Merge branch 'hotfixes-20111024/josef/for-chris' into btrfs-next-stable

10 files changed, 107 insertions, 48 deletions

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index eb159aa..89b156d 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -59,22 +59,19 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 		if (!value)
 			return ERR_PTR(-ENOMEM);
 		size = __btrfs_getxattr(inode, name, value, size);
-		if (size > 0) {
-			acl = posix_acl_from_xattr(value, size);
-			if (IS_ERR(acl)) {
-				kfree(value);
-				return acl;
-			}
-			set_cached_acl(inode, type, acl);
-		}
-		kfree(value);
+	}
+	if (size > 0) {
+		acl = posix_acl_from_xattr(value, size);
 	} else if (size == -ENOENT || size == -ENODATA || size == 0) {
 		/* FIXME, who returns -ENOENT?  I think nobody */
 		acl = NULL;
-		set_cached_acl(inode, type, acl);
 	} else {
 		acl = ERR_PTR(-EIO);
 	}
+	kfree(value);
+
+	if (!IS_ERR(acl))
+		set_cached_acl(inode, type, acl);
 
 	return acl;
 }
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 011cab3..0fe615e 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -902,9 +902,10 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 
 	orig_ptr = btrfs_node_blockptr(mid, orig_slot);
 
-	if (level < BTRFS_MAX_LEVEL - 1)
+	if (level < BTRFS_MAX_LEVEL - 1) {
 		parent = path->nodes[level + 1];
-	pslot = path->slots[level + 1];
+		pslot = path->slots[level + 1];
+	}
 
 	/*
 	 * deal with the case where there is only one pointer in the root
@@ -1107,9 +1108,10 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
 	mid = path->nodes[level];
 	WARN_ON(btrfs_header_generation(mid) != trans->transid);
 
-	if (level < BTRFS_MAX_LEVEL - 1)
+	if (level < BTRFS_MAX_LEVEL - 1) {
 		parent = path->nodes[level + 1];
-	pslot = path->slots[level + 1];
+		pslot = path->slots[level + 1];
+	}
 
 	if (!parent)
 		return 1;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 4eb7d2b..cef355f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4954,6 +4954,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 	bool failed_cluster_refill = false;
 	bool failed_alloc = false;
 	bool use_cluster = true;
+	bool have_caching_bg = false;
 	u64 ideal_cache_percent = 0;
 	u64 ideal_cache_offset = 0;
 
@@ -5036,6 +5037,7 @@ ideal_cache:
 		}
 	}
 search:
+	have_caching_bg = false;
 	down_read(&space_info->groups_sem);
 	list_for_each_entry(block_group, &space_info->block_groups[index],
 			    list) {
@@ -5244,6 +5246,8 @@ refill_cluster:
 			failed_alloc = true;
 			goto have_block_group;
 		} else if (!offset) {
+			if (!cached)
+				have_caching_bg = true;
 			goto loop;
 		}
 checks:
@@ -5294,6 +5298,9 @@ loop:
 	}
 	up_read(&space_info->groups_sem);
 
+	if (!ins->objectid && loop >= LOOP_CACHING_WAIT && have_caching_bg)
+		goto search;
+
 	if (!ins->objectid && ++index < BTRFS_NR_RAID_TYPES)
 		goto search;
 
@@ -7312,7 +7319,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	inode = lookup_free_space_inode(root, block_group, path);
+	inode = lookup_free_space_inode(tree_root, block_group, path);
 	if (!IS_ERR(inode)) {
 		ret = btrfs_orphan_add(trans, inode);
 		BUG_ON(ret);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 0ada0b7..f284d4e 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1107,7 +1107,7 @@ int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end,
 			struct extent_state **cached_state, gfp_t mask)
 {
 	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_DIRTY | EXTENT_UPTODATE,
+			      EXTENT_DELALLOC | EXTENT_UPTODATE,
 			      0, NULL, cached_state, mask);
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f12747c..65474d9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -393,7 +393,10 @@ again:
 	     (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS))) {
 		WARN_ON(pages);
 		pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
-		BUG_ON(!pages);
+		if (!pages) {
+			/* just bail out to the uncompressed code */
+			goto cont;
+		}
 
 		if (BTRFS_I(inode)->force_compress)
 			compress_type = BTRFS_I(inode)->force_compress;
@@ -424,6 +427,7 @@ again:
 			will_compress = 1;
 		}
 	}
+cont:
 	if (start == 0) {
 		trans = btrfs_join_transaction(root);
 		BUG_ON(IS_ERR(trans));
@@ -5773,8 +5777,7 @@ again:
 	if (test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) {
 		ret = btrfs_ordered_update_i_size(inode, 0, ordered);
 		if (!ret)
-			ret = btrfs_update_inode(trans, root, inode);
-		err = ret;
+			err = btrfs_update_inode(trans, root, inode);
 		goto out;
 	}
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 877727b..33aae13 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -282,6 +282,7 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 	struct fstrim_range range;
 	u64 minlen = ULLONG_MAX;
 	u64 num_devices = 0;
+	u64 total_bytes = btrfs_super_total_bytes(&root->fs_info->super_copy);
 	int ret;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -300,12 +301,15 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 		}
 	}
 	rcu_read_unlock();
+
 	if (!num_devices)
 		return -EOPNOTSUPP;
-
 	if (copy_from_user(&range, arg, sizeof(range)))
 		return -EFAULT;
+	if (range.start > total_bytes)
+		return -EINVAL;
 
+	range.len = min(range.len, total_bytes - range.start);
 	range.minlen = max(range.minlen, minlen);
 	ret = btrfs_trim_fs(root, &range);
 	if (ret < 0)
@@ -765,7 +769,7 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len,
 	int ret = 1;
 
 	/*
-	 * make sure that once we start defragging and extent, we keep on
+	 * make sure that once we start defragging an extent, we keep on
 	 * defragging it
 	 */
 	if (start < *defrag_end)
@@ -810,7 +814,6 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len,
 	 * extent will force at least part of that big extent to be defragged.
 	 */
 	if (ret) {
-		*last_len += len;
 		*defrag_end = extent_map_end(em);
 	} else {
 		*last_len = 0;
@@ -978,18 +981,20 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 	struct btrfs_super_block *disk_super;
 	struct file_ra_state *ra = NULL;
 	unsigned long last_index;
+	u64 isize = i_size_read(inode);
 	u64 features;
 	u64 last_len = 0;
 	u64 skip = 0;
 	u64 defrag_end = 0;
 	u64 newer_off = range->start;
-	int newer_left = 0;
 	unsigned long i;
+	unsigned long ra_index = 0;
 	int ret;
 	int defrag_count = 0;
 	int compress_type = BTRFS_COMPRESS_ZLIB;
 	int extent_thresh = range->extent_thresh;
-	int newer_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
+	int max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
+	int cluster = max_cluster;
 	u64 new_align = ~((u64)128 * 1024 - 1);
 	struct page **pages = NULL;
 
@@ -1003,7 +1008,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 			compress_type = range->compress_type;
 	}
 
-	if (inode->i_size == 0)
+	if (isize == 0)
 		return 0;
 
 	/*
@@ -1019,7 +1024,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 		ra = &file->f_ra;
 	}
 
-	pages = kmalloc(sizeof(struct page *) * newer_cluster,
+	pages = kmalloc(sizeof(struct page *) * max_cluster,
 			GFP_NOFS);
 	if (!pages) {
 		ret = -ENOMEM;
@@ -1028,10 +1033,10 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 
 	/* find the last page to defrag */
 	if (range->start + range->len > range->start) {
-		last_index = min_t(u64, inode->i_size - 1,
+		last_index = min_t(u64, isize - 1,
 			 range->start + range->len - 1) >> PAGE_CACHE_SHIFT;
 	} else {
-		last_index = (inode->i_size - 1) >> PAGE_CACHE_SHIFT;
+		last_index = (isize - 1) >> PAGE_CACHE_SHIFT;
 	}
 
 	if (newer_than) {
@@ -1044,14 +1049,13 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 			 * the extents in the file evenly spaced
 			 */
 			i = (newer_off & new_align) >> PAGE_CACHE_SHIFT;
-			newer_left = newer_cluster;
 		} else
 			goto out_ra;
 	} else {
 		i = range->start >> PAGE_CACHE_SHIFT;
 	}
 	if (!max_to_defrag)
-		max_to_defrag = last_index - 1;
+		max_to_defrag = last_index;
 
 	/*
 	 * make writeback starts from i, so the defrag range can be
@@ -1085,18 +1089,31 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 			i = max(i + 1, next);
 			continue;
 		}
+
+		if (!newer_than) {
+			cluster = (PAGE_CACHE_ALIGN(defrag_end) >>
+				   PAGE_CACHE_SHIFT) - i;
+			cluster = min(cluster, max_cluster);
+		} else {
+			cluster = max_cluster;
+		}
+
 		if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
 			BTRFS_I(inode)->force_compress = compress_type;
 
-		btrfs_force_ra(inode->i_mapping, ra, file, i, newer_cluster);
+		if (i + cluster > ra_index) {
+			ra_index = max(i, ra_index);
+			btrfs_force_ra(inode->i_mapping, ra, file, ra_index,
+				       cluster);
+			ra_index += max_cluster;
+		}
 
-		ret = cluster_pages_for_defrag(inode, pages, i, newer_cluster);
+		ret = cluster_pages_for_defrag(inode, pages, i, cluster);
 		if (ret < 0)
 			goto out_ra;
 
 		defrag_count += ret;
 		balance_dirty_pages_ratelimited_nr(inode->i_mapping, ret);
-		i += ret;
 
 		if (newer_than) {
 			if (newer_off == (u64)-1)
@@ -1111,12 +1128,17 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 			if (!ret) {
 				range->start = newer_off;
 				i = (newer_off & new_align) >> PAGE_CACHE_SHIFT;
-				newer_left = newer_cluster;
 			} else {
 				break;
 			}
 		} else {
-			i++;
+			if (ret > 0) {
+				i += ret;
+				last_len += ret << PAGE_CACHE_SHIFT;
+			} else {
+				i++;
+				last_len = 0;
+			}
 		}
 	}
 
@@ -1149,9 +1171,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 		btrfs_set_super_incompat_flags(disk_super, features);
 	}
 
-	if (!file)
-		kfree(ra);
-	return defrag_count;
+	ret = defrag_count;
 
 out_ra:
 	if (!file)
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index fb2605d..f38e452 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -158,8 +158,7 @@ static void print_extent_ref_v0(struct extent_buffer *eb, int slot)
 void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 {
 	int i;
-	u32 type;
-	u32 nr = btrfs_header_nritems(l);
+	u32 type, nr;
 	struct btrfs_item *item;
 	struct btrfs_root_item *ri;
 	struct btrfs_dir_item *di;
@@ -172,6 +171,11 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 	struct btrfs_key key;
 	struct btrfs_key found_key;
 
+	if (!l)
+		return;
+
+	nr = btrfs_header_nritems(l);
+
 	printk(KERN_INFO "leaf %llu total ptrs %d free space %d\n",
 		(unsigned long long)btrfs_header_bytenr(l), nr,
 		btrfs_leaf_free_space(root, l));
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 10af6a0..24d654c 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3322,8 +3322,11 @@ static int find_data_references(struct reloc_control *rc,
 	}
 
 	key.objectid = ref_objectid;
-	key.offset = ref_offset;
 	key.type = BTRFS_EXTENT_DATA_KEY;
+	if (ref_offset > ((u64)-1 << 32))
+		key.offset = 0;
+	else
+		key.offset = ref_offset;
 
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 266d1f3..5429b1f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -419,7 +419,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 		u64 *subvol_rootid, struct btrfs_fs_devices **fs_devices)
 {
 	substring_t args[MAX_OPT_ARGS];
-	char *opts, *orig, *p;
+	char *device_name, *opts, *orig, *p;
 	int error = 0;
 	int intarg;
 
@@ -470,8 +470,14 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 			}
 			break;
 		case Opt_device:
-			error = btrfs_scan_one_device(match_strdup(&args[0]),
+			device_name = match_strdup(&args[0]);
+			if (!device_name) {
+				error = -ENOMEM;
+				goto out;
+			}
+			error = btrfs_scan_one_device(device_name,
 					flags, holder, fs_devices);
+			kfree(device_name);
 			if (error)
 				goto out;
 			break;
@@ -735,6 +741,16 @@ static int btrfs_set_super(struct super_block *s, void *data)
 }
 
 /*
+ * subvolumes are identified by ino 256
+ */
+static inline int is_subvolume_inode(struct inode *inode)
+{
+	if (inode && inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)
+		return 1;
+	return 0;
+}
+
+/*
  * This will strip out the subvol=%s argument for an argument string and add
  * subvolid=0 to make sure we get the actual tree root for path walking to the
  * subvol we want.
@@ -837,6 +853,15 @@ static struct dentry *mount_subvol(const char *subvol_name, int flags,
 	if (error)
 		return ERR_PTR(error);
 
+	if (!is_subvolume_inode(path.dentry->d_inode)) {
+		path_put(&path);
+		mntput(mnt);
+		error = -EINVAL;
+		printk(KERN_ERR "btrfs: '%s' is not a valid subvolume\n",
+				subvol_name);
+		return ERR_PTR(-EINVAL);
+	}
+
 	/* Get a ref to the sb and the dentry we found and return it */
 	s = path.mnt->mnt_sb;
 	atomic_inc(&s->s_active);
@@ -933,6 +958,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 
 		s->s_flags = flags | MS_NOSEC;
 		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
+		btrfs_sb(s)->fs_info->bdev_holder = fs_type;
 		error = btrfs_fill_super(s, fs_devices, data,
 					 flags & MS_SILENT ? 1 : 0);
 		if (error) {
@@ -940,7 +966,6 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 			return ERR_PTR(error);
 		}
 
-		btrfs_sb(s)->fs_info->bdev_holder = fs_type;
 		s->s_flags |= MS_ACTIVE;
 	}
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index e138af7..c6938b4 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -597,10 +597,8 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		set_blocksize(bdev, 4096);
 
 		bh = btrfs_read_dev_super(bdev);
-		if (!bh) {
-			ret = -EINVAL;
+		if (!bh)
 			goto error_close;
-		}
 
 		disk_super = (struct btrfs_super_block *)bh->b_data;
 		devid = btrfs_stack_device_id(&disk_super->dev_item);
@@ -655,7 +653,7 @@ error:
 		continue;
 	}
 	if (fs_devices->open_devices == 0) {
-		ret = -EIO;
+		ret = -EINVAL;
 		goto out;
 	}
 	fs_devices->seeding = seeding;