Merge tag 'for-chris' of git://git.kernel.org/pub/scm/linux/kernel/gi…

…t/kdave/linux into for-linus-4.6

Btrfs patchsets for 4.6

Documentation/filesystems/btrfs.txt

@@ -168,10 +168,23 @@ Options with (*) are default options and will not show in the mount options.
   notreelog
 	Enable/disable the tree logging used for fsync and O_SYNC writes.
 
-  recovery
-	Enable autorecovery attempts if a bad tree root is found at mount time.
-	Currently this scans a list of several previous tree roots and tries to
+  nologreplay
+	Disable the log tree replay at mount time to prevent filesystem
+	from getting modified.
+	Must be used with 'ro' mount option.
+	A filesystem mounted with this option cannot transition to a
+	read-write mount via remount,rw - the filesystem must be unmounted
+	and mounted back again if read-write access is desired.
+
+  usebackuproot
+	Enable attempts to use backup tree roots if a bad tree root is found at
+	mount time.
+	Currently this scans a list of 4 previous tree roots and tries to
 	use the first readable.
+	And since the mount option doesn't affect any behavior after mount,
+	it won't be shown in mount info.
+	Prior to 4.6, this was done by 'recovery' option that has been
+	deprecated, but will work.
 
   rescan_uuid_tree
 	Force check and rebuild procedure of the UUID tree. This should not

fs/btrfs/backref.c

@@ -148,8 +148,7 @@ int __init btrfs_prelim_ref_init(void)
 
 void btrfs_prelim_ref_exit(void)
 {
-	if (btrfs_prelim_ref_cache)
-		kmem_cache_destroy(btrfs_prelim_ref_cache);
+	kmem_cache_destroy(btrfs_prelim_ref_cache);
 }
 
 /*
@@ -566,17 +565,14 @@ static void __merge_refs(struct list_head *head, int mode)
 		struct __prelim_ref *pos2 = pos1, *tmp;
 
 		list_for_each_entry_safe_continue(pos2, tmp, head, list) {
-			struct __prelim_ref *xchg, *ref1 = pos1, *ref2 = pos2;
+			struct __prelim_ref *ref1 = pos1, *ref2 = pos2;
 			struct extent_inode_elem *eie;
 
 			if (!ref_for_same_block(ref1, ref2))
 				continue;
 			if (mode == 1) {
-				if (!ref1->parent && ref2->parent) {
-					xchg = ref1;
-					ref1 = ref2;
-					ref2 = xchg;
-				}
+				if (!ref1->parent && ref2->parent)
+					swap(ref1, ref2);
 			} else {
 				if (ref1->parent != ref2->parent)
 					continue;

fs/btrfs/ctree.c

@@ -311,7 +311,7 @@ struct tree_mod_root {
 
 struct tree_mod_elem {
 	struct rb_node node;
-	u64 index;		/* shifted logical */
+	u64 logical;
 	u64 seq;
 	enum mod_log_op op;
 
@@ -435,11 +435,11 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 
 /*
  * key order of the log:
- *       index -> sequence
+ *       node/leaf start address -> sequence
  *
- * the index is the shifted logical of the *new* root node for root replace
- * operations, or the shifted logical of the affected block for all other
- * operations.
+ * The 'start address' is the logical address of the *new* root node
+ * for root replace operations, or the logical address of the affected
+ * block for all other operations.
  *
  * Note: must be called with write lock (tree_mod_log_write_lock).
  */
@@ -460,9 +460,9 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
 	while (*new) {
 		cur = container_of(*new, struct tree_mod_elem, node);
 		parent = *new;
-		if (cur->index < tm->index)
+		if (cur->logical < tm->logical)
 			new = &((*new)->rb_left);
-		else if (cur->index > tm->index)
+		else if (cur->logical > tm->logical)
 			new = &((*new)->rb_right);
 		else if (cur->seq < tm->seq)
 			new = &((*new)->rb_left);
@@ -523,7 +523,7 @@ alloc_tree_mod_elem(struct extent_buffer *eb, int slot,
 	if (!tm)
 		return NULL;
 
-	tm->index = eb->start >> PAGE_CACHE_SHIFT;
+	tm->logical = eb->start;
 	if (op != MOD_LOG_KEY_ADD) {
 		btrfs_node_key(eb, &tm->key, slot);
 		tm->blockptr = btrfs_node_blockptr(eb, slot);
@@ -588,7 +588,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
 		goto free_tms;
 	}
 
-	tm->index = eb->start >> PAGE_CACHE_SHIFT;
+	tm->logical = eb->start;
 	tm->slot = src_slot;
 	tm->move.dst_slot = dst_slot;
 	tm->move.nr_items = nr_items;
@@ -699,7 +699,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
 		goto free_tms;
 	}
 
-	tm->index = new_root->start >> PAGE_CACHE_SHIFT;
+	tm->logical = new_root->start;
 	tm->old_root.logical = old_root->start;
 	tm->old_root.level = btrfs_header_level(old_root);
 	tm->generation = btrfs_header_generation(old_root);
@@ -739,16 +739,15 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq,
 	struct rb_node *node;
 	struct tree_mod_elem *cur = NULL;
 	struct tree_mod_elem *found = NULL;
-	u64 index = start >> PAGE_CACHE_SHIFT;
 
 	tree_mod_log_read_lock(fs_info);
 	tm_root = &fs_info->tree_mod_log;
 	node = tm_root->rb_node;
 	while (node) {
 		cur = container_of(node, struct tree_mod_elem, node);
-		if (cur->index < index) {
+		if (cur->logical < start) {
 			node = node->rb_left;
-		} else if (cur->index > index) {
+		} else if (cur->logical > start) {
 			node = node->rb_right;
 		} else if (cur->seq < min_seq) {
 			node = node->rb_left;
@@ -1230,9 +1229,10 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info,
 		return NULL;
 
 	/*
-	 * the very last operation that's logged for a root is the replacement
-	 * operation (if it is replaced at all). this has the index of the *new*
-	 * root, making it the very first operation that's logged for this root.
+	 * the very last operation that's logged for a root is the
+	 * replacement operation (if it is replaced at all). this has
+	 * the logical address of the *new* root, making it the very
+	 * first operation that's logged for this root.
 	 */
 	while (1) {
 		tm = tree_mod_log_search_oldest(fs_info, root_logical,
@@ -1336,7 +1336,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
 		if (!next)
 			break;
 		tm = container_of(next, struct tree_mod_elem, node);
-		if (tm->index != first_tm->index)
+		if (tm->logical != first_tm->logical)
 			break;
 	}
 	tree_mod_log_read_unlock(fs_info);
@@ -5361,7 +5361,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 		goto out;
 	}
 
-	tmp_buf = kmalloc(left_root->nodesize, GFP_NOFS);
+	tmp_buf = kmalloc(left_root->nodesize, GFP_KERNEL);
 	if (!tmp_buf) {
 		ret = -ENOMEM;
 		goto out;

fs/btrfs/ctree.h

@@ -100,6 +100,9 @@ struct btrfs_ordered_sum;
 /* tracks free space in block groups. */
 #define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL
 
+/* device stats in the device tree */
+#define BTRFS_DEV_STATS_OBJECTID 0ULL
+
 /* for storing balance parameters in the root tree */
 #define BTRFS_BALANCE_OBJECTID -4ULL
 
@@ -1002,8 +1005,10 @@ struct btrfs_dev_replace {
 	pid_t lock_owner;
 	atomic_t nesting_level;
 	struct mutex lock_finishing_cancel_unmount;
-	struct mutex lock_management_lock;
-	struct mutex lock;
+	rwlock_t lock;
+	atomic_t read_locks;
+	atomic_t blocking_readers;
+	wait_queue_head_t read_lock_wq;
 
 	struct btrfs_scrub_progress scrub_progress;
 };
@@ -1822,6 +1827,9 @@ struct btrfs_fs_info {
 	spinlock_t reada_lock;
 	struct radix_tree_root reada_tree;
 
+	/* readahead works cnt */
+	atomic_t reada_works_cnt;
+
 	/* Extent buffer radix tree */
 	spinlock_t buffer_lock;
 	struct radix_tree_root buffer_radix;
@@ -2185,13 +2193,43 @@ struct btrfs_ioctl_defrag_range_args {
  */
 #define BTRFS_QGROUP_RELATION_KEY       246
 
+/*
+ * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY.
+ */
 #define BTRFS_BALANCE_ITEM_KEY	248
 
 /*
- * Persistantly stores the io stats in the device tree.
- * One key for all stats, (0, BTRFS_DEV_STATS_KEY, devid).
+ * The key type for tree items that are stored persistently, but do not need to
+ * exist for extended period of time. The items can exist in any tree.
+ *
+ * [subtype, BTRFS_TEMPORARY_ITEM_KEY, data]
+ *
+ * Existing items:
+ *
+ * - balance status item
+ *   (BTRFS_BALANCE_OBJECTID, BTRFS_TEMPORARY_ITEM_KEY, 0)
  */
-#define BTRFS_DEV_STATS_KEY	249
+#define BTRFS_TEMPORARY_ITEM_KEY	248
+
+/*
+ * Obsolete name, see BTRFS_PERSISTENT_ITEM_KEY
+ */
+#define BTRFS_DEV_STATS_KEY		249
+
+/*
+ * The key type for tree items that are stored persistently and usually exist
+ * for a long period, eg. filesystem lifetime. The item kinds can be status
+ * information, stats or preference values. The item can exist in any tree.
+ *
+ * [subtype, BTRFS_PERSISTENT_ITEM_KEY, data]
+ *
+ * Existing items:
+ *
+ * - device statistics, store IO stats in the device tree, one key for all
+ *   stats
+ *   (BTRFS_DEV_STATS_OBJECTID, BTRFS_DEV_STATS_KEY, 0)
+ */
+#define BTRFS_PERSISTENT_ITEM_KEY	249
 
 /*
  * Persistantly stores the device replace state in the device tree.
@@ -2241,7 +2279,7 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_MOUNT_ENOSPC_DEBUG	 (1 << 15)
 #define BTRFS_MOUNT_AUTO_DEFRAG		(1 << 16)
 #define BTRFS_MOUNT_INODE_MAP_CACHE	(1 << 17)
-#define BTRFS_MOUNT_RECOVERY		(1 << 18)
+#define BTRFS_MOUNT_USEBACKUPROOT	(1 << 18)
 #define BTRFS_MOUNT_SKIP_BALANCE	(1 << 19)
 #define BTRFS_MOUNT_CHECK_INTEGRITY	(1 << 20)
 #define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
@@ -2250,9 +2288,10 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_MOUNT_FRAGMENT_DATA	(1 << 24)
 #define BTRFS_MOUNT_FRAGMENT_METADATA	(1 << 25)
 #define BTRFS_MOUNT_FREE_SPACE_TREE	(1 << 26)
+#define BTRFS_MOUNT_NOLOGREPLAY		(1 << 27)
 
 #define BTRFS_DEFAULT_COMMIT_INTERVAL	(30)
-#define BTRFS_DEFAULT_MAX_INLINE	(8192)
+#define BTRFS_DEFAULT_MAX_INLINE	(2048)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
@@ -2353,6 +2392,9 @@ struct btrfs_map_token {
 	unsigned long offset;
 };
 
+#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
+				((bytes) >> (fs_info)->sb->s_blocksize_bits)
+
 static inline void btrfs_init_map_token (struct btrfs_map_token *token)
 {
 	token->kaddr = NULL;
@@ -3448,8 +3490,7 @@ u64 btrfs_csum_bytes_to_leaves(struct btrfs_root *root, u64 csum_bytes);
 static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root,
 						 unsigned num_items)
 {
-	return (root->nodesize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) *
-		2 * num_items;
+	return root->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
 }
 
 /*
@@ -4027,7 +4068,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct inode *dir, u64 objectid,
 			const char *name, int name_len);
-int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
+int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 			int front);
 int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,
@@ -4089,6 +4130,7 @@ void btrfs_test_inode_set_ops(struct inode *inode);
 
 /* ioctl.c */
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int btrfs_ioctl_get_supported_features(void __user *arg);
 void btrfs_update_iflags(struct inode *inode);
 void btrfs_inherit_iflags(struct inode *inode, struct inode *dir);
 int btrfs_is_empty_uuid(u8 *uuid);
@@ -4151,7 +4193,8 @@ void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info);
 ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
 
 /* super.c */
-int btrfs_parse_options(struct btrfs_root *root, char *options);
+int btrfs_parse_options(struct btrfs_root *root, char *options,
+			unsigned long new_flags);
 int btrfs_sync_fs(struct super_block *sb, int wait);
 
 #ifdef CONFIG_PRINTK
@@ -4525,8 +4568,8 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 			      struct btrfs_key *start, struct btrfs_key *end);
 int btrfs_reada_wait(void *handle);
 void btrfs_reada_detach(void *handle);
-int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
-			 u64 start, int err);
+int btree_readahead_hook(struct btrfs_fs_info *fs_info,
+			 struct extent_buffer *eb, u64 start, int err);
 
 static inline int is_fstree(u64 rootid)
 {

fs/btrfs/delayed-inode.c

@@ -43,8 +43,7 @@ int __init btrfs_delayed_inode_init(void)
 
 void btrfs_delayed_inode_exit(void)
 {
-	if (delayed_node_cache)
-		kmem_cache_destroy(delayed_node_cache);
+	kmem_cache_destroy(delayed_node_cache);
 }
 
 static inline void btrfs_init_delayed_node(

fs/btrfs/delayed-ref.c

@@ -929,14 +929,10 @@ btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
 
 void btrfs_delayed_ref_exit(void)
 {
-	if (btrfs_delayed_ref_head_cachep)
-		kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
-	if (btrfs_delayed_tree_ref_cachep)
-		kmem_cache_destroy(btrfs_delayed_tree_ref_cachep);
-	if (btrfs_delayed_data_ref_cachep)
-		kmem_cache_destroy(btrfs_delayed_data_ref_cachep);
-	if (btrfs_delayed_extent_op_cachep)
-		kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
+	kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
+	kmem_cache_destroy(btrfs_delayed_tree_ref_cachep);
+	kmem_cache_destroy(btrfs_delayed_data_ref_cachep);
+	kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
 }
 
 int btrfs_delayed_ref_init(void)