btrfs: use an efficient way to represent source of duplicated stripes

For btrfs dev-replace, we have to duplicate writes to the source
device into the target device.

For non-RAID56, all writes into the same mapped ranges are sharing the
same content, thus they don't really need to bother anything.
(E.g. in btrfs_submit_bio() for non-RAID56 range we just submit the
same write to all involved devices).

But for RAID56, all stripes contain different content, thus we must
have a clear mapping of which stripe is duplicated from which original
stripe.

Currently we use a complex way using tgtdev_map[] array, e.g:

 num_tgtdevs = 1
 tgtdev_map[0] = 0    <- Means stripes[0] is not involved in replace.
 tgtdev_map[1] = 3    <- Means stripes[1] is involved in replace,
			 and it's duplicated to stripes[3].
 tgtdev_map[2] = 0    <- Means stripes[2] is not involved in replace.

But this is wasting some space, and ignores one important thing for
dev-replace, there is at most one running replace.

Thus we can change it to a fixed array to represent the mapping:

 replace_nr_stripes = 1
 replace_stripe_src = 1    <- Means stripes[1] is involved in replace.
			      thus the extra stripe is a copy of
			      stripes[1]

By this we can save some space for bioc on RAID56 chunks with many
devices.  And we get rid of one variable sized array from bioc.

Thus the patch involves the following changes:

- Replace @num_tgtdevs and @tgtdev_map[] with @replace_nr_stripes
  and @replace_stripe_src.

  @num_tgtdevs is just renamed to @replace_nr_stripes.
  While the mapping is completely changed.

- Add extra ASSERT()s for RAID56 code

- Only add two more extra stripes for dev-replace cases.
  As we have an upper limit on how many dev-replace stripes we can have.

- Unify the behavior of handle_ops_on_dev_replace()
  Previously handle_ops_on_dev_replace() go two different paths for
  WRITE and GET_READ_MIRRORS.
  Now unify them by always going the WRITE path first (with at most 2
  replace stripes), then if we're doing GET_READ_MIRRORS and we have 2
  extra stripes, just drop one stripe.

- Remove the @real_stripes argument from alloc_btrfs_io_context()
  As we don't need the old variable length array any more.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 28 insertions, 8 deletions

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index a68fe51861ac..0ac1fc7896dd 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -906,7 +906,7 @@ static struct sector_ptr *sector_in_rbio(struct btrfs_raid_bio *rbio,
 static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
 					 struct btrfs_io_context *bioc)
 {
-	const unsigned int real_stripes = bioc->num_stripes - bioc->num_tgtdevs;
+	const unsigned int real_stripes = bioc->num_stripes - bioc->replace_nr_stripes;
 	const unsigned int stripe_npages = BTRFS_STRIPE_LEN >> PAGE_SHIFT;
 	const unsigned int num_pages = stripe_npages * real_stripes;
 	const unsigned int stripe_nsectors =
@@ -1276,10 +1276,16 @@ static int rmw_assemble_write_bios(struct btrfs_raid_bio *rbio,
 			goto error;
 	}
 
-	if (likely(!rbio->bioc->num_tgtdevs))
+	if (likely(!rbio->bioc->replace_nr_stripes))
 		return 0;
 
-	/* Make a copy for the replace target device. */
+	/*
+	 * Make a copy for the replace target device.
+	 *
+	 * Thus the source stripe number (in replace_stripe_src) should be valid.
+	 */
+	ASSERT(rbio->bioc->replace_stripe_src >= 0);
+
 	for (total_sector_nr = 0; total_sector_nr < rbio->nr_sectors;
 	     total_sector_nr++) {
 		struct sector_ptr *sector;
@@ -1287,7 +1293,12 @@ static int rmw_assemble_write_bios(struct btrfs_raid_bio *rbio,
 		stripe = total_sector_nr / rbio->stripe_nsectors;
 		sectornr = total_sector_nr % rbio->stripe_nsectors;
 
-		if (!rbio->bioc->tgtdev_map[stripe]) {
+		/*
+		 * For RAID56, there is only one device that can be replaced,
+		 * and replace_stripe_src[0] indicates the stripe number we
+		 * need to copy from.
+		 */
+		if (stripe != rbio->bioc->replace_stripe_src) {
 			/*
 			 * We can skip the whole stripe completely, note
 			 * total_sector_nr will be increased by one anyway.
@@ -1310,7 +1321,7 @@ static int rmw_assemble_write_bios(struct btrfs_raid_bio *rbio,
 		}
 
 		ret = rbio_add_io_sector(rbio, bio_list, sector,
-					 rbio->bioc->tgtdev_map[stripe],
+					 rbio->real_stripes,
 					 sectornr, REQ_OP_WRITE);
 		if (ret)
 			goto error;
@@ -2436,7 +2447,11 @@ static int finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check)
 	else
 		BUG();
 
-	if (bioc->num_tgtdevs && bioc->tgtdev_map[rbio->scrubp]) {
+	/*
+	 * Replace is running and our P/Q stripe is being replaced, then we
+	 * need to duplicate the final write to replace target.
+	 */
+	if (bioc->replace_nr_stripes && bioc->replace_stripe_src == rbio->scrubp) {
 		is_replace = 1;
 		bitmap_copy(pbitmap, &rbio->dbitmap, rbio->stripe_nsectors);
 	}
@@ -2538,13 +2553,18 @@ writeback:
 	if (!is_replace)
 		goto submit_write;
 
+	/*
+	 * Replace is running and our parity stripe needs to be duplicated to
+	 * the target device.  Check we have a valid source stripe number.
+	 */
+	ASSERT(rbio->bioc->replace_stripe_src >= 0);
 	for_each_set_bit(sectornr, pbitmap, rbio->stripe_nsectors) {
 		struct sector_ptr *sector;
 
 		sector = rbio_stripe_sector(rbio, rbio->scrubp, sectornr);
 		ret = rbio_add_io_sector(rbio, &bio_list, sector,
-				       bioc->tgtdev_map[rbio->scrubp],
-				       sectornr, REQ_OP_WRITE);
+					 rbio->real_stripes,
+					 sectornr, REQ_OP_WRITE);
 		if (ret)
 			goto cleanup;
 	}