Merge tag 'for-4.16-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Features or user visible changes:

   - fallocate: implement zero range mode

   - avoid losing data raid profile when deleting a device

   - tree item checker: more checks for directory items and xattrs

  Notable fixes:

   - raid56 recovery: don't use cached stripes, that could be
     potentially changed and a later RMW or recovery would lead to
     corruptions or failures

   - let raid56 try harder to rebuild damaged data, reading from all
     stripes if necessary

   - fix scrub to repair raid56 in a similar way as in the case above

  Other:

   - cleanups: device freeing, removed some call indirections, redundant
     bio_put/_get, unused parameters, refactorings and renames

   - RCU list traversal fixups

   - simplify mount callchain, remove recursing back when mounting a
     subvolume

   - plug for fsync, may improve bio merging on multiple devices

   - compression heurisic: replace heap sort with radix sort, gains some
     performance

   - add extent map selftests, buffered write vs dio"

* tag 'for-4.16-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (155 commits)
  btrfs: drop devid as device_list_add() arg
  btrfs: get device pointer from device_list_add()
  btrfs: set the total_devices in device_list_add()
  btrfs: move pr_info into device_list_add
  btrfs: make btrfs_free_stale_devices() to match the path
  btrfs: rename btrfs_free_stale_devices() arg to skip_dev
  btrfs: make btrfs_free_stale_devices() argument optional
  btrfs: make btrfs_free_stale_device() to iterate all stales
  btrfs: no need to check for btrfs_fs_devices::seeding
  btrfs: Use IS_ALIGNED in btrfs_truncate_block instead of opencoding it
  Btrfs: noinline merge_extent_mapping
  Btrfs: add WARN_ONCE to detect unexpected error from merge_extent_mapping
  Btrfs: extent map selftest: dio write vs dio read
  Btrfs: extent map selftest: buffered write vs dio read
  Btrfs: add extent map selftests
  Btrfs: move extent map specific code to extent_map.c
  Btrfs: add helper for em merge logic
  Btrfs: fix unexpected EEXIST from btrfs_get_extent
  Btrfs: fix incorrect block_len in merge_extent_mapping
  btrfs: Remove unused readahead spinlock
  ...

44 files changed, 2259 insertions, 1399 deletions

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 6fe881d5cb38..0c4373628eb4 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -19,4 +19,4 @@ btrfs-$(CONFIG_BTRFS_FS_REF_VERIFY) += ref-verify.o
 btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o \
 	tests/extent-buffer-tests.o tests/btrfs-tests.o \
 	tests/extent-io-tests.o tests/inode-tests.o tests/qgroup-tests.o \
-	tests/free-space-tree-tests.o
+	tests/free-space-tree-tests.o tests/extent-map-tests.o
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 7d0dc100a09a..e4054e533f6d 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -216,7 +216,8 @@ static int prelim_ref_compare(struct prelim_ref *ref1,
 	return 0;
 }
 
-void update_share_count(struct share_check *sc, int oldcount, int newcount)
+static void update_share_count(struct share_check *sc, int oldcount,
+			       int newcount)
 {
 	if ((!sc) || (oldcount == 0 && newcount < 1))
 		return;
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 75610d23d197..07d049c0c20f 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -33,7 +33,6 @@
 #include <linux/bit_spinlock.h>
 #include <linux/slab.h>
 #include <linux/sched/mm.h>
-#include <linux/sort.h>
 #include <linux/log2.h>
 #include "ctree.h"
 #include "disk-io.h"
@@ -45,6 +44,21 @@
 #include "extent_io.h"
 #include "extent_map.h"
 
+static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" };
+
+const char* btrfs_compress_type2str(enum btrfs_compression_type type)
+{
+	switch (type) {
+	case BTRFS_COMPRESS_ZLIB:
+	case BTRFS_COMPRESS_LZO:
+	case BTRFS_COMPRESS_ZSTD:
+	case BTRFS_COMPRESS_NONE:
+		return btrfs_compress_types[type];
+	}
+
+	return NULL;
+}
+
 static int btrfs_decompress_bio(struct compressed_bio *cb);
 
 static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
@@ -348,8 +362,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		page->mapping = NULL;
 		if (submit || bio_add_page(bio, page, PAGE_SIZE, 0) <
 		    PAGE_SIZE) {
-			bio_get(bio);
-
 			/*
 			 * inc the count before we submit the bio so
 			 * we know the end IO handler won't happen before
@@ -372,8 +384,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				bio_endio(bio);
 			}
 
-			bio_put(bio);
-
 			bio = btrfs_bio_alloc(bdev, first_byte);
 			bio->bi_opf = REQ_OP_WRITE | write_flags;
 			bio->bi_private = cb;
@@ -389,7 +399,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		first_byte += PAGE_SIZE;
 		cond_resched();
 	}
-	bio_get(bio);
 
 	ret = btrfs_bio_wq_end_io(fs_info, bio, BTRFS_WQ_ENDIO_DATA);
 	BUG_ON(ret); /* -ENOMEM */
@@ -405,7 +414,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		bio_endio(bio);
 	}
 
-	bio_put(bio);
 	return 0;
 }
 
@@ -638,8 +646,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		page->mapping = NULL;
 		if (submit || bio_add_page(comp_bio, page, PAGE_SIZE, 0) <
 		    PAGE_SIZE) {
-			bio_get(comp_bio);
-
 			ret = btrfs_bio_wq_end_io(fs_info, comp_bio,
 						  BTRFS_WQ_ENDIO_DATA);
 			BUG_ON(ret); /* -ENOMEM */
@@ -666,8 +672,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				bio_endio(comp_bio);
 			}
 
-			bio_put(comp_bio);
-
 			comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte);
 			bio_set_op_attrs(comp_bio, REQ_OP_READ, 0);
 			comp_bio->bi_private = cb;
@@ -677,7 +681,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		}
 		cur_disk_byte += PAGE_SIZE;
 	}
-	bio_get(comp_bio);
 
 	ret = btrfs_bio_wq_end_io(fs_info, comp_bio, BTRFS_WQ_ENDIO_DATA);
 	BUG_ON(ret); /* -ENOMEM */
@@ -693,7 +696,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		bio_endio(comp_bio);
 	}
 
-	bio_put(comp_bio);
 	return 0;
 
 fail2:
@@ -752,6 +754,8 @@ struct heuristic_ws {
 	u32 sample_size;
 	/* Buckets store counters for each byte value */
 	struct bucket_item *bucket;
+	/* Sorting buffer */
+	struct bucket_item *bucket_b;
 	struct list_head list;
 };
 
@@ -763,6 +767,7 @@ static void free_heuristic_ws(struct list_head *ws)
 
 	kvfree(workspace->sample);
 	kfree(workspace->bucket);
+	kfree(workspace->bucket_b);
 	kfree(workspace);
 }
 
@@ -782,6 +787,10 @@ static struct list_head *alloc_heuristic_ws(void)
 	if (!ws->bucket)
 		goto fail;
 
+	ws->bucket_b = kcalloc(BUCKET_SIZE, sizeof(*ws->bucket_b), GFP_KERNEL);
+	if (!ws->bucket_b)
+		goto fail;
+
 	INIT_LIST_HEAD(&ws->list);
 	return &ws->list;
 fail:
@@ -1278,13 +1287,103 @@ static u32 shannon_entropy(struct heuristic_ws *ws)
 	return entropy_sum * 100 / entropy_max;
 }
 
-/* Compare buckets by size, ascending */
-static int bucket_comp_rev(const void *lv, const void *rv)
+#define RADIX_BASE		4U
+#define COUNTERS_SIZE		(1U << RADIX_BASE)
+
+static u8 get4bits(u64 num, int shift) {
+	u8 low4bits;
+
+	num >>= shift;
+	/* Reverse order */
+	low4bits = (COUNTERS_SIZE - 1) - (num % COUNTERS_SIZE);
+	return low4bits;
+}
+
+/*
+ * Use 4 bits as radix base
+ * Use 16 u32 counters for calculating new possition in buf array
+ *
+ * @array     - array that will be sorted
+ * @array_buf - buffer array to store sorting results
+ *              must be equal in size to @array
+ * @num       - array size
+ */
+static void radix_sort(struct bucket_item *array, struct bucket_item *array_buf,
+		       int num)
 {
-	const struct bucket_item *l = (const struct bucket_item *)lv;
-	const struct bucket_item *r = (const struct bucket_item *)rv;
+	u64 max_num;
+	u64 buf_num;
+	u32 counters[COUNTERS_SIZE];
+	u32 new_addr;
+	u32 addr;
+	int bitlen;
+	int shift;
+	int i;
 
-	return r->count - l->count;
+	/*
+	 * Try avoid useless loop iterations for small numbers stored in big
+	 * counters.  Example: 48 33 4 ... in 64bit array
+	 */
+	max_num = array[0].count;
+	for (i = 1; i < num; i++) {
+		buf_num = array[i].count;
+		if (buf_num > max_num)
+			max_num = buf_num;
+	}
+
+	buf_num = ilog2(max_num);
+	bitlen = ALIGN(buf_num, RADIX_BASE * 2);
+
+	shift = 0;
+	while (shift < bitlen) {
+		memset(counters, 0, sizeof(counters));
+
+		for (i = 0; i < num; i++) {
+			buf_num = array[i].count;
+			addr = get4bits(buf_num, shift);
+			counters[addr]++;
+		}
+
+		for (i = 1; i < COUNTERS_SIZE; i++)
+			counters[i] += counters[i - 1];
+
+		for (i = num - 1; i >= 0; i--) {
+			buf_num = array[i].count;
+			addr = get4bits(buf_num, shift);
+			counters[addr]--;
+			new_addr = counters[addr];
+			array_buf[new_addr] = array[i];
+		}
+
+		shift += RADIX_BASE;
+
+		/*
+		 * Normal radix expects to move data from a temporary array, to
+		 * the main one.  But that requires some CPU time. Avoid that
+		 * by doing another sort iteration to original array instead of
+		 * memcpy()
+		 */
+		memset(counters, 0, sizeof(counters));
+
+		for (i = 0; i < num; i ++) {
+			buf_num = array_buf[i].count;
+			addr = get4bits(buf_num, shift);
+			counters[addr]++;
+		}
+
+		for (i = 1; i < COUNTERS_SIZE; i++)
+			counters[i] += counters[i - 1];
+
+		for (i = num - 1; i >= 0; i--) {
+			buf_num = array_buf[i].count;
+			addr = get4bits(buf_num, shift);
+			counters[addr]--;
+			new_addr = counters[addr];
+			array[new_addr] = array_buf[i];
+		}
+
+		shift += RADIX_BASE;
+	}
 }
 
 /*
@@ -1314,7 +1413,7 @@ static int byte_core_set_size(struct heuristic_ws *ws)
 	struct bucket_item *bucket = ws->bucket;
 
 	/* Sort in reverse order */
-	sort(bucket, BUCKET_SIZE, sizeof(*bucket), &bucket_comp_rev, NULL);
+	radix_sort(ws->bucket, ws->bucket_b, BUCKET_SIZE);
 
 	for (i = 0; i < BYTE_CORE_SET_LOW; i++)
 		coreset_sum += bucket[i].count;
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 0868cc554f14..677fa4aa0bd7 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -75,7 +75,7 @@ struct compressed_bio {
 	u32 sums;
 };
 
-void btrfs_init_compress(void);
+void __init btrfs_init_compress(void);
 void btrfs_exit_compress(void);
 
 int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
@@ -137,6 +137,8 @@ extern const struct btrfs_compress_op btrfs_zlib_compress;
 extern const struct btrfs_compress_op btrfs_lzo_compress;
 extern const struct btrfs_compress_op btrfs_zstd_compress;
 
+const char* btrfs_compress_type2str(enum btrfs_compression_type type);
+
 int btrfs_compress_heuristic(struct inode *inode, u64 start, u64 end);
 
 #endif
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 1e74cf826532..b88a79e69ddf 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1807,8 +1807,8 @@ static noinline int generic_bin_search(struct extent_buffer *eb,
  * simple bin_search frontend that does the right thing for
  * leaves vs nodes
  */
-static int bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
-		      int level, int *slot)
+int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
+		     int level, int *slot)
 {
 	if (level == 0)
 		return generic_bin_search(eb,
@@ -1824,12 +1824,6 @@ static int bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
 					  slot);
 }
 
-int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
-		     int level, int *slot)
-{
-	return bin_search(eb, key, level, slot);
-}
-
 static void root_add_used(struct btrfs_root *root, u32 size)
 {
 	spin_lock(&root->accounting_lock);
@@ -2614,7 +2608,7 @@ static int key_search(struct extent_buffer *b, const struct btrfs_key *key,
 		      int level, int *prev_cmp, int *slot)
 {
 	if (*prev_cmp != 0) {
-		*prev_cmp = bin_search(b, key, level, slot);
+		*prev_cmp = btrfs_bin_search(b, key, level, slot);
 		return *prev_cmp;
 	}
 
@@ -2660,17 +2654,29 @@ int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
 }
 
 /*
- * look for key in the tree.  path is filled in with nodes along the way
- * if key is found, we return zero and you can find the item in the leaf
- * level of the path (level 0)
+ * btrfs_search_slot - look for a key in a tree and perform necessary
+ * modifications to preserve tree invariants.
+ *
+ * @trans:	Handle of transaction, used when modifying the tree
+ * @p:		Holds all btree nodes along the search path
+ * @root:	The root node of the tree
+ * @key:	The key we are looking for
+ * @ins_len:	Indicates purpose of search, for inserts it is 1, for
+ *		deletions it's -1. 0 for plain searches
+ * @cow:	boolean should CoW operations be performed. Must always be 1
+ *		when modifying the tree.
+ *
+ * If @ins_len > 0, nodes and leaves will be split as we walk down the tree.
+ * If @ins_len < 0, nodes will be merged as we walk down the tree (if possible)
  *
- * If the key isn't found, the path points to the slot where it should
- * be inserted, and 1 is returned.  If there are other errors during the
- * search a negative error number is returned.
+ * If @key is found, 0 is returned and you can find the item in the leaf level
+ * of the path (level 0)
  *
- * if ins_len > 0, nodes and leaves will be split as we walk down the
- * tree.  if ins_len < 0, nodes will be merged as we walk down the tree (if
- * possible)
+ * If @key isn't found, 1 is returned and the leaf level of the path (level 0)
+ * points to the slot where it should be inserted
+ *
+ * If an error is encountered while searching the tree a negative error number
+ * is returned
  */
 int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		      const struct btrfs_key *key, struct btrfs_path *p,
@@ -2774,6 +2780,8 @@ again:
 		 * contention with the cow code
 		 */
 		if (cow) {
+			bool last_level = (level == (BTRFS_MAX_LEVEL - 1));
+
 			/*
 			 * if we don't really need to cow this block
 			 * then we don't want to set the path blocking,
@@ -2798,9 +2806,13 @@ again:
 			}
 
 			btrfs_set_path_blocking(p);
-			err = btrfs_cow_block(trans, root, b,
-					      p->nodes[level + 1],
-					      p->slots[level + 1], &b);
+			if (last_level)
+				err = btrfs_cow_block(trans, root, b, NULL, 0,
+						      &b);
+			else
+				err = btrfs_cow_block(trans, root, b,
+						      p->nodes[level + 1],
+						      p->slots[level + 1], &b);
 			if (err) {
 				ret = err;
 				goto done;
@@ -5175,7 +5187,7 @@ again:
 	while (1) {
 		nritems = btrfs_header_nritems(cur);
 		level = btrfs_header_level(cur);
-		sret = bin_search(cur, min_key, level, &slot);
+		sret = btrfs_bin_search(cur, min_key, level, &slot);
 
 		/* at the lowest level, we're done, setup the path and exit */
 		if (level == path->lowest_level) {
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 13c260b525a1..1a462ab85c49 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -679,7 +679,6 @@ enum btrfs_orphan_cleanup_state {
 /* used by the raid56 code to lock stripes for read/modify/write */
 struct btrfs_stripe_hash {
 	struct list_head hash_list;
-	wait_queue_head_t wait;
 	spinlock_t lock;
 };
 
@@ -3060,15 +3059,10 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
 					  struct btrfs_path *path, u64 dir,
 					  const char *name, u16 name_len,
 					  int mod);
-int verify_dir_item(struct btrfs_fs_info *fs_info,
-		    struct extent_buffer *leaf, int slot,
-		    struct btrfs_dir_item *dir_item);
 struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info,
 						 struct btrfs_path *path,
 						 const char *name,
 						 int name_len);
-bool btrfs_is_name_len_valid(struct extent_buffer *leaf, int slot,
-			     unsigned long start, u16 name_len);
 
 /* orphan.c */
 int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
@@ -3197,7 +3191,7 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
 struct inode *btrfs_alloc_inode(struct super_block *sb);
 void btrfs_destroy_inode(struct inode *inode);
 int btrfs_drop_inode(struct inode *inode);
-int btrfs_init_cachep(void);
+int __init btrfs_init_cachep(void);
 void btrfs_destroy_cachep(void);
 long btrfs_ioctl_trans_end(struct file *file);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
@@ -3248,7 +3242,7 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 			   struct file *dst_file, u64 dst_loff);
 
 /* file.c */
-int btrfs_auto_defrag_init(void);
+int __init btrfs_auto_defrag_init(void);
 void btrfs_auto_defrag_exit(void);
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 			   struct btrfs_inode *inode);
@@ -3283,7 +3277,7 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root);
 
 /* sysfs.c */
-int btrfs_init_sysfs(void);
+int __init btrfs_init_sysfs(void);
 void 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);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index d4db406e2d39..0530f6f2e4ba 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1303,40 +1303,42 @@ static void btrfs_async_run_delayed_root(struct btrfs_work *work)
 	if (!path)
 		goto out;
 
-again:
-	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND / 2)
-		goto free_path;
+	do {
+		if (atomic_read(&delayed_root->items) <
+		    BTRFS_DELAYED_BACKGROUND / 2)
+			break;
 
-	delayed_node = btrfs_first_prepared_delayed_node(delayed_root);
-	if (!delayed_node)
-		goto free_path;
+		delayed_node = btrfs_first_prepared_delayed_node(delayed_root);
+		if (!delayed_node)
+			break;
 
-	path->leave_spinning = 1;
-	root = delayed_node->root;
+		path->leave_spinning = 1;
+		root = delayed_node->root;
 
-	trans = btrfs_join_transaction(root);
-	if (IS_ERR(trans))
-		goto release_path;
+		trans = btrfs_join_transaction(root);
+		if (IS_ERR(trans)) {
+			btrfs_release_path(path);
+			btrfs_release_prepared_delayed_node(delayed_node);
+			total_done++;
+			continue;
+		}
 
-	block_rsv = trans->block_rsv;
-	trans->block_rsv = &root->fs_info->delayed_block_rsv;
+		block_rsv = trans->block_rsv;
+		trans->block_rsv = &root->fs_info->delayed_block_rsv;
 
-	__btrfs_commit_inode_delayed_items(trans, path, delayed_node);
+		__btrfs_commit_inode_delayed_items(trans, path, delayed_node);
 
-	trans->block_rsv = block_rsv;
-	btrfs_end_transaction(trans);
-	btrfs_btree_balance_dirty_nodelay(root->fs_info);
+		trans->block_rsv = block_rsv;
+		btrfs_end_transaction(trans);
+		btrfs_btree_balance_dirty_nodelay(root->fs_info);
 
-release_path:
-	btrfs_release_path(path);
-	total_done++;
+		btrfs_release_path(path);
+		btrfs_release_prepared_delayed_node(delayed_node);
+		total_done++;
 
-	btrfs_release_prepared_delayed_node(delayed_node);
-	if ((async_work->nr == 0 && total_done < BTRFS_DELAYED_WRITEBACK) ||
-	    total_done < async_work->nr)
-		goto again;
+	} while ((async_work->nr == 0 && total_done < BTRFS_DELAYED_WRITEBACK)
+		 || total_done < async_work->nr);
 
-free_path:
 	btrfs_free_path(path);
 out:
 	wake_up(&delayed_root->wait);
@@ -1349,10 +1351,6 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 {
 	struct btrfs_async_delayed_work *async_work;
 
-	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND ||
-	    btrfs_workqueue_normal_congested(fs_info->delayed_workers))
-		return 0;
-
 	async_work = kmalloc(sizeof(*async_work), GFP_NOFS);
 	if (!async_work)
 		return -ENOMEM;
@@ -1388,7 +1386,8 @@ void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_delayed_root *delayed_root = fs_info->delayed_root;
 
-	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
+	if ((atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND) ||
+		btrfs_workqueue_normal_congested(fs_info->delayed_workers))
 		return;
 
 	if (atomic_read(&delayed_root->items) >= BTRFS_DELAYED_WRITEBACK) {
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 83be8f9fd906..a1a40cf382e3 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -937,7 +937,7 @@ void btrfs_delayed_ref_exit(void)
 	kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
 }
 
-int btrfs_delayed_ref_init(void)
+int __init btrfs_delayed_ref_init(void)
 {
 	btrfs_delayed_ref_head_cachep = kmem_cache_create(
 				"btrfs_delayed_ref_head",
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index a43af432f859..c4f625e5a691 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -203,7 +203,7 @@ extern struct kmem_cache *btrfs_delayed_tree_ref_cachep;
 extern struct kmem_cache *btrfs_delayed_data_ref_cachep;
 extern struct kmem_cache *btrfs_delayed_extent_op_cachep;
 
-int btrfs_delayed_ref_init(void);
+int __init btrfs_delayed_ref_init(void);
 void btrfs_delayed_ref_exit(void);
 
 static inline struct btrfs_delayed_extent_op *
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 7c655f9a7a50..7efbc4d1128b 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -172,7 +172,8 @@ no_valid_dev_replace_entry_found:
 				dev_replace->tgtdev->commit_bytes_used =
 					dev_replace->srcdev->commit_bytes_used;
 			}
-			dev_replace->tgtdev->is_tgtdev_for_dev_replace = 1;
+			set_bit(BTRFS_DEV_STATE_REPLACE_TGT,
+				&dev_replace->tgtdev->dev_state);
 			btrfs_init_dev_replace_tgtdev_for_resume(fs_info,
 				dev_replace->tgtdev);
 		}
@@ -304,6 +305,14 @@ void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info)
 		dev_replace->cursor_left_last_write_of_item;
 }
 
+static char* btrfs_dev_name(struct btrfs_device *device)
+{
+	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
+		return "<missing disk>";
+	else
+		return rcu_str_deref(device->name);
+}
+
 int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 		const char *tgtdev_name, u64 srcdevid, const char *srcdev_name,
 		int read_src)
@@ -363,8 +372,7 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 
 	btrfs_info_in_rcu(fs_info,
 		      "dev_replace from %s (devid %llu) to %s started",
-		      src_device->missing ? "<missing disk>" :
-		        rcu_str_deref(src_device->name),
+		      btrfs_dev_name(src_device),
 		      src_device->devid,
 		      rcu_str_deref(tgt_device->name));
 
@@ -538,8 +546,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	} else {
 		btrfs_err_in_rcu(fs_info,
 				 "btrfs_scrub_dev(%s, %llu, %s) failed %d",
-				 src_device->missing ? "<missing disk>" :
-				 rcu_str_deref(src_device->name),
+				 btrfs_dev_name(src_device),
 				 src_device->devid,
 				 rcu_str_deref(tgt_device->name), scrub_ret);
 		btrfs_dev_replace_unlock(dev_replace, 1);
@@ -557,11 +564,10 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 
 	btrfs_info_in_rcu(fs_info,
 			  "dev_replace from %s (devid %llu) to %s finished",
-			  src_device->missing ? "<missing disk>" :
-			  rcu_str_deref(src_device->name),
+			  btrfs_dev_name(src_device),
 			  src_device->devid,
 			  rcu_str_deref(tgt_device->name));
-	tgt_device->is_tgtdev_for_dev_replace = 0;
+	clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &tgt_device->dev_state);
 	tgt_device->devid = src_device->devid;
 	src_device->devid = BTRFS_DEV_REPLACE_DEVID;
 	memcpy(uuid_tmp, tgt_device->uuid, sizeof(uuid_tmp));
@@ -814,12 +820,10 @@ static int btrfs_dev_replace_kthread(void *data)