Merge tag 'for-5.20-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This brings some long awaited changes, the send protocol bump,
  otherwise lots of small improvements and fixes. The main core part is
  reworking bio handling, cleaning up the submission and endio and
  improving error handling.

  There are some changes outside of btrfs adding helpers or updating
  API, listed at the end of the changelog.

  Features:

   - sysfs:
      - export chunk size, in debug mode add tunable for setting its size
      - show zoned among features (was only in debug mode)
      - show commit stats (number, last/max/total duration)

   - send protocol updated to 2
      - new commands:
         - ability write larger data chunks than 64K
         - send raw compressed extents (uses the encoded data ioctls),
           ie. no decompression on send side, no compression needed on
           receive side if supported
         - send 'otime' (inode creation time) among other timestamps
         - send file attributes (a.k.a file flags and xflags)
      - this is first version bump, backward compatibility on send and
        receive side is provided
      - there are still some known and wanted commands that will be
        implemented in the near future, another version bump will be
        needed, however we want to minimize that to avoid causing
        usability issues

   - print checksum type and implementation at mount time

   - don't print some messages at mount (mentioned as people asked about
     it), we want to print messages namely for new features so let's
     make some space for that
      - big metadata - this has been supported for a long time and is
        not a feature that's worth mentioning
      - skinny metadata - same reason, set by default by mkfs

  Performance improvements:

   - reduced amount of reserved metadata for delayed items
      - when inserted items can be batched into one leaf
      - when deleting batched directory index items
      - when deleting delayed items used for deletion
      - overall improved count of files/sec, decreased subvolume lock
        contention

   - metadata item access bounds checker micro-optimized, with a few
     percent of improved runtime for metadata-heavy operations

   - increase direct io limit for read to 256 sectors, improved
     throughput by 3x on sample workload

  Notable fixes:

   - raid56
      - reduce parity writes, skip sectors of stripe when there are no
        data updates
      - restore reading from on-disk data instead of using stripe cache,
        this reduces chances to damage correct data due to RMW cycle

   - refuse to replay log with unknown incompat read-only feature bit
     set

   - zoned
      - fix page locking when COW fails in the middle of allocation
      - improved tracking of active zones, ZNS drives may limit the
        number and there are ENOSPC errors due to that limit and not
        actual lack of space
      - adjust maximum extent size for zone append so it does not cause
        late ENOSPC due to underreservation

   - mirror reading error messages show the mirror number

   - don't fallback to buffered IO for NOWAIT direct IO writes, we don't
     have the NOWAIT semantics for buffered io yet

   - send, fix sending link commands for existing file paths when there
     are deleted and created hardlinks for same files

   - repair all mirrors for profiles with more than 1 copy (raid1c34)

   - fix repair of compressed extents, unify where error detection and
     repair happen

  Core changes:

   - bio completion cleanups
      - don't double defer compression bios
      - simplify endio workqueues
      - add more data to btrfs_bio to avoid allocation for read requests
      - rework bio error handling so it's same what block layer does,
        the submission works and errors are consumed in endio
      - when asynchronous bio offload fails fall back to synchronous
        checksum calculation to avoid errors under writeback or memory
        pressure

   - new trace points
      - raid56 events
      - ordered extent operations

   - super block log_root_transid deprecated (never used)

   - mixed_backref and big_metadata sysfs feature files removed, they've
     been default for sufficiently long time, there are no known users
     and mixed_backref could be confused with mixed_groups

  Non-btrfs changes, API updates:

   - minor highmem API update to cover const arguments

   - switch all kmap/kmap_atomic to kmap_local

   - remove redundant flush_dcache_page()

   - address_space_operations::writepage callback removed

   - add bdev_max_segments() helper"

* tag 'for-5.20-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (163 commits)
  btrfs: don't call btrfs_page_set_checked in finish_compressed_bio_read
  btrfs: fix repair of compressed extents
  btrfs: remove the start argument to check_data_csum and export
  btrfs: pass a btrfs_bio to btrfs_repair_one_sector
  btrfs: simplify the pending I/O counting in struct compressed_bio
  btrfs: repair all known bad mirrors
  btrfs: merge btrfs_dev_stat_print_on_error with its only caller
  btrfs: join running log transaction when logging new name
  btrfs: simplify error handling in btrfs_lookup_dentry
  btrfs: send: always use the rbtree based inode ref management infrastructure
  btrfs: send: fix sending link commands for existing file paths
  btrfs: send: introduce recorded_ref_alloc and recorded_ref_free
  btrfs: zoned: wait until zone is finished when allocation didn't progress
  btrfs: zoned: write out partially allocated region
  btrfs: zoned: activate necessary block group
  btrfs: zoned: activate metadata block group on flush_space
  btrfs: zoned: disable metadata overcommit for zoned
  btrfs: zoned: introduce space_info->active_total_bytes
  btrfs: zoned: finish least available block group on data bg allocation
  btrfs: let can_allocate_chunk return error
  ...

1 files changed, 400 insertions, 364 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3867cb0646e9..f0c97d25b4a0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -114,21 +114,17 @@ struct kmem_cache *btrfs_free_space_bitmap_cachep;
 
 static int btrfs_setsize(struct inode *inode, struct iattr *attr);
 static int btrfs_truncate(struct inode *inode, bool skip_writeback);
-static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent);
 static noinline int cow_file_range(struct btrfs_inode *inode,
 				   struct page *locked_page,
 				   u64 start, u64 end, int *page_started,
-				   unsigned long *nr_written, int unlock);
+				   unsigned long *nr_written, int unlock,
+				   u64 *done_offset);
 static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
 				       u64 len, u64 orig_start, u64 block_start,
 				       u64 block_len, u64 orig_block_len,
 				       u64 ram_bytes, int compress_type,
 				       int type);
 
-static void __endio_write_update_ordered(struct btrfs_inode *inode,
-					 const u64 offset, const u64 bytes,
-					 const bool uptodate);
-
 /*
  * btrfs_inode_lock - lock inode i_rwsem based on arguments passed
  *
@@ -195,11 +191,14 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
 {
 	unsigned long index = offset >> PAGE_SHIFT;
 	unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT;
-	u64 page_start = page_offset(locked_page);
-	u64 page_end = page_start + PAGE_SIZE - 1;
-
+	u64 page_start, page_end;
 	struct page *page;
 
+	if (locked_page) {
+		page_start = page_offset(locked_page);
+		page_end = page_start + PAGE_SIZE - 1;
+	}
+
 	while (index <= end_index) {
 		/*
 		 * For locked page, we will call end_extent_writepage() on it
@@ -212,7 +211,7 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
 		 * btrfs_mark_ordered_io_finished() would skip the accounting
 		 * for the page range, and the ordered extent will never finish.
 		 */
-		if (index == (page_offset(locked_page) >> PAGE_SHIFT)) {
+		if (locked_page && index == (page_start >> PAGE_SHIFT)) {
 			index++;
 			continue;
 		}
@@ -223,7 +222,7 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
 
 		/*
 		 * Here we just clear all Ordered bits for every page in the
-		 * range, then __endio_write_update_ordered() will handle
+		 * range, then btrfs_mark_ordered_io_finished() will handle
 		 * the ordered extent accounting for the range.
 		 */
 		btrfs_page_clamp_clear_ordered(inode->root->fs_info, page,
@@ -231,20 +230,23 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
 		put_page(page);
 	}
 
-	/* The locked page covers the full range, nothing needs to be done */
-	if (bytes + offset <= page_offset(locked_page) + PAGE_SIZE)
-		return;
-	/*
-	 * In case this page belongs to the delalloc range being instantiated
-	 * then skip it, since the first page of a range is going to be
-	 * properly cleaned up by the caller of run_delalloc_range
-	 */
-	if (page_start >= offset && page_end <= (offset + bytes - 1)) {
-		bytes = offset + bytes - page_offset(locked_page) - PAGE_SIZE;
-		offset = page_offset(locked_page) + PAGE_SIZE;
+	if (locked_page) {
+		/* The locked page covers the full range, nothing needs to be done */
+		if (bytes + offset <= page_start + PAGE_SIZE)
+			return;
+		/*
+		 * In case this page belongs to the delalloc range being
+		 * instantiated then skip it, since the first page of a range is
+		 * going to be properly cleaned up by the caller of
+		 * run_delalloc_range
+		 */
+		if (page_start >= offset && page_end <= (offset + bytes - 1)) {
+			bytes = offset + bytes - page_offset(locked_page) - PAGE_SIZE;
+			offset = page_offset(locked_page) + PAGE_SIZE;
+		}
 	}
 
-	return __endio_write_update_ordered(inode, offset, bytes, false);
+	return btrfs_mark_ordered_io_finished(inode, NULL, offset, bytes, false);
 }
 
 static int btrfs_dirty_inode(struct inode *inode);
@@ -332,9 +334,9 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 			cur_size = min_t(unsigned long, compressed_size,
 				       PAGE_SIZE);
 
-			kaddr = kmap_atomic(cpage);
+			kaddr = kmap_local_page(cpage);
 			write_extent_buffer(leaf, kaddr, ptr, cur_size);
-			kunmap_atomic(kaddr);
+			kunmap_local(kaddr);
 
 			i++;
 			ptr += cur_size;
@@ -345,9 +347,9 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 	} else {
 		page = find_get_page(inode->vfs_inode.i_mapping, 0);
 		btrfs_set_file_extent_compression(leaf, ei, 0);
-		kaddr = kmap_atomic(page);
+		kaddr = kmap_local_page(page);
 		write_extent_buffer(leaf, kaddr, ptr, size);
-		kunmap_atomic(kaddr);
+		kunmap_local(kaddr);
 		put_page(page);
 	}
 	btrfs_mark_buffer_dirty(leaf);
@@ -560,8 +562,8 @@ static inline int inode_need_compress(struct btrfs_inode *inode, u64 start,
 	 * will unlock the full page.
 	 */
 	if (fs_info->sectorsize < PAGE_SIZE) {
-		if (!IS_ALIGNED(start, PAGE_SIZE) ||
-		    !IS_ALIGNED(end + 1, PAGE_SIZE))
+		if (!PAGE_ALIGNED(start) ||
+		    !PAGE_ALIGNED(end + 1))
 			return 0;
 	}
 
@@ -678,8 +680,8 @@ again:
 	 * Thus we must also check against @actual_end, not just @end.
 	 */
 	if (blocksize < PAGE_SIZE) {
-		if (!IS_ALIGNED(start, PAGE_SIZE) ||
-		    !IS_ALIGNED(round_up(actual_end, blocksize), PAGE_SIZE))
+		if (!PAGE_ALIGNED(start) ||
+		    !PAGE_ALIGNED(round_up(actual_end, blocksize)))
 			goto cleanup_and_bail_uncompressed;
 	}
 
@@ -920,15 +922,25 @@ static int submit_uncompressed_range(struct btrfs_inode *inode,
 	 * can directly submit them without interruption.
 	 */
 	ret = cow_file_range(inode, locked_page, start, end, &page_started,
-			     &nr_written, 0);
+			     &nr_written, 0, NULL);
 	/* Inline extent inserted, page gets unlocked and everything is done */
 	if (page_started) {
 		ret = 0;
 		goto out;
 	}
 	if (ret < 0) {
-		if (locked_page)
+		btrfs_cleanup_ordered_extents(inode, locked_page, start, end - start + 1);
+		if (locked_page) {
+			const u64 page_start = page_offset(locked_page);
+			const u64 page_end = page_start + PAGE_SIZE - 1;
+
+			btrfs_page_set_error(inode->root->fs_info, locked_page,
+					     page_start, PAGE_SIZE);
+			set_page_writeback(locked_page);
+			end_page_writeback(locked_page);
+			end_extent_writepage(locked_page, ret, page_start, page_end);
 			unlock_page(locked_page);
+		}
 		goto out;
 	}
 
@@ -1133,15 +1145,39 @@ static u64 get_extent_allocation_hint(struct btrfs_inode *inode, u64 start,
  * *page_started is set to one if we unlock locked_page and do everything
  * required to start IO on it.  It may be clean and already done with
  * IO when we return.
+ *
+ * When unlock == 1, we unlock the pages in successfully allocated regions.
+ * When unlock == 0, we leave them locked for writing them out.
+ *
+ * However, we unlock all the pages except @locked_page in case of failure.
+ *
+ * In summary, page locking state will be as follow:
+ *
+ * - page_started == 1 (return value)
+ *     - All the pages are unlocked. IO is started.
+ *     - Note that this can happen only on success
+ * - unlock == 1
+ *     - All the pages except @locked_page are unlocked in any case
+ * - unlock == 0
+ *     - On success, all the pages are locked for writing out them
+ *     - On failure, all the pages except @locked_page are unlocked
+ *
+ * When a failure happens in the second or later iteration of the
+ * while-loop, the ordered extents created in previous iterations are kept
+ * intact. So, the caller must clean them up by calling
+ * btrfs_cleanup_ordered_extents(). See btrfs_run_delalloc_range() for
+ * example.
  */
 static noinline int cow_file_range(struct btrfs_inode *inode,
 				   struct page *locked_page,
 				   u64 start, u64 end, int *page_started,
-				   unsigned long *nr_written, int unlock)
+				   unsigned long *nr_written, int unlock,
+				   u64 *done_offset)
 {
 	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 alloc_hint = 0;
+	u64 orig_start = start;
 	u64 num_bytes;
 	unsigned long ram_size;
 	u64 cur_alloc_size = 0;
@@ -1329,18 +1365,62 @@ out_reserve:
 	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
 	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
 out_unlock:
+	/*
+	 * If done_offset is non-NULL and ret == -EAGAIN, we expect the
+	 * caller to write out the successfully allocated region and retry.
+	 */
+	if (done_offset && ret == -EAGAIN) {
+		if (orig_start < start)
+			*done_offset = start - 1;
+		else
+			*done_offset = start;
+		return ret;
+	} else if (ret == -EAGAIN) {
+		/* Convert to -ENOSPC since the caller cannot retry. */
+		ret = -ENOSPC;
+	}
+
+	/*
+	 * Now, we have three regions to clean up:
+	 *
+	 * |-------(1)----|---(2)---|-------------(3)----------|
+	 * `- orig_start  `- start  `- start + cur_alloc_size  `- end
+	 *
+	 * We process each region below.
+	 */
+
 	clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
 		EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
 	page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK;
+
+	/*
+	 * For the range (1). We have already instantiated the ordered extents
+	 * for this region. They are cleaned up by
+	 * btrfs_cleanup_ordered_extents() in e.g,
+	 * btrfs_run_delalloc_range(). EXTENT_LOCKED | EXTENT_DELALLOC are
+	 * already cleared in the above loop. And, EXTENT_DELALLOC_NEW |
+	 * EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV are handled by the cleanup
+	 * function.
+	 *
+	 * However, in case of unlock == 0, we still need to unlock the pages
+	 * (except @locked_page) to ensure all the pages are unlocked.
+	 */
+	if (!unlock && orig_start < start) {
+		if (!locked_page)
+			mapping_set_error(inode->vfs_inode.i_mapping, ret);
+		extent_clear_unlock_delalloc(inode, orig_start, start - 1,
+					     locked_page, 0, page_ops);
+	}
+
 	/*
-	 * If we reserved an extent for our delalloc range (or a subrange) and
-	 * failed to create the respective ordered extent, then it means that
-	 * when we reserved the extent we decremented the extent's size from
-	 * the data space_info's bytes_may_use counter and incremented the
-	 * space_info's bytes_reserved counter by the same amount. We must make
-	 * sure extent_clear_unlock_delalloc() does not try to decrement again
-	 * the data space_info's bytes_may_use counter, therefore we do not pass
-	 * it the flag EXTENT_CLEAR_DATA_RESV.
+	 * For the range (2). If we reserved an extent for our delalloc range
+	 * (or a subrange) and failed to create the respective ordered extent,
+	 * then it means that when we reserved the extent we decremented the
+	 * extent's size from the data space_info's bytes_may_use counter and
+	 * incremented the space_info's bytes_reserved counter by the same
+	 * amount. We must make sure extent_clear_unlock_delalloc() does not try
+	 * to decrement again the data space_info's bytes_may_use counter,
+	 * therefore we do not pass it the flag EXTENT_CLEAR_DATA_RESV.
 	 */
 	if (extent_reserved) {
 		extent_clear_unlock_delalloc(inode, start,
@@ -1350,12 +1430,19 @@ out_unlock:
 					     page_ops);
 		start += cur_alloc_size;
 		if (start >= end)
-			goto out;
+			return ret;
 	}
+
+	/*
+	 * For the range (3). We never touched the region. In addition to the
+	 * clear_bits above, we add EXTENT_CLEAR_DATA_RESV to release the data
+	 * space_info's bytes_may_use counter, reserved in
+	 * btrfs_check_data_free_space().
+	 */
 	extent_clear_unlock_delalloc(inode, start, end, locked_page,
 				     clear_bits | EXTENT_CLEAR_DATA_RESV,
 				     page_ops);
-	goto out;
+	return ret;
 }
 
 /*
@@ -1538,19 +1625,42 @@ static noinline int run_delalloc_zoned(struct btrfs_inode *inode,
 				       u64 end, int *page_started,
 				       unsigned long *nr_written)
 {
+	u64 done_offset = end;
 	int ret;
+	bool locked_page_done = false;
 
-	ret = cow_file_range(inode, locked_page, start, end, page_started,
-			     nr_written, 0);
-	if (ret)
-		return ret;
+	while (start <= end) {
+		ret = cow_file_range(inode, locked_page, start, end, page_started,
+				     nr_written, 0, &done_offset);
+		if (ret && ret != -EAGAIN)
+			return ret;
 
-	if (*page_started)
-		return 0;
+		if (*page_started) {
+			ASSERT(ret == 0);
+			return 0;
+		}
+
+		if (ret == 0)
+			done_offset = end;
+
+		if (done_offset == start) {
+			struct btrfs_fs_info *info = inode->root->fs_info;
+
+			wait_var_event(&info->zone_finish_wait,
+				       !test_bit(BTRFS_FS_NEED_ZONE_FINISH, &info->flags));
+			continue;
+		}
+
+		if (!locked_page_done) {
+			__set_page_dirty_nobuffers(locked_page);
+			account_page_redirty(locked_page);
+		}
+		locked_page_done = true;
+		extent_write_locked_range(&inode->vfs_inode, start, done_offset);
+
+		start = done_offset + 1;
+	}
 
-	__set_page_dirty_nobuffers(locked_page);
-	account_page_redirty(locked_page);
-	extent_write_locked_range(&inode->vfs_inode, start, end);
 	*page_started = 1;
 
 	return 0;
@@ -1642,7 +1752,7 @@ static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page,
 	}
 
 	return cow_file_range(inode, locked_page, start, end, page_started,
-			      nr_written, 1);
+			      nr_written, 1, NULL);
 }
 
 struct can_nocow_file_extent_args {
@@ -2115,7 +2225,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page
 						 page_started, nr_written);
 		else
 			ret = cow_file_range(inode, locked_page, start, end,
-					     page_started, nr_written, 1);
+					     page_started, nr_written, 1, NULL);
 	} else {
 		set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags);
 		ret = cow_file_range_async(inode, wbc, locked_page, start, end,
@@ -2131,6 +2241,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page
 void btrfs_split_delalloc_extent(struct inode *inode,
 				 struct extent_state *orig, u64 split)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	u64 size;
 
 	/* not delalloc, ignore it */
@@ -2138,7 +2249,7 @@ void btrfs_split_delalloc_extent(struct inode *inode,
 		return;
 
 	size = orig->end - orig->start + 1;
-	if (size > BTRFS_MAX_EXTENT_SIZE) {
+	if (size > fs_info->max_extent_size) {
 		u32 num_extents;
 		u64 new_size;
 
@@ -2147,10 +2258,10 @@ void btrfs_split_delalloc_extent(struct inode *inode,
 		 * applies here, just in reverse.
 		 */
 		new_size = orig->end - split + 1;
-		num_extents = count_max_extents(new_size);
+		num_extents = count_max_extents(fs_info, new_size);
 		new_size = split - orig->start;
-		num_extents += count_max_extents(new_size);
-		if (count_max_extents(size) >= num_extents)
+		num_extents += count_max_extents(fs_info, new_size);
+		if (count_max_extents(fs_info, size) >= num_extents)
 			return;
 	}
 
@@ -2167,6 +2278,7 @@ void btrfs_split_delalloc_extent(struct inode *inode,
 void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
 				 struct extent_state *other)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	u64 new_size, old_size;
 	u32 num_extents;
 
@@ -2180,7 +2292,7 @@ void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
 		new_size = other->end - new->start + 1;
 
 	/* we're not bigger than the max, unreserve the space and go */
-	if (new_size <= BTRFS_MAX_EXTENT_SIZE) {
+	if (new_size <= fs_info->max_extent_size) {
 		spin_lock(&BTRFS_I(inode)->lock);
 		btrfs_mod_outstanding_extents(BTRFS_I(inode), -1);
 		spin_unlock(&BTRFS_I(inode)->lock);
@@ -2206,10 +2318,10 @@ void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
 	 * this case.
 	 */
 	old_size = other->end - other->start + 1;
-	num_extents = count_max_extents(old_size);
+	num_extents = count_max_extents(fs_info, old_size);
 	old_size = new->end - new->start + 1;
-	num_extents += count_max_extents(old_size);
-	if (count_max_extents(new_size) >= num_extents)
+	num_extents += count_max_extents(fs_info, old_size);
+	if (count_max_extents(fs_info, new_size) >= num_extents)
 		return;
 
 	spin_lock(&BTRFS_I(inode)->lock);
@@ -2274,21 +2386,21 @@ static void btrfs_del_delalloc_inode(struct btrfs_root *root,
  * list of inodes that have pending delalloc work to be done.
  */
 void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
-			       unsigned *bits)
+			       u32 bits)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 
-	if ((*bits & EXTENT_DEFRAG) && !(*bits & EXTENT_DELALLOC))
+	if ((bits & EXTENT_DEFRAG) && !(bits & EXTENT_DELALLOC))
 		WARN_ON(1);
 	/*
 	 * set_bit and clear bit hooks normally require _irqsave/restore
 	 * but in this case, we are only testing for the DELALLOC
 	 * bit, which is only set or cleared with irqs on
 	 */
-	if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
+	if (!(state->state & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = BTRFS_I(inode)->root;
 		u64 len = state->end + 1 - state->start;
-		u32 num_extents = count_max_extents(len);
+		u32 num_extents = count_max_extents(fs_info, len);
 		bool do_list = !btrfs_is_free_space_inode(BTRFS_I(inode));
 
 		spin_lock(&BTRFS_I(inode)->lock);
@@ -2303,7 +2415,7 @@ void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
 					 fs_info->delalloc_batch);
 		spin_lock(&BTRFS_I(inode)->lock);
 		BTRFS_I(inode)->delalloc_bytes += len;
-		if (*bits & EXTENT_DEFRAG)
+		if (bits & EXTENT_DEFRAG)
 			BTRFS_I(inode)->defrag_bytes += len;
 		if (do_list && !test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
 					 &BTRFS_I(inode)->runtime_flags))
@@ -2312,7 +2424,7 @@ void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
 	}
 
 	if (!(state->state & EXTENT_DELALLOC_NEW) &&
-	    (*bits & EXTENT_DELALLOC_NEW)) {
+	    (bits & EXTENT_DELALLOC_NEW)) {
 		spin_lock(&BTRFS_I(inode)->lock);
 		BTRFS_I(inode)->new_delalloc_bytes += state->end + 1 -
 			state->start;
@@ -2325,14 +2437,14 @@ void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
  * accounting happens.
  */
 void btrfs_clear_delalloc_extent(struct inode *vfs_inode,
-				 struct extent_state *state, unsigned *bits)
+				 struct extent_state *state, u32 bits)
 {
 	struct btrfs_inode *inode = BTRFS_I(vfs_inode);
 	struct btrfs_fs_info *fs_info = btrfs_sb(vfs_inode->i_sb);
 	u64 len = state->end + 1 - state->start;
-	u32 num_extents = count_max_extents(len);
+	u32 num_extents = count_max_extents(fs_info, len);
 
-	if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG)) {
+	if ((state->state & EXTENT_DEFRAG) && (bits & EXTENT_DEFRAG)) {
 		spin_lock(&inode->lock);
 		inode->defrag_bytes -= len;
 		spin_unlock(&inode->lock);
@@ -2343,7 +2455,7 @@ void btrfs_clear_delalloc_extent(struct inode *vfs_inode,
 	 * but in this case, we are only testing for the DELALLOC
 	 * bit, which is only set or cleared with irqs on
 	 */
-	if ((state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
+	if ((state->state & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = inode->root;
 		bool do_list = !btrfs_is_free_space_inode(inode);
 
@@ -2356,7 +2468,7 @@ void btrfs_clear_delalloc_extent(struct inode *vfs_inode,
 		 * don't need to call delalloc_release_metadata if there is an
 		 * error.
 		 */
-		if (*bits & EXTENT_CLEAR_META_RESV &&
+		if (bits & EXTENT_CLEAR_META_RESV &&
 		    root != fs_info->tree_root)
 			btrfs_delalloc_release_metadata(inode, len, false);
 
@@ -2366,7 +2478,7 @@ void btrfs_clear_delalloc_extent(struct inode *vfs_inode,
 
 		if (!btrfs_is_data_reloc_root(root) &&
 		    do_list && !(state->state & EXTENT_NORESERVE) &&
-		    (*bits & EXTENT_CLEAR_DATA_RESV))
+		    (bits & EXTENT_CLEAR_DATA_RESV))
 			btrfs_free_reserved_data_space_noquota(fs_info, len);
 
 		percpu_counter_add_batch(&fs_info->delalloc_bytes, -len,
@@ -2381,11 +2493,11 @@ void btrfs_clear_delalloc_extent(struct inode *vfs_inode,
 	}
 
 	if ((state->state & EXTENT_DELALLOC_NEW) &&
-	    (*bits & EXTENT_DELALLOC_NEW)) {
+	    (bits & EXTENT_DELALLOC_NEW)) {
 		spin_lock(&inode->lock);
 		ASSERT(inode->new_delalloc_bytes >= len);
 		inode->new_delalloc_bytes -= len;
-		if (*bits & EXTENT_ADD_INODE_BYTES)
+		if (bits & EXTENT_ADD_INODE_BYTES)
 			inode_add_bytes(&inode->vfs_inode, len);
 		spin_unlock(&inode->lock);
 	}
@@ -2580,95 +2692,78 @@ out:
 	return errno_to_blk_status(ret);
 }
 
-/*
- * extent_io.c submission hook. This does the right thing for csum calculation
- * on write, or reading the csums from the tree before a read.
- *
- * Rules about async/sync submit,
- * a) read:				sync submit
- *
- * b) write without checksum:		sync submit
- *
- * c) write with checksum:
- *    c-1) if bio is issued by fsync:	sync submit
- *         (sync_writers != 0)
- *
- *    c-2) if root is reloc root:	sync submit
- *         (only in case of buffered IO)
- *
- *    c-3) otherwise:			async submit
- */
-void btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
-			   int mirror_num, enum btrfs_compression_type compress_type)
+void btrfs_submit_data_write_bio(struct inode *inode, struct bio *bio, int mirror_num)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA;
-	blk_status_t ret = 0;
-	int skip_sum;
-	int async = !atomic_read(&BTRFS_I(inode)->sync_writers);
-
-	skip_sum = (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) ||
-		test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state);
-
-	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
-		metadata = BTRFS_WQ_ENDIO_FREE_SPACE;
+	struct btrfs_inode *bi = BTRFS_I(inode);
+	blk_status_t ret;
 
 	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-		struct page *page = bio_first_bvec_all(bio)->bv_page;
-		loff_t file_offset = page_offset(page);
-
-		ret = extract_ordered_extent(BTRFS_I(inode), bio, file_offset);
+		ret = extract_ordered_extent(bi, bio,
+				page_offset(bio_first_bvec_all(bio)->bv_page));
 		if (ret)
 			goto out;
 	}
 
-	if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
-		ret = btrfs_bio_wq_end_io(fs_info, bio, metadata);
-		if (ret)
-			goto out;
-
-		if (compress_type != BTRFS_COMPRESS_NONE) {
-			/*
-			 * btrfs_submit_compressed_read will handle completing
-			 * the bio if there were any errors, so just return
-			 * here.
-			 */
-			btrfs_submit_compressed_read(inode, bio, mirror_num);
+	/*
+	 * If we need to checksum, and the I/O is not issued by fsync and
+	 * friends, that is ->sync_writers != 0, defer the submission to a
+	 * workqueue to parallelize it.
+	 *
+	 * Csum items for reloc roots have already been cloned at this point,
+	 * so they are handled as part of the no-checksum case.
+	 */
+	if (!(bi->flags & BTRFS_INODE_NODATASUM) &&
+	    !test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state) &&
+	    !btrfs_is_data_reloc_root(bi->root)) {
+		if (!atomic_read(&bi->sync_writers) &&
+		    btrfs_wq_submit_bio(inode, bio, mirror_num, 0,
+					btrfs_submit_bio_start))
 			return;
-		} else {
-			/*
-			 * Lookup bio sums does extra checks around whether we
-			 * need to csum or not, which is why we ignore skip_sum
-			 * here.
-			 */
-			ret = btrfs_lookup_bio_sums(inode, bio, NULL);
-			if (ret)
-				goto out;
-		}
-		goto mapit;
-	} else if (async && !skip_sum) {
-		/* csum items have already been cloned */
-		if (btrfs_is_data_reloc_root(root))
-			goto mapit;
-		/* we're doing a write, do the async checksumming */
-		ret = btrfs_wq_submit_bio(inode, bio, mirror_num,
-					  0, btrfs_submit_bio_start);
-		goto out;
-	} else if (!skip_sum) {
-		ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, (u64)-1, false);
+
+		ret = btrfs_csum_one_bio(bi, bio, (u64)-1, false);
 		if (ret)
 			goto out;
 	}
+	btrfs_submit_bio(fs_info, bio, mirror_num);
+	return;
+out:
+	if (ret) {
+		bio->bi_status = ret;
+		bio_endio(bio);
+	}
+}
 
-mapit:
-	ret = btrfs_map_bio(fs_info, bio, mirror_num);
+void btrfs_submit_data_read_bio(struct inode *inode, struct bio *bio,
+			int mirror_num, enum btrfs_compression_type compress_type)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	blk_status_t ret;
 
-out:
+	if (compress_type != BTRFS_COMPRESS_NONE) {
+		/*
+		 * btrfs_submit_compressed_read will handle completing the bio
+		 * if there were any errors, so just return here.
+		 */
+		btrfs_submit_compressed_read(inode, bio, mirror_num);
+		return;
+	}
+
+	/* Save the original iter for read repair */
+	btrfs_bio(bio)->iter = bio->bi_iter;
+
+	/*
+	 * Lookup bio sums does extra checks around whether we need to csum or
+	 * not, which is why we ignore skip_sum here.
+	 */
+	ret = btrfs_lookup_bio_sums(inode, bio, NULL);
 	if (ret) {
 		bio->bi_status = ret;
 		bio_endio(bio);
+		return;
 	}
+
+	btrfs_submit_bio(fs_info, bio, mirror_num);
 }
 
 /*
@@ -3075,8 +3170,10 @@ static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans,
 	btrfs_set_stack_file_extent_disk_num_bytes(&stack_fi,
 						   oe->disk_num_bytes);
 	btrfs_set_stack_file_extent_offset(&stack_fi, oe->offset);
-	if (test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags))
-		num_bytes = ram_bytes = oe->truncated_len;
+	if (test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags)) {
+		num_bytes = oe->truncated_len;
+		ram_bytes = num_bytes;
+	}
 	btrfs_set_stack_file_extent_num_bytes(&stack_fi, num_bytes);
 	btrfs_set_stack_file_extent_ram_bytes(&stack_fi, ram_bytes);
 	btrfs_set_stack_file_extent_compression(&stack_fi, oe->compress_type);
@@ -3102,7 +3199,7 @@ static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans,
  * an ordered extent if the range of bytes in the file it covers are
  * fully written.
  */
-static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
+int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 {
 	struct btrfs_inode *inode = BTRFS_I(ordered_extent->inode);
 	struct btrfs_root *root = inode->root;
@@ -3311,65 +3408,71 @@ out:
 	return ret;
 }
 
-static void finish_ordered_fn(struct btrfs_work *work)
-{
-	struct btrfs_ordered_extent *ordered_extent;
-	ordered_extent = container_of(work, struct btrfs_ordered_extent, work);
-	btrfs_finish_ordered_io(ordered_extent);
-}
-
 void btrfs_writepage_endio_finish_ordered(struct btrfs_inode *inode,
 					  struct page *page, u64 start,
 					  u64 end, bool uptodate)
 {
 	trace_btrfs_writepage_end_io_hook(inode, start, end, uptodate);
 
-	btrfs_mark_ordered_io_finished(inode, page, start, end + 1 - start,
-				       finish_ordered_fn, uptodate);
+	btrfs_mark_ordered_io_finished(inode, page, start, end + 1 - start, uptodate);
+}
+
+/*
+ * Verify the checksum for a single sector without any extra action that depend
+ * on the type of I/O.
+ */
+int btrfs_check_sector_csum(struct btrfs_fs_info *fs_info, struct page *page,
+			    u32 pgoff, u8 *csum, const u8 * const csum_expected)
+{
+	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
+	char *kaddr;
+
+	ASSERT(pgoff + fs_info->sectorsize <= PAGE_SIZE);
+
+	shash->tfm = fs_info->csum_shash;
+
+	kaddr = kmap_local_page(page) + pgoff;
+	crypto_shash_digest(shash, kaddr, fs_info->sectorsize, csum);
+	kunmap_local(kaddr);
+
+	if (memcmp(csum, csum_expected, fs_info->csum_size))
+		return -EIO;
+	return 0;
 }
 
 /*
  * check_data_csum - verify checksum of one sector of uncompressed data
  * @inode:	inode
- * @io_bio:	btrfs_io_bio which contains the csum
+ * @bbio:	btrfs_bio which contains the csum
  * @bio_offset:	offset to the beginning of the bio (in bytes)
  * @page:	page where is the data to be verified
  * @pgoff:	offset inside the page
- * @start:	logical offset in the file
  *
  * The length of such check is always one sector size.
+ *
+ * When csum mismatch is detected, we will also report the error and fill the
+ * corrupted range with zero. (Thus it needs the extra parameters)
  */
-static int check_data_csum(struct inode *inode, struct btrfs_bio *bbio,
-			   u32 bio_offset, struct page *page, u32 pgoff,
-			   u64 start)
+int btrfs_check_data_csum(struct inode *inode, struct btrfs_bio *bbio,
+			  u32 bio_offset, struct page *page, u32 pgoff)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
-	char *kaddr;
 	u32 len = fs_info->sectorsize;
-	const u32 csum_size = fs_info->csum_size;
-	unsigned int offset_sectors;
 	u8 *csum_expected;
 	u8 csum[BTRFS_CSUM_SIZE];
 
 	ASSERT(pgoff + len <= PAGE_SIZE);
 
-	offset_sectors = bio_offset >> fs_info->sectorsize_bits;
-	csum_expected = ((u8 *)bbio->csum) + offset_sectors * csum_size;
-
-	kaddr = kmap_atomic(page);
-	shash->tfm = fs_info->csum_shash;
-
-	crypto_shash_digest(shash, kaddr + pgoff, len, csum);
-	kunmap_atomic(kaddr);
+	csum_expected = btrfs_csum_ptr(fs_info, bbio->csum, bio_offset);
 
-	if (memcmp(csum, csum_expected, csum_size))
+	if (btrfs_check_sector_csum(fs_info, page, pgoff, csum, csum_expected))
 		goto zeroit;
-
 	return 0;
+
 zeroit:
-	btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
-				    bbio->mirror_num);
+	btrfs_print_data_csum_error(BTRFS_I(inode),
+				    bbio->file_offset + bio_offset,
+				    csum, csum_expected, bbio->mirror_num);
 	if (bbio->device)
 		btrfs_dev_stat_inc_and_print(bbio->device,
 					     BTRFS_DEV_STAT_CORRUPTION_ERRS);
@@ -3401,11 +3504,6 @@ unsigned int btrfs_verify_data_csum(struct btrfs_bio *bbio,
 	u32 pg_off;
 	unsigned int result = 0;
 
-	if (btrfs_page_test_checked(fs_info, page, start, end + 1 - start)) {
-		btrfs_page_clear_checked(fs_info, page, start, end + 1 - start);
-		return 0;
-	}
-
 	/*
 	 * This only happens for NODATASUM or compressed read.
 	 * Normally this should be covered by above check for compressed read
@@ -3438,8 +3536,7 @@ unsigned int btrfs_verify_data_csum(struct btrfs_bio *bbio,
 					  EXTENT_NODATASUM);
 			continue;
 		}
-		ret = check_data_csum(inode, bbio, bio_offset, page, pg_off,
-				      page_offset(page) + pg_off);
+		ret = btrfs_check_data_csum(inode, bbio, bio_offset, page, pg_off);
 		if (ret < 0) {
 			const int nr_bit = (pg_off - offset_in_page(start)) >>
 				     root->fs_info->sectorsize_bits;
@@ -4228,7 +4325,7 @@ skip_backref:
 	/*
 	 * If we are in a rename context, we don't need to update anything in the
 	 * log. That will be done later during the rename by btrfs_log_new_name().
-	 * Besides that, doing it here would only cause extra unncessary btree
+	 * Besides that, doing it here would only cause extra unnecessary btree
 	 * operations on the log tree, increasing latency for applications.
 	 */
 	if (!rename_ctx) {
@@ -4256,8 +4353,9 @@ err:
 	btrfs_i_size_write(dir, dir->vfs_inode.i_size - name_len * 2);
 	inode_inc_iversion(&inode->vfs_inode);
 	inode_inc_iversion(&dir->vfs_inode);
-	inode->vfs_inode.i_ctime = dir->vfs_inode.i_mtime =
-		dir->vfs_inode.i_ctime = current_time(&inode->vfs_inode);
+	inode->vfs_inode.i_ctime = current_time(&inode->vfs_inode);
+	dir->vfs_inode.i_mtime = inode->vfs_inode.i_ctime;
+	dir->vfs_inode.i_ctime = inode->vfs_inode.i_ctime;
 	ret = btrfs_update_inode(trans, root, dir);
 out:
 	return ret;
@@ -4419,7 +4517,8 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 
 	btrfs_i_size_write(BTRFS_I(dir), dir->i_size - name_len * 2);
 	inode_inc_iversion(dir);
-	dir->i_mtime = dir->i_ctime = current_time(dir);
+	dir->i_mtime = current_time(dir);
+	dir->i_ctime = dir->i_mtime;
 	ret = btrfs_update_inode_fallback(trans, root, BTRFS_I(dir));
 	if (ret)
 		btrfs_abort_transaction(trans, ret);
@@ -4858,7 +4957,6 @@ again:
 		else
 			memzero_page(page, (block_start - page_offset(page)) + offset,
 				     len);
-		flush_dcache_page(page);
 	}
 	btrfs_page_clear_checked(fs_info, page, block_start,
 				 block_end + 1 - block_start);
@@ -5061,9 +5159,10 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 	 */
 	if (newsize != oldsize) {
 		inode_inc_iversion(inode);
-		if (!(mask & (ATTR_CTIME | ATTR_MTIME)))
-			inode->i_ctime = inode->i_mtime =
-				current_time(inode);
+		if (!(mask & (ATTR_CTIME | ATTR_MTIME))) {
+			inode->i_mtime = current_time(inode);
+			inode->i_ctime = inode->i_mtime;
+		}
 	}
 
 	if (newsize > oldsize) {
@@ -5371,7 +5470,7 @@ void btrfs_evict_inode(struct inode *inode)
 	if (!rsv)
 		goto no_delete;
 	rsv->size = btrfs_calc_metadata_size(fs_info, 1);
-	rsv->failfast = 1;
+	rsv->failfast = true;
 
 	btrfs_i_size_write(BTRFS_I(inode), 0);
 
@@ -5763,14 +5862,14 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 		if (ret != -ENOENT)
 			inode = ERR_PTR(ret);
 		else
-			inode = new_simple_dir(dir->i_sb, &location, sub_root);
+			inode = new_simple_dir(dir->i_sb, &location, root);
 	} else {
 		inode = btrfs_iget(dir->i_sb, location.objectid, sub_root);
-	}
-	if (root != sub_root)
 		btrfs_put_root(sub_root);
 
-	if (!IS_ERR(inode) && root != sub_root) {
+		if (IS_ERR(inode))
+			return inode;
+
 		down_read(&fs_info->cleanup_work_sem);
 		if (!sb_rdonly(inode->i_sb))
 			ret = btrfs_orphan_cleanup(sub_root);
@@ -6366,7 +6465,13 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 	}
 
 	btrfs_mark_buffer_dirty(path->nodes[0]);
-	btrfs_release_path(path);
+	/*
+	 * We don't need the path anymore, plus inheriting properties, adding
+	 * ACLs, security xattrs, orphan item or adding the link, will result in
+	 * allocating yet another path. So just free our path.
+	 */
+	btrfs_free_path(path);
+	path = NULL;
 
 	if (args->subvol) {
 		struct inode *parent;
@@ -6423,8 +6528,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 		goto discard;
 	}
 
-	ret = 0;
-	goto out;
+	return 0;
 
 discard:
 	/*
@@ -7506,7 +7610,8 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 		btrfs_dec_nocow_writers(bg);
 		if (type == BTRFS_ORDERED_PREALLOC) {
 			free_extent_map(em);
-			*map = em = em2;
+			*map = em2;
+			em = em2;
 		}
 
 		if (IS_ERR(em2)) {
@@ -7588,8 +7693,12 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	const u64 data_alloc_len = length;
 	bool unlock_extents = false;
 
+	/*
+	 * Cap the size of reads to that usually seen in buffered I/O as we need
+	 * to allocate a contiguous array for the checksums.
+	 */
 	if (!write)
-		len = min_t(u64, len, fs_info->sectorsize);
+		len = min_t(u64, len, fs_info->sectorsize * BTRFS_MAX_BIO_SECTORS);
 
 	lockstart = start;
 	lockend = start + len - 1;
@@ -7824,8 +7933,8 @@ static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 		pos += submitted;
 		length -= submitted;
 		if (write)
-			__endio_write_update_ordered(BTRFS_I(inode), pos,
-					length, false);
+			btrfs_mark_ordered_io_finished(BTRFS_I(inode), NULL,
+						       pos, length, false);
 		else
 			unlock_extent(&BTRFS_I(inode)->io_tree, pos,
 				      pos + length - 1);
@@ -7847,10 +7956,9 @@ static void btrfs_dio_private_put(struct btrfs_dio_private *dip)
 		return;
 
 	if (btrfs_op(&dip->bio) == BTRFS_MAP_WRITE) {
-		__endio_write_update_ordered(BTRFS_I(dip->inode),
-					     dip->file_offset,
-					     dip->bytes,
-					     !dip->bio.bi_status);
+		btrfs_mark_ordered_io_finished(BTRFS_I(dip->inode), NULL,
+					       dip->file_offset, dip->bytes,
+					       !dip->bio.bi_status);
 	} else {
 		unlock_extent(&BTRFS_I(dip->inode)->io_tree,
 			      dip->file_offset,
@@ -7870,12 +7978,8 @@ static void submit_dio_repair_bio(struct inode *inode, struct bio *bio,
 
 	BUG_ON(bio_op(bio) == REQ_OP_WRITE);
 
-	if (btrfs_bio_wq_end_io(fs_info, bio, BTRFS_WQ_ENDIO_DATA))
-		return;
-
 	refcount_inc(&dip->refs);
-	if (btrfs_map_bio(fs_info, bio, mirror_num))
-		refcount_dec(&dip->refs);
+	btrfs_submit_bio(fs_info, bio, mirror_num);
 }
 
 static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip,
@@ -7884,56 +7988,35 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip,
 {
 	struct inode *inode = dip->inode;
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
-	const u32 sectorsize = fs_info->sectorsize;
 	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM);
-	struct bio_vec bvec;
-	struct bvec_iter iter;
-	u32 bio_offset = 0;
 	blk_status_t err = BLK_STS_OK;
+	struct bvec_iter iter;
+	struct bio_vec bv;
+	u32 offset;
+
+	btrfs_bio_for_each_sector(fs_info, bv, bbio, iter, offset) {
+		u64 start = bbio->file_offset + offset;
+
+		if (uptodate &&
+		    (!csum || !btrfs_check_data_csum(inode, bbio, offset, bv.bv_page,
+					       bv.bv_offset))) {
+			clean_io_failure(fs_info, failure_tree, io_tree, start,
+					 bv.bv_page, btrfs_ino(BTRFS_I(inode)),
+					 bv.bv_offset);
+		} else {
+			int ret;
 
-	__bio_for_each_segment(bvec, &bbio->bio, iter, bbio->iter) {
-		unsigned int i, nr_sectors, pgoff;
-
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
-		pgoff = bvec.bv_offset;
-		for (i = 0; i < nr_sectors; i++) {
-			u64 start = bbio->file_offset + bio_offset;
-
-			ASSERT(pgoff < PAGE_SIZE);
-			if (uptodate &&
-			    (!csum || !check_data_csum(inode, bbio,
-						       bio_offset, bvec.bv_page,
-						       pgoff, start))) {
-				clean_io_failure(fs_info, failure_tree, io_tree,
-						 start, bvec.bv_page,
-						 btrfs_ino(BTRFS_I(inode)),
-						 pgoff);
-			} else {
-				int ret;
-
-				ret = btrfs_repair_one_sector(inode, &bbio->bio,
-						bio_offset, bvec.bv_page, pgoff,
-						start, bbio->mirror_num,
-						submit_dio_repair_bio);
-				if (ret)
-					err = errno_to_blk_status(ret);
-			}
-			ASSERT(bio_offset + sectorsize > bio_offset);
-			bio_offset += sectorsize;
-			pgoff += sectorsize;
+			ret = btrfs_repair_one_sector(inode, bbio, offset,
+					bv.bv_page, bv.bv_offset,
+					submit_dio_repair_bio);
+			if (ret)
+				err = errno_to_blk_status(ret);
 		}
 	}
-	return err;
-}
 
-static void __endio_write_update_ordered(struct btrfs_inode *inode,
-					 const u64 offset, const u64 bytes,
-					 const bool uptodate)
-{
-	btrfs_mark_ordered_io_finished(inode, NULL, offset, bytes,
-				       finish_ordered_fn, uptodate);
+	return err;
 }
 
 static blk_status_t btrfs_submit_bio_start_direct_io(struct inode *inode,
@@ -7968,51 +8051,43 @@ static void btrfs_end_dio_bio(struct bio *bio)
 	btrfs_dio_private_put(dip);
 }
 
-static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
-		struct inode *inode, u64 file_offset, int async_submit)
+static void btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
+				 u64 file_offset, int async_submit)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_dio_private *dip = bio->bi_private;
-	bool write = btrfs_op(bio) == BTRFS_MAP_WRITE;
 	blk_status_t ret;
 
-	/* Check btrfs_submit_bio_hook() for rules about async submit. */
-	if (async_submit)
-		async_submit = !atomic_read(&BTRFS_I(inode)->sync_writers);
-
-	if (!write) {
-		ret = btrfs_bio_wq_end_io(fs_info, bio, BTRFS_WQ_ENDIO_DATA);
-		if (ret)
-			goto err;
-	}
+	/* Save the original iter for read repair */
+	if (btrfs_op(bio) == BTRFS_MAP_READ)
+		btrfs_bio(bio)->iter = bio->bi_iter;
 
 	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
 		goto map;
 
-	if (write && async_submit) {
-		ret = btrfs_wq_submit_bio(inode, bio, 0, file_offset,
-					  btrfs_submit_bio_start_direct_io);
-		goto err;
-	} else if (write) {
+	if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
+		/* Check btrfs_submit_data_write_bio() for async submit rules */
+		if (async_submit && !atomic_read(&BTRFS_I(inode)->sync_writers) &&
+		    btrfs_wq_submit_bio(inode, bio, 0, file_offset,
+					btrfs_submit_bio_start_direct_io))
+			return;
+
 		/*
 		 * If we aren't doing async submit, calculate the csum of the
 		 * bio now.
 		 */
 		ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, file_offset, false);
-		if (ret)
-			goto err;
+		if (ret) {
+			bio->bi_status = ret;
+			bio_endio(bio);
+			return;
+		}
 	} else {
-		u64 csum_offset;
-
-		csum_offset = file_offset - dip->file_offset;
-		csum_offset >>= fs_info->sectorsize_bits;
-		csum_offset *= fs_info->csum_size;
-		btrfs_bio(bio)->csum = dip->csums + csum_offset;
+		btrfs_bio(bio)->csum = btrfs_csum_ptr(fs_info, dip->csums,
+						      file_offset - dip->file_offset);
 	}
 map:
-	ret = btrfs_map_bio(fs_info, bio, 0);
-err:
-	return ret;
+	btrfs_submit_bio(fs_info, bio, 0);
 }
 
 static void btrfs_submit_direct(const struct iomap_iter *iter,
@@ -8125,14 +8200,7 @@ static void btrfs_submit_direct(const struct iomap_iter *iter,
 				async_submit = 1;
 		}
 
-		status = btrfs_submit_dio_bio(bio, inode, file_offset,
-						async_submit);
-		if (status) {
-			bio_put(bio);
-			if (submit_len > 0)
-				refcount_dec(&dip->refs);
-			goto out_err_em;
-		}
+		btrfs_submit_dio_bio(bio, inode, file_offset, async_submit);
 
 		dio_data->submitted += clone_len;
 		clone_offset += clone_len;
@@ -8181,31 +8249,6 @@ static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	return extent_fiemap(BTRFS_I(inode), fieinfo, start, len);
 }
 
-static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-	int ret;
-
-	if (current->flags & PF_MEMALLOC) {
-		redirty_page_for_writepage(wbc, page);
-		unlock_page(page);
-		return 0;
-	}
-
-	/*
-	 * If we are under memory pressure we will call this directly from the
-	 * VM, we need to make sure we have the inode referenced for the ordered
-	 * extent.  If not just return like we didn't do anything.
-	 */
-	if (!igrab(inode)) {
-		redirty_page_for_writepage(wbc, page);
-		return AOP_WRITEPAGE_ACTIVATE;
-	}
-	ret = extent_write_full_page(page, wbc);
-	btrfs_add_delayed_iput(inode);
-	return ret;
-}
-
 static int btrfs_writepages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
@@ -8503,7 +8546,7 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
 	 * Reserving delalloc space after obtaining the page lock can lead to
 	 * deadlock. For example, if a dirty page is locked by this function
 	 * and the call to btrfs_delalloc_reserve_space() ends up triggering
-	 * dirty page write out, then the btrfs_writepage() function could
+	 * dirty page write out, then the btrfs_writepages() function could
 	 * end up waiting indefinitely to get a lock on the page currently
 	 * being processed by btrfs_page_mkwrite() function.
 	 */
@@ -8594,10 +8637,9 @@ again:
 	else
 		zero_start = PAGE_SIZE;
 
-	if (zero_start != PAGE_SIZE) {
+	if (zero_start != PAGE_SIZE)
 		memzero_page(page, zero_start, PAGE_SIZE - zero_start);
-		flush_dcache_page(page);
-	}
+
 	btrfs_page_clear_checked(fs_info, page, page_start, PAGE_SIZE);
 	btrfs_page_set_dirty(fs_info, page, page_start, end + 1 - page_start);
 	btrfs_page_set_uptodate(fs_info, page, page_start, end + 1 - page_start);
@@ -8680,7 +8722,7 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
 	if (!rsv)
 		return -ENOMEM;
 	rsv->size = min_size;
-	rsv->failfast = 1;
+	rsv->failfast = true;
 
 	/*
 	 * 1 for the truncate slack space
@@ -9201,8 +9243,10 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	inode_inc_iversion(new_dir);
 	inode_inc_iversion(old_inode);
 	inode_inc_iversion(new_inode);
-	old_dir->i_ctime = old_dir->i_mtime = ctime;
-	new_dir->i_ctime = new_dir->i_mtime = ctime;
+	old_dir->i_mtime = ctime;
+	old_dir->i_ctime = ctime;
+	new_dir->i_mtime = ctime;
+	new_dir->i_ctime = ctime;
 	old_inode->i_ctime = ctime;
 	new_inode->i_ctime = ctime;
 
@@ -9465,9 +9509,11 @@ static int btrfs_rename(struct user_namespace *mnt_userns,
 	inode_inc_iversion(old_dir);
 	inode_inc_iversion(new_dir);
 	inode_inc_iversion(old_inode);
-	old_dir->i_ctime = old_dir->i_mtime =
-	new_dir->i_ctime = new_dir->i_mtime =
-	old_inode->i_ctime = current_time(old_dir);
+	old_dir->i_mtime = current_time(old_dir);
+	old_dir->i_ctime = old_dir->i_mtime;
+	new_dir->i_mtime = old_dir->i_mtime;
+	new_dir->i_ctime = old_dir->i_mtime;
+	old_inode->i_ctime = old_dir->i_mtime;
 
 	if (old_dentry->d_parent != new_dentry->d_parent)
 		btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
@@ -9555,15 +9601,21 @@ static int btrfs_rename2(struct user_namespace *mnt_userns, struct inode *old_di
 			 struct dentry *old_dentry, struct inode *new_dir,
 			 struct dentry *new_dentry, unsigned int flags)
 {
+	int ret;
+
 	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
 		return -EINVAL;
 
 	if (flags & RENAME_EXCHANGE)
-		return btrfs_rename_exchange(old_dir, old_dentry, new_dir,
-					  new_dentry);
+		ret = btrfs_rename_exchange(old_dir, old_dentry, new_dir,
+					    new_dentry);
+	else
+		ret = btrfs_rename(mnt_userns, old_dir, old_dentry, new_dir,
+				   new_dentry, flags);
 
-	return btrfs_rename(mnt_userns, old_dir, old_dentry, new_dir,
-			    new_dentry, flags);
+	btrfs_btree_balance_dirty(BTRFS_I(new_dir)->root->fs_info);
+
+	return ret;
 }
 
 struct btrfs_delalloc_work {
@@ -10183,9 +10235,8 @@ void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end)
 	}
 }
 
-static int btrfs_encoded_io_compression_from_extent(
-				struct btrfs_fs_info *fs_info,
-				int compress_type)
+int btrfs_encoded_io_compression_from_extent(struct btrfs_fs_info *fs_info,
+					     int compress_type)
 {
 	switch (compress_type) {
 	case BTRFS_COMPRESS_NONE:
@@ -10308,7 +10359,6 @@ static blk_status_t submit_encoded_read_bio(struct btrfs_inode *inode,
 					    struct bio *bio, int mirror_num)
 {
 	struct btrfs_encoded_read_private *priv = bio->bi_private;
-	struct btrfs_bio *bbio = btrfs_bio(bio);
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	blk_status_t ret;
 
@@ -10318,19 +10368,9 @@ static blk_status_t submit_encoded_read_bio(struct btrfs_inode *inode,
 			return ret;
 	}
 
-	ret = btrfs_bio_wq_end_io(fs_info, bio, BTRFS_WQ_ENDIO_DATA);
-	if (ret) {
-		btrfs_bio_free_csum(bbio);
-		return ret;
-	}
-
 	atomic_inc(&priv->pending);
-	ret = btrfs_map_bio(fs_info, bio, mirror_num);
-	if (ret) {
-		atomic_dec(&priv->pending);
-		btrfs_bio_free_csum(bbio);
-	}
-	return ret;
+	btrfs_submit_bio(fs_info, bio, mirror_num);
+	return BLK_STS_OK;
 }
 
 static blk_status_t btrfs_encoded_read_verify_csum(struct btrfs_bio *bbio)
@@ -10342,7 +10382,6 @@ static blk_status_t btrfs_encoded_read_verify_csum(struct btrfs_bio *bbio)
 	u32 sectorsize = fs_info->sectorsize;
 	struct bio_vec *bvec;
 	struct bvec_iter_all iter_all;
-	u64 start = priv->file_offset;
 	u32 bio_offset = 0;
 
 	if (priv->skip_csum || !uptodate)
@@ -10355,10 +10394,9 @@ static blk_status_t btrfs_encoded_read_verify_csum(struct btrfs_bio *bbio)
 		pgoff = bvec->bv_offset;
 		for (i = 0; i < nr_sectors; i++) {
 			ASSERT(pgoff < PAGE_SIZE);
-			if (check_data_csum(&inode->vfs_inode, bbio, bio_offset,
-					    bvec->bv_page, pgoff, start))
+			if (btrfs_check_data_csum(&inode->vfs_inode, bbio, bio_offset,
+					    bvec->bv_page, pgoff))
 				return BLK_STS_IOERR;
-			start += sectorsize;
 			bio_offset += sectorsize;
 			pgoff += sectorsize;
 		}
@@ -10390,11 +10428,9 @@ static void btrfs_encoded_read_endio(struct bio *bio)
 	bio_put(bio);
 }
 
-static int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
-						 u64 file_offset,
-						 u64 disk_bytenr,
-						 u64 disk_io_size,
-						 struct page **pages)
+int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
+					  u64 file_offset, u64 disk_bytenr,
+					  u64 disk_io_size, struct page **pages)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_encoded_read_private priv = {
@@ -10625,7 +10661,8 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 			ret = -ENOBUFS;
 			goto out_em;
 		}
-		disk_io_size = count = em->block_len;
+		disk_io_size = em->block_len;
+		count = em->block_len;
 		encoded->unencoded_len = em->ram_bytes;
 		encoded->unencoded_offset = iocb->ki_pos - em->orig_start;
 		ret = btrfs_encoded_io_compression_from_extent(fs_info,
@@ -10788,15 +10825,15 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 			ret = -ENOMEM;
 			goto out_pages;
 		}
-		kaddr = kmap(pages[i]);
+		kaddr = kmap_local_page(pages[i]);
 		if (copy_from_iter(kaddr, bytes, from) != bytes) {
-			kunmap(pages[i]);
+			kunmap_local(kaddr);
 			ret = -EFAULT;
 			goto out_pages;
 		}
 		if (bytes < PAGE_SIZE)
 			memset(kaddr + bytes, 0, PAGE_SIZE - bytes);
-		kunmap(pages[i]);
+		kunmap_local(kaddr);
 	}
 
 	for (;;) {
@@ -11425,7 +11462,6 @@ static const struct file_operations btrfs_dir_file_operations = {
  */
 static const struct address_space_operations btrfs_aops = {
 	.read_folio	= btrfs_read_folio,
-	.writepage	= btrfs_writepage,
 	.writepages	= btrfs_writepages,
 	.readahead	= btrfs_readahead,
 	.direct_IO	= noop_direct_IO,