		 */
+		key[1].objectid = objectid;
+		btrfs_set_key_type(&key[1], BTRFS_INODE_REF_KEY);
+		key[1].offset = ref_objectid;
+
+		sizes[1] = name_len + sizeof(*ref);
+	}
 
 	path->leave_spinning = 1;
-	ret = btrfs_insert_empty_items(trans, root, path, key, sizes, 2);
+	ret = btrfs_insert_empty_items(trans, root, path, key, sizes, nitems);
 	if (ret != 0)
 		goto fail;
 
@@ -5632,12 +5645,14 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 			     sizeof(*inode_item));
 	fill_inode_item(trans, path->nodes[0], inode_item, inode);
 
-	ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
-			     struct btrfs_inode_ref);
-	btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
-	btrfs_set_inode_ref_index(path->nodes[0], ref, *index);
-	ptr = (unsigned long)(ref + 1);
-	write_extent_buffer(path->nodes[0], name, ptr, name_len);
+	if (name) {
+		ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
+				     struct btrfs_inode_ref);
+		btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
+		btrfs_set_inode_ref_index(path->nodes[0], ref, *index);
+		ptr = (unsigned long)(ref + 1);
+		write_extent_buffer(path->nodes[0], name, ptr, name_len);
+	}
 
 	btrfs_mark_buffer_dirty(path->nodes[0]);
 	btrfs_free_path(path);
@@ -5673,7 +5688,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 
 	return inode;
 fail:
-	if (dir)
+	if (dir && name)
 		BTRFS_I(dir)->index_cnt--;
 	btrfs_free_path(path);
 	iput(inode);
@@ -5958,6 +5973,15 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		err = btrfs_update_inode(trans, root, inode);
 		if (err)
 			goto fail;
+		if (inode->i_nlink == 1) {
+			/*
+			 * If new hard link count is 1, it's a file created
+			 * with open(2) O_TMPFILE flag.
+			 */
+			err = btrfs_orphan_del(trans, inode);
+			if (err)
+				goto fail;
+		}
 		d_instantiate(dentry, inode);
 		btrfs_log_new_name(trans, inode, NULL, parent);
 	}
@@ -6086,16 +6110,8 @@ static noinline int uncompress_inline(struct btrfs_path *path,
 	max_size = min_t(unsigned long, PAGE_CACHE_SIZE, max_size);
 	ret = btrfs_decompress(compress_type, tmp, page,
 			       extent_offset, inline_size, max_size);
-	if (ret) {
-		char *kaddr = kmap_atomic(page);
-		unsigned long copy_size = min_t(u64,
-				  PAGE_CACHE_SIZE - pg_offset,
-				  max_size - extent_offset);
-		memset(kaddr + pg_offset, 0, copy_size);
-		kunmap_atomic(kaddr);
-	}
 	kfree(tmp);
-	return 0;
+	return ret;
 }
 
 /*
@@ -6113,7 +6129,6 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 {
 	int ret;
 	int err = 0;
-	u64 bytenr;
 	u64 extent_start = 0;
 	u64 extent_end = 0;
 	u64 objectid = btrfs_ino(inode);
@@ -6127,7 +6142,7 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_trans_handle *trans = NULL;
-	int compress_type;
+	const bool new_inline = !page || create;
 
 again:
 	read_lock(&em_tree->lock);
@@ -6201,7 +6216,6 @@ again:
 
 	found_type = btrfs_file_extent_type(leaf, item);
 	extent_start = found_key.offset;
-	compress_type = btrfs_file_extent_compression(leaf, item);
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
 		extent_end = extent_start +
@@ -6236,32 +6250,10 @@ next:
 		goto not_found_em;
 	}
 
-	em->ram_bytes = btrfs_file_extent_ram_bytes(leaf, item);
+	btrfs_extent_item_to_extent_map(inode, path, item, new_inline, em);
+
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
-		em->start = extent_start;
-		em->len = extent_end - extent_start;
-		em->orig_start = extent_start -
-				 btrfs_file_extent_offset(leaf, item);
-		em->orig_block_len = btrfs_file_extent_disk_num_bytes(leaf,
-								      item);
-		bytenr = btrfs_file_extent_disk_bytenr(leaf, item);
-		if (bytenr == 0) {
-			em->block_start = EXTENT_MAP_HOLE;
-			goto insert;
-		}
-		if (compress_type != BTRFS_COMPRESS_NONE) {
-			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
-			em->compress_type = compress_type;
-			em->block_start = bytenr;
-			em->block_len = em->orig_block_len;
-		} else {
-			bytenr += btrfs_file_extent_offset(leaf, item);
-			em->block_start = bytenr;
-			em->block_len = em->len;
-			if (found_type == BTRFS_FILE_EXTENT_PREALLOC)
-				set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
-		}
 		goto insert;
 	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
 		unsigned long ptr;
@@ -6270,12 +6262,8 @@ next:
 		size_t extent_offset;
 		size_t copy_size;
 
-		em->block_start = EXTENT_MAP_INLINE;
-		if (!page || create) {
-			em->start = extent_start;
-			em->len = extent_end - extent_start;
+		if (new_inline)
 			goto out;
-		}
 
 		size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
 		extent_offset = page_offset(page) + pg_offset - extent_start;
@@ -6285,10 +6273,6 @@ next:
 		em->len = ALIGN(copy_size, root->sectorsize);
 		em->orig_block_len = em->len;
 		em->orig_start = em->start;
-		if (compress_type) {
-			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
-			em->compress_type = compress_type;
-		}
 		ptr = btrfs_file_extent_inline_start(item) + extent_offset;
 		if (create == 0 && !PageUptodate(page)) {
 			if (btrfs_file_extent_compression(leaf, item) !=
@@ -6296,7 +6280,10 @@ next:
 				ret = uncompress_inline(path, inode, page,
 							pg_offset,
 							extent_offset, item);
-				BUG_ON(ret); /* -ENOMEM */
+				if (ret) {
+					err = ret;
+					goto out;
+				}
 			} else {
 				map = kmap(page);
 				read_extent_buffer(leaf, map + pg_offset, ptr,
@@ -6332,8 +6319,6 @@ next:
 		set_extent_uptodate(io_tree, em->start,
 				    extent_map_end(em) - 1, NULL, GFP_NOFS);
 		goto insert;
-	} else {
-		WARN(1, KERN_ERR "btrfs unknown found_type %d\n", found_type);
 	}
 not_found:
 	em->start = start;
@@ -6717,6 +6702,76 @@ out:
 	return ret;
 }
 
+bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
+{
+	struct radix_tree_root *root = &inode->i_mapping->page_tree;
+	int found = false;
+	void **pagep = NULL;
+	struct page *page = NULL;
+	int start_idx;
+	int end_idx;
+
+	start_idx = start >> PAGE_CACHE_SHIFT;
+
+	/*
+	 * end is the last byte in the last page.  end == start is legal
+	 */
+	end_idx = end >> PAGE_CACHE_SHIFT;
+
+	rcu_read_lock();
+
+	/* Most of the code in this while loop is lifted from
+	 * find_get_page.  It's been modified to begin searching from a
+	 * page and return just the first page found in that range.  If the
+	 * found idx is less than or equal to the end idx then we know that
+	 * a page exists.  If no pages are found or if those pages are
+	 * outside of the range then we're fine (yay!) */
+	while (page == NULL &&
+	       radix_tree_gang_lookup_slot(root, &pagep, NULL, start_idx, 1)) {
+		page = radix_tree_deref_slot(pagep);
+		if (unlikely(!page))
+			break;
+
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page)) {
+				page = NULL;
+				continue;
+			}
+			/*
+			 * Otherwise, shmem/tmpfs must be storing a swap entry
+			 * here as an exceptional entry: so return it without
+			 * attempting to raise page count.
+			 */
+			page = NULL;
+			break; /* TODO: Is this relevant for this use case? */
+		}
+
+		if (!page_cache_get_speculative(page)) {
+			page = NULL;
+			continue;
+		}
+
+		/*
+		 * Has the page moved?
+		 * This is part of the lockless pagecache protocol. See
+		 * include/linux/pagemap.h for details.
+		 */
+		if (unlikely(page != *pagep)) {
+			page_cache_release(page);
+			page = NULL;
+		}
+	}
+
+	if (page) {
+		if (page->index <= end_idx)
+			found = true;
+		page_cache_release(page);
+	}
+
+	rcu_read_unlock();
+	return found;
+}
+
 static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 			      struct extent_state **cached_state, int writing)
 {
@@ -6741,10 +6796,9 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 		 * invalidate needs to happen so that reads after a write do not
 		 * get stale data.
 		 */
-		if (!ordered && (!writing ||
-		    !test_range_bit(&BTRFS_I(inode)->io_tree,
-				    lockstart, lockend, EXTENT_UPTODATE, 0,
-				    *cached_state)))
+		if (!ordered &&
+		    (!writing ||
+		     !btrfs_page_exists_in_range(inode, lockstart, lockend)))
 			break;
 
 		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
@@ -7992,7 +8046,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 	err = btrfs_subvol_inherit_props(trans, new_root, parent_root);
 	if (err)
 		btrfs_err(new_root->fs_info,
-			  "error inheriting subvolume %llu properties: %d\n",
+			  "error inheriting subvolume %llu properties: %d",
 			  new_root->root_key.objectid, err);
 
 	err = btrfs_update_inode(trans, new_root, inode);
@@ -8311,7 +8365,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	BTRFS_I(old_inode)->dir_index = 0ULL;
 	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		/* force full log commit if subvolume involved. */
-		root->fs_info->last_trans_log_full_commit = trans->transid;
+		btrfs_set_log_full_commit(root->fs_info, trans);
 	} else {
 		ret = btrfs_insert_inode_ref(trans, dest,
 					     new_dentry->d_name.name,
@@ -8889,6 +8943,66 @@ static int btrfs_permission(struct inode *inode, int mask)
 	return generic_permission(inode, mask);
 }
 
+static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	struct btrfs_trans_handle *trans;
+	struct btrfs_root *root = BTRFS_I(dir)->root;
+	struct inode *inode = NULL;
+	u64 objectid;
+	u64 index;
+	int ret = 0;
+
+	/*
+	 * 5 units required for adding orphan entry
+	 */
+	trans = btrfs_start_transaction(root, 5);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+
+	ret = btrfs_find_free_ino(root, &objectid);
+	if (ret)
+		goto out;
+
+	inode = btrfs_new_inode(trans, root, dir, NULL, 0,
+				btrfs_ino(dir), objectid, mode, &index);
+	if (IS_ERR(inode)) {
+		ret = PTR_ERR(inode);
+		inode = NULL;
+		goto out;
+	}
+
+	ret = btrfs_init_inode_security(trans, inode, dir, NULL);
+	if (ret)
+		goto out;
+
+	ret = btrfs_update_inode(trans, root, inode);
+	if (ret)
+		goto out;
+
+	inode->i_fop = &btrfs_file_operations;
+	inode->i_op = &btrfs_file_inode_operations;
+
+	inode->i_mapping->a_ops = &btrfs_aops;
+	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
+	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+
+	ret = btrfs_orphan_add(trans, inode);
+	if (ret)
+		goto out;
+
+	d_tmpfile(dentry, inode);
+	mark_inode_dirty(inode);
+
+out:
+	btrfs_end_transaction(trans, root);
+	if (ret)
+		iput(inode);
+	btrfs_balance_delayed_items(root);
+	btrfs_btree_balance_dirty(root);
+
+	return ret;
+}
+
 static const struct inode_operations btrfs_dir_inode_operations = {
 	.getattr	= btrfs_getattr,
 	.lookup		= btrfs_lookup,
@@ -8909,6 +9023,7 @@ static const struct inode_operations btrfs_dir_inode_operations = {
 	.get_acl	= btrfs_get_acl,
 	.set_acl	= btrfs_set_acl,
 	.update_time	= btrfs_update_time,
+	.tmpfile        = btrfs_tmpfile,
 };
 static const struct inode_operations btrfs_dir_ro_inode_operations = {
 	.lookup		= btrfs_lookup,