btrfs: add support for inserting raid stripe extents

Add support for inserting stripe extents into the raid stripe tree on
completion of every write that needs an extra logical-to-physical
translation when using RAID.

Inserting the stripe extents happens after the data I/O has completed,
this is done to

  a) support zone-append and
  b) rule out the possibility of a RAID-write-hole.

Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 21 insertions, 0 deletions

diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 964714258f86..ac6bc4f43ffb 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -14,6 +14,7 @@
 #include "rcu-string.h"
 #include "zoned.h"
 #include "file-item.h"
+#include "raid-stripe-tree.h"
 
 static struct bio_set btrfs_bioset;
 static struct bio_set btrfs_clone_bioset;
@@ -415,6 +416,9 @@ static void btrfs_orig_write_end_io(struct bio *bio)
 	else
 		bio->bi_status = BLK_STS_OK;
 
+	if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status)
+		stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
+
 	btrfs_orig_bbio_end_io(bbio);
 	btrfs_put_bioc(bioc);
 }
@@ -426,6 +430,8 @@ static void btrfs_clone_write_end_io(struct bio *bio)
 	if (bio->bi_status) {
 		atomic_inc(&stripe->bioc->error);
 		btrfs_log_dev_io_error(bio, stripe->dev);
+	} else if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+		stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 	}
 
 	/* Pass on control to the original bio this one was cloned from */
@@ -487,6 +493,7 @@ static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr)
 	bio->bi_private = &bioc->stripes[dev_nr];
 	bio->bi_iter.bi_sector = bioc->stripes[dev_nr].physical >> SECTOR_SHIFT;
 	bioc->stripes[dev_nr].bioc = bioc;
+	bioc->size = bio->bi_iter.bi_size;
 	btrfs_submit_dev_bio(bioc->stripes[dev_nr].dev, bio);
 }
 
@@ -496,6 +503,8 @@ static void __btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc,
 	if (!bioc) {
 		/* Single mirror read/write fast path. */
 		btrfs_bio(bio)->mirror_num = mirror_num;
+		if (bio_op(bio) != REQ_OP_READ)
+			btrfs_bio(bio)->orig_physical = smap->physical;
 		bio->bi_iter.bi_sector = smap->physical >> SECTOR_SHIFT;
 		if (bio_op(bio) != REQ_OP_READ)
 			btrfs_bio(bio)->orig_physical = smap->physical;
@@ -688,6 +697,18 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 			bio->bi_opf |= REQ_OP_ZONE_APPEND;
 		}
 
+		if (is_data_bbio(bbio) && bioc &&
+		    btrfs_need_stripe_tree_update(bioc->fs_info, bioc->map_type)) {
+			/*
+			 * No locking for the list update, as we only add to
+			 * the list in the I/O submission path, and list
+			 * iteration only happens in the completion path, which
+			 * can't happen until after the last submission.
+			 */
+			btrfs_get_bioc(bioc);
+			list_add_tail(&bioc->rst_ordered_entry, &bbio->ordered->bioc_list);
+		}
+
 		/*
 		 * Csum items for reloc roots have already been cloned at this
 		 * point, so they are handled as part of the no-checksum case.