btrfs: Introduce extent_read_full_page_nolock()

We want this for btrfs_extent_same. Basically readpage and friends do their
own extent locking but for the purposes of dedupe, we want to have both
files locked down across a set of readpage operations (so that we can
compare data). Introduce this variant and a flag which can be set for
extent_read_full_page() to indicate that we are already locked.

Partial credit for this patch goes to Gabriel de Perthuis <g2p.code@gmail.com>
as I have included a fix from him to the original patch which avoids a
deadlock on compressed extents.

Signed-off-by: Mark Fasheh <mfasheh@suse.de>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

Author: Mark Fasheh

fs/btrfs/compression.c

@@ -639,7 +639,11 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	faili = nr_pages - 1;
 	cb->nr_pages = nr_pages;
 
-	add_ra_bio_pages(inode, em_start + em_len, cb);
+	/* In the parent-locked case, we only locked the range we are
+	 * interested in.  In all other cases, we can opportunistically
+	 * cache decompressed data that goes beyond the requested range. */
+	if (!(bio_flags & EXTENT_BIO_PARENT_LOCKED))
+		add_ra_bio_pages(inode, em_start + em_len, cb);
 
 	/* include any pages we added in add_ra-bio_pages */
 	uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;

fs/btrfs/extent_io.c

@@ -2764,11 +2764,12 @@ static int __do_readpage(struct extent_io_tree *tree,
 	struct block_device *bdev;
 	int ret;
 	int nr = 0;
+	int parent_locked = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
 	size_t pg_offset = 0;
 	size_t iosize;
 	size_t disk_io_size;
 	size_t blocksize = inode->i_sb->s_blocksize;
-	unsigned long this_bio_flag = 0;
+	unsigned long this_bio_flag = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
 
 	set_page_extent_mapped(page);
 
@@ -2807,23 +2808,26 @@ static int __do_readpage(struct extent_io_tree *tree,
 			kunmap_atomic(userpage);
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			unlock_extent_cached(tree, cur, cur + iosize - 1,
-					     &cached, GFP_NOFS);
+			if (!parent_locked)
+				unlock_extent_cached(tree, cur,
+						     cur + iosize - 1,
+						     &cached, GFP_NOFS);
 			break;
 		}
 		em = __get_extent_map(inode, page, pg_offset, cur,
 				      end - cur + 1, get_extent, em_cached);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
-			unlock_extent(tree, cur, end);
+			if (!parent_locked)
+				unlock_extent(tree, cur, end);
 			break;
 		}
 		extent_offset = cur - em->start;
 		BUG_ON(extent_map_end(em) <= cur);
 		BUG_ON(end < cur);
 
 		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
-			this_bio_flag = EXTENT_BIO_COMPRESSED;
+			this_bio_flag |= EXTENT_BIO_COMPRESSED;
 			extent_set_compress_type(&this_bio_flag,
 						 em->compress_type);
 		}
@@ -2867,7 +2871,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 		if (test_range_bit(tree, cur, cur_end,
 				   EXTENT_UPTODATE, 1, NULL)) {
 			check_page_uptodate(tree, page);
-			unlock_extent(tree, cur, cur + iosize - 1);
+			if (!parent_locked)
+				unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -2877,7 +2882,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 		 */
 		if (block_start == EXTENT_MAP_INLINE) {
 			SetPageError(page);
-			unlock_extent(tree, cur, cur + iosize - 1);
+			if (!parent_locked)
+				unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -2895,7 +2901,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 			*bio_flags = this_bio_flag;
 		} else {
 			SetPageError(page);
-			unlock_extent(tree, cur, cur + iosize - 1);
+			if (!parent_locked)
+				unlock_extent(tree, cur, cur + iosize - 1);
 		}
 		cur = cur + iosize;
 		pg_offset += iosize;
@@ -3021,6 +3028,20 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	return ret;
 }
 
+int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
+				 get_extent_t *get_extent, int mirror_num)
+{
+	struct bio *bio = NULL;
+	unsigned long bio_flags = EXTENT_BIO_PARENT_LOCKED;
+	int ret;
+
+	ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num,
+				      &bio_flags, READ);
+	if (bio)
+		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
+	return ret;
+}
+
 static noinline void update_nr_written(struct page *page,
 				      struct writeback_control *wbc,
 				      unsigned long nr_written)

fs/btrfs/extent_io.h

@@ -29,6 +29,7 @@
  */
 #define EXTENT_BIO_COMPRESSED 1
 #define EXTENT_BIO_TREE_LOG 2
+#define EXTENT_BIO_PARENT_LOCKED 4
 #define EXTENT_BIO_FLAG_SHIFT 16
 
 /* these are bit numbers for test/set bit */
@@ -199,6 +200,8 @@ int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end,
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 			  get_extent_t *get_extent, int mirror_num);
+int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
+				 get_extent_t *get_extent, int mirror_num);
 int __init extent_io_init(void);
 void extent_io_exit(void);