diff --git a/fs/buffer.c b/fs/buffer.c
index f25f58096428cb3b43d5ae59bde49f4d5168925a..e7a1461f4387fd4f255cd3afc61eb99b96eb9bce 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -426,8 +426,10 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	if (all_mapped) {
 		printk("__find_get_block_slow() failed. "
 			"block=%llu, b_blocknr=%llu\n",
-			(unsigned long long)block, (unsigned long long)bh->b_blocknr);
-		printk("b_state=0x%08lx, b_size=%u\n", bh->b_state, bh->b_size);
+			(unsigned long long)block,
+			(unsigned long long)bh->b_blocknr);
+		printk("b_state=0x%08lx, b_size=%zu\n",
+			bh->b_state, bh->b_size);
 		printk("device blocksize: %d\n", 1 << bd_inode->i_blkbits);
 	}
 out_unlock:
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 90641929a437fc64c3db3be1e3b6fba65117668d..6a610ae5358394710688e518d022f25e85a51b41 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -377,7 +377,7 @@ int ocfs2_journal_access(struct ocfs2_journal_handle *handle,
 	BUG_ON(!bh);
 	BUG_ON(!(handle->flags & OCFS2_HANDLE_STARTED));
 
-	mlog_entry("bh->b_blocknr=%llu, type=%d (\"%s\"), bh->b_size = %hu\n",
+	mlog_entry("bh->b_blocknr=%llu, type=%d (\"%s\"), bh->b_size = %zu\n",
 		   (unsigned long long)bh->b_blocknr, type,
 		   (type == OCFS2_JOURNAL_ACCESS_CREATE) ?
 		   "OCFS2_JOURNAL_ACCESS_CREATE" :
diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c
index 78b40621b88b7571e5065aa005feae888092cb0e..27bd3a1df2ad0146663c995856c319a78d9fc2f2 100644
--- a/fs/reiserfs/prints.c
+++ b/fs/reiserfs/prints.c
@@ -143,7 +143,7 @@ static void sprintf_buffer_head(char *buf, struct buffer_head *bh)
 	char b[BDEVNAME_SIZE];
 
 	sprintf(buf,
-		"dev %s, size %d, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
+		"dev %s, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
 		bdevname(bh->b_bdev, b), bh->b_size,
 		(unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)),
 		bh->b_state, bh->b_page,
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index da917ed096a3271f231756bdd299e043e9549aca..464f068f8b168eaf3bb5b89c99345497e068f612 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -46,25 +46,28 @@ struct address_space;
 typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate);
 
 /*
- * Keep related fields in common cachelines.  The most commonly accessed
- * field (b_state) goes at the start so the compiler does not generate
- * indexed addressing for it.
+ * Historically, a buffer_head was used to map a single block
+ * within a page, and of course as the unit of I/O through the
+ * filesystem and block layers.  Nowadays the basic I/O unit
+ * is the bio, and buffer_heads are used for extracting block
+ * mappings (via a get_block_t call), for tracking state within
+ * a page (via a page_mapping) and for wrapping bio submission
+ * for backward compatibility reasons (e.g. submit_bh).
  */
 struct buffer_head {
-	/* First cache line: */
 	unsigned long b_state;		/* buffer state bitmap (see above) */
 	struct buffer_head *b_this_page;/* circular list of page's buffers */
 	struct page *b_page;		/* the page this bh is mapped to */
-	atomic_t b_count;		/* users using this block */
-	u32 b_size;			/* block size */
 
-	sector_t b_blocknr;		/* block number */
-	char *b_data;			/* pointer to data block */
+	sector_t b_blocknr;		/* start block number */
+	size_t b_size;			/* size of mapping */
+	char *b_data;			/* pointer to data within the page */
 
 	struct block_device *b_bdev;
 	bh_end_io_t *b_end_io;		/* I/O completion */
  	void *b_private;		/* reserved for b_end_io */
 	struct list_head b_assoc_buffers; /* associated with another mapping */
+	atomic_t b_count;		/* users using this buffer_head */
 };
 
 /*