Merge tag 'for-5.2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This time the majority of changes are cleanups, though there's still a
  number of changes of user interest.

  User visible changes:

   - better read time and write checks to catch errors early and before
     writing data to disk (to catch potential memory corruption on data
     that get checksummed)

   - qgroups + metadata relocation: last speed up patch int the series
     to address the slowness, there should be no overhead comparing
     balance with and without qgroups

   - FIEMAP ioctl does not start a transaction unnecessarily, this can
     result in a speed up and less blocking due to IO

   - LOGICAL_INO (v1, v2) does not start transaction unnecessarily, this
     can speed up the mentioned ioctl and scrub as well

   - fsync on files with many (but not too many) hardlinks is faster,
     finer decision if the links should be fsynced individually or
     completely

   - send tries harder to find ranges to clone

   - trim/discard will skip unallocated chunks that haven't been touched
     since the last mount

  Fixes:

   - send flushes delayed allocation before start, otherwise it could
     miss some changes in case of a very recent rw->ro switch of a
     subvolume

   - fix fallocate with qgroups that could lead to space accounting
     underflow, reported as a warning

   - trim/discard ioctl honours the requested range

   - starting send and dedupe on a subvolume at the same time will let
     only one of them succeed, this is to prevent changes that send
     could miss due to dedupe; both operations are restartable

  Core changes:

   - more tree-checker validations, errors reported by fuzzing tools:
      - device item
      - inode item
      - block group profiles

   - tracepoints for extent buffer locking

   - async cow preallocates memory to avoid errors happening too deep in
     the call chain

   - metadata reservations for delalloc reworked to better adapt in
     many-writers/low-space scenarios

   - improved space flushing logic for intense DIO vs buffered workloads

   - lots of cleanups
      - removed unused struct members
      - redundant argument removal
      - properties and xattrs
      - extent buffer locking
      - selftests
      - use common file type conversions
      - many-argument functions reduction"

* tag 'for-5.2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (227 commits)
  btrfs: Use kvmalloc for allocating compressed path context
  btrfs: Factor out common extent locking code in submit_compressed_extents
  btrfs: Set io_tree only once in submit_compressed_extents
  btrfs: Replace clear_extent_bit with unlock_extent
  btrfs: Make compress_file_range take only struct async_chunk
  btrfs: Remove fs_info from struct async_chunk
  btrfs: Rename async_cow to async_chunk
  btrfs: Preallocate chunks in cow_file_range_async
  btrfs: reserve delalloc metadata differently
  btrfs: track DIO bytes in flight
  btrfs: merge calls of btrfs_setxattr and btrfs_setxattr_trans in btrfs_set_prop
  btrfs: delete unused function btrfs_set_prop_trans
  btrfs: start transaction in xattr_handler_set_prop
  btrfs: drop local copy of inode i_mode
  btrfs: drop old_fsflags in btrfs_ioctl_setflags
  btrfs: modify local copy of btrfs_inode flags
  btrfs: drop useless inode i_flags copy and restore
  btrfs: start transaction in btrfs_ioctl_setflags()
  btrfs: export btrfs_set_prop
  btrfs: refactor btrfs_set_props to validate externally
  ...

1 files changed, 248 insertions, 108 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index ca8b8e785cf3..13fca7bfc1f2 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -109,8 +109,6 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller,
 #define btrfs_debug_check_extent_io_range(c, s, e)	do {} while (0)
 #endif
 
-#define BUFFER_LRU_MAX 64
-
 struct tree_entry {
 	u64 start;
 	u64 end;
@@ -151,34 +149,51 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
 				       unsigned long bio_flags)
 {
 	blk_status_t ret = 0;
-	struct bio_vec *bvec = bio_last_bvec_all(bio);
-	struct bio_vec bv;
 	struct extent_io_tree *tree = bio->bi_private;
-	u64 start;
-
-	mp_bvec_last_segment(bvec, &bv);
-	start = page_offset(bv.bv_page) + bv.bv_offset;
 
 	bio->bi_private = NULL;
 
 	if (tree->ops)
 		ret = tree->ops->submit_bio_hook(tree->private_data, bio,
-					   mirror_num, bio_flags, start);
+						 mirror_num, bio_flags);
 	else
 		btrfsic_submit_bio(bio);
 
 	return blk_status_to_errno(ret);
 }
 
-static void flush_write_bio(struct extent_page_data *epd)
+/* Cleanup unsubmitted bios */
+static void end_write_bio(struct extent_page_data *epd, int ret)
 {
 	if (epd->bio) {
-		int ret;
+		epd->bio->bi_status = errno_to_blk_status(ret);
+		bio_endio(epd->bio);
+		epd->bio = NULL;
+	}
+}
 
+/*
+ * Submit bio from extent page data via submit_one_bio
+ *
+ * Return 0 if everything is OK.
+ * Return <0 for error.
+ */
+static int __must_check flush_write_bio(struct extent_page_data *epd)
+{
+	int ret = 0;
+
+	if (epd->bio) {
 		ret = submit_one_bio(epd->bio, 0, 0);
-		BUG_ON(ret < 0); /* -ENOMEM */
+		/*
+		 * Clean up of epd->bio is handled by its endio function.
+		 * And endio is either triggered by successful bio execution
+		 * or the error handler of submit bio hook.
+		 * So at this point, no matter what happened, we don't need
+		 * to clean up epd->bio.
+		 */
 		epd->bio = NULL;
 	}
+	return ret;
 }
 
 int __init extent_io_init(void)
@@ -232,14 +247,46 @@ void __cold extent_io_exit(void)
 	bioset_exit(&btrfs_bioset);
 }
 
-void extent_io_tree_init(struct extent_io_tree *tree,
+void extent_io_tree_init(struct btrfs_fs_info *fs_info,
+			 struct extent_io_tree *tree, unsigned int owner,
 			 void *private_data)
 {
+	tree->fs_info = fs_info;
 	tree->state = RB_ROOT;
 	tree->ops = NULL;
 	tree->dirty_bytes = 0;
 	spin_lock_init(&tree->lock);
 	tree->private_data = private_data;
+	tree->owner = owner;
+}
+
+void extent_io_tree_release(struct extent_io_tree *tree)
+{
+	spin_lock(&tree->lock);
+	/*
+	 * Do a single barrier for the waitqueue_active check here, the state
+	 * of the waitqueue should not change once extent_io_tree_release is
+	 * called.
+	 */
+	smp_mb();
+	while (!RB_EMPTY_ROOT(&tree->state)) {
+		struct rb_node *node;
+		struct extent_state *state;
+
+		node = rb_first(&tree->state);
+		state = rb_entry(node, struct extent_state, rb_node);
+		rb_erase(&state->rb_node, &tree->state);
+		RB_CLEAR_NODE(&state->rb_node);
+		/*
+		 * btree io trees aren't supposed to have tasks waiting for
+		 * changes in the flags of extent states ever.
+		 */
+		ASSERT(!waitqueue_active(&state->wq));
+		free_extent_state(state);
+
+		cond_resched_lock(&tree->lock);
+	}
+	spin_unlock(&tree->lock);
 }
 
 static struct extent_state *alloc_extent_state(gfp_t mask)
@@ -400,7 +447,7 @@ static void merge_state(struct extent_io_tree *tree,
 	struct extent_state *other;
 	struct rb_node *other_node;
 
-	if (state->state & (EXTENT_IOBITS | EXTENT_BOUNDARY))
+	if (state->state & (EXTENT_LOCKED | EXTENT_BOUNDARY))
 		return;
 
 	other_node = rb_prev(&state->rb_node);
@@ -611,6 +658,7 @@ int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	int clear = 0;
 
 	btrfs_debug_check_extent_io_range(tree, start, end);
+	trace_btrfs_clear_extent_bit(tree, start, end - start + 1, bits);
 
 	if (bits & EXTENT_DELALLOC)
 		bits |= EXTENT_NORESERVE;
@@ -618,7 +666,7 @@ int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	if (delete)
 		bits |= ~EXTENT_CTLBITS;
 
-	if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY))
+	if (bits & (EXTENT_LOCKED | EXTENT_BOUNDARY))
 		clear = 1;
 again:
 	if (!prealloc && gfpflags_allow_blocking(mask)) {
@@ -850,7 +898,7 @@ static void cache_state(struct extent_state *state,
 			struct extent_state **cached_ptr)
 {
 	return cache_state_if_flags(state, cached_ptr,
-				    EXTENT_IOBITS | EXTENT_BOUNDARY);
+				    EXTENT_LOCKED | EXTENT_BOUNDARY);
 }
 
 /*
@@ -880,6 +928,7 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	u64 last_end;
 
 	btrfs_debug_check_extent_io_range(tree, start, end);
+	trace_btrfs_set_extent_bit(tree, start, end - start + 1, bits);
 
 again:
 	if (!prealloc && gfpflags_allow_blocking(mask)) {
@@ -1112,6 +1161,8 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	bool first_iteration = true;
 
 	btrfs_debug_check_extent_io_range(tree, start, end);
+	trace_btrfs_convert_extent_bit(tree, start, end - start + 1, bits,
+				       clear_bits);
 
 again:
 	if (!prealloc) {
@@ -1311,6 +1362,13 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 				changeset);
 }
 
+int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
+			   unsigned bits)
+{
+	return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL,
+				GFP_NOWAIT, NULL);
+}
+
 int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		     unsigned bits, int wake, int delete,
 		     struct extent_state **cached)
@@ -1478,6 +1536,79 @@ out:
 	return ret;
 }
 
+/**
+ * find_first_clear_extent_bit - finds the first range that has @bits not set
+ * and that starts after @start
+ *
+ * @tree - the tree to search
+ * @start - the offset at/after which the found extent should start
+ * @start_ret - records the beginning of the range
+ * @end_ret - records the end of the range (inclusive)
+ * @bits - the set of bits which must be unset
+ *
+ * Since unallocated range is also considered one which doesn't have the bits
+ * set it's possible that @end_ret contains -1, this happens in case the range
+ * spans (last_range_end, end of device]. In this case it's up to the caller to
+ * trim @end_ret to the appropriate size.
+ */
+void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
+				 u64 *start_ret, u64 *end_ret, unsigned bits)
+{
+	struct extent_state *state;
+	struct rb_node *node, *prev = NULL, *next;
+
+	spin_lock(&tree->lock);
+
+	/* Find first extent with bits cleared */
+	while (1) {
+		node = __etree_search(tree, start, &next, &prev, NULL, NULL);
+		if (!node) {
+			node = next;
+			if (!node) {
+				/*
+				 * We are past the last allocated chunk,
+				 * set start at the end of the last extent. The
+				 * device alloc tree should never be empty so
+				 * prev is always set.
+				 */
+				ASSERT(prev);
+				state = rb_entry(prev, struct extent_state, rb_node);
+				*start_ret = state->end + 1;
+				*end_ret = -1;
+				goto out;
+			}
+		}
+		state = rb_entry(node, struct extent_state, rb_node);
+		if (in_range(start, state->start, state->end - state->start + 1) &&
+			(state->state & bits)) {
+			start = state->end + 1;
+		} else {
+			*start_ret = start;
+			break;
+		}
+	}
+
+	/*
+	 * Find the longest stretch from start until an entry which has the
+	 * bits set
+	 */
+	while (1) {
+		state = rb_entry(node, struct extent_state, rb_node);
+		if (state->end >= start && !(state->state & bits)) {
+			*end_ret = state->end;
+		} else {
+			*end_ret = state->start - 1;
+			break;
+		}
+
+		node = rb_next(node);
+		if (!node)
+			break;
+	}
+out:
+	spin_unlock(&tree->lock);
+}
+
 /*
  * find a contiguous range of bytes in the file marked as delalloc, not
  * more than 'max_bytes'.  start and end are used to return the range,
@@ -2061,9 +2192,9 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 	return 0;
 }
 
-int repair_eb_io_failure(struct btrfs_fs_info *fs_info,
-			 struct extent_buffer *eb, int mirror_num)
+int btrfs_repair_eb_io_failure(struct extent_buffer *eb, int mirror_num)
 {
+	struct btrfs_fs_info *fs_info = eb->fs_info;
 	u64 start = eb->start;
 	int i, num_pages = num_extent_pages(eb);
 	int ret = 0;
@@ -2409,7 +2540,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 		read_mode, failrec->this_mirror, failrec->in_validation);
 
 	status = tree->ops->submit_bio_hook(tree->private_data, bio, failrec->this_mirror,
-					 failrec->bio_flags, 0);
+					 failrec->bio_flags);
 	if (status) {
 		free_io_failure(failure_tree, tree, failrec);
 		bio_put(bio);
@@ -2607,8 +2738,6 @@ static void end_bio_extent_readpage(struct bio *bio)
 			if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD,
 					       &eb->bflags))
 				btree_readahead_hook(eb, -EIO);
-
-			ret = -EIO;
 		}
 readpage_ok:
 		if (likely(uptodate)) {
@@ -3069,7 +3198,7 @@ out:
 	return ret;
 }
 
-static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
+static inline void contiguous_readpages(struct extent_io_tree *tree,
 					     struct page *pages[], int nr_pages,
 					     u64 start, u64 end,
 					     struct extent_map **em_cached,
@@ -3100,46 +3229,6 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 	}
 }
 
-static void __extent_readpages(struct extent_io_tree *tree,
-			       struct page *pages[],
-			       int nr_pages,
-			       struct extent_map **em_cached,
-			       struct bio **bio, unsigned long *bio_flags,
-			       u64 *prev_em_start)
-{
-	u64 start = 0;
-	u64 end = 0;
-	u64 page_start;
-	int index;
-	int first_index = 0;
-
-	for (index = 0; index < nr_pages; index++) {
-		page_start = page_offset(pages[index]);
-		if (!end) {
-			start = page_start;
-			end = start + PAGE_SIZE - 1;
-			first_index = index;
-		} else if (end + 1 == page_start) {
-			end += PAGE_SIZE;
-		} else {
-			__do_contiguous_readpages(tree, &pages[first_index],
-						  index - first_index, start,
-						  end, em_cached,
-						  bio, bio_flags,
-						  prev_em_start);
-			start = page_start;
-			end = start + PAGE_SIZE - 1;
-			first_index = index;
-		}
-	}
-
-	if (end)
-		__do_contiguous_readpages(tree, &pages[first_index],
-					  index - first_index, start,
-					  end, em_cached, bio,
-					  bio_flags, prev_em_start);
-}
-
 static int __extent_read_full_page(struct extent_io_tree *tree,
 				   struct page *page,
 				   get_extent_t *get_extent,
@@ -3419,6 +3508,9 @@ done:
  * records are inserted to lock ranges in the tree, and as dirty areas
  * are found, they are marked writeback.  Then the lock bits are removed
  * and the end_io handler clears the writeback ranges
+ *
+ * Return 0 if everything goes well.
+ * Return <0 for error.
  */
 static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 			      struct extent_page_data *epd)
@@ -3488,6 +3580,7 @@ done:
 		end_extent_writepage(page, ret, start, page_end);
 	}
 	unlock_page(page);
+	ASSERT(ret <= 0);
 	return ret;
 
 done_unlocked:
@@ -3500,18 +3593,26 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
 		       TASK_UNINTERRUPTIBLE);
 }
 
-static noinline_for_stack int
-lock_extent_buffer_for_io(struct extent_buffer *eb,
-			  struct btrfs_fs_info *fs_info,
+/*
+ * Lock eb pages and flush the bio if we can't the locks
+ *
+ * Return  0 if nothing went wrong
+ * Return >0 is same as 0, except bio is not submitted
+ * Return <0 if something went wrong, no page is locked
+ */
+static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb,
 			  struct extent_page_data *epd)
 {
-	int i, num_pages;
+	struct btrfs_fs_info *fs_info = eb->fs_info;
+	int i, num_pages, failed_page_nr;
 	int flush = 0;
 	int ret = 0;
 
 	if (!btrfs_try_tree_write_lock(eb)) {
+		ret = flush_write_bio(epd);
+		if (ret < 0)
+			return ret;
 		flush = 1;
-		flush_write_bio(epd);
 		btrfs_tree_lock(eb);
 	}
 
@@ -3520,7 +3621,9 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
 		if (!epd->sync_io)
 			return 0;
 		if (!flush) {
-			flush_write_bio(epd);
+			ret = flush_write_bio(epd);
+			if (ret < 0)
+				return ret;
 			flush = 1;
 		}
 		while (1) {
@@ -3561,7 +3664,11 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
 
 		if (!trylock_page(p)) {
 			if (!flush) {
-				flush_write_bio(epd);
+				ret = flush_write_bio(epd);
+				if (ret < 0) {
+					failed_page_nr = i;
+					goto err_unlock;
+				}
 				flush = 1;
 			}
 			lock_page(p);
@@ -3569,6 +3676,11 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
 	}
 
 	return ret;
+err_unlock:
+	/* Unlock already locked pages */
+	for (i = 0; i < failed_page_nr; i++)
+		unlock_page(eb->pages[i]);
+	return ret;
 }
 
 static void end_extent_buffer_writeback(struct extent_buffer *eb)
@@ -3672,10 +3784,10 @@ static void end_bio_extent_buffer_writepage(struct bio *bio)
 }
 
 static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
-			struct btrfs_fs_info *fs_info,
 			struct writeback_control *wbc,
 			struct extent_page_data *epd)
 {
+	struct btrfs_fs_info *fs_info = eb->fs_info;
 	struct block_device *bdev = fs_info->fs_devices->latest_bdev;
 	struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
 	u64 offset = eb->start;
@@ -3701,7 +3813,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 		 * header 0 1 2 .. N ... data_N .. data_2 data_1 data_0
 		 */
 		start = btrfs_item_nr_offset(nritems);
-		end = BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, eb);
+		end = BTRFS_LEAF_DATA_OFFSET + leaf_data_end(eb);
 		memzero_extent_buffer(eb, start, end - start);
 	}
 
@@ -3744,7 +3856,6 @@ int btree_write_cache_pages(struct address_space *mapping,
 				   struct writeback_control *wbc)
 {
 	struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree;
-	struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info;
 	struct extent_buffer *eb, *prev_eb = NULL;
 	struct extent_page_data epd = {
 		.bio = NULL,
@@ -3819,13 +3930,13 @@ retry:
 				continue;
 
 			prev_eb = eb;
-			ret = lock_extent_buffer_for_io(eb, fs_info, &epd);
+			ret = lock_extent_buffer_for_io(eb, &epd);
 			if (!ret) {
 				free_extent_buffer(eb);
 				continue;
 			}
 
-			ret = write_one_eb(eb, fs_info, wbc, &epd);
+			ret = write_one_eb(eb, wbc, &epd);
 			if (ret) {
 				done = 1;
 				free_extent_buffer(eb);
@@ -3852,7 +3963,12 @@ retry:
 		index = 0;
 		goto retry;
 	}
-	flush_write_bio(&epd);
+	ASSERT(ret <= 0);
+	if (ret < 0) {
+		end_write_bio(&epd, ret);
+		return ret;
+	}
+	ret = flush_write_bio(&epd);
 	return ret;
 }
 
@@ -3949,7 +4065,8 @@ retry:
 			 * tmpfs file mapping
 			 */
 			if (!trylock_page(page)) {
-				flush_write_bio(epd);
+				ret = flush_write_bio(epd);
+				BUG_ON(ret < 0);
 				lock_page(page);
 			}
 
@@ -3959,8 +4076,10 @@ retry:
 			}
 
 			if (wbc->sync_mode != WB_SYNC_NONE) {
-				if (PageWriteback(page))
-					flush_write_bio(epd);
+				if (PageWriteback(page)) {
+					ret = flush_write_bio(epd);
+					BUG_ON(ret < 0);
+				}
 				wait_on_page_writeback(page);
 			}
 
@@ -3971,11 +4090,6 @@ retry:
 			}
 
 			ret = __extent_writepage(page, wbc, epd);
-
-			if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) {
-				unlock_page(page);
-				ret = 0;
-			}
 			if (ret < 0) {
 				/*
 				 * done_index is set past this page,
@@ -4029,8 +4143,14 @@ int extent_write_full_page(struct page *page, struct writeback_control *wbc)
 	};
 
 	ret = __extent_writepage(page, wbc, &epd);
+	ASSERT(ret <= 0);
+	if (ret < 0) {
+		end_write_bio(&epd, ret);
+		return ret;
+	}
 
-	flush_write_bio(&epd);
+	ret = flush_write_bio(&epd);
+	ASSERT(ret <= 0);
 	return ret;
 }
 
@@ -4070,7 +4190,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 		start += PAGE_SIZE;
 	}
 
-	flush_write_bio(&epd);
+	ASSERT(ret <= 0);
+	if (ret < 0) {
+		end_write_bio(&epd, ret);
+		return ret;
+	}
+	ret = flush_write_bio(&epd);
 	return ret;
 }
 
@@ -4086,7 +4211,12 @@ int extent_writepages(struct address_space *mapping,
 	};
 
 	ret = extent_write_cache_pages(mapping, wbc, &epd);
-	flush_write_bio(&epd);
+	ASSERT(ret <= 0);
+	if (ret < 0) {
+		end_write_bio(&epd, ret);
+		return ret;
+	}
+	ret = flush_write_bio(&epd);
 	return ret;
 }
 
@@ -4102,6 +4232,8 @@ int extent_readpages(struct address_space *mapping, struct list_head *pages,
 	u64 prev_em_start = (u64)-1;
 
 	while (!list_empty(pages)) {
+		u64 contig_end = 0;
+
 		for (nr = 0; nr < ARRAY_SIZE(pagepool) && !list_empty(pages);) {
 			struct page *page = lru_to_page(pages);
 
@@ -4110,14 +4242,22 @@ int extent_readpages(struct address_space *mapping, struct list_head *pages,
 			if (add_to_page_cache_lru(page, mapping, page->index,
 						readahead_gfp_mask(mapping))) {
 				put_page(page);
-				continue;
+				break;
 			}
 
 			pagepool[nr++] = page;
+			contig_end = page_offset(page) + PAGE_SIZE - 1;
 		}
 
-		__extent_readpages(tree, pagepool, nr, &em_cached, &bio,
-				   &bio_flags, &prev_em_start);
+		if (nr) {
+			u64 contig_start = page_offset(pagepool[0]);
+
+			ASSERT(contig_start + nr * PAGE_SIZE - 1 == contig_end);
+
+			contiguous_readpages(tree, pagepool, nr, contig_start,
+				     contig_end, &em_cached, &bio, &bio_flags,
+				     &prev_em_start);
+		}
 	}
 
 	if (em_cached)
@@ -4166,10 +4306,9 @@ static int try_release_extent_state(struct extent_io_tree *tree,
 	u64 end = start + PAGE_SIZE - 1;
 	int ret = 1;
 
-	if (test_range_bit(tree, start, end,
-			   EXTENT_IOBITS, 0, NULL))
+	if (test_range_bit(tree, start, end, EXTENT_LOCKED, 0, NULL)) {
 		ret = 0;
-	else {
+	} else {
 		/*
 		 * at this point we can safely clear everything except the
 		 * locked bit and the nodatasum bit
@@ -4222,8 +4361,7 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 			}
 			if (!test_range_bit(tree, em->start,
 					    extent_map_end(em) - 1,
-					    EXTENT_LOCKED | EXTENT_WRITEBACK,
-					    0, NULL)) {
+					    EXTENT_LOCKED, 0, NULL)) {
 				set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 					&btrfs_inode->runtime_flags);
 				remove_extent_mapping(map, em);
@@ -4372,8 +4510,7 @@ try_submit_last:
  * In this case, the first extent range will be cached but not emitted.
  * So we must emit it before ending extent_fiemap().
  */
-static int emit_last_fiemap_cache(struct btrfs_fs_info *fs_info,
-				  struct fiemap_extent_info *fieinfo,
+static int emit_last_fiemap_cache(struct fiemap_extent_info *fieinfo,
 				  struct fiemap_cache *cache)
 {
 	int ret;
@@ -4580,7 +4717,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	}
 out_free:
 	if (!ret)
-		ret = emit_last_fiemap_cache(root->fs_info, fieinfo, &cache);
+		ret = emit_last_fiemap_cache(fieinfo, &cache);
 	free_extent_map(em);
 out:
 	btrfs_free_path(path);
@@ -4672,13 +4809,9 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
 	eb->fs_info = fs_info;
 	eb->bflags = 0;
 	rwlock_init(&eb->lock);
-	atomic_set(&eb->write_locks, 0);
-	atomic_set(&eb->read_locks, 0);
 	atomic_set(&eb->blocking_readers, 0);
 	atomic_set(&eb->blocking_writers, 0);
-	atomic_set(&eb->spinning_readers, 0);
-	atomic_set(&eb->spinning_writers, 0);
-	eb->lock_nested = 0;
+	eb->lock_nested = false;
 	init_waitqueue_head(&eb->write_lock_wq);
 	init_waitqueue_head(&eb->read_lock_wq);
 
@@ -4695,6 +4828,13 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
 		> MAX_INLINE_EXTENT_BUFFER_SIZE);
 	BUG_ON(len > MAX_INLINE_EXTENT_BUFFER_SIZE);
 
+#ifdef CONFIG_BTRFS_DEBUG
+	atomic_set(&eb->spinning_writers, 0);
+	atomic_set(&eb->spinning_readers, 0);
+	atomic_set(&eb->read_locks, 0);
+	atomic_set(&eb->write_locks, 0);
+#endif
+
 	return eb;
 }
 
@@ -5183,8 +5323,7 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb)
 	}
 }
 
-int read_extent_buffer_pages(struct extent_io_tree *tree,
-			     struct extent_buffer *eb, int wait, int mirror_num)
+int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num)
 {
 	int i;
 	struct page *page;
@@ -5196,6 +5335,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	unsigned long num_reads = 0;
 	struct bio *bio = NULL;
 	unsigned long bio_flags = 0;
+	struct extent_io_tree *tree = &BTRFS_I(eb->fs_info->btree_inode)->io_tree;
 
 	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
 		return 0;
@@ -5746,13 +5886,13 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 		btrfs_err(fs_info,
 			"memmove bogus src_offset %lu move len %lu dst len %lu",
 			 src_offset, len, dst->len);
-		BUG_ON(1);
+		BUG();
 	}
 	if (dst_offset + len > dst->len) {
 		btrfs_err(fs_info,
 			"memmove bogus dst_offset %lu move len %lu dst len %lu",
 			 dst_offset, len, dst->len);
-		BUG_ON(1);
+		BUG();
 	}
 
 	while (len > 0) {
@@ -5793,13 +5933,13 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 		btrfs_err(fs_info,
 			  "memmove bogus src_offset %lu move len %lu len %lu",
 			  src_offset, len, dst->len);
-		BUG_ON(1);
+		BUG();
 	}
 	if (dst_offset + len > dst->len) {
 		btrfs_err(fs_info,
 			  "memmove bogus dst_offset %lu move len %lu len %lu",
 			  dst_offset, len, dst->len);
-		BUG_ON(1);
+		BUG();
 	}
 	if (dst_offset < src_offset) {
 		memcpy_extent_buffer(dst, dst_offset, src_offset, len);