btrfs: only write the sectors in the vertical stripe which has data s…

…tripes

commit bd8f7e6 upstream.

If we have only 8K partial write at the beginning of a full RAID56
stripe, we will write the following contents:

                    0  8K           32K             64K
Disk 1	(data):     |XX|            |               |
Disk 2  (data):     |               |               |
Disk 3  (parity):   |XXXXXXXXXXXXXXX|XXXXXXXXXXXXXXX|

|X| means the sector will be written back to disk.

Note that, although we won't write any sectors from disk 2, but we will
write the full 64KiB of parity to disk.

This behavior is fine for now, but not for the future (especially for
RAID56J, as we waste quite some space to journal the unused parity
stripes).

So here we will also utilize the btrfs_raid_bio::dbitmap, anytime we
queue a higher level bio into an rbio, we will update rbio::dbitmap to
indicate which vertical stripes we need to writeback.

And at finish_rmw(), we also check dbitmap to see if we need to write
any sector in the vertical stripe.

So after the patch, above example will only lead to the following
writeback pattern:

                    0  8K           32K             64K
Disk 1	(data):     |XX|            |               |
Disk 2  (data):     |               |               |
Disk 3  (parity):   |XX|            |               |

Acked-by: David Sterba <dsterba@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

fs/btrfs/raid56.c

@@ -323,6 +323,9 @@ static void merge_rbio(struct btrfs_raid_bio *dest,
 {
 	bio_list_merge(&dest->bio_list, &victim->bio_list);
 	dest->bio_list_bytes += victim->bio_list_bytes;
+	/* Also inherit the bitmaps from @victim. */
+	bitmap_or(dest->dbitmap, victim->dbitmap, dest->dbitmap,
+		  dest->stripe_npages);
 	dest->generic_bio_cnt += victim->generic_bio_cnt;
 	bio_list_init(&victim->bio_list);
 }
@@ -864,6 +867,12 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, blk_status_t err)
 
 	if (rbio->generic_bio_cnt)
 		btrfs_bio_counter_sub(rbio->bioc->fs_info, rbio->generic_bio_cnt);
+	/*
+	 * Clear the data bitmap, as the rbio may be cached for later usage.
+	 * do this before before unlock_stripe() so there will be no new bio
+	 * for this bio.
+	 */
+	bitmap_clear(rbio->dbitmap, 0, rbio->stripe_npages);
 
 	/*
 	 * At this moment, rbio->bio_list is empty, however since rbio does not
@@ -1195,6 +1204,9 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	else
 		BUG();
 
+	/* We should have at least one data sector. */
+	ASSERT(bitmap_weight(rbio->dbitmap, rbio->stripe_npages));
+
 	/* at this point we either have a full stripe,
 	 * or we've read the full stripe from the drive.
 	 * recalculate the parity and write the new results.
@@ -1266,6 +1278,11 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
 		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *page;
+
+			/* This vertical stripe has no data, skip it. */
+			if (!test_bit(pagenr, rbio->dbitmap))
+				continue;
+
 			if (stripe < rbio->nr_data) {
 				page = page_in_rbio(rbio, stripe, pagenr, 1);
 				if (!page)
@@ -1290,6 +1307,11 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 
 		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *page;
+
+			/* This vertical stripe has no data, skip it. */
+			if (!test_bit(pagenr, rbio->dbitmap))
+				continue;
+
 			if (stripe < rbio->nr_data) {
 				page = page_in_rbio(rbio, stripe, pagenr, 1);
 				if (!page)
@@ -1713,6 +1735,33 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	run_plug(plug);
 }
 
+/* Add the original bio into rbio->bio_list, and update rbio::dbitmap. */
+static void rbio_add_bio(struct btrfs_raid_bio *rbio, struct bio *orig_bio)
+{
+	const struct btrfs_fs_info *fs_info = rbio->bioc->fs_info;
+	const u64 orig_logical = orig_bio->bi_iter.bi_sector << SECTOR_SHIFT;
+	const u64 full_stripe_start = rbio->bioc->raid_map[0];
+	const u32 orig_len = orig_bio->bi_iter.bi_size;
+	const u32 sectorsize = fs_info->sectorsize;
+	u64 cur_logical;
+
+	ASSERT(orig_logical >= full_stripe_start &&
+	       orig_logical + orig_len <= full_stripe_start +
+	       rbio->nr_data * rbio->stripe_len);
+
+	bio_list_add(&rbio->bio_list, orig_bio);
+	rbio->bio_list_bytes += orig_bio->bi_iter.bi_size;
+
+	/* Update the dbitmap. */
+	for (cur_logical = orig_logical; cur_logical < orig_logical + orig_len;
+	     cur_logical += sectorsize) {
+		int bit = ((u32)(cur_logical - full_stripe_start) >>
+			   fs_info->sectorsize_bits) % rbio->stripe_npages;
+
+		set_bit(bit, rbio->dbitmap);
+	}
+}
+
 /*
  * our main entry point for writes from the rest of the FS.
  */
@@ -1730,9 +1779,8 @@ int raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc,
 		btrfs_put_bioc(bioc);
 		return PTR_ERR(rbio);
 	}
-	bio_list_add(&rbio->bio_list, bio);
-	rbio->bio_list_bytes = bio->bi_iter.bi_size;
 	rbio->operation = BTRFS_RBIO_WRITE;
+	rbio_add_bio(rbio, bio);
 
 	btrfs_bio_counter_inc_noblocked(fs_info);
 	rbio->generic_bio_cnt = 1;
@@ -2134,8 +2182,7 @@ int raid56_parity_recover(struct bio *bio, struct btrfs_io_context *bioc,
 	}
 
 	rbio->operation = BTRFS_RBIO_READ_REBUILD;
-	bio_list_add(&rbio->bio_list, bio);
-	rbio->bio_list_bytes = bio->bi_iter.bi_size;
+	rbio_add_bio(rbio, bio);
 
 	rbio->faila = find_logical_bio_stripe(rbio, bio);
 	if (rbio->faila == -1) {