Merge tag 'for-4.17-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "There are a several user visible changes, the rest is mostly invisible
  and continues to clean up the whole code base.

  User visible changes:
   - new mount option nossd_spread (pair for ssd_spread)

   - mount option subvolid will detect junk after the number and fail
     the mount

   - add message after cancelled device replace

   - direct module dependency on libcrc32, removed own crc wrappers

   - removed user space transaction ioctls

   - use lighter locking when reading /proc/self/mounts, RCU instead of
     mutex to avoid unnecessary contention

  Enhancements:
   - skip writeback of last page when truncating file to same size

   - send: do not issue unnecessary truncate operations

   - mount option token specifiers: use %u for unsigned values, more
     validation

   - selftests: more tree block validations

  qgroups:
   - preparatory work for splitting reservation types for data and
     metadata, this should allow for more accurate tracking and fix some
     issues with underflows or do further enhancements

   - split metadata reservations for started and joined transaction so
     they do not get mixed up and are accounted correctly at commit time

   - with the above, it's possible to revert patch that potentially
     deadlocks when trying to make more space by explicitly committing
     when the quota limit is hit

   - fix root item corruption when multiple same source snapshots are
     created with quota enabled

  RAID56:
   - make sure target is identical to source when raid56 rebuild fails
     after dev-replace

   - faster rebuild during scrub, batch by stripes and not
     block-by-block

   - make more use of cached data when rebuilding from a missing device

  Fixes:
   - null pointer deref when device replace target is missing

   - fix fsync after hole punching when using no-holes feature

   - fix lockdep splat when allocating percpu data with wrong GFP flags

  Cleanups, refactoring, core changes:
   - drop redunant parameters from various functions

   - kill and opencode trivial helpers

   - __cold/__exit function annotations

   - dead code removal

   - continued audit and documentation of memory barriers

   - error handling: handle removal from uuid tree

   - error handling: remove handling of impossible condtitons

   - more debugging or error messages

   - updated tracepoints

   - one VLA use removal (and one still left)"

* tag 'for-4.17-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (164 commits)
  btrfs: lift errors from add_extent_changeset to the callers
  Btrfs: print error messages when failing to read trees
  btrfs: user proper type for btrfs_mask_flags flags
  btrfs: split dev-replace locking helpers for read and write
  btrfs: remove stale comments about fs_mutex
  btrfs: use RCU in btrfs_show_devname for device list traversal
  btrfs: update barrier in should_cow_block
  btrfs: use lockdep_assert_held for mutexes
  btrfs: use lockdep_assert_held for spinlocks
  btrfs: Validate child tree block's level and first key
  btrfs: tests/qgroup: Fix wrong tree backref level
  Btrfs: fix copy_items() return value when logging an inode
  Btrfs: fix fsync after hole punching when using no-holes feature
  btrfs: use helper to set ulist aux from a qgroup
  Revert "btrfs: qgroups: Retry after commit on getting EDQUOT"
  btrfs: qgroup: Update trace events for metadata reservation
  btrfs: qgroup: Use root::qgroup_meta_rsv_* to record qgroup meta reserved space
  btrfs: delayed-inode: Use new qgroup meta rsv for delayed inode and item
  btrfs: qgroup: Use separate meta reservation type for delalloc
  btrfs: qgroup: Introduce function to convert META_PREALLOC into META_PERTRANS
  ...

1 files changed, 50 insertions, 36 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index da308774b8a4..0eb55825862a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -40,6 +40,7 @@
 #include <linux/sizes.h>
 #include <linux/dynamic_debug.h>
 #include <linux/refcount.h>
+#include <linux/crc32c.h>
 #include "extent_io.h"
 #include "extent_map.h"
 #include "async-thread.h"
@@ -65,6 +66,8 @@ struct btrfs_ordered_sum;
 
 #define BTRFS_MAX_LEVEL 8
 
+#define BTRFS_OLDEST_GENERATION	0ULL
+
 #define BTRFS_COMPAT_EXTENT_TREE_V0
 
 /*
@@ -86,9 +89,9 @@ struct btrfs_ordered_sum;
  */
 #define BTRFS_LINK_MAX 65535U
 
+/* four bytes for CRC32 */
 static const int btrfs_csum_sizes[] = { 4 };
 
-/* four bytes for CRC32 */
 #define BTRFS_EMPTY_DIR_SIZE 0
 
 /* ioprio of readahead is set to idle */
@@ -98,6 +101,7 @@ static const int btrfs_csum_sizes[] = { 4 };
 
 #define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
+
 /*
  * Count how many BTRFS_MAX_EXTENT_SIZE cover the @size
  */
@@ -381,8 +385,9 @@ struct btrfs_dev_replace {
 
 /* For raid type sysfs entries */
 struct raid_kobject {
-	int raid_type;
+	u64 flags;
 	struct kobject kobj;
+	struct list_head list;
 };
 
 struct btrfs_space_info {
@@ -707,7 +712,6 @@ struct btrfs_delayed_root;
 #define BTRFS_FS_LOG_RECOVERING			4
 #define BTRFS_FS_OPEN				5
 #define BTRFS_FS_QUOTA_ENABLED			6
-#define BTRFS_FS_QUOTA_ENABLING			7
 #define BTRFS_FS_UPDATE_UUID_TREE_GEN		9
 #define BTRFS_FS_CREATING_FREE_SPACE_TREE	10
 #define BTRFS_FS_BTREE_ERR			11
@@ -788,7 +792,7 @@ struct btrfs_fs_info {
 	unsigned long pending_changes;
 	unsigned long compress_type:4;
 	unsigned int compress_level;
-	int commit_interval;
+	u32 commit_interval;
 	/*
 	 * It is a suggestive number, the read side is safe even it gets a
 	 * wrong number because we will write out the data into a regular
@@ -877,7 +881,6 @@ struct btrfs_fs_info {
 	struct rb_root tree_mod_log;
 
 	atomic_t async_delalloc_pages;
-	atomic_t open_ioctl_trans;
 
 	/*
 	 * this is used to protect the following list -- ordered_roots.
@@ -935,9 +938,11 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *extent_workers;
 	struct task_struct *transaction_kthread;
 	struct task_struct *cleaner_kthread;
-	int thread_pool_size;
+	u32 thread_pool_size;
 
 	struct kobject *space_info_kobj;
+	struct list_head pending_raid_kobjs;
+	spinlock_t pending_raid_kobjs_lock; /* uncontended */
 
 	u64 total_pinned;
 
@@ -952,9 +957,9 @@ struct btrfs_fs_info {
 	struct btrfs_fs_devices *fs_devices;
 
 	/*
-	 * the space_info list is almost entirely read only.  It only changes
-	 * when we add a new raid type to the FS, and that happens
-	 * very rarely.  RCU is used to protect it.
+	 * The space_info list is effectively read only after initial
+	 * setup.  It is populated at mount time and cleaned up after
+	 * all block groups are removed.  RCU is used to protect it.
 	 */
 	struct list_head space_info;
 
@@ -993,8 +998,8 @@ struct btrfs_fs_info {
 	struct btrfs_balance_control *balance_ctl;
 	wait_queue_head_t balance_wait_q;
 
-	unsigned data_chunk_allocations;
-	unsigned metadata_ratio;
+	u32 data_chunk_allocations;
+	u32 metadata_ratio;
 
 	void *bdev_holder;
 
@@ -1260,12 +1265,13 @@ struct btrfs_root {
 	struct btrfs_subvolume_writers *subv_writers;
 	atomic_t will_be_snapshotted;
 
-	/* For qgroup metadata space reserve */
-	atomic64_t qgroup_meta_rsv;
+	/* For qgroup metadata reserved space */
+	spinlock_t qgroup_meta_rsv_lock;
+	u64 qgroup_meta_rsv_pertrans;
+	u64 qgroup_meta_rsv_prealloc;
 };
 
 struct btrfs_file_private {
-	struct btrfs_trans_handle *trans;
 	void *filldir_buf;
 };
 
@@ -2554,6 +2560,20 @@ BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_cursor_right,
 	((unsigned long)(BTRFS_LEAF_DATA_OFFSET + \
 	btrfs_item_offset_nr(leaf, slot)))
 
+static inline u64 btrfs_name_hash(const char *name, int len)
+{
+       return crc32c((u32)~1, name, len);
+}
+
+/*
+ * Figure the key offset of an extended inode ref
+ */
+static inline u64 btrfs_extref_hash(u64 parent_objectid, const char *name,
+                                   int len)
+{
+       return (u64) crc32c(parent_objectid, name, len);
+}
+
 static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info)
 {
 	return ((space_info->flags & BTRFS_BLOCK_GROUP_METADATA) &&
@@ -2608,7 +2628,7 @@ void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
 void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg);
 void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
-			   struct btrfs_fs_info *fs_info, unsigned long count);
+			   unsigned long count);
 int btrfs_async_run_delayed_refs(struct btrfs_fs_info *fs_info,
 				 unsigned long count, u64 transid, int wait);
 int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len);
@@ -2628,7 +2648,6 @@ struct btrfs_block_group_cache *btrfs_lookup_block_group(
 						 u64 bytenr);
 void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
-int get_block_group_index(struct btrfs_block_group_cache *cache);
 struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 					     struct btrfs_root *root,
 					     u64 parent, u64 root_objectid,
@@ -2668,15 +2687,13 @@ int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
 int btrfs_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info,
 				       u64 start, u64 len);
 void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info);
-int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info);
+int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans);
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root,
 			 u64 bytenr, u64 num_bytes, u64 parent,
 			 u64 root_objectid, u64 owner, u64 offset);
 
-int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info);
+int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 				   struct btrfs_fs_info *fs_info);
 int btrfs_setup_space_cache(struct btrfs_trans_handle *trans,
@@ -2688,6 +2705,7 @@ int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr);
 int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info, u64 bytes_used,
 			   u64 type, u64 chunk_offset, u64 size);
+void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info);
 struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 				struct btrfs_fs_info *fs_info,
 				const u64 chunk_offset);
@@ -2697,8 +2715,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
 void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
-void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
-				       struct btrfs_fs_info *fs_info);
+void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
 u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info);
 u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info);
 u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info);
@@ -2730,11 +2747,10 @@ int btrfs_check_data_free_space(struct inode *inode,
 void btrfs_free_reserved_data_space(struct inode *inode,
 			struct extent_changeset *reserved, u64 start, u64 len);
 void btrfs_delalloc_release_space(struct inode *inode,
-			struct extent_changeset *reserved, u64 start, u64 len);
+				  struct extent_changeset *reserved,
+				  u64 start, u64 len, bool qgroup_free);
 void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
 					    u64 len);
-void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info);
 void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
 int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
 				  struct btrfs_inode *inode);
@@ -2745,10 +2761,12 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     u64 *qgroup_reserved, bool use_global_rsv);
 void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
 				      struct btrfs_block_rsv *rsv);
-void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
+void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
+				    bool qgroup_free);
 
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
-void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes);
+void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
+				     bool qgroup_free);
 int btrfs_delalloc_reserve_space(struct inode *inode,
 			struct extent_changeset **reserved, u64 start, u64 len);
 void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
@@ -2792,7 +2810,6 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range);
 int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
 int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
 					 struct btrfs_fs_info *fs_info);
-int __get_raid_index(u64 flags);
 int btrfs_start_write_no_snapshotting(struct btrfs_root *root);
 void btrfs_end_write_no_snapshotting(struct btrfs_root *root);
 void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
@@ -3195,8 +3212,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb);
 void btrfs_destroy_inode(struct inode *inode);
 int btrfs_drop_inode(struct inode *inode);
 int __init btrfs_init_cachep(void);
-void btrfs_destroy_cachep(void);
-long btrfs_ioctl_trans_end(struct file *file);
+void __cold btrfs_destroy_cachep(void);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 			 struct btrfs_root *root, int *was_new);
 struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
@@ -3246,7 +3262,7 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 
 /* file.c */
 int __init btrfs_auto_defrag_init(void);
-void btrfs_auto_defrag_exit(void);
+void __cold btrfs_auto_defrag_exit(void);
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 			   struct btrfs_inode *inode);
 int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info);
@@ -3281,25 +3297,23 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 
 /* sysfs.c */
 int __init btrfs_init_sysfs(void);
-void btrfs_exit_sysfs(void);
+void __cold btrfs_exit_sysfs(void);
 int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info);
 void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info);
 
-/* xattr.c */
-ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
-
 /* super.c */
 int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 			unsigned long new_flags);
 int btrfs_sync_fs(struct super_block *sb, int wait);
 
-static inline __printf(2, 3)
+static inline __printf(2, 3) __cold
 void btrfs_no_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
 {
 }
 
 #ifdef CONFIG_PRINTK
 __printf(2, 3)
+__cold
 void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...);
 #else
 #define btrfs_printk(fs_info, fmt, args...) \