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

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

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

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

   - add message after cancelled device replace

   - direct module dependency on libcrc32, removed own crc wrappers

   - removed user space transaction ioctls

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

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

   - send: do not issue unnecessary truncate operations

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

   - selftests: more tree block validations

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

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

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

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

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

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

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

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

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

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

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

   - kill and opencode trivial helpers

   - __cold/__exit function annotations

   - dead code removal

   - continued audit and documentation of memory barriers

   - error handling: handle removal from uuid tree

   - error handling: remove handling of impossible condtitons

   - more debugging or error messages

   - updated tracepoints

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

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

1 files changed, 41 insertions, 41 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index dfeb74a0be77..47a8fe9d22e8 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -76,8 +76,8 @@ void btrfs_leak_debug_check(void)
 
 	while (!list_empty(&buffers)) {
 		eb = list_entry(buffers.next, struct extent_buffer, leak_list);
-		pr_err("BTRFS: buffer leak start %llu len %lu refs %d\n",
-		       eb->start, eb->len, atomic_read(&eb->refs));
+		pr_err("BTRFS: buffer leak start %llu len %lu refs %d bflags %lu\n",
+		       eb->start, eb->len, atomic_read(&eb->refs), eb->bflags);
 		list_del(&eb->leak_list);
 		kmem_cache_free(extent_buffer_cache, eb);
 	}
@@ -119,23 +119,22 @@ struct extent_page_data {
 	unsigned int sync_io:1;
 };
 
-static void add_extent_changeset(struct extent_state *state, unsigned bits,
+static int add_extent_changeset(struct extent_state *state, unsigned bits,
 				 struct extent_changeset *changeset,
 				 int set)
 {
 	int ret;
 
 	if (!changeset)
-		return;
+		return 0;
 	if (set && (state->state & bits) == bits)
-		return;
+		return 0;
 	if (!set && (state->state & bits) == 0)
-		return;
+		return 0;
 	changeset->bytes_changed += state->end - state->start + 1;
 	ret = ulist_add(&changeset->range_changed, state->start, state->end,
 			GFP_ATOMIC);
-	/* ENOMEM */
-	BUG_ON(ret < 0);
+	return ret;
 }
 
 static void flush_write_bio(struct extent_page_data *epd);
@@ -187,7 +186,7 @@ free_state_cache:
 	return -ENOMEM;
 }
 
-void extent_io_exit(void)
+void __cold extent_io_exit(void)
 {
 	btrfs_leak_debug_check();
 
@@ -527,6 +526,7 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
 {
 	struct extent_state *next;
 	unsigned bits_to_clear = *bits & ~EXTENT_CTLBITS;
+	int ret;
 
 	if ((bits_to_clear & EXTENT_DIRTY) && (state->state & EXTENT_DIRTY)) {
 		u64 range = state->end - state->start + 1;
@@ -534,7 +534,8 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
 		tree->dirty_bytes -= range;
 	}
 	clear_state_cb(tree, state, bits);
-	add_extent_changeset(state, bits_to_clear, changeset, 0);
+	ret = add_extent_changeset(state, bits_to_clear, changeset, 0);
+	BUG_ON(ret < 0);
 	state->state &= ~bits_to_clear;
 	if (wake)
 		wake_up(&state->wq);
@@ -805,13 +806,15 @@ static void set_state_bits(struct extent_io_tree *tree,
 			   unsigned *bits, struct extent_changeset *changeset)
 {
 	unsigned bits_to_set = *bits & ~EXTENT_CTLBITS;
+	int ret;
 
 	set_state_cb(tree, state, bits);
 	if ((bits_to_set & EXTENT_DIRTY) && !(state->state & EXTENT_DIRTY)) {
 		u64 range = state->end - state->start + 1;
 		tree->dirty_bytes += range;
 	}
-	add_extent_changeset(state, bits_to_set, changeset, 1);
+	ret = add_extent_changeset(state, bits_to_set, changeset, 1);
+	BUG_ON(ret < 0);
 	state->state |= bits_to_set;
 }
 
@@ -2744,20 +2747,21 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
 	return blk_status_to_errno(ret);
 }
 
-static int merge_bio(struct extent_io_tree *tree, struct page *page,
-		     unsigned long offset, size_t size, struct bio *bio,
-		     unsigned long bio_flags)
-{
-	int ret = 0;
-	if (tree->ops)
-		ret = tree->ops->merge_bio_hook(page, offset, size, bio,
-						bio_flags);
-	return ret;
-
-}
-
 /*
  * @opf:	bio REQ_OP_* and REQ_* flags as one value
+ * @tree:	tree so we can call our merge_bio hook
+ * @wbc:	optional writeback control for io accounting
+ * @page:	page to add to the bio
+ * @pg_offset:	offset of the new bio or to check whether we are adding
+ *              a contiguous page to the previous one
+ * @size:	portion of page that we want to write
+ * @offset:	starting offset in the page
+ * @bdev:	attach newly created bios to this bdev
+ * @bio_ret:	must be valid pointer, newly allocated bio will be stored there
+ * @end_io_func:     end_io callback for new bio
+ * @mirror_num:	     desired mirror to read/write
+ * @prev_bio_flags:  flags of previous bio to see if we can merge the current one
+ * @bio_flags:	flags of the current bio to see if we can merge them
  */
 static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 			      struct writeback_control *wbc,
@@ -2773,21 +2777,27 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 {
 	int ret = 0;
 	struct bio *bio;
-	int contig = 0;
-	int old_compressed = prev_bio_flags & EXTENT_BIO_COMPRESSED;
 	size_t page_size = min_t(size_t, size, PAGE_SIZE);
 	sector_t sector = offset >> 9;
 
-	if (bio_ret && *bio_ret) {
+	ASSERT(bio_ret);
+
+	if (*bio_ret) {
+		bool contig;
+		bool can_merge = true;
+
 		bio = *bio_ret;
-		if (old_compressed)
+		if (prev_bio_flags & EXTENT_BIO_COMPRESSED)
 			contig = bio->bi_iter.bi_sector == sector;
 		else
 			contig = bio_end_sector(bio) == sector;
 
-		if (prev_bio_flags != bio_flags || !contig ||
+		if (tree->ops && tree->ops->merge_bio_hook(page, offset,
+					page_size, bio, bio_flags))
+			can_merge = false;
+
+		if (prev_bio_flags != bio_flags || !contig || !can_merge ||
 		    force_bio_submit ||
-		    merge_bio(tree, page, pg_offset, page_size, bio, bio_flags) ||
 		    bio_add_page(bio, page, page_size, pg_offset) < page_size) {
 			ret = submit_one_bio(bio, mirror_num, prev_bio_flags);
 			if (ret < 0) {
@@ -2813,10 +2823,7 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 		wbc_account_io(wbc, page, page_size);
 	}
 
-	if (bio_ret)
-		*bio_ret = bio;
-	else
-		ret = submit_one_bio(bio, mirror_num, bio_flags);
+	*bio_ret = bio;
 
 	return ret;
 }
@@ -2886,8 +2893,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 {
 	struct inode *inode = page->mapping->host;
 	u64 start = page_offset(page);
-	u64 page_end = start + PAGE_SIZE - 1;
-	u64 end;
+	const u64 end = start + PAGE_SIZE - 1;
 	u64 cur = start;
 	u64 extent_offset;
 	u64 last_byte = i_size_read(inode);
@@ -2905,7 +2911,6 @@ static int __do_readpage(struct extent_io_tree *tree,
 
 	set_page_extent_mapped(page);
 
-	end = page_end;
 	if (!PageUptodate(page)) {
 		if (cleancache_get_page(page) == 0) {
 			BUG_ON(blocksize != PAGE_SIZE);
@@ -5230,11 +5235,6 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb)
 	}
 }
 
-int extent_buffer_uptodate(struct extent_buffer *eb)
-{
-	return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-}
-
 int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     struct extent_buffer *eb, int wait, int mirror_num)
 {