Merge branch 'for-chris' of git://git.kernel.org/pub/scm/linux/kernel/git/josef/btrfs-next into linus

fs/btrfs/extent-tree.c

@@ -3997,7 +3997,7 @@ again:
 	 * We make the other tasks wait for the flush only when we can flush
 	 * all things.
 	 */
-	if (ret && flush == BTRFS_RESERVE_FLUSH_ALL) {
+	if (ret && flush != BTRFS_RESERVE_NO_FLUSH) {
 		flushing = true;
 		space_info->flush = 1;
 	}
@@ -5560,7 +5560,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 	int empty_cluster = 2 * 1024 * 1024;
 	struct btrfs_space_info *space_info;
 	int loop = 0;
-	int index = 0;
+	int index = __get_raid_index(data);
 	int alloc_type = (data & BTRFS_BLOCK_GROUP_DATA) ?
 		RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC;
 	bool found_uncached_bg = false;
@@ -6788,11 +6788,13 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 						       &wc->flags[level]);
 			if (ret < 0) {
 				btrfs_tree_unlock_rw(eb, path->locks[level]);
+				path->locks[level] = 0;
 				return ret;
 			}
 			BUG_ON(wc->refs[level] == 0);
 			if (wc->refs[level] == 1) {
 				btrfs_tree_unlock_rw(eb, path->locks[level]);
+				path->locks[level] = 0;
 				return 1;
 			}
 		}

fs/btrfs/file.c

@@ -2242,6 +2242,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int origin)
 	if (lockend <= lockstart)
 		lockend = lockstart + root->sectorsize;
 
+	lockend--;
 	len = lockend - lockstart + 1;
 
 	len = max_t(u64, len, root->sectorsize);
@@ -2308,9 +2309,12 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int origin)
 					}
 				}
 
-				*offset = start;
-				free_extent_map(em);
-				break;
+				if (!test_bit(EXTENT_FLAG_PREALLOC,
+					      &em->flags)) {
+					*offset = start;
+					free_extent_map(em);
+					break;
+				}
 			}
 		}
 

fs/btrfs/inode.c

@@ -88,7 +88,7 @@ static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
 	[S_IFLNK >> S_SHIFT]	= BTRFS_FT_SYMLINK,
 };
 
-static int btrfs_setsize(struct inode *inode, loff_t newsize);
+static int btrfs_setsize(struct inode *inode, struct iattr *attr);
 static int btrfs_truncate(struct inode *inode);
 static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent);
 static noinline int cow_file_range(struct inode *inode,
@@ -2478,6 +2478,18 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 				continue;
 			}
 			nr_truncate++;
+
+			/* 1 for the orphan item deletion. */
+			trans = btrfs_start_transaction(root, 1);
+			if (IS_ERR(trans)) {
+				ret = PTR_ERR(trans);
+				goto out;
+			}
+			ret = btrfs_orphan_add(trans, inode);
+			btrfs_end_transaction(trans, root);
+			if (ret)
+				goto out;
+
 			ret = btrfs_truncate(inode);
 		} else {
 			nr_unlink++;
@@ -3665,6 +3677,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 				block_end - cur_offset, 0);
 		if (IS_ERR(em)) {
 			err = PTR_ERR(em);
+			em = NULL;
 			break;
 		}
 		last_byte = min(extent_map_end(em), block_end);
@@ -3748,16 +3761,27 @@ next:
 	return err;
 }
 
-static int btrfs_setsize(struct inode *inode, loff_t newsize)
+static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
 	loff_t oldsize = i_size_read(inode);
+	loff_t newsize = attr->ia_size;
+	int mask = attr->ia_valid;
 	int ret;
 
 	if (newsize == oldsize)
 		return 0;
 
+	/*
+	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
+	 * special case where we need to update the times despite not having
+	 * these flags set.  For all other operations the VFS set these flags
+	 * explicitly if it wants a timestamp update.
+	 */
+	if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME))))
+		inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
+
 	if (newsize > oldsize) {
 		truncate_pagecache(inode, oldsize, newsize);
 		ret = btrfs_cont_expand(inode, oldsize, newsize);
@@ -3783,9 +3807,34 @@ static int btrfs_setsize(struct inode *inode, loff_t newsize)
 			set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
 				&BTRFS_I(inode)->runtime_flags);
 
+		/*
+		 * 1 for the orphan item we're going to add
+		 * 1 for the orphan item deletion.
+		 */
+		trans = btrfs_start_transaction(root, 2);
+		if (IS_ERR(trans))
+			return PTR_ERR(trans);
+
+		/*
+		 * We need to do this in case we fail at _any_ point during the
+		 * actual truncate.  Once we do the truncate_setsize we could
+		 * invalidate pages which forces any outstanding ordered io to
+		 * be instantly completed which will give us extents that need
+		 * to be truncated.  If we fail to get an orphan inode down we
+		 * could have left over extents that were never meant to live,
+		 * so we need to garuntee from this point on that everything
+		 * will be consistent.
+		 */
+		ret = btrfs_orphan_add(trans, inode);
+		btrfs_end_transaction(trans, root);
+		if (ret)
+			return ret;
+
 		/* we don't support swapfiles, so vmtruncate shouldn't fail */
 		truncate_setsize(inode, newsize);
 		ret = btrfs_truncate(inode);
+		if (ret && inode->i_nlink)
+			btrfs_orphan_del(NULL, inode);
 	}
 
 	return ret;
@@ -3805,7 +3854,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
 		return err;
 
 	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
-		err = btrfs_setsize(inode, attr->ia_size);
+		err = btrfs_setsize(inode, attr);
 		if (err)
 			return err;
 	}
@@ -5586,10 +5635,13 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
 		return em;
 	if (em) {
 		/*
-		 * if our em maps to a hole, there might
-		 * actually be delalloc bytes behind it
+		 * if our em maps to
+		 * -  a hole or
+		 * -  a pre-alloc extent,
+		 * there might actually be delalloc bytes behind it.
 		 */
-		if (em->block_start != EXTENT_MAP_HOLE)
+		if (em->block_start != EXTENT_MAP_HOLE &&
+		    !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			return em;
 		else
 			hole_em = em;
@@ -5671,6 +5723,8 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
 			 */
 			em->block_start = hole_em->block_start;
 			em->block_len = hole_len;
+			if (test_bit(EXTENT_FLAG_PREALLOC, &hole_em->flags))
+				set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
 		} else {
 			em->start = range_start;
 			em->len = found;
@@ -6929,11 +6983,9 @@ static int btrfs_truncate(struct inode *inode)
 
 	/*
 	 * 1 for the truncate slack space
-	 * 1 for the orphan item we're going to add
-	 * 1 for the orphan item deletion
 	 * 1 for updating the inode.
 	 */
-	trans = btrfs_start_transaction(root, 4);
+	trans = btrfs_start_transaction(root, 2);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
 		goto out;
@@ -6944,12 +6996,6 @@ static int btrfs_truncate(struct inode *inode)
 				      min_size);
 	BUG_ON(ret);
 
-	ret = btrfs_orphan_add(trans, inode);
-	if (ret) {
-		btrfs_end_transaction(trans, root);
-		goto out;
-	}
-
 	/*
 	 * setattr is responsible for setting the ordered_data_close flag,
 	 * but that is only tested during the last file release.  That
@@ -7018,12 +7064,6 @@ static int btrfs_truncate(struct inode *inode)
 		ret = btrfs_orphan_del(trans, inode);
 		if (ret)
 			err = ret;
-	} else if (ret && inode->i_nlink > 0) {
-		/*
-		 * Failed to do the truncate, remove us from the in memory
-		 * orphan list.
-		 */
-		ret = btrfs_orphan_del(NULL, inode);
 	}
 
 	if (trans) {

fs/btrfs/ioctl.c

@@ -1339,6 +1339,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
 			1)) {
 		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
+		mnt_drop_write_file(file);
 		return -EINPROGRESS;
 	}
 
@@ -1362,6 +1363,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		printk(KERN_INFO "btrfs: resizing devid %llu\n",
 		       (unsigned long long)devid);
 	}
+
 	device = btrfs_find_device(root->fs_info, devid, NULL, NULL);
 	if (!device) {
 		printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
@@ -1369,9 +1371,10 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		ret = -EINVAL;
 		goto out_free;
 	}
-	if (device->fs_devices && device->fs_devices->seeding) {
+
+	if (!device->writeable) {
 		printk(KERN_INFO "btrfs: resizer unable to apply on "
-		       "seeding device %llu\n",
+		       "readonly device %llu\n",
 		       (unsigned long long)devid);
 		ret = -EINVAL;
 		goto out_free;
@@ -2095,13 +2098,13 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		err = inode_permission(inode, MAY_WRITE | MAY_EXEC);
 		if (err)
 			goto out_dput;
-
-		/* check if subvolume may be deleted by a non-root user */
-		err = btrfs_may_delete(dir, dentry, 1);
-		if (err)
-			goto out_dput;
 	}
 
+	/* check if subvolume may be deleted by a user */
+	err = btrfs_may_delete(dir, dentry, 1);
+	if (err)
+		goto out_dput;
+
 	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
 		err = -EINVAL;
 		goto out_dput;
@@ -3698,6 +3701,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 		goto drop_write;
 	}
 
+	if (!sa->qgroupid) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);

fs/btrfs/send.c

@@ -1814,8 +1814,10 @@ static int name_cache_insert(struct send_ctx *sctx,
 			(unsigned long)nce->ino);
 	if (!nce_head) {
 		nce_head = kmalloc(sizeof(*nce_head), GFP_NOFS);
-		if (!nce_head)
+		if (!nce_head) {
+			kfree(nce);
 			return -ENOMEM;
+		}
 		INIT_LIST_HEAD(nce_head);
 
 		ret = radix_tree_insert(&sctx->name_cache, nce->ino, nce_head);

fs/btrfs/volumes.c

@@ -1431,7 +1431,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		}
 	} else {
 		ret = btrfs_get_bdev_and_sb(device_path,
-					    FMODE_READ | FMODE_EXCL,
+					    FMODE_WRITE | FMODE_EXCL,
 					    root->fs_info->bdev_holder, 0,
 					    &bdev, &bh);
 		if (ret)