btrfs: determine stripe boundary at bio allocation time in btrfs_submit_compressed_read

Currently btrfs_submit_compressed_read() will check
btrfs_bio_fits_in_stripe() each time a new page is going to be added.
Even if compressed extent is small, we don't really need to do that for
every page.

This patch will align the behavior to extent_io.c, by determining the
stripe boundary when allocating a bio.

Unlike extent_io.c, in compressed.c we don't need to bother things like
different bio flags, thus no need to re-use bio_ctrl.

Here we just manually introduce new local variable, next_stripe_start,
and teach alloc_compressed_bio() to calculate the stripe boundary.

Then each time we add some page range into the bio, we check if we
reached the boundary.  And if reached, submit it.

Also, since we have @cur_disk_byte to determine whether we're the last
bio, we don't need a explicit last_bio: tag for error handling any more.

And we can use @cur_disk_byte to track which range has been added to
bio, we can also use @cur_disk_byte to calculate the wait condition, no
need for @pending_bios.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/compression.c

@@ -435,12 +435,31 @@ static blk_status_t submit_compressed_bio(struct btrfs_fs_info *fs_info,
 }
 
 /*
- * Allocate a compressed_bio, which will be used to read/write on-disk data.
+ * Allocate a compressed_bio, which will be used to read/write on-disk
+ * (aka, compressed) * data.
+ *
+ * @cb:                 The compressed_bio structure, which records all the needed
+ *                      information to bind the compressed data to the uncompressed
+ *                      page cache.
+ * @disk_byten:         The logical bytenr where the compressed data will be read
+ *                      from or written to.
+ * @endio_func:         The endio function to call after the IO for compressed data
+ *                      is finished.
+ * @next_stripe_start:  Return value of logical bytenr of where next stripe starts.
+ *                      Let the caller know to only fill the bio up to the stripe
+ *                      boundary.
  */
+
+
 static struct bio *alloc_compressed_bio(struct compressed_bio *cb, u64 disk_bytenr,
-					unsigned int opf, bio_end_io_t endio_func)
+					unsigned int opf, bio_end_io_t endio_func,
+					u64 *next_stripe_start)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
+	struct btrfs_io_geometry geom;
+	struct extent_map *em;
 	struct bio *bio;
+	int ret;
 
 	bio = btrfs_bio_alloc(BIO_MAX_VECS);
 
@@ -449,18 +468,23 @@ static struct bio *alloc_compressed_bio(struct compressed_bio *cb, u64 disk_byte
 	bio->bi_private = cb;
 	bio->bi_end_io = endio_func;
 
-	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-		struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
-		struct btrfs_device *device;
+	em = btrfs_get_chunk_map(fs_info, disk_bytenr, fs_info->sectorsize);
+	if (IS_ERR(em)) {
+		bio_put(bio);
+		return ERR_CAST(em);
+	}
 
-		device = btrfs_zoned_get_device(fs_info, disk_bytenr,
-						fs_info->sectorsize);
-		if (IS_ERR(device)) {
-			bio_put(bio);
-			return ERR_CAST(device);
-		}
-		bio_set_dev(bio, device->bdev);
+	if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+		bio_set_dev(bio, em->map_lookup->stripes[0].dev->bdev);
+
+	ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(bio), disk_bytenr, &geom);
+	free_extent_map(em);
+	if (ret < 0) {
+		bio_put(bio);
+		return ERR_PTR(ret);
 	}
+	*next_stripe_start = disk_bytenr + geom.len;
+
 	return bio;
 }
 
@@ -488,6 +512,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	int pg_index = 0;
 	struct page *page;
 	u64 first_byte = disk_start;
+	u64 next_stripe_start;
 	blk_status_t ret;
 	int skip_sum = inode->flags & BTRFS_INODE_NODATASUM;
 	const bool use_append = btrfs_use_zone_append(inode, disk_start);
@@ -510,7 +535,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	cb->nr_pages = nr_pages;
 
 	bio = alloc_compressed_bio(cb, first_byte, bio_op | write_flags,
-				   end_compressed_bio_write);
+				   end_compressed_bio_write, &next_stripe_start);
 	if (IS_ERR(bio)) {
 		kfree(cb);
 		return errno_to_blk_status(PTR_ERR(bio));
@@ -559,7 +584,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 
 			bio = alloc_compressed_bio(cb, first_byte,
 					bio_op | write_flags,
-					end_compressed_bio_write);
+					end_compressed_bio_write,
+					&next_stripe_start);
 			if (IS_ERR(bio)) {
 				ret = errno_to_blk_status(PTR_ERR(bio));
 				bio = NULL;
@@ -790,9 +816,10 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	unsigned int compressed_len;
 	unsigned int nr_pages;
 	unsigned int pg_index;
-	struct page *page;
-	struct bio *comp_bio;
-	u64 cur_disk_byte = bio->bi_iter.bi_sector << 9;
+	struct bio *comp_bio = NULL;
+	const u64 disk_bytenr = bio->bi_iter.bi_sector << SECTOR_SHIFT;
+	u64 cur_disk_byte = disk_bytenr;
+	u64 next_stripe_start;
 	u64 file_offset;
 	u64 em_len;
 	u64 em_start;
@@ -860,39 +887,58 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	/* include any pages we added in add_ra-bio_pages */
 	cb->len = bio->bi_iter.bi_size;
 
-	comp_bio = alloc_compressed_bio(cb, cur_disk_byte, REQ_OP_READ,
-					end_compressed_bio_read);
-	if (IS_ERR(comp_bio)) {
-		ret = errno_to_blk_status(PTR_ERR(comp_bio));
-		comp_bio = NULL;
-		goto fail2;
-	}
+	while (cur_disk_byte < disk_bytenr + compressed_len) {
+		u64 offset = cur_disk_byte - disk_bytenr;
+		unsigned int index = offset >> PAGE_SHIFT;
+		unsigned int real_size;
+		unsigned int added;
+		struct page *page = cb->compressed_pages[index];
+		bool submit = false;
 
-	for (pg_index = 0; pg_index < nr_pages; pg_index++) {
-		u32 pg_len = PAGE_SIZE;
-		int submit = 0;
+		/* Allocate new bio if submitted or not yet allocated */
+		if (!comp_bio) {
+			comp_bio = alloc_compressed_bio(cb, cur_disk_byte,
+					REQ_OP_READ, end_compressed_bio_read,
+					&next_stripe_start);
+			if (IS_ERR(comp_bio)) {
+				ret = errno_to_blk_status(PTR_ERR(comp_bio));
+				comp_bio = NULL;
+				goto finish_cb;
+			}
+		}
+		/*
+		 * We should never reach next_stripe_start start as we will
+		 * submit comp_bio when reach the boundary immediately.
+		 */
+		ASSERT(cur_disk_byte != next_stripe_start);
+		/*
+		 * We have various limit on the real read size:
+		 * - stripe boundary
+		 * - page boundary
+		 * - compressed length boundary
+		 */
+		real_size = min_t(u64, U32_MAX, next_stripe_start - cur_disk_byte);
+		real_size = min_t(u64, real_size, PAGE_SIZE - offset_in_page(offset));
+		real_size = min_t(u64, real_size, compressed_len - offset);
+		ASSERT(IS_ALIGNED(real_size, fs_info->sectorsize));
 
+		added = bio_add_page(comp_bio, page, real_size, offset_in_page(offset));
 		/*
-		 * To handle subpage case, we need to make sure the bio only
-		 * covers the range we need.
-		 *
-		 * If we're at the last page, truncate the length to only cover
-		 * the remaining part.
+		 * Maximum compressed extent is smaller than bio size limit,
+		 * thus bio_add_page() should always success.
 		 */
-		if (pg_index == nr_pages - 1)
-			pg_len = min_t(u32, PAGE_SIZE,
-					compressed_len - pg_index * PAGE_SIZE);
+		ASSERT(added == real_size);
+		cur_disk_byte += added;
 
-		page = cb->compressed_pages[pg_index];
-		page->mapping = inode->i_mapping;
-		page->index = em_start >> PAGE_SHIFT;
+		/* Reached stripe boundary, need to submit */
+		if (cur_disk_byte == next_stripe_start)
+			submit = true;
 
-		if (comp_bio->bi_iter.bi_size)
-			submit = btrfs_bio_fits_in_stripe(page, pg_len,
-							  comp_bio, 0);
+		/* Has finished the range, need to submit */
+		if (cur_disk_byte == disk_bytenr + compressed_len)
+			submit = true;
 
-		page->mapping = NULL;
-		if (submit || bio_add_page(comp_bio, page, pg_len, 0) < pg_len) {
+		if (submit) {
 			unsigned int nr_sectors;
 
 			ret = btrfs_lookup_bio_sums(inode, comp_bio, sums);
@@ -906,29 +952,9 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			ret = submit_compressed_bio(fs_info, cb, comp_bio, mirror_num);
 			if (ret)
 				goto finish_cb;
-
-			comp_bio = alloc_compressed_bio(cb, cur_disk_byte,
-					REQ_OP_READ,
-					end_compressed_bio_read);
-			if (IS_ERR(comp_bio)) {
-				ret = errno_to_blk_status(PTR_ERR(comp_bio));
-				comp_bio = NULL;
-				goto finish_cb;
-			}
-
-			bio_add_page(comp_bio, page, pg_len, 0);
+			comp_bio = NULL;
 		}
-		cur_disk_byte += pg_len;
 	}
-
-	ret = btrfs_lookup_bio_sums(inode, comp_bio, sums);
-	if (ret)
-		goto last_bio;
-
-	ret = submit_compressed_bio(fs_info, cb, comp_bio, mirror_num);
-	if (ret)
-		goto last_bio;
-
 	return 0;
 
 fail2:
@@ -943,18 +969,18 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 out:
 	free_extent_map(em);
 	return ret;
-last_bio:
-	comp_bio->bi_status = ret;
-	/* This is the last bio, endio functions will free @cb */
-	bio_endio(comp_bio);
-	return ret;
-
 finish_cb:
 	if (comp_bio) {
 		comp_bio->bi_status = ret;
 		bio_endio(comp_bio);
 	}
-	wait_var_event(cb, atomic_read(&cb->pending_bios) == 0);
+	/* All bytes of @cb is submitted, endio will free @cb */
+	if (cur_disk_byte == disk_bytenr + compressed_len)
+		return ret;
+
+	wait_var_event(cb, refcount_read(&cb->pending_sectors) ==
+			   (disk_bytenr + compressed_len - cur_disk_byte) >>
+			   fs_info->sectorsize_bits);
 	/*
 	 * Even with previous bio ended, we should still have io not yet
 	 * submitted, thus need to finish @cb manually.