btrfs: integrate page status update for data read path into begin/end_page_read

In btrfs data page read path, the page status update are handled in two
different locations:

  btrfs_do_read_page()
  {
	while (cur <= end) {
		/* No need to read from disk */
		if (HOLE/PREALLOC/INLINE){
			memset();
			set_extent_uptodate();
			continue;
		}
		/* Read from disk */
		ret = submit_extent_page(end_bio_extent_readpage);
  }

  end_bio_extent_readpage()
  {
	endio_readpage_uptodate_page_status();
  }

This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.

But for subpage, there is more work to be done in page status update:

- Page Unlock condition
  Unlike regular page size == sectorsize case, we can no longer just
  unlock a page.
  Only the last reader of the page can unlock the page.
  This means, we can unlock the page either in the while() loop, or in
  the endio function.

- Page uptodate condition
  Since we have multiple sectors to read for a page, we can only mark
  the full page uptodate if all sectors are uptodate.

To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:

- begin_page_read()
  For regular case, it does nothing.
  For subpage case, it updates the reader counters so that later
  end_page_read() can know who is the last one to unlock the page.

- end_page_read()
  This is just endio_readpage_uptodate_page_status() renamed.
  The original name is a little too long and too specific for endio.

  The new thing added is the condition for page unlock.
  Now for subpage data, we unlock the page if we're the last reader.

This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.

Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 43 insertions, 10 deletions

diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 2c51ab71e000..c69049e7daa9 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -54,6 +54,8 @@ int btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info,
 	spin_lock_init(&(*ret)->lock);
 	if (type == BTRFS_SUBPAGE_METADATA)
 		atomic_set(&(*ret)->eb_refs, 0);
+	else
+		atomic_set(&(*ret)->readers, 0);
 	return 0;
 }
 
@@ -102,22 +104,13 @@ void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info,
 	atomic_dec(&subpage->eb_refs);
 }
 
-/*
- * Convert the [start, start + len) range into a u16 bitmap
- *
- * For example: if start == page_offset() + 16K, len = 16K, we get 0x00f0.
- */
-static u16 btrfs_subpage_calc_bitmap(const struct btrfs_fs_info *fs_info,
+static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
 		struct page *page, u64 start, u32 len)
 {
-	const int bit_start = offset_in_page(start) >> fs_info->sectorsize_bits;
-	const int nbits = len >> fs_info->sectorsize_bits;
-
 	/* Basic checks */
 	ASSERT(PagePrivate(page) && page->private);
 	ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
 	       IS_ALIGNED(len, fs_info->sectorsize));
-
 	/*
 	 * The range check only works for mapped page, we can still have
 	 * unmapped page like dummy extent buffer pages.
@@ -125,6 +118,46 @@ static u16 btrfs_subpage_calc_bitmap(const struct btrfs_fs_info *fs_info,
 	if (page->mapping)
 		ASSERT(page_offset(page) <= start &&
 		       start + len <= page_offset(page) + PAGE_SIZE);
+}
+
+void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info,
+		struct page *page, u64 start, u32 len)
+{
+	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+	const int nbits = len >> fs_info->sectorsize_bits;
+	int ret;
+
+	btrfs_subpage_assert(fs_info, page, start, len);
+
+	ret = atomic_add_return(nbits, &subpage->readers);
+	ASSERT(ret == nbits);
+}
+
+void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
+		struct page *page, u64 start, u32 len)
+{
+	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+	const int nbits = len >> fs_info->sectorsize_bits;
+
+	btrfs_subpage_assert(fs_info, page, start, len);
+	ASSERT(atomic_read(&subpage->readers) >= nbits);
+	if (atomic_sub_and_test(nbits, &subpage->readers))
+		unlock_page(page);
+}
+
+/*
+ * Convert the [start, start + len) range into a u16 bitmap
+ *
+ * For example: if start == page_offset() + 16K, len = 16K, we get 0x00f0.
+ */
+static u16 btrfs_subpage_calc_bitmap(const struct btrfs_fs_info *fs_info,
+		struct page *page, u64 start, u32 len)
+{
+	const int bit_start = offset_in_page(start) >> fs_info->sectorsize_bits;
+	const int nbits = len >> fs_info->sectorsize_bits;
+
+	btrfs_subpage_assert(fs_info, page, start, len);
+
 	/*
 	 * Here nbits can be 16, thus can go beyond u16 range. We make the
 	 * first left shift to be calculate in unsigned long (at least u32),