@@ -24,6 +24,7 @@
 #include "rcu-string.h"
 #include "backref.h"
 #include "disk-io.h"
+#include "subpage.h"
 
 static struct kmem_cache *extent_state_cache;
 static struct kmem_cache *extent_buffer_cache;

@@ -3140,22 +3141,41 @@ static int submit_extent_page(unsigned int opf,
 	return ret;
 }
 
-static void attach_extent_buffer_page(struct extent_buffer *eb,
+static int attach_extent_buffer_page(struct extent_buffer *eb,
 				      struct page *page)
 {
-	/*
-	 * If the page is mapped to btree inode, we should hold the private
-	 * lock to prevent race.
-	 * For cloned or dummy extent buffers, their pages are not mapped and
-	 * will not race with any other ebs.
-	 */
-	if (page->mapping)
-		lockdep_assert_held(&page->mapping->private_lock);
+	struct btrfs_fs_info *fs_info = eb->fs_info;
+	int ret;
 
-	if (!PagePrivate(page))
-		attach_page_private(page, eb);
-	else
-		WARN_ON(page->private != (unsigned long)eb);
+	if (fs_info->sectorsize == PAGE_SIZE) {
+		/*
+		 * If the page is mapped to btree inode, we should hold the
+		 * private lock to prevent race.
+		 * For cloned or dummy extent buffers, their pages are not
+		 * mapped and will not race with any other ebs.
+		 */
+		if (page->mapping)
+			lockdep_assert_held(&page->mapping->private_lock);
+
+		if (!PagePrivate(page))
+			attach_page_private(page, eb);
+		else
+			WARN_ON(page->private != (unsigned long)eb);
+		return 0;
+	}
+
+	/* Already mapped, just update the existing range */
+	if (PagePrivate(page))
+		goto update_bitmap;
+
+	/* Do new allocation to attach subpage */
+	ret = btrfs_attach_subpage(fs_info, page);
+	if (ret < 0)
+		return ret;
+
+update_bitmap:
+	btrfs_subpage_set_tree_block(fs_info, page, eb->start, eb->len);
+	return 0;
 }
 
 void set_page_extent_mapped(struct page *page)

@@ -5063,21 +5083,29 @@ struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src)
 	if (new == NULL)
 		return NULL;
 
+	set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags);
+	set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags);
+
 	for (i = 0; i < num_pages; i++) {
+		int ret;
+
 		p = alloc_page(GFP_NOFS);
 		if (!p) {
 			btrfs_release_extent_buffer(new);
 			return NULL;
 		}
-		attach_extent_buffer_page(new, p);
+		ret = attach_extent_buffer_page(new, p);
+		if (ret < 0) {
+			put_page(p);
+			btrfs_release_extent_buffer(new);
+			return NULL;
+		}
 		WARN_ON(PageDirty(p));
 		SetPageUptodate(p);
 		new->pages[i] = p;
 		copy_page(page_address(p), page_address(src->pages[i]));
 	}
 
-	set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags);
-	set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags);
 
 	return new;
 }

@@ -5316,6 +5344,18 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 			goto free_eb;
 		}
 
+		/*
+		 * Preallocate page->private for subpage case, so that
+		 * we won't allocate memory with private_lock hold.
+		 */
+		ret = btrfs_attach_subpage(fs_info, p);
+		if (ret < 0) {
+			unlock_page(p);
+			put_page(p);
+			exists = ERR_PTR(-ENOMEM);
+			goto free_eb;
+		}
+
 		spin_lock(&mapping->private_lock);
 		exists = grab_extent_buffer(p);
 		if (exists) {

@@ -5325,8 +5365,10 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 			mark_extent_buffer_accessed(exists, p);
 			goto free_eb;
 		}
+		/* Should not fail, as we have attached the subpage already */
 		attach_extent_buffer_page(eb, p);
 		spin_unlock(&mapping->private_lock);
+
 		WARN_ON(PageDirty(p));
 		eb->pages[i] = p;
 		if (!PageUptodate(p))

@@ -23,9 +23,59 @@
 struct btrfs_subpage {
 	/* Common members for both data and metadata pages */
 	spinlock_t lock;
+	union {
+		/* Structures only used by metadata */
+		struct {
+			u16 tree_block_bitmap;
+		};
+		/* structures only used by data */
+	};
 };
 
 int btrfs_attach_subpage(struct btrfs_fs_info *fs_info, struct page *page);
 void btrfs_detach_subpage(struct btrfs_fs_info *fs_info, struct page *page);
 
+/*
+ * Convert the [start, start + len) range into a u16 bitmap
+ *
+ * E.g. if start == page_offset() + 16K, len = 16K, we get 0x00f0.
+ */
+static inline u16 btrfs_subpage_calc_bitmap(struct btrfs_fs_info *fs_info,
+			struct page *page, u64 start, u32 len)
+{
+	int bit_start = offset_in_page(start) >> fs_info->sectorsize_bits;
+	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 unampped page like dummy extent buffer pages.
+	 */
+	if (page->mapping)
+		ASSERT(page_offset(page) <= start &&
+			start + len <= page_offset(page) + PAGE_SIZE);
+	/*
+	 * Here nbits can be 16, thus can go beyond u16 range. Here we make the
+	 * first left shift to be calculated in unsigned long (u32), then
+	 * truncate the result to u16.
+	 */
+	return (u16)(((1UL << nbits) - 1) << bit_start);
+}
+
+static inline void btrfs_subpage_set_tree_block(struct btrfs_fs_info *fs_info,
+			struct page *page, u64 start, u32 len)
+{
+	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+	unsigned long flags;
+	u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
+
+	spin_lock_irqsave(&subpage->lock, flags);
+	subpage->tree_block_bitmap |= tmp;
+	spin_unlock_irqrestore(&subpage->lock, flags);
+}
+
 #endif /* BTRFS_SUBPAGE_H */