btrfs: zoned: load zone's allocation offset

A zoned filesystem must allocate blocks at the zones' write pointer. The
device's write pointer position can be mapped to a logical address within
a block group. To facilitate this, add an "alloc_offset" to the
block-group to track the logical addresses of the write pointer.

This logical address is populated in btrfs_load_block_group_zone_info()
from the write pointers of corresponding zones.

For now, zoned filesystems the single profile. Supporting non-single
profile with zone append writing is not trivial. For example, in the DUP
profile, we send a zone append writing IO to two zones on a device. The
device reply with written LBAs for the IOs. If the offsets of the
returned addresses from the beginning of the zone are different, then it
results in different logical addresses.

We need fine-grained logical to physical mapping to support such separated
physical address issue. Since it should require additional metadata type,
disable non-single profiles for now.

This commit supports the case all the zones in a block group are
sequential. The next patch will handle the case having a conventional
zone.

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

1 files changed, 151 insertions, 0 deletions

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 69fd0d078b9b..0a7cd00f405f 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -3,14 +3,20 @@
 #include <linux/bitops.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "volumes.h"
 #include "zoned.h"
 #include "rcu-string.h"
 #include "disk-io.h"
+#include "block-group.h"
 
 /* Maximum number of zones to report per blkdev_report_zones() call */
 #define BTRFS_REPORT_NR_ZONES   4096
+/* Invalid allocation pointer value for missing devices */
+#define WP_MISSING_DEV ((u64)-1)
+/* Pseudo write pointer value for conventional zone */
+#define WP_CONVENTIONAL ((u64)-2)
 
 /* Number of superblock log zones */
 #define BTRFS_NR_SB_LOG_ZONES 2
@@ -920,3 +926,148 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size)
 
 	return 0;
 }
+
+int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache)
+{
+	struct btrfs_fs_info *fs_info = cache->fs_info;
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
+	struct extent_map *em;
+	struct map_lookup *map;
+	struct btrfs_device *device;
+	u64 logical = cache->start;
+	u64 length = cache->length;
+	u64 physical = 0;
+	int ret;
+	int i;
+	unsigned int nofs_flag;
+	u64 *alloc_offsets = NULL;
+	u32 num_sequential = 0, num_conventional = 0;
+
+	if (!btrfs_is_zoned(fs_info))
+		return 0;
+
+	/* Sanity check */
+	if (!IS_ALIGNED(length, fs_info->zone_size)) {
+		btrfs_err(fs_info,
+		"zoned: block group %llu len %llu unaligned to zone size %llu",
+			  logical, length, fs_info->zone_size);
+		return -EIO;
+	}
+
+	/* Get the chunk mapping */
+	read_lock(&em_tree->lock);
+	em = lookup_extent_mapping(em_tree, logical, length);
+	read_unlock(&em_tree->lock);
+
+	if (!em)
+		return -EINVAL;
+
+	map = em->map_lookup;
+
+	alloc_offsets = kcalloc(map->num_stripes, sizeof(*alloc_offsets), GFP_NOFS);
+	if (!alloc_offsets) {
+		free_extent_map(em);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < map->num_stripes; i++) {
+		bool is_sequential;
+		struct blk_zone zone;
+
+		device = map->stripes[i].dev;
+		physical = map->stripes[i].physical;
+
+		if (device->bdev == NULL) {
+			alloc_offsets[i] = WP_MISSING_DEV;
+			continue;
+		}
+
+		is_sequential = btrfs_dev_is_sequential(device, physical);
+		if (is_sequential)
+			num_sequential++;
+		else
+			num_conventional++;
+
+		if (!is_sequential) {
+			alloc_offsets[i] = WP_CONVENTIONAL;
+			continue;
+		}
+
+		/*
+		 * This zone will be used for allocation, so mark this zone
+		 * non-empty.
+		 */
+		btrfs_dev_clear_zone_empty(device, physical);
+
+		/*
+		 * The group is mapped to a sequential zone. Get the zone write
+		 * pointer to determine the allocation offset within the zone.
+		 */
+		WARN_ON(!IS_ALIGNED(physical, fs_info->zone_size));
+		nofs_flag = memalloc_nofs_save();
+		ret = btrfs_get_dev_zone(device, physical, &zone);
+		memalloc_nofs_restore(nofs_flag);
+		if (ret == -EIO || ret == -EOPNOTSUPP) {
+			ret = 0;
+			alloc_offsets[i] = WP_MISSING_DEV;
+			continue;
+		} else if (ret) {
+			goto out;
+		}
+
+		switch (zone.cond) {
+		case BLK_ZONE_COND_OFFLINE:
+		case BLK_ZONE_COND_READONLY:
+			btrfs_err(fs_info,
+		"zoned: offline/readonly zone %llu on device %s (devid %llu)",
+				  physical >> device->zone_info->zone_size_shift,
+				  rcu_str_deref(device->name), device->devid);
+			alloc_offsets[i] = WP_MISSING_DEV;
+			break;
+		case BLK_ZONE_COND_EMPTY:
+			alloc_offsets[i] = 0;
+			break;
+		case BLK_ZONE_COND_FULL:
+			alloc_offsets[i] = fs_info->zone_size;
+			break;
+		default:
+			/* Partially used zone */
+			alloc_offsets[i] =
+					((zone.wp - zone.start) << SECTOR_SHIFT);
+			break;
+		}
+	}
+
+	if (num_conventional > 0) {
+		/*
+		 * Since conventional zones do not have a write pointer, we
+		 * cannot determine alloc_offset from the pointer
+		 */
+		ret = -EINVAL;
+		goto out;
+	}
+
+	switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+	case 0: /* single */
+		cache->alloc_offset = alloc_offsets[0];
+		break;
+	case BTRFS_BLOCK_GROUP_DUP:
+	case BTRFS_BLOCK_GROUP_RAID1:
+	case BTRFS_BLOCK_GROUP_RAID0:
+	case BTRFS_BLOCK_GROUP_RAID10:
+	case BTRFS_BLOCK_GROUP_RAID5:
+	case BTRFS_BLOCK_GROUP_RAID6:
+		/* non-single profiles are not supported yet */
+	default:
+		btrfs_err(fs_info, "zoned: profile %s not yet supported",
+			  btrfs_bg_type_to_raid_name(map->type));
+		ret = -EINVAL;
+		goto out;
+	}
+
+out:
+	kfree(alloc_offsets);
+	free_extent_map(em);
+
+	return ret;
+}