btrfs: zoned: implement cloning for zoned device-replace

This is 2/4 patch to implement device replace for zoned filesystems.

In zoned mode, a block group must be either copied (from the source
device to the target device) or cloned (to both devices).

Implement the cloning part. If a block group targeted by an IO is marked
to copy, we should not clone the IO to the destination device, because
the block group is eventually copied by the replace process.

This commit also handles cloning of device reset.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 42 insertions, 15 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d976c56b3a56..cd308bf3a220 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -35,6 +35,7 @@
 #include "discard.h"
 #include "rcu-string.h"
 #include "zoned.h"
+#include "dev-replace.h"
 
 #undef SCRAMBLE_DELAYED_REFS
 
@@ -1265,6 +1266,46 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
 	return ret;
 }
 
+static int do_discard_extent(struct btrfs_bio_stripe *stripe, u64 *bytes)
+{
+	struct btrfs_device *dev = stripe->dev;
+	struct btrfs_fs_info *fs_info = dev->fs_info;
+	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
+	u64 phys = stripe->physical;
+	u64 len = stripe->length;
+	u64 discarded = 0;
+	int ret = 0;
+
+	/* Zone reset on a zoned filesystem */
+	if (btrfs_can_zone_reset(dev, phys, len)) {
+		u64 src_disc;
+
+		ret = btrfs_reset_device_zone(dev, phys, len, &discarded);
+		if (ret)
+			goto out;
+
+		if (!btrfs_dev_replace_is_ongoing(dev_replace) ||
+		    dev != dev_replace->srcdev)
+			goto out;
+
+		src_disc = discarded;
+
+		/* Send to replace target as well */
+		ret = btrfs_reset_device_zone(dev_replace->tgtdev, phys, len,
+					      &discarded);
+		discarded += src_disc;
+	} else if (blk_queue_discard(bdev_get_queue(stripe->dev->bdev))) {
+		ret = btrfs_issue_discard(dev->bdev, phys, len, &discarded);
+	} else {
+		ret = 0;
+		*bytes = 0;
+	}
+
+out:
+	*bytes = discarded;
+	return ret;
+}
+
 int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 			 u64 num_bytes, u64 *actual_bytes)
 {
@@ -1298,28 +1339,14 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 
 		stripe = bbio->stripes;
 		for (i = 0; i < bbio->num_stripes; i++, stripe++) {
-			struct btrfs_device *dev = stripe->dev;
-			u64 physical = stripe->physical;
-			u64 length = stripe->length;
 			u64 bytes;
-			struct request_queue *req_q;
 
 			if (!stripe->dev->bdev) {
 				ASSERT(btrfs_test_opt(fs_info, DEGRADED));
 				continue;
 			}
 
-			req_q = bdev_get_queue(stripe->dev->bdev);
-			/* Zone reset on zoned filesystems */
-			if (btrfs_can_zone_reset(dev, physical, length))
-				ret = btrfs_reset_device_zone(dev, physical,
-							      length, &bytes);
-			else if (blk_queue_discard(req_q))
-				ret = btrfs_issue_discard(dev->bdev, physical,
-							  length, &bytes);
-			else
-				continue;
-
+			ret = do_discard_extent(stripe, &bytes);
 			if (!ret) {
 				discarded_bytes += bytes;
 			} else if (ret != -EOPNOTSUPP) {