Merge tag 'for-5.5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "User visible changes:
   - new block group profiles: RAID1 with 3- and 4- copies
       - RAID1 in btrfs has always 2 copies, now add support for 3 and 4
       - this is an incompat feature (named RAID1C34)
       - recommended use of RAID1C3 is replacement of RAID6 profile on
         metadata, this brings a more reliable resiliency against 2
         device loss/damage

   - support for new checksums
       - per-filesystem, set at mkfs time
       - fast hash (crc32c successor): xxhash, 64bit digest
       - strong hashes (both 256bit): sha256 (slower, FIPS), blake2b
         (faster)
       - the blake2b module goes via the crypto tree, btrfs.ko has a
         soft dependency

   - speed up lseek, don't take inode locks unnecessarily, this can
     speed up parallel SEEK_CUR/SEEK_SET/SEEK_END by 80%

   - send:
       - allow clone operations within the same file
       - limit maximum number of sent clone references to avoid slow
         backref walking

   - error message improvements: device scan prints process name and PID

  Core changes:
   - cleanups
       - remove unique workqueue helpers, used to provide a way to avoid
         deadlocks in the workqueue code, now done in a simpler way
       - remove lots of indirect function calls in compression code
       - extent IO tree code moved out of extent_io.c
       - cleanup backup superblock handling at mount time
       - transaction life cycle documentation and cleanups
       - locking code cleanups, annotations and documentation
       - add more cold, const, pure function attributes
       - removal of unused or redundant struct members or variables

   - new tree-checker sanity tests
       - try to detect missing INODE_ITEM, cross-reference checks of
         DIR_ITEM, DIR_INDEX, INODE_REF, and XATTR_* items

   - remove own bio scheduling code (used to avoid checksum submissions
     being stuck behind other IO), replaced by cgroup controller-based
     code to allow better control and avoid priority inversions in cases
     where the custom and cgroup scheduling disagreed

  Fixes:
   - avoid getting stuck during cyclic writebacks

   - fix trimming of ranges crossing block group boundaries

   - fix rename exchange on subvolumes, all involved subvolumes need to
     be recorded in the transaction"

* tag 'for-5.5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (137 commits)
  btrfs: drop bdev argument from submit_extent_page
  btrfs: remove extent_map::bdev
  btrfs: drop bio_set_dev where not needed
  btrfs: get bdev directly from fs_devices in submit_extent_page
  btrfs: record all roots for rename exchange on a subvol
  Btrfs: fix block group remaining RO forever after error during device replace
  btrfs: scrub: Don't check free space before marking a block group RO
  btrfs: change btrfs_fs_devices::rotating to bool
  btrfs: change btrfs_fs_devices::seeding to bool
  btrfs: rename btrfs_block_group_cache
  btrfs: block-group: Reuse the item key from caller of read_one_block_group()
  btrfs: block-group: Refactor btrfs_read_block_groups()
  btrfs: document extent buffer locking
  btrfs: access eb::blocking_writers according to ACCESS_ONCE policies
  btrfs: set blocking_writers directly, no increment or decrement
  btrfs: merge blocking_writers branches in btrfs_tree_read_lock
  btrfs: drop incompat bit for raid1c34 after last block group is gone
  btrfs: add incompat for raid1 with 3, 4 copies
  btrfs: add support for 4-copy replication (raid1c4)
  btrfs: add support for 3-copy replication (raid1c3)
  ...

fs/btrfs/Kconfig

@@ -5,6 +5,8 @@ config BTRFS_FS
 	select CRYPTO
 	select CRYPTO_CRC32C
 	select LIBCRC32C
+	select CRYPTO_XXHASH
+	select CRYPTO_SHA256
 	select ZLIB_INFLATE
 	select ZLIB_DEFLATE
 	select LZO_COMPRESS

fs/btrfs/async-thread.c

@@ -53,24 +53,12 @@ struct btrfs_workqueue {
 	struct __btrfs_workqueue *high;
 };
 
-static void normal_work_helper(struct btrfs_work *work);
-
-#define BTRFS_WORK_HELPER(name)					\
-noinline_for_stack void btrfs_##name(struct work_struct *arg)		\
-{									\
-	struct btrfs_work *work = container_of(arg, struct btrfs_work,	\
-					       normal_work);		\
-	normal_work_helper(work);					\
-}
-
-struct btrfs_fs_info *
-btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
+struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
 {
 	return wq->fs_info;
 }
 
-struct btrfs_fs_info *
-btrfs_work_owner(const struct btrfs_work *work)
+struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work)
 {
 	return work->wq->fs_info;
 }
@@ -89,29 +77,6 @@ bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq)
 	return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2;
 }
 
-BTRFS_WORK_HELPER(worker_helper);
-BTRFS_WORK_HELPER(delalloc_helper);
-BTRFS_WORK_HELPER(flush_delalloc_helper);
-BTRFS_WORK_HELPER(cache_helper);
-BTRFS_WORK_HELPER(submit_helper);
-BTRFS_WORK_HELPER(fixup_helper);
-BTRFS_WORK_HELPER(endio_helper);
-BTRFS_WORK_HELPER(endio_meta_helper);
-BTRFS_WORK_HELPER(endio_meta_write_helper);
-BTRFS_WORK_HELPER(endio_raid56_helper);
-BTRFS_WORK_HELPER(endio_repair_helper);
-BTRFS_WORK_HELPER(rmw_helper);
-BTRFS_WORK_HELPER(endio_write_helper);
-BTRFS_WORK_HELPER(freespace_write_helper);
-BTRFS_WORK_HELPER(delayed_meta_helper);
-BTRFS_WORK_HELPER(readahead_helper);
-BTRFS_WORK_HELPER(qgroup_rescan_helper);
-BTRFS_WORK_HELPER(extent_refs_helper);
-BTRFS_WORK_HELPER(scrub_helper);
-BTRFS_WORK_HELPER(scrubwrc_helper);
-BTRFS_WORK_HELPER(scrubnc_helper);
-BTRFS_WORK_HELPER(scrubparity_helper);
-
 static struct __btrfs_workqueue *
 __btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name,
 			unsigned int flags, int limit_active, int thresh)
@@ -252,16 +217,16 @@ static inline void thresh_exec_hook(struct __btrfs_workqueue *wq)
 	}
 }
 
-static void run_ordered_work(struct __btrfs_workqueue *wq)
+static void run_ordered_work(struct __btrfs_workqueue *wq,
+			     struct btrfs_work *self)
 {
 	struct list_head *list = &wq->ordered_list;
 	struct btrfs_work *work;
 	spinlock_t *lock = &wq->list_lock;
 	unsigned long flags;
+	bool free_self = false;
 
 	while (1) {
-		void *wtag;
-
 		spin_lock_irqsave(lock, flags);
 		if (list_empty(list))
 			break;
@@ -287,22 +252,53 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
 		list_del(&work->ordered_list);
 		spin_unlock_irqrestore(lock, flags);
 
-		/*
-		 * We don't want to call the ordered free functions with the
-		 * lock held though. Save the work as tag for the trace event,
-		 * because the callback could free the structure.
-		 */
-		wtag = work;
-		work->ordered_free(work);
-		trace_btrfs_all_work_done(wq->fs_info, wtag);
+		if (work == self) {
+			/*
+			 * This is the work item that the worker is currently
+			 * executing.
+			 *
+			 * The kernel workqueue code guarantees non-reentrancy
+			 * of work items. I.e., if a work item with the same
+			 * address and work function is queued twice, the second
+			 * execution is blocked until the first one finishes. A
+			 * work item may be freed and recycled with the same
+			 * work function; the workqueue code assumes that the
+			 * original work item cannot depend on the recycled work
+			 * item in that case (see find_worker_executing_work()).
+			 *
+			 * Note that different types of Btrfs work can depend on
+			 * each other, and one type of work on one Btrfs
+			 * filesystem may even depend on the same type of work
+			 * on another Btrfs filesystem via, e.g., a loop device.
+			 * Therefore, we must not allow the current work item to
+			 * be recycled until we are really done, otherwise we
+			 * break the above assumption and can deadlock.
+			 */
+			free_self = true;
+		} else {
+			/*
+			 * We don't want to call the ordered free functions with
+			 * the lock held.
+			 */
+			work->ordered_free(work);
+			/* NB: work must not be dereferenced past this point. */
+			trace_btrfs_all_work_done(wq->fs_info, work);
+		}
 	}
 	spin_unlock_irqrestore(lock, flags);
+
+	if (free_self) {
+		self->ordered_free(self);
+		/* NB: self must not be dereferenced past this point. */
+		trace_btrfs_all_work_done(wq->fs_info, self);
+	}
 }
 
-static void normal_work_helper(struct btrfs_work *work)
+static void btrfs_work_helper(struct work_struct *normal_work)
 {
+	struct btrfs_work *work = container_of(normal_work, struct btrfs_work,
+					       normal_work);
 	struct __btrfs_workqueue *wq;
-	void *wtag;
 	int need_order = 0;
 
 	/*
@@ -316,29 +312,26 @@ static void normal_work_helper(struct btrfs_work *work)
 	if (work->ordered_func)
 		need_order = 1;
 	wq = work->wq;
-	/* Safe for tracepoints in case work gets freed by the callback */
-	wtag = work;
 
 	trace_btrfs_work_sched(work);
 	thresh_exec_hook(wq);
 	work->func(work);
 	if (need_order) {
 		set_bit(WORK_DONE_BIT, &work->flags);
-		run_ordered_work(wq);
+		run_ordered_work(wq, work);
+	} else {
+		/* NB: work must not be dereferenced past this point. */
+		trace_btrfs_all_work_done(wq->fs_info, work);
 	}
-	if (!need_order)
-		trace_btrfs_all_work_done(wq->fs_info, wtag);
 }
 
-void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
-		     btrfs_func_t func,
-		     btrfs_func_t ordered_func,
-		     btrfs_func_t ordered_free)
+void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
+		     btrfs_func_t ordered_func, btrfs_func_t ordered_free)
 {
 	work->func = func;
 	work->ordered_func = ordered_func;
 	work->ordered_free = ordered_free;
-	INIT_WORK(&work->normal_work, uniq_func);
+	INIT_WORK(&work->normal_work, btrfs_work_helper);
 	INIT_LIST_HEAD(&work->ordered_list);
 	work->flags = 0;
 }

fs/btrfs/async-thread.h

@@ -29,49 +29,20 @@ struct btrfs_work {
 	unsigned long flags;
 };
 
-#define BTRFS_WORK_HELPER_PROTO(name)					\
-void btrfs_##name(struct work_struct *arg)
-
-BTRFS_WORK_HELPER_PROTO(worker_helper);
-BTRFS_WORK_HELPER_PROTO(delalloc_helper);
-BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper);
-BTRFS_WORK_HELPER_PROTO(cache_helper);
-BTRFS_WORK_HELPER_PROTO(submit_helper);
-BTRFS_WORK_HELPER_PROTO(fixup_helper);
-BTRFS_WORK_HELPER_PROTO(endio_helper);
-BTRFS_WORK_HELPER_PROTO(endio_meta_helper);
-BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper);
-BTRFS_WORK_HELPER_PROTO(endio_raid56_helper);
-BTRFS_WORK_HELPER_PROTO(endio_repair_helper);
-BTRFS_WORK_HELPER_PROTO(rmw_helper);
-BTRFS_WORK_HELPER_PROTO(endio_write_helper);
-BTRFS_WORK_HELPER_PROTO(freespace_write_helper);
-BTRFS_WORK_HELPER_PROTO(delayed_meta_helper);
-BTRFS_WORK_HELPER_PROTO(readahead_helper);
-BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper);
-BTRFS_WORK_HELPER_PROTO(extent_refs_helper);
-BTRFS_WORK_HELPER_PROTO(scrub_helper);
-BTRFS_WORK_HELPER_PROTO(scrubwrc_helper);
-BTRFS_WORK_HELPER_PROTO(scrubnc_helper);
-BTRFS_WORK_HELPER_PROTO(scrubparity_helper);
-
-
 struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
 					      const char *name,
 					      unsigned int flags,
 					      int limit_active,
 					      int thresh);
-void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper,
-		     btrfs_func_t func,
-		     btrfs_func_t ordered_func,
-		     btrfs_func_t ordered_free);
+void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
+		     btrfs_func_t ordered_func, btrfs_func_t ordered_free);
 void btrfs_queue_work(struct btrfs_workqueue *wq,
 		      struct btrfs_work *work);
 void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
 void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
 void btrfs_set_work_high_priority(struct btrfs_work *work);
-struct btrfs_fs_info *btrfs_work_owner(const struct btrfs_work *work);
-struct btrfs_fs_info *btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
+struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work);
+struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
 bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq);
 
 #endif

fs/btrfs/block-group.h

@@ -34,7 +34,7 @@ struct btrfs_caching_control {
 	struct mutex mutex;
 	wait_queue_head_t wait;
 	struct btrfs_work work;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	u64 progress;
 	refcount_t count;
 };
@@ -42,14 +42,15 @@ struct btrfs_caching_control {
 /* Once caching_thread() finds this much free space, it will wake up waiters. */
 #define CACHING_CTL_WAKE_UP SZ_2M
 
-struct btrfs_block_group_cache {
-	struct btrfs_key key;
-	struct btrfs_block_group_item item;
+struct btrfs_block_group {
 	struct btrfs_fs_info *fs_info;
 	struct inode *inode;
 	spinlock_t lock;
+	u64 start;
+	u64 length;
 	u64 pinned;
 	u64 reserved;
+	u64 used;
 	u64 delalloc_bytes;
 	u64 bytes_super;
 	u64 flags;
@@ -159,7 +160,7 @@ struct btrfs_block_group_cache {
 
 #ifdef CONFIG_BTRFS_DEBUG
 static inline int btrfs_should_fragment_free_space(
-		struct btrfs_block_group_cache *block_group)
+		struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 
@@ -170,29 +171,29 @@ static inline int btrfs_should_fragment_free_space(
 }
 #endif
 
-struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
+struct btrfs_block_group *btrfs_lookup_first_block_group(
 		struct btrfs_fs_info *info, u64 bytenr);
-struct btrfs_block_group_cache *btrfs_lookup_block_group(
+struct btrfs_block_group *btrfs_lookup_block_group(
 		struct btrfs_fs_info *info, u64 bytenr);
-struct btrfs_block_group_cache *btrfs_next_block_group(
-		struct btrfs_block_group_cache *cache);
-void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
-void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
+struct btrfs_block_group *btrfs_next_block_group(
+		struct btrfs_block_group *cache);
+void btrfs_get_block_group(struct btrfs_block_group *cache);
+void btrfs_put_block_group(struct btrfs_block_group *cache);
 void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
 					const u64 start);
-void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
+void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg);
 bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
 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_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
+void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
+void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 				           u64 num_bytes);
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache);
-int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
+int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
+int btrfs_cache_block_group(struct btrfs_block_group *cache,
 			    int load_cache_only);
 void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
 struct btrfs_caching_control *btrfs_get_caching_control(
-		struct btrfs_block_group_cache *cache);
-u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
+		struct btrfs_block_group *cache);
+u64 add_new_free_space(struct btrfs_block_group *block_group,
 		       u64 start, u64 end);
 struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 				struct btrfs_fs_info *fs_info,
@@ -200,21 +201,22 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 			     u64 group_start, struct extent_map *em);
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
-void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
+void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
 int btrfs_read_block_groups(struct btrfs_fs_info *info);
 int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 			   u64 type, u64 chunk_offset, u64 size);
 void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
-int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
-void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
+int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
+			     bool do_chunk_alloc);
+void btrfs_dec_block_group_ro(struct btrfs_block_group *cache);
 int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans);
 int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
 int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			     u64 bytenr, u64 num_bytes, int alloc);
-int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
 			     u64 ram_bytes, u64 num_bytes, int delalloc);
-void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
 			       u64 num_bytes, int delalloc);
 int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 		      enum btrfs_chunk_alloc_enum force);
@@ -239,8 +241,7 @@ static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
 	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
 }
 
-static inline int btrfs_block_group_cache_done(
-		struct btrfs_block_group_cache *cache)
+static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
 {
 	smp_mb();
 	return cache->cached == BTRFS_CACHE_FINISHED ||

fs/btrfs/btrfs_inode.h

@@ -63,9 +63,6 @@ struct btrfs_inode {
 	/* held while logging the inode in tree-log.c */
 	struct mutex log_mutex;
 
-	/* held while doing delalloc reservations */
-	struct mutex delalloc_mutex;
-
 	/* used to order data wrt metadata */
 	struct btrfs_ordered_inode_tree ordered_tree;
 

fs/btrfs/compression.h

@@ -93,7 +93,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				  unsigned long compressed_len,
 				  struct page **compressed_pages,
 				  unsigned long nr_pages,
-				  unsigned int write_flags);
+				  unsigned int write_flags,
+				  struct cgroup_subsys_state *blkcg_css);
 blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags);
 
@@ -104,11 +105,10 @@ enum btrfs_compression_type {
 	BTRFS_COMPRESS_ZLIB  = 1,
 	BTRFS_COMPRESS_LZO   = 2,
 	BTRFS_COMPRESS_ZSTD  = 3,
-	BTRFS_COMPRESS_TYPES = 3,
+	BTRFS_NR_COMPRESS_TYPES = 4,
 };
 
 struct workspace_manager {
-	const struct btrfs_compress_op *ops;
 	struct list_head idle_ws;
 	spinlock_t ws_lock;
 	/* Number of free workspaces */
@@ -119,50 +119,18 @@ struct workspace_manager {
 	wait_queue_head_t ws_wait;
 };
 
-void btrfs_init_workspace_manager(struct workspace_manager *wsm,
-				  const struct btrfs_compress_op *ops);
-struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
-				      unsigned int level);
-void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws);
-void btrfs_cleanup_workspace_manager(struct workspace_manager *wsm);
+struct list_head *btrfs_get_workspace(int type, unsigned int level);
+void btrfs_put_workspace(int type, struct list_head *ws);
 
 struct btrfs_compress_op {
-	void (*init_workspace_manager)(void);
-
-	void (*cleanup_workspace_manager)(void);
-
-	struct list_head *(*get_workspace)(unsigned int level);
-
-	void (*put_workspace)(struct list_head *ws);
-
-	struct list_head *(*alloc_workspace)(unsigned int level);
-
-	void (*free_workspace)(struct list_head *workspace);
-
-	int (*compress_pages)(struct list_head *workspace,
-			      struct address_space *mapping,
-			      u64 start,
-			      struct page **pages,
-			      unsigned long *out_pages,
-			      unsigned long *total_in,
-			      unsigned long *total_out);
-
-	int (*decompress_bio)(struct list_head *workspace,
-				struct compressed_bio *cb);
-
-	int (*decompress)(struct list_head *workspace,
-			  unsigned char *data_in,
-			  struct page *dest_page,
-			  unsigned long start_byte,
-			  size_t srclen, size_t destlen);
-
+	struct workspace_manager *workspace_manager;
 	/* Maximum level supported by the compression algorithm */
 	unsigned int max_level;
 	unsigned int default_level;
 };
 
 /* The heuristic workspaces are managed via the 0th workspace manager */
-#define BTRFS_NR_WORKSPACE_MANAGERS	(BTRFS_COMPRESS_TYPES + 1)
+#define BTRFS_NR_WORKSPACE_MANAGERS	BTRFS_NR_COMPRESS_TYPES
 
 extern const struct btrfs_compress_op btrfs_heuristic_compress;
 extern const struct btrfs_compress_op btrfs_zlib_compress;

fs/btrfs/ctree.h

@@ -28,6 +28,7 @@
 #include <linux/dynamic_debug.h>
 #include <linux/refcount.h>
 #include <linux/crc32c.h>
+#include "extent-io-tree.h"
 #include "extent_io.h"
 #include "extent_map.h"
 #include "async-thread.h"
@@ -38,7 +39,7 @@ struct btrfs_transaction;
 struct btrfs_pending_snapshot;
 struct btrfs_delayed_ref_root;
 struct btrfs_space_info;
-struct btrfs_block_group_cache;
+struct btrfs_block_group;
 extern struct kmem_cache *btrfs_trans_handle_cachep;
 extern struct kmem_cache *btrfs_bit_radix_cachep;
 extern struct kmem_cache *btrfs_path_cachep;
@@ -56,9 +57,9 @@ struct btrfs_ref;
  * filesystem data as well that can be used to read data in order to repair
  * read errors on other disks.
  *
- * Current value is derived from RAID1 with 2 copies.
+ * Current value is derived from RAID1C4 with 4 copies.
  */
-#define BTRFS_MAX_MIRRORS (2 + 1)
+#define BTRFS_MAX_MIRRORS (4 + 1)
 
 #define BTRFS_MAX_LEVEL 8
 
@@ -291,7 +292,8 @@ struct btrfs_super_block {
 	 BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF |		\
 	 BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA |	\
 	 BTRFS_FEATURE_INCOMPAT_NO_HOLES	|	\
-	 BTRFS_FEATURE_INCOMPAT_METADATA_UUID)
+	 BTRFS_FEATURE_INCOMPAT_METADATA_UUID	|	\
+	 BTRFS_FEATURE_INCOMPAT_RAID1C34)
 
 #define BTRFS_FEATURE_INCOMPAT_SAFE_SET			\
 	(BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
@@ -413,7 +415,7 @@ struct btrfs_free_cluster {
 	/* We did a full search and couldn't create a cluster */
 	bool fragmented;
 
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	/*
 	 * when a cluster is allocated from a block group, we put the
 	 * cluster onto a list in the block group so that it can
@@ -476,8 +478,8 @@ struct btrfs_swapfile_pin {
 	void *ptr;
 	struct inode *inode;
 	/*
-	 * If true, ptr points to a struct btrfs_block_group_cache. Otherwise,
-	 * ptr points to a struct btrfs_device.
+	 * If true, ptr points to a struct btrfs_block_group. Otherwise, ptr
+	 * points to a struct btrfs_device.
 	 */
 	bool is_block_group;
 };
@@ -722,7 +724,6 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *endio_meta_write_workers;
 	struct btrfs_workqueue *endio_write_workers;
 	struct btrfs_workqueue *endio_freespace_worker;
-	struct btrfs_workqueue *submit_workers;
 	struct btrfs_workqueue *caching_workers;
 	struct btrfs_workqueue *readahead_workers;
 
@@ -1519,18 +1520,18 @@ static inline u64 btrfs_stripe_devid_nr(struct extent_buffer *eb,
 }
 
 /* struct btrfs_block_group_item */
-BTRFS_SETGET_STACK_FUNCS(block_group_used, struct btrfs_block_group_item,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_used, struct btrfs_block_group_item,
 			 used, 64);
-BTRFS_SETGET_FUNCS(disk_block_group_used, struct btrfs_block_group_item,
+BTRFS_SETGET_FUNCS(block_group_used, struct btrfs_block_group_item,
 			 used, 64);
-BTRFS_SETGET_STACK_FUNCS(block_group_chunk_objectid,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_chunk_objectid,
 			struct btrfs_block_group_item, chunk_objectid, 64);
 
-BTRFS_SETGET_FUNCS(disk_block_group_chunk_objectid,
+BTRFS_SETGET_FUNCS(block_group_chunk_objectid,
 		   struct btrfs_block_group_item, chunk_objectid, 64);
-BTRFS_SETGET_FUNCS(disk_block_group_flags,
+BTRFS_SETGET_FUNCS(block_group_flags,
 		   struct btrfs_block_group_item, flags, 64);
-BTRFS_SETGET_STACK_FUNCS(block_group_flags,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_flags,
 			struct btrfs_block_group_item, flags, 64);
 
 /* struct btrfs_free_space_info */
@@ -2163,6 +2164,9 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
 
 int btrfs_super_csum_size(const struct btrfs_super_block *s);
 const char *btrfs_super_csum_name(u16 csum_type);
+const char *btrfs_super_csum_driver(u16 csum_type);
+size_t __const btrfs_get_num_csums(void);
+
 
 /*
  * The leaf data grows from end-to-front in the node.
@@ -2397,7 +2401,7 @@ static inline u64 btrfs_calc_metadata_size(struct btrfs_fs_info *fs_info,
 
 int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info,
 			      u64 start, u64 num_bytes);
-void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache);
+void btrfs_free_excluded_extents(struct btrfs_block_group *cache);
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   unsigned long count);
 void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
@@ -2453,8 +2457,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_ref *generic_ref);
 
 int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr);
-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_get_block_group_trimming(struct btrfs_block_group *cache);
+void btrfs_put_block_group_trimming(struct btrfs_block_group *cache);
 void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
 
 enum btrfs_reserve_flush_enum {
@@ -2507,7 +2511,7 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
 		     int level, int *slot);
-int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
+int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
 int btrfs_previous_item(struct btrfs_root *root,
 			struct btrfs_path *path, u64 min_objectid,
 			int type);
@@ -2567,8 +2571,6 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 void btrfs_release_path(struct btrfs_path *p);
 struct btrfs_path *btrfs_alloc_path(void);
 void btrfs_free_path(struct btrfs_path *p);
-void btrfs_set_path_blocking(struct btrfs_path *p);
-void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
 
 int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		   struct btrfs_path *path, int slot, int nr);
@@ -2870,10 +2872,9 @@ int btrfs_drop_inode(struct inode *inode);
 int __init btrfs_init_cachep(void);
 void __cold btrfs_destroy_cachep(void);
 struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
-			      struct btrfs_root *root, int *new,
-			      struct btrfs_path *path);
+			      struct btrfs_root *root, struct btrfs_path *path);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
-			 struct btrfs_root *root, int *was_new);
+			 struct btrfs_root *root);
 struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 				    struct page *page, size_t pg_offset,
 				    u64 start, u64 end, int create);
@@ -2909,7 +2910,7 @@ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int btrfs_ioctl_get_supported_features(void __user *arg);
 void btrfs_sync_inode_flags_to_i_flags(struct inode *inode);
-int btrfs_is_empty_uuid(u8 *uuid);
+int __pure btrfs_is_empty_uuid(u8 *uuid);
 int btrfs_defrag_file(struct inode *inode, struct file *file,
 		      struct btrfs_ioctl_defrag_range_args *range,
 		      u64 newer_than, unsigned long max_pages);
@@ -3143,7 +3144,7 @@ __cold
 void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
 		     unsigned int line, int errno, const char *fmt, ...);
 
-const char *btrfs_decode_error(int errno);
+const char * __attribute_const__ btrfs_decode_error(int errno);
 
 __cold
 void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,

fs/btrfs/delalloc-space.c

@@ -307,7 +307,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	unsigned nr_extents;
 	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
 	int ret = 0;
-	bool delalloc_lock = true;
 
 	/*
 	 * If we are a free space inode we need to not flush since we will be in
@@ -320,7 +319,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	 */
 	if (btrfs_is_free_space_inode(inode)) {
 		flush = BTRFS_RESERVE_NO_FLUSH;
-		delalloc_lock = false;
 	} else {
 		if (current->journal_info)
 			flush = BTRFS_RESERVE_FLUSH_LIMIT;
@@ -329,9 +327,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 			schedule_timeout(1);
 	}
 
-	if (delalloc_lock)
-		mutex_lock(&inode->delalloc_mutex);
-
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 
 	/*
@@ -348,10 +343,12 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 				&qgroup_reserve);
 	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true);
 	if (ret)
-		goto out_fail;
+		return ret;
 	ret = btrfs_reserve_metadata_bytes(root, block_rsv, meta_reserve, flush);
-	if (ret)
-		goto out_qgroup;
+	if (ret) {
+		btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
+		return ret;
+	}
 
 	/*
 	 * Now we need to update our outstanding extents and csum bytes _first_
@@ -375,15 +372,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	block_rsv->qgroup_rsv_reserved += qgroup_reserve;
 	spin_unlock(&block_rsv->lock);
 
-	if (delalloc_lock)
-		mutex_unlock(&inode->delalloc_mutex);
 	return 0;
-out_qgroup:
-	btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
-out_fail:
-	if (delalloc_lock)
-		mutex_unlock(&inode->delalloc_mutex);
-	return ret;
 }
 
 /**

fs/btrfs/delayed-inode.c

@@ -12,6 +12,7 @@
 #include "transaction.h"
 #include "ctree.h"
 #include "qgroup.h"
+#include "locking.h"
 
 #define BTRFS_DELAYED_WRITEBACK		512
 #define BTRFS_DELAYED_BACKGROUND	128
@@ -1367,8 +1368,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 		return -ENOMEM;
 
 	async_work->delayed_root = delayed_root;
-	btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper,
-			btrfs_async_run_delayed_root, NULL, NULL);
+	btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root, NULL,
+			NULL);
 	async_work->nr = nr;
 
 	btrfs_queue_work(fs_info->delayed_workers, &async_work->work);
@@ -1949,12 +1950,19 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
 		}
 
 		inode_id = delayed_nodes[n - 1]->inode_id + 1;
-
-		for (i = 0; i < n; i++)
-			refcount_inc(&delayed_nodes[i]->refs);
+		for (i = 0; i < n; i++) {
+			/*
+			 * Don't increase refs in case the node is dead and
+			 * about to be removed from the tree in the loop below
+			 */
+			if (!refcount_inc_not_zero(&delayed_nodes[i]->refs))
+				delayed_nodes[i] = NULL;
+		}
 		spin_unlock(&root->inode_lock);
 
 		for (i = 0; i < n; i++) {
+			if (!delayed_nodes[i])
+				continue;
 			__btrfs_kill_delayed_node(delayed_nodes[i]);
 			btrfs_release_delayed_node(delayed_nodes[i]);
 		}

fs/btrfs/dev-replace.c

@@ -986,7 +986,7 @@ static int btrfs_dev_replace_kthread(void *data)
 	return 0;
 }
 
-int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
+int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
 {
 	if (!dev_replace->is_valid)
 		return 0;

fs/btrfs/dev-replace.h

@@ -17,6 +17,6 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info);
 void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info);
 int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info);
-int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
+int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
 
 #endif

fs/btrfs/disk-io.h

@@ -49,10 +49,10 @@ struct extent_buffer *btrfs_find_create_tree_block(
 						struct btrfs_fs_info *fs_info,
 						u64 bytenr);
 void btrfs_clean_tree_block(struct extent_buffer *buf);
-int open_ctree(struct super_block *sb,
+int __cold open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options);
-void close_ctree(struct btrfs_fs_info *fs_info);
+void __cold close_ctree(struct btrfs_fs_info *fs_info);
 int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
 struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
 int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num,

fs/btrfs/export.c

@@ -87,7 +87,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	inode = btrfs_iget(sb, &key, root, NULL);
+	inode = btrfs_iget(sb, &key, root);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto fail;
@@ -214,7 +214,7 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
 
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root, NULL));
+	return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root));
 fail:
 	btrfs_free_path(path);
 	return ERR_PTR(ret);

fs/btrfs/extent-io-tree.h

+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_EXTENT_IO_TREE_H
+#define BTRFS_EXTENT_IO_TREE_H
+
+struct extent_changeset;
+struct io_failure_record;
+
+/* Bits for the extent state */
+#define EXTENT_DIRTY		(1U << 0)
+#define EXTENT_UPTODATE		(1U << 1)
+#define EXTENT_LOCKED		(1U << 2)
+#define EXTENT_NEW		(1U << 3)
+#define EXTENT_DELALLOC		(1U << 4)
+#define EXTENT_DEFRAG		(1U << 5)
+#define EXTENT_BOUNDARY		(1U << 6)
+#define EXTENT_NODATASUM	(1U << 7)
+#define EXTENT_CLEAR_META_RESV	(1U << 8)
+#define EXTENT_NEED_WAIT	(1U << 9)
+#define EXTENT_DAMAGED		(1U << 10)
+#define EXTENT_NORESERVE	(1U << 11)
+#define EXTENT_QGROUP_RESERVED	(1U << 12)
+#define EXTENT_CLEAR_DATA_RESV	(1U << 13)
+#define EXTENT_DELALLOC_NEW	(1U << 14)
+#define EXTENT_DO_ACCOUNTING    (EXTENT_CLEAR_META_RESV | \
+				 EXTENT_CLEAR_DATA_RESV)
+#define EXTENT_CTLBITS		(EXTENT_DO_ACCOUNTING)
+
+/*
+ * Redefined bits above which are used only in the device allocation tree,
+ * shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV
+ * / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit
+ * manipulation functions
+ */
+#define CHUNK_ALLOCATED				EXTENT_DIRTY
+#define CHUNK_TRIMMED				EXTENT_DEFRAG
+
+enum {
+	IO_TREE_FS_INFO_FREED_EXTENTS0,
+	IO_TREE_FS_INFO_FREED_EXTENTS1,
+	IO_TREE_INODE_IO,
+	IO_TREE_INODE_IO_FAILURE,
+	IO_TREE_RELOC_BLOCKS,
+	IO_TREE_TRANS_DIRTY_PAGES,
+	IO_TREE_ROOT_DIRTY_LOG_PAGES,
+	IO_TREE_SELFTEST,
+};
+
+struct extent_io_tree {
+	struct rb_root state;
+	struct btrfs_fs_info *fs_info;
+	void *private_data;
+	u64 dirty_bytes;
+	bool track_uptodate;
+
+	/* Who owns this io tree, should be one of IO_TREE_* */
+	u8 owner;
+
+	spinlock_t lock;
+	const struct extent_io_ops *ops;
+};
+
+struct extent_state {
+	u64 start;
+	u64 end; /* inclusive */
+	struct rb_node rb_node;
+
+	/* ADD NEW ELEMENTS AFTER THIS */
+	wait_queue_head_t wq;
+	refcount_t refs;
+	unsigned state;
+
+	struct io_failure_record *failrec;
+
+#ifdef CONFIG_BTRFS_DEBUG
+	struct list_head leak_list;
+#endif
+};
+
+int __init extent_state_cache_init(void);
+void __cold extent_state_cache_exit(void);
+
+void extent_io_tree_init(struct btrfs_fs_info *fs_info,
+			 struct extent_io_tree *tree, unsigned int owner,
+			 void *private_data);
+void extent_io_tree_release(struct extent_io_tree *tree);
+
+int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+		     struct extent_state **cached);
+
+static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
+{
+	return lock_extent_bits(tree, start, end, NULL);
+}
+
+int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
+
+int __init extent_io_init(void);
+void __cold extent_io_exit(void);
+
+u64 count_range_bits(struct extent_io_tree *tree,
+		     u64 *start, u64 search_end,
+		     u64 max_bytes, unsigned bits, int contig);
+
+void free_extent_state(struct extent_state *state);
+int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		   unsigned bits, int filled,
+		   struct extent_state *cached_state);
+int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+		unsigned bits, struct extent_changeset *changeset);
+int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		     unsigned bits, int wake, int delete,
+		     struct extent_state **cached);
+int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		     unsigned bits, int wake, int delete,
+		     struct extent_state **cached, gfp_t mask,
+		     struct extent_changeset *changeset);
+
+static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
+{
+	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
+}
+
+static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached)
+{
+	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+				GFP_NOFS, NULL);
+}
+
+static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
+		u64 start, u64 end, struct extent_state **cached)
+{
+	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+				GFP_ATOMIC, NULL);
+}
+
+static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
+		u64 end, unsigned bits)
+{
+	int wake = 0;
+
+	if (bits & EXTENT_LOCKED)
+		wake = 1;
+
+	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
+}
+
+int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+			   unsigned bits, struct extent_changeset *changeset);
+int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		   unsigned bits, u64 *failed_start,
+		   struct extent_state **cached_state, gfp_t mask);
+int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
+			   unsigned bits);
+
+static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
+		u64 end, unsigned bits)
+{
+	return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
+}
+
+static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state)
+{
+	return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
+				cached_state, GFP_NOFS, NULL);
+}
+
+static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
+		u64 end, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
+			      NULL, mask);
+}
+
+static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
+				     u64 end, struct extent_state **cached)
+{
+	return clear_extent_bit(tree, start, end,
+				EXTENT_DIRTY | EXTENT_DELALLOC |
+				EXTENT_DO_ACCOUNTING, 0, 0, cached);
+}
+
+int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		       unsigned bits, unsigned clear_bits,
+		       struct extent_state **cached_state);
+
+static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
+				      u64 end, unsigned int extra_bits,
+				      struct extent_state **cached_state)
+{
+	return set_extent_bit(tree, start, end,
+			      EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
+			      NULL, cached_state, GFP_NOFS);
+}
+
+static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state)
+{
+	return set_extent_bit(tree, start, end,
+			      EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
+			      NULL, cached_state, GFP_NOFS);
+}
+
+static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
+		u64 end)
+{
+	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
+			GFP_NOFS);
+}
+
+static inline int set_extent_uptodate(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_UPTODATE, NULL,
+			      cached_state, mask);
+}
+
+int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
+			  u64 *start_ret, u64 *end_ret, unsigned bits,
+			  struct extent_state **cached_state);
+void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
+				 u64 *start_ret, u64 *end_ret, unsigned bits);
+int extent_invalidatepage(struct extent_io_tree *tree,
+			  struct page *page, unsigned long offset);
+bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
+			       u64 *end, u64 max_bytes,
+			       struct extent_state **cached_state);
+
+/* This should be reworked in the future and put elsewhere. */
+int get_state_failrec(struct extent_io_tree *tree, u64 start,
+		      struct io_failure_record **failrec);
+int set_state_failrec(struct extent_io_tree *tree, u64 start,
+		      struct io_failure_record *failrec);
+void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
+		u64 end);
+int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
+				struct io_failure_record **failrec_ret);
+int free_io_failure(struct extent_io_tree *failure_tree,
+		    struct extent_io_tree *io_tree,
+		    struct io_failure_record *rec);
+int clean_io_failure(struct btrfs_fs_info *fs_info,
+		     struct extent_io_tree *failure_tree,
+		     struct extent_io_tree *io_tree, u64 start,
+		     struct page *page, u64 ino, unsigned int pg_offset);
+
+#endif /* BTRFS_EXTENT_IO_TREE_H */

fs/btrfs/extent_map.c

@@ -214,9 +214,13 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next)
 	ASSERT(next->block_start != EXTENT_MAP_DELALLOC &&
 	       prev->block_start != EXTENT_MAP_DELALLOC);
 
+	if (prev->map_lookup || next->map_lookup)
+		ASSERT(test_bit(EXTENT_FLAG_FS_MAPPING, &prev->flags) &&
+		       test_bit(EXTENT_FLAG_FS_MAPPING, &next->flags));
+
 	if (extent_map_end(prev) == next->start &&
 	    prev->flags == next->flags &&
-	    prev->bdev == next->bdev &&
+	    prev->map_lookup == next->map_lookup &&
 	    ((next->block_start == EXTENT_MAP_HOLE &&
 	      prev->block_start == EXTENT_MAP_HOLE) ||
 	     (next->block_start == EXTENT_MAP_INLINE &&

fs/btrfs/extent_map.h

@@ -42,15 +42,8 @@ struct extent_map {
 	u64 block_len;
 	u64 generation;
 	unsigned long flags;
-	union {
-		struct block_device *bdev;
-
-		/*
-		 * used for chunk mappings
-		 * flags & EXTENT_FLAG_FS_MAPPING must be set
-		 */
-		struct map_lookup *map_lookup;
-	};
+	/* Used for chunk mappings, flag EXTENT_FLAG_FS_MAPPING must be set */
+	struct map_lookup *map_lookup;
 	refcount_t refs;
 	unsigned int compress_type;
 	struct list_head list;

fs/btrfs/file-item.c

@@ -945,7 +945,6 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 	u8 type = btrfs_file_extent_type(leaf, fi);
 	int compress_type = btrfs_file_extent_compression(leaf, fi);
 
-	em->bdev = fs_info->fs_devices->latest_bdev;
 	btrfs_item_key_to_cpu(leaf, &key, slot);
 	extent_start = key.offset;
 

fs/btrfs/file.c

@@ -296,7 +296,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 	key.objectid = defrag->ino;
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, inode_root);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
 		goto cleanup;
@@ -667,7 +667,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 			}
 
 			split->generation = gen;
-			split->bdev = em->bdev;
 			split->flags = flags;
 			split->compress_type = em->compress_type;
 			replace_extent_mapping(em_tree, em, split, modified);
@@ -680,7 +679,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 
 			split->start = start + len;
 			split->len = em->start + em->len - (start + len);
-			split->bdev = em->bdev;
 			split->flags = flags;
 			split->compress_type = em->compress_type;
 			split->generation = gen;
@@ -1636,6 +1634,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
 			break;
 		}
 
+		only_release_metadata = false;
 		sector_offset = pos & (fs_info->sectorsize - 1);
 		reserve_bytes = round_up(write_bytes + sector_offset,
 				fs_info->sectorsize);
@@ -1791,7 +1790,6 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
 			set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
 				       lockend, EXTENT_NORESERVE, NULL,
 				       NULL, GFP_NOFS);
-			only_release_metadata = false;
 		}
 
 		btrfs_drop_pages(pages, num_pages);
@@ -1903,9 +1901,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	    (iocb->ki_flags & IOCB_NOWAIT))
 		return -EOPNOTSUPP;
 
-	if (!inode_trylock(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
 			return -EAGAIN;
+	} else {
 		inode_lock(inode);
 	}
 
@@ -2359,7 +2358,6 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		hole_em->block_start = EXTENT_MAP_HOLE;
 		hole_em->block_len = 0;
 		hole_em->orig_block_len = 0;
-		hole_em->bdev = fs_info->fs_devices->latest_bdev;
 		hole_em->compress_type = BTRFS_COMPRESS_NONE;
 		hole_em->generation = trans->transid;
 
@@ -3350,29 +3348,30 @@ static long btrfs_fallocate(struct file *file, int mode,
 	return ret;
 }
 
-static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
+static loff_t find_desired_extent(struct inode *inode, loff_t offset,
+				  int whence)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_map *em = NULL;
 	struct extent_state *cached_state = NULL;
+	loff_t i_size = inode->i_size;
 	u64 lockstart;
 	u64 lockend;
 	u64 start;
 	u64 len;
 	int ret = 0;
 
-	if (inode->i_size == 0)
+	if (i_size == 0 || offset >= i_size)
 		return -ENXIO;
 
 	/*
-	 * *offset can be negative, in this case we start finding DATA/HOLE from
+	 * offset can be negative, in this case we start finding DATA/HOLE from
 	 * the very start of the file.
 	 */
-	start = max_t(loff_t, 0, *offset);
+	start = max_t(loff_t, 0, offset);
 
 	lockstart = round_down(start, fs_info->sectorsize);
-	lockend = round_up(i_size_read(inode),
-			   fs_info->sectorsize);
+	lockend = round_up(i_size, fs_info->sectorsize);
 	if (lockend <= lockstart)
 		lockend = lockstart + fs_info->sectorsize;
 	lockend--;
@@ -3381,7 +3380,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			 &cached_state);
 
-	while (start < inode->i_size) {
+	while (start < i_size) {
 		em = btrfs_get_extent_fiemap(BTRFS_I(inode), start, len);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
@@ -3404,46 +3403,39 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 		cond_resched();
 	}
 	free_extent_map(em);
-	if (!ret) {
-		if (whence == SEEK_DATA && start >= inode->i_size)
-			ret = -ENXIO;
-		else
-			*offset = min_t(loff_t, start, inode->i_size);
-	}
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			     &cached_state);
-	return ret;
+	if (ret) {
+		offset = ret;
+	} else {
+		if (whence == SEEK_DATA && start >= i_size)
+			offset = -ENXIO;
+		else
+			offset = min_t(loff_t, start, i_size);
+	}
+
+	return offset;
 }
 
 static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
-	int ret;
 
-	inode_lock(inode);
 	switch (whence) {
-	case SEEK_END:
-	case SEEK_CUR:
-		offset = generic_file_llseek(file, offset, whence);
-		goto out;
+	default:
+		return generic_file_llseek(file, offset, whence);
 	case SEEK_DATA:
 	case SEEK_HOLE:
-		if (offset >= i_size_read(inode)) {
-			inode_unlock(inode);
-			return -ENXIO;
-		}
-
-		ret = find_desired_extent(inode, &offset, whence);
-		if (ret) {
-			inode_unlock(inode);
-			return ret;
-		}
+		inode_lock_shared(inode);
+		offset = find_desired_extent(inode, offset, whence);
+		inode_unlock_shared(inode);
+		break;
 	}
 
-	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
-out:
-	inode_unlock(inode);
-	return offset;
+	if (offset < 0)
+		return offset;
+
+	return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 }
 
 static int btrfs_file_open(struct inode *inode, struct file *filp)

fs/btrfs/free-space-tree.h

@@ -16,14 +16,14 @@ struct btrfs_caching_control;
 #define BTRFS_FREE_SPACE_BITMAP_SIZE 256
 #define BTRFS_FREE_SPACE_BITMAP_BITS (BTRFS_FREE_SPACE_BITMAP_SIZE * BITS_PER_BYTE)
 
-void set_free_space_tree_thresholds(struct btrfs_block_group_cache *block_group);
+void set_free_space_tree_thresholds(struct btrfs_block_group *block_group);
 int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info);
 int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info);
 int load_free_space_tree(struct btrfs_caching_control *caching_ctl);
 int add_block_group_free_space(struct btrfs_trans_handle *trans,
-			       struct btrfs_block_group_cache *block_group);
+			       struct btrfs_block_group *block_group);
 int remove_block_group_free_space(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group);
+				  struct btrfs_block_group *block_group);
 int add_to_free_space_tree(struct btrfs_trans_handle *trans,
 			   u64 start, u64 size);
 int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
@@ -32,21 +32,21 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 struct btrfs_free_space_info *
 search_free_space_info(struct btrfs_trans_handle *trans,
-		       struct btrfs_block_group_cache *block_group,
+		       struct btrfs_block_group *block_group,
 		       struct btrfs_path *path, int cow);
 int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
-			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_block_group *block_group,
 			     struct btrfs_path *path, u64 start, u64 size);
 int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path, u64 start, u64 size);
 int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path);
 int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path);
-int free_space_test_bit(struct btrfs_block_group_cache *block_group,
+int free_space_test_bit(struct btrfs_block_group *block_group,
 			struct btrfs_path *path, u64 offset);
 #endif