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>

3 files changed, 80 insertions, 17 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) {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a4d47c6050f7..52ec6721ada2 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5973,9 +5973,29 @@ static int get_extra_mirror_from_replace(struct btrfs_fs_info *fs_info,
 	return ret;
 }
 
+static bool is_block_group_to_copy(struct btrfs_fs_info *fs_info, u64 logical)
+{
+	struct btrfs_block_group *cache;
+	bool ret;
+
+	/* Non-ZONED mode does not use "to_copy" flag */
+	if (!btrfs_is_zoned(fs_info))
+		return false;
+
+	cache = btrfs_lookup_block_group(fs_info, logical);
+
+	spin_lock(&cache->lock);
+	ret = cache->to_copy;
+	spin_unlock(&cache->lock);
+
+	btrfs_put_block_group(cache);
+	return ret;
+}
+
 static void handle_ops_on_dev_replace(enum btrfs_map_op op,
 				      struct btrfs_bio **bbio_ret,
 				      struct btrfs_dev_replace *dev_replace,
+				      u64 logical,
 				      int *num_stripes_ret, int *max_errors_ret)
 {
 	struct btrfs_bio *bbio = *bbio_ret;
@@ -5989,6 +6009,13 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op,
 		int index_where_to_add;
 
 		/*
+		 * A block group which have "to_copy" set will eventually
+		 * copied by dev-replace process. We can avoid cloning IO here.
+		 */
+		if (is_block_group_to_copy(dev_replace->srcdev->fs_info, logical))
+			return;
+
+		/*
 		 * duplicate the write operations while the dev replace
 		 * procedure is running. Since the copying of the old disk to
 		 * the new disk takes place at run time while the filesystem is
@@ -6376,8 +6403,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 
 	if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL &&
 	    need_full_stripe(op)) {
-		handle_ops_on_dev_replace(op, &bbio, dev_replace, &num_stripes,
-					  &max_errors);
+		handle_ops_on_dev_replace(op, &bbio, dev_replace, logical,
+					  &num_stripes, &max_errors);
 	}
 
 	*bbio_ret = bbio;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index b2a6553b2db0..15288f766842 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -11,6 +11,7 @@
 #include "disk-io.h"
 #include "block-group.h"
 #include "transaction.h"
+#include "dev-replace.h"
 
 /* Maximum number of zones to report per blkdev_report_zones() call */
 #define BTRFS_REPORT_NR_ZONES   4096
@@ -1036,6 +1037,8 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	for (i = 0; i < map->num_stripes; i++) {
 		bool is_sequential;
 		struct blk_zone zone;
+		struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
+		int dev_replace_is_ongoing = 0;
 
 		device = map->stripes[i].dev;
 		physical = map->stripes[i].physical;
@@ -1062,6 +1065,12 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		 */
 		btrfs_dev_clear_zone_empty(device, physical);
 
+		down_read(&dev_replace->rwsem);
+		dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
+		if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL)
+			btrfs_dev_clear_zone_empty(dev_replace->tgtdev, physical);
+		up_read(&dev_replace->rwsem);
+
 		/*
 		 * The group is mapped to a sequential zone. Get the zone write
 		 * pointer to determine the allocation offset within the zone.