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

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
  Btrfs: set i_size properly when fallocating and we already
  btrfs: unlock on error in btrfs_file_llseek()
  btrfs: btrfs_permission's RO check shouldn't apply to device nodes
  Btrfs: truncate pages from clone ioctl target range
  Btrfs: fix uninitialized sync_pending
  Btrfs: fix wrong free space information
  btrfs: memory leak in btrfs_add_inode_defrag()
  Btrfs: use plain page_address() in header fields setget functions
  Btrfs: forced readonly when btrfs_drop_snapshot() fails
  Btrfs: check if there is enough space for balancing smarter
  Btrfs: fix a bug of balance on full multi-disk partitions
  Btrfs: fix an oops of log replay
  Btrfs: detect wether a device supports discard
  Btrfs: force unplugs when switching from high to regular priority bios

9 files changed, 183 insertions, 43 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0469263e327..03912c5c6f4 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1415,17 +1415,15 @@ void btrfs_set_##name(struct extent_buffer *eb, type *s, u##bits val);
 #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits)		\
 static inline u##bits btrfs_##name(struct extent_buffer *eb)		\
 {									\
-	type *p = kmap_atomic(eb->first_page, KM_USER0);		\
+	type *p = page_address(eb->first_page);				\
 	u##bits res = le##bits##_to_cpu(p->member);			\
-	kunmap_atomic(p, KM_USER0);					\
 	return res;							\
 }									\
 static inline void btrfs_set_##name(struct extent_buffer *eb,		\
 				    u##bits val)			\
 {									\
-	type *p = kmap_atomic(eb->first_page, KM_USER0);		\
+	type *p = page_address(eb->first_page);				\
 	p->member = cpu_to_le##bits(val);				\
-	kunmap_atomic(p, KM_USER0);					\
 }
 
 #define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits)		\
@@ -2367,8 +2365,8 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans,
 int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path);
 int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
 int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf);
-int btrfs_drop_snapshot(struct btrfs_root *root,
-			struct btrfs_block_rsv *block_rsv, int update_ref);
+void btrfs_drop_snapshot(struct btrfs_root *root,
+			 struct btrfs_block_rsv *block_rsv, int update_ref);
 int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct extent_buffer *node,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 66bac226944..80d6148f60a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1782,6 +1782,9 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 
 
 		for (i = 0; i < multi->num_stripes; i++, stripe++) {
+			if (!stripe->dev->can_discard)
+				continue;
+
 			ret = btrfs_issue_discard(stripe->dev->bdev,
 						  stripe->physical,
 						  stripe->length);
@@ -1789,11 +1792,16 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 				discarded_bytes += stripe->length;
 			else if (ret != -EOPNOTSUPP)
 				break;
+
+			/*
+			 * Just in case we get back EOPNOTSUPP for some reason,
+			 * just ignore the return value so we don't screw up
+			 * people calling discard_extent.
+			 */
+			ret = 0;
 		}
 		kfree(multi);
 	}
-	if (discarded_bytes && ret == -EOPNOTSUPP)
-		ret = 0;
 
 	if (actual_bytes)
 		*actual_bytes = discarded_bytes;
@@ -6269,8 +6277,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
  * also make sure backrefs for the shared block and all lower level
  * blocks are properly updated.
  */
-int btrfs_drop_snapshot(struct btrfs_root *root,
-			struct btrfs_block_rsv *block_rsv, int update_ref)
+void btrfs_drop_snapshot(struct btrfs_root *root,
+			 struct btrfs_block_rsv *block_rsv, int update_ref)
 {
 	struct btrfs_path *path;
 	struct btrfs_trans_handle *trans;
@@ -6283,13 +6291,16 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	int level;
 
 	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
+	if (!path) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	wc = kzalloc(sizeof(*wc), GFP_NOFS);
 	if (!wc) {
 		btrfs_free_path(path);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto out;
 	}
 
 	trans = btrfs_start_transaction(tree_root, 0);
@@ -6318,7 +6329,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		path->lowest_level = 0;
 		if (ret < 0) {
 			err = ret;
-			goto out;
+			goto out_free;
 		}
 		WARN_ON(ret > 0);
 
@@ -6425,11 +6436,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		free_extent_buffer(root->commit_root);
 		kfree(root);
 	}
-out:
+out_free:
 	btrfs_end_transaction_throttle(trans, tree_root);
 	kfree(wc);
 	btrfs_free_path(path);
-	return err;
+out:
+	if (err)
+		btrfs_std_error(root->fs_info, err);
+	return;
 }
 
 /*
@@ -6720,6 +6734,10 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	struct btrfs_space_info *space_info;
 	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
 	struct btrfs_device *device;
+	u64 min_free;
+	int index;
+	int dev_nr = 0;
+	int dev_min = 1;
 	int full = 0;
 	int ret = 0;
 
@@ -6729,8 +6747,10 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	if (!block_group)
 		return -1;
 
+	min_free = btrfs_block_group_used(&block_group->item);
+
 	/* no bytes used, we're good */
-	if (!btrfs_block_group_used(&block_group->item))
+	if (!min_free)
 		goto out;
 
 	space_info = block_group->space_info;
@@ -6746,10 +6766,9 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	 * all of the extents from this block group.  If we can, we're good
 	 */
 	if ((space_info->total_bytes != block_group->key.offset) &&
-	   (space_info->bytes_used + space_info->bytes_reserved +
-	    space_info->bytes_pinned + space_info->bytes_readonly +
-	    btrfs_block_group_used(&block_group->item) <
-	    space_info->total_bytes)) {
+	    (space_info->bytes_used + space_info->bytes_reserved +
+	     space_info->bytes_pinned + space_info->bytes_readonly +
+	     min_free < space_info->total_bytes)) {
 		spin_unlock(&space_info->lock);
 		goto out;
 	}
@@ -6766,9 +6785,29 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	if (full)
 		goto out;
 
+	/*
+	 * index:
+	 *      0: raid10
+	 *      1: raid1
+	 *      2: dup
+	 *      3: raid0
+	 *      4: single
+	 */
+	index = get_block_group_index(block_group);
+	if (index == 0) {
+		dev_min = 4;
+		min_free /= 2;
+	} else if (index == 1) {
+		dev_min = 2;
+	} else if (index == 2) {
+		min_free *= 2;
+	} else if (index == 3) {
+		dev_min = fs_devices->rw_devices;
+		min_free /= dev_min;
+	}
+
 	mutex_lock(&root->fs_info->chunk_mutex);
 	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
-		u64 min_free = btrfs_block_group_used(&block_group->item);
 		u64 dev_offset;
 
 		/*
@@ -6779,7 +6818,11 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 			ret = find_free_dev_extent(NULL, device, min_free,
 						   &dev_offset, NULL);
 			if (!ret)
+				dev_nr++;
+
+			if (dev_nr >= dev_min)
 				break;
+
 			ret = -1;
 		}
 	}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 658d66959ab..e7872e485f1 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -150,6 +150,8 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 	spin_lock(&root->fs_info->defrag_inodes_lock);
 	if (!BTRFS_I(inode)->in_defrag)
 		__btrfs_add_inode_defrag(inode, defrag);
+	else
+		kfree(defrag);
 	spin_unlock(&root->fs_info->defrag_inodes_lock);
 	return 0;
 }
@@ -1638,11 +1640,15 @@ static long btrfs_fallocate(struct file *file, int mode,
 
 	cur_offset = alloc_start;
 	while (1) {
+		u64 actual_end;
+
 		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
 				      alloc_end - cur_offset, 0);
 		BUG_ON(IS_ERR_OR_NULL(em));
 		last_byte = min(extent_map_end(em), alloc_end);
+		actual_end = min_t(u64, extent_map_end(em), offset + len);
 		last_byte = (last_byte + mask) & ~mask;
+
 		if (em->block_start == EXTENT_MAP_HOLE ||
 		    (cur_offset >= inode->i_size &&
 		     !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
@@ -1655,6 +1661,16 @@ static long btrfs_fallocate(struct file *file, int mode,
 				free_extent_map(em);
 				break;
 			}
+		} else if (actual_end > inode->i_size &&
+			   !(mode & FALLOC_FL_KEEP_SIZE)) {
+			/*
+			 * We didn't need to allocate any more space, but we
+			 * still extended the size of the file so we need to
+			 * update i_size.
+			 */
+			inode->i_ctime = CURRENT_TIME;
+			i_size_write(inode, actual_end);
+			btrfs_ordered_update_i_size(inode, actual_end, NULL);
 		}
 		free_extent_map(em);
 
@@ -1804,10 +1820,14 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
 		}
 	}
 
-	if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
-		return -EINVAL;
-	if (offset > inode->i_sb->s_maxbytes)
-		return -EINVAL;
+	if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) {
+		ret = -EINVAL;
+		goto out;
+	}
+	if (offset > inode->i_sb->s_maxbytes) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	/* Special lock needed here? */
 	if (offset != file->f_pos) {
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 6377713f639..6a265b9f85f 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1168,9 +1168,9 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
 		div64_u64(extent_bytes, (sizeof(struct btrfs_free_space)));
 }
 
-static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
-			      struct btrfs_free_space *info, u64 offset,
-			      u64 bytes)
+static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
+				       struct btrfs_free_space *info,
+				       u64 offset, u64 bytes)
 {
 	unsigned long start, count;
 
@@ -1181,6 +1181,13 @@ static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
 	bitmap_clear(info->bitmap, start, count);
 
 	info->bytes -= bytes;
+}
+
+static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
+			      struct btrfs_free_space *info, u64 offset,
+			      u64 bytes)
+{
+	__bitmap_clear_bits(ctl, info, offset, bytes);
 	ctl->free_space -= bytes;
 }
 
@@ -1984,7 +1991,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
 		return 0;
 
 	ret = search_start;
-	bitmap_clear_bits(ctl, entry, ret, bytes);
+	__bitmap_clear_bits(ctl, entry, ret, bytes);
 
 	return ret;
 }
@@ -2039,7 +2046,6 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 				continue;
 			}
 		} else {
-
 			ret = entry->offset;
 
 			entry->offset += bytes;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 15fceefbca0..0ccc7438ad3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7354,11 +7354,15 @@ static int btrfs_set_page_dirty(struct page *page)
 static int btrfs_permission(struct inode *inode, int mask)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
+	umode_t mode = inode->i_mode;
 
-	if (btrfs_root_readonly(root) && (mask & MAY_WRITE))
-		return -EROFS;
-	if ((BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) && (mask & MAY_WRITE))
-		return -EACCES;
+	if (mask & MAY_WRITE &&
+	    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {
+		if (btrfs_root_readonly(root))
+			return -EROFS;
+		if (BTRFS_I(inode)->flags & BTRFS_INODE_READONLY)
+			return -EACCES;
+	}
 	return generic_permission(inode, mask);
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 7cf01334994..970977aab22 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2236,6 +2236,10 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 		btrfs_wait_ordered_range(src, off, len);
 	}
 
+	/* truncate page cache pages from target inode range */
+	truncate_inode_pages_range(&inode->i_data, off,
+				   ALIGN(off + len, PAGE_CACHE_SIZE) - 1);
+
 	/* clone data */
 	key.objectid = btrfs_ino(src);
 	key.type = BTRFS_EXTENT_DATA_KEY;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index babee65f8ed..786639fca06 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -799,14 +799,15 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				  struct extent_buffer *eb, int slot,
 				  struct btrfs_key *key)
 {
-	struct inode *dir;
-	int ret;
 	struct btrfs_inode_ref *ref;
+	struct btrfs_dir_item *di;
+	struct inode *dir;
 	struct inode *inode;
-	char *name;
-	int namelen;
 	unsigned long ref_ptr;
 	unsigned long ref_end;
+	char *name;
+	int namelen;
+	int ret;
 	int search_done = 0;
 
 	/*
@@ -909,6 +910,25 @@ again:
 	}
 	btrfs_release_path(path);
 
+	/* look for a conflicting sequence number */
+	di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir),
+					 btrfs_inode_ref_index(eb, ref),
+					 name, namelen, 0);
+	if (di && !IS_ERR(di)) {
+		ret = drop_one_dir_item(trans, root, path, dir, di);
+		BUG_ON(ret);
+	}
+	btrfs_release_path(path);
+
+	/* look for a conflicing name */
+	di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir),
+				   name, namelen, 0);
+	if (di && !IS_ERR(di)) {
+		ret = drop_one_dir_item(trans, root, path, dir, di);
+		BUG_ON(ret);
+	}
+	btrfs_release_path(path);
+
 insert:
 	/* insert our name */
 	ret = btrfs_add_link(trans, dir, inode, name, namelen, 0,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 53875ae73ad..f2a4cc79da6 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -142,6 +142,7 @@ static noinline int run_scheduled_bios(struct btrfs_device *device)
 	unsigned long limit;
 	unsigned long last_waited = 0;
 	int force_reg = 0;
+	int sync_pending = 0;
 	struct blk_plug plug;
 
 	/*
@@ -229,6 +230,22 @@ loop_lock:
 
 		BUG_ON(atomic_read(&cur->bi_cnt) == 0);
 
+		/*
+		 * if we're doing the sync list, record that our
+		 * plug has some sync requests on it
+		 *
+		 * If we're doing the regular list and there are
+		 * sync requests sitting around, unplug before
+		 * we add more
+		 */
+		if (pending_bios == &device->pending_sync_bios) {
+			sync_pending = 1;
+		} else if (sync_pending) {
+			blk_finish_plug(&plug);
+			blk_start_plug(&plug);
+			sync_pending = 0;
+		}
+
 		submit_bio(cur->bi_rw, cur);
 		num_run++;
 		batch_run++;
@@ -500,6 +517,9 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 			fs_devices->rw_devices--;
 		}
 
+		if (device->can_discard)
+			fs_devices->num_can_discard--;
+
 		new_device = kmalloc(sizeof(*new_device), GFP_NOFS);
 		BUG_ON(!new_device);
 		memcpy(new_device, device, sizeof(*new_device));
@@ -508,6 +528,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 		new_device->bdev = NULL;
 		new_device->writeable = 0;
 		new_device->in_fs_metadata = 0;
+		new_device->can_discard = 0;
 		list_replace_rcu(&device->dev_list, &new_device->dev_list);
 
 		call_rcu(&device->rcu, free_device);
@@ -547,6 +568,7 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 				fmode_t flags, void *holder)
 {
+	struct request_queue *q;
 	struct block_device *bdev;
 	struct list_head *head = &fs_devices->devices;
 	struct btrfs_device *device;
@@ -603,6 +625,12 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 			seeding = 0;
 		}
 
+		q = bdev_get_queue(bdev);
+		if (blk_queue_discard(q)) {
+			device->can_discard = 1;
+			fs_devices->num_can_discard++;
+		}
+
 		device->bdev = bdev;
 		device->in_fs_metadata = 0;
 		device->mode = flags;
@@ -835,6 +863,7 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
 
 	max_hole_start = search_start;
 	max_hole_size = 0;
+	hole_size = 0;
 
 	if (search_start >= search_end) {
 		ret = -ENOSPC;
@@ -917,7 +946,14 @@ next:
 		cond_resched();
 	}
 
-	hole_size = search_end- search_start;
+	/*
+	 * At this point, search_start should be the end of
+	 * allocated dev extents, and when shrinking the device,
+	 * search_end may be smaller than search_start.
+	 */
+	if (search_end > search_start)
+		hole_size = search_end - search_start;
+
 	if (hole_size > max_hole_size) {
 		max_hole_start = search_start;
 		max_hole_size = hole_size;
@@ -1543,6 +1579,7 @@ error:
 
 int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 {
+	struct request_queue *q;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
 	struct block_device *bdev;
@@ -1612,6 +1649,9 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 
 	lock_chunks(root);
 
+	q = bdev_get_queue(bdev);
+	if (blk_queue_discard(q))
+		device->can_discard = 1;
 	device->writeable = 1;
 	device->work.func = pending_bios_fn;
 	generate_random_uuid(device->uuid);
@@ -1647,6 +1687,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	root->fs_info->fs_devices->num_devices++;
 	root->fs_info->fs_devices->open_devices++;
 	root->fs_info->fs_devices->rw_devices++;
+	if (device->can_discard)
+		root->fs_info->fs_devices->num_can_discard++;
 	root->fs_info->fs_devices->total_rw_bytes += device->total_bytes;
 
 	if (!blk_queue_nonrot(bdev_get_queue(bdev)))
@@ -2413,9 +2455,10 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 			total_avail = device->total_bytes - device->bytes_used;
 		else
 			total_avail = 0;
-		/* avail is off by max(alloc_start, 1MB), but that is the same
-		 * for all devices, so it doesn't hurt the sorting later on
-		 */
+
+		/* If there is no space on this device, skip it. */
+		if (total_avail == 0)
+			continue;
 
 		ret = find_free_dev_extent(trans, device,
 					   max_stripe_size * dev_stripes,
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 7c12d61ae7a..6d866db4e17 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -48,6 +48,7 @@ struct btrfs_device {
 	int writeable;
 	int in_fs_metadata;
 	int missing;
+	int can_discard;
 
 	spinlock_t io_lock;
 
@@ -104,6 +105,7 @@ struct btrfs_fs_devices {
 	u64 rw_devices;
 	u64 missing_devices;
 	u64 total_rw_bytes;
+	u64 num_can_discard;
 	struct block_device *latest_bdev;
 
 	/* all of the devices in the FS, protected by a mutex