btrfs: support subpage in try_release_extent_buffer()

Unlike the original try_release_extent_buffer(),
try_release_subpage_extent_buffer() will iterate through all the ebs in
the page, and try to release each.

We can release the full page only after there's no private attached,
which means all ebs of that page have been released as well.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
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, 104 insertions, 2 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6b27daf62d94..a6102e795af5 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -6318,13 +6318,115 @@ void memmove_extent_buffer(const struct extent_buffer *dst,
 	}
 }
 
+static struct extent_buffer *get_next_extent_buffer(
+		struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
+{
+	struct extent_buffer *gang[BTRFS_SUBPAGE_BITMAP_SIZE];
+	struct extent_buffer *found = NULL;
+	u64 page_start = page_offset(page);
+	int ret;
+	int i;
+
+	ASSERT(in_range(bytenr, page_start, PAGE_SIZE));
+	ASSERT(PAGE_SIZE / fs_info->nodesize <= BTRFS_SUBPAGE_BITMAP_SIZE);
+	lockdep_assert_held(&fs_info->buffer_lock);
+
+	ret = radix_tree_gang_lookup(&fs_info->buffer_radix, (void **)gang,
+			bytenr >> fs_info->sectorsize_bits,
+			PAGE_SIZE / fs_info->nodesize);
+	for (i = 0; i < ret; i++) {
+		/* Already beyond page end */
+		if (gang[i]->start >= page_start + PAGE_SIZE)
+			break;
+		/* Found one */
+		if (gang[i]->start >= bytenr) {
+			found = gang[i];
+			break;
+		}
+	}
+	return found;
+}
+
+static int try_release_subpage_extent_buffer(struct page *page)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+	u64 cur = page_offset(page);
+	const u64 end = page_offset(page) + PAGE_SIZE;
+	int ret;
+
+	while (cur < end) {
+		struct extent_buffer *eb = NULL;
+
+		/*
+		 * Unlike try_release_extent_buffer() which uses page->private
+		 * to grab buffer, for subpage case we rely on radix tree, thus
+		 * we need to ensure radix tree consistency.
+		 *
+		 * We also want an atomic snapshot of the radix tree, thus go
+		 * with spinlock rather than RCU.
+		 */
+		spin_lock(&fs_info->buffer_lock);
+		eb = get_next_extent_buffer(fs_info, page, cur);
+		if (!eb) {
+			/* No more eb in the page range after or at cur */
+			spin_unlock(&fs_info->buffer_lock);
+			break;
+		}
+		cur = eb->start + eb->len;
+
+		/*
+		 * The same as try_release_extent_buffer(), to ensure the eb
+		 * won't disappear out from under us.
+		 */
+		spin_lock(&eb->refs_lock);
+		if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
+			spin_unlock(&eb->refs_lock);
+			spin_unlock(&fs_info->buffer_lock);
+			break;
+		}
+		spin_unlock(&fs_info->buffer_lock);
+
+		/*
+		 * If tree ref isn't set then we know the ref on this eb is a
+		 * real ref, so just return, this eb will likely be freed soon
+		 * anyway.
+		 */
+		if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
+			spin_unlock(&eb->refs_lock);
+			break;
+		}
+
+		/*
+		 * Here we don't care about the return value, we will always
+		 * check the page private at the end.  And
+		 * release_extent_buffer() will release the refs_lock.
+		 */
+		release_extent_buffer(eb);
+	}
+	/*
+	 * Finally to check if we have cleared page private, as if we have
+	 * released all ebs in the page, the page private should be cleared now.
+	 */
+	spin_lock(&page->mapping->private_lock);
+	if (!PagePrivate(page))
+		ret = 1;
+	else
+		ret = 0;
+	spin_unlock(&page->mapping->private_lock);
+	return ret;
+
+}
+
 int try_release_extent_buffer(struct page *page)
 {
 	struct extent_buffer *eb;
 
+	if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE)
+		return try_release_subpage_extent_buffer(page);
+
 	/*
-	 * We need to make sure nobody is attaching this page to an eb right
-	 * now.
+	 * We need to make sure nobody is changing page->private, as we rely on
+	 * page->private as the pointer to extent buffer.
 	 */
 	spin_lock(&page->mapping->private_lock);
 	if (!PagePrivate(page)) {