btrfs: zoned: support dev-replace in zoned filesystems

This is 4/4 patch to implement device-replace on zoned filesystems.

Even after the copying is done, the write pointers of the source device
and the destination device may not be synchronized. For example, when
the last allocated extent is freed before device-replace process, the
extent is not copied, leaving a hole there.

Synchronize the write pointers by writing zeroes to the destination
device.
Reviewed-by: NJosef Bacik <josef@toxicpanda.com>
Signed-off-by: NNaohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: NDavid Sterba <dsterba@suse.com>

fs/btrfs/scrub.c

@@ -1628,6 +1628,9 @@ static int fill_writer_pointer_gap(struct scrub_ctx *sctx, u64 physical)
 	if (!btrfs_is_zoned(sctx->fs_info))
 		return 0;
 
+	if (!btrfs_dev_is_sequential(sctx->wr_tgtdev, physical))
+		return 0;
+
 	if (sctx->write_pointer < physical) {
 		length = physical - sctx->write_pointer;
 
@@ -3069,6 +3072,32 @@ static void sync_replace_for_zoned(struct scrub_ctx *sctx)
 	wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0);
 }
 
+static int sync_write_pointer_for_zoned(struct scrub_ctx *sctx, u64 logical,
+					u64 physical, u64 physical_end)
+{
+	struct btrfs_fs_info *fs_info = sctx->fs_info;
+	int ret = 0;
+
+	if (!btrfs_is_zoned(fs_info))
+		return 0;
+
+	wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0);
+
+	mutex_lock(&sctx->wr_lock);
+	if (sctx->write_pointer < physical_end) {
+		ret = btrfs_sync_zone_write_pointer(sctx->wr_tgtdev, logical,
+						    physical,
+						    sctx->write_pointer);
+		if (ret)
+			btrfs_err(fs_info,
+				  "zoned: failed to recover write pointer");
+	}
+	mutex_unlock(&sctx->wr_lock);
+	btrfs_dev_clear_zone_empty(sctx->wr_tgtdev, physical);
+
+	return ret;
+}
+
 static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 					   struct map_lookup *map,
 					   struct btrfs_device *scrub_dev,
@@ -3475,6 +3504,17 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	blk_finish_plug(&plug);
 	btrfs_free_path(path);
 	btrfs_free_path(ppath);
+
+	if (sctx->is_dev_replace && ret >= 0) {
+		int ret2;
+
+		ret2 = sync_write_pointer_for_zoned(sctx, base + offset,
+						    map->stripes[num].physical,
+						    physical_end);
+		if (ret2)
+			ret = ret2;
+	}
+
 	return ret < 0 ? ret : 0;
 }
 

fs/btrfs/zoned.c

@@ -12,6 +12,7 @@
 #include "block-group.h"
 #include "transaction.h"
 #include "dev-replace.h"
+#include "space-info.h"
 
 /* Maximum number of zones to report per blkdev_report_zones() call */
 #define BTRFS_REPORT_NR_ZONES   4096
@@ -1385,3 +1386,76 @@ int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 len
 	return blkdev_issue_zeroout(device->bdev, physical >> SECTOR_SHIFT,
 				    length >> SECTOR_SHIFT, GFP_NOFS, 0);
 }
+
+static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical,
+			  struct blk_zone *zone)
+{
+	struct btrfs_bio *bbio = NULL;
+	u64 mapped_length = PAGE_SIZE;
+	unsigned int nofs_flag;
+	int nmirrors;
+	int i, ret;
+
+	ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
+			       &mapped_length, &bbio);
+	if (ret || !bbio || mapped_length < PAGE_SIZE) {
+		btrfs_put_bbio(bbio);
+		return -EIO;
+	}
+
+	if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK)
+		return -EINVAL;
+
+	nofs_flag = memalloc_nofs_save();
+	nmirrors = (int)bbio->num_stripes;
+	for (i = 0; i < nmirrors; i++) {
+		u64 physical = bbio->stripes[i].physical;
+		struct btrfs_device *dev = bbio->stripes[i].dev;
+
+		/* Missing device */
+		if (!dev->bdev)
+			continue;
+
+		ret = btrfs_get_dev_zone(dev, physical, zone);
+		/* Failing device */
+		if (ret == -EIO || ret == -EOPNOTSUPP)
+			continue;
+		break;
+	}
+	memalloc_nofs_restore(nofs_flag);
+
+	return ret;
+}
+
+/*
+ * Synchronize write pointer in a zone at @physical_start on @tgt_dev, by
+ * filling zeros between @physical_pos to a write pointer of dev-replace
+ * source device.
+ */
+int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
+				    u64 physical_start, u64 physical_pos)
+{
+	struct btrfs_fs_info *fs_info = tgt_dev->fs_info;
+	struct blk_zone zone;
+	u64 length;
+	u64 wp;
+	int ret;
+
+	if (!btrfs_dev_is_sequential(tgt_dev, physical_pos))
+		return 0;
+
+	ret = read_zone_info(fs_info, logical, &zone);
+	if (ret)
+		return ret;
+
+	wp = physical_start + ((zone.wp - zone.start) << SECTOR_SHIFT);
+
+	if (physical_pos == wp)
+		return 0;
+
+	if (physical_pos > wp)
+		return -EUCLEAN;
+
+	length = wp - physical_pos;
+	return btrfs_zoned_issue_zeroout(tgt_dev, physical_pos, length);
+}

fs/btrfs/zoned.h

@@ -56,6 +56,8 @@ bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
 void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache,
 				     struct extent_buffer *eb);
 int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length);
+int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
+				  u64 physical_start, u64 physical_pos);
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
 				     struct blk_zone *zone)
@@ -176,6 +178,13 @@ static inline int btrfs_zoned_issue_zeroout(struct btrfs_device *device,
 	return -EOPNOTSUPP;
 }
 
+static inline int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev,
+						u64 logical, u64 physical_start,
+						u64 physical_pos)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif
 
 static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)