@@ -31,6 +31,9 @@
#define BTRFS_REPORT_NR_ZONES 8192
+/* Invalid allocation pointer value for missing devices */
+#define WP_MISSING_DEV ((u64)-1)
+
enum btrfs_zoned_model zoned_model(const char *file)
{
char model[32];
@@ -346,3 +349,212 @@ bool btrfs_check_allocatable_zones(struct btrfs_device *device, u64 pos,
return true;
}
+
+int btrfs_load_block_group_zone_info(struct btrfs_fs_info *fs_info,
+ struct btrfs_block_group_cache *cache)
+{
+ struct btrfs_device *device;
+ struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
+ struct cache_extent *ce;
+ struct map_lookup *map;
+ u64 logical = cache->key.objectid;
+ u64 length = cache->key.offset;
+ u64 physical = 0;
+ int ret = 0;
+ int alloc_type;
+ int i, j;
+ u64 zone_size = fs_info->fs_devices->zone_size;
+ u64 *alloc_offsets = NULL;
+
+ if (!btrfs_fs_incompat(fs_info, HMZONED))
+ return 0;
+
+ /* Sanity check */
+ if (logical == BTRFS_BLOCK_RESERVED_1M_FOR_SUPER) {
+ if (length + SZ_1M != zone_size) {
+ error("unaligned initial system block group");
+ return -EIO;
+ }
+ } else if (!IS_ALIGNED(length, zone_size)) {
+ error("unaligned block group at %llu + %llu", logical, length);
+ return -EIO;
+ }
+
+ /* Get the chunk mapping */
+ ce = search_cache_extent(&map_tree->cache_tree, logical);
+ if (!ce) {
+ error("failed to find block group at %llu", logical);
+ return -ENOENT;
+ }
+ map = container_of(ce, struct map_lookup, ce);
+
+ /*
+ * Get the zone type: if the group is mapped to a non-sequential zone,
+ * there is no need for the allocation offset (fit allocation is OK).
+ */
+ alloc_type = -1;
+ alloc_offsets = calloc(map->num_stripes, sizeof(*alloc_offsets));
+ if (!alloc_offsets) {
+ error("failed to allocate alloc_offsets");
+ 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;
+
+ is_sequential = btrfs_dev_is_sequential(device, physical);
+ if (alloc_type == -1)
+ alloc_type = is_sequential ?
+ BTRFS_ALLOC_SEQ : BTRFS_ALLOC_FIT;
+
+ if ((is_sequential && alloc_type != BTRFS_ALLOC_SEQ) ||
+ (!is_sequential && alloc_type == BTRFS_ALLOC_SEQ)) {
+ error("found block group of mixed zone types");
+ ret = -EIO;
+ goto out;
+ }
+
+ if (!is_sequential)
+ continue;
+
+ /*
+ * 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, zone_size));
+ zone = device->zone_info.zones[physical / zone_size];
+
+ switch (zone.cond) {
+ case BLK_ZONE_COND_OFFLINE:
+ case BLK_ZONE_COND_READONLY:
+ error("Offline/readonly zone %llu",
+ physical / fs_info->fs_devices->zone_size);
+ ret = -EIO;
+ goto out;
+ case BLK_ZONE_COND_EMPTY:
+ alloc_offsets[i] = 0;
+ break;
+ case BLK_ZONE_COND_FULL:
+ alloc_offsets[i] = zone_size;
+ break;
+ default:
+ /* Partially used zone */
+ alloc_offsets[i] = ((zone.wp - zone.start) << 9);
+ break;
+ }
+ }
+
+ if (alloc_type == BTRFS_ALLOC_FIT)
+ goto out;
+
+ switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+ case 0: /* single */
+ case BTRFS_BLOCK_GROUP_DUP:
+ case BTRFS_BLOCK_GROUP_RAID1:
+ cache->alloc_offset = WP_MISSING_DEV;
+ for (i = 0; i < map->num_stripes; i++) {
+ if (alloc_offsets[i] == WP_MISSING_DEV)
+ continue;
+ if (cache->alloc_offset == WP_MISSING_DEV)
+ cache->alloc_offset = alloc_offsets[i];
+ if (alloc_offsets[i] == cache->alloc_offset)
+ continue;
+
+ error("write pointer mismatch: block group %llu",
+ logical);
+ ret = -EIO;
+ goto out;
+ }
+ break;
+ case BTRFS_BLOCK_GROUP_RAID0:
+ cache->alloc_offset = 0;
+ for (i = 0; i < map->num_stripes; i++) {
+ if (alloc_offsets[i] == WP_MISSING_DEV) {
+ error("cannot recover write pointer: block group %llu",
+ logical);
+ ret = -EIO;
+ goto out;
+ }
+
+ if (alloc_offsets[0] < alloc_offsets[i]) {
+ error(
+ "write pointer mismatch: block group %llu",
+ logical);
+ ret = -EIO;
+ goto out;
+
+ }
+
+ cache->alloc_offset += alloc_offsets[i];
+ }
+ break;
+ case BTRFS_BLOCK_GROUP_RAID10:
+ /*
+ * Pass1: check write pointer of RAID1 level: each pointer
+ * should be equal.
+ */
+ for (i = 0; i < map->num_stripes / map->sub_stripes; i++) {
+ int base = i * map->sub_stripes;
+ u64 offset = WP_MISSING_DEV;
+
+ for (j = 0; j < map->sub_stripes; j++) {
+ if (alloc_offsets[base + j] == WP_MISSING_DEV)
+ continue;
+ if (offset == WP_MISSING_DEV)
+ offset = alloc_offsets[base+j];
+ if (alloc_offsets[base + j] == offset)
+ continue;
+
+ error(
+ "write pointer mismatch: block group %llu",
+ logical);
+ ret = -EIO;
+ goto out;
+ }
+ for (j = 0; j < map->sub_stripes; j++)
+ alloc_offsets[base + j] = offset;
+ }
+
+ /* Pass2: check write pointer of RAID1 level */
+ cache->alloc_offset = 0;
+ for (i = 0; i < map->num_stripes / map->sub_stripes; i++) {
+ int base = i * map->sub_stripes;
+
+ if (alloc_offsets[base] == WP_MISSING_DEV) {
+ error(
+ "cannot recover write pointer: block group %llu",
+ logical);
+ ret = -EIO;
+ goto out;
+ }
+
+ if (alloc_offsets[0] < alloc_offsets[base]) {
+ error(
+ "write pointer mismatch: block group %llu",
+ logical);
+ ret = -EIO;
+ goto out;
+ }
+
+ cache->alloc_offset += alloc_offsets[base];
+ }
+ break;
+ case BTRFS_BLOCK_GROUP_RAID5:
+ case BTRFS_BLOCK_GROUP_RAID6:
+ /* RAID5/6 is not supported yet */
+ default:
+ error("Unsupported profile %llu",
+ map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK);
+ ret = -EINVAL;
+ goto out;
+ }
+
+out:
+ cache->alloc_type = alloc_type;
+ free(alloc_offsets);
+ return ret;
+}
@@ -61,6 +61,8 @@ bool zone_is_sequential(struct btrfs_zone_info *zinfo, u64 bytenr);
int btrfs_discard_all_zones(int fd, struct btrfs_zone_info *zinfo);
int zero_zone_blocks(int fd, struct btrfs_zone_info *zinfo, off_t start,
size_t len);
+int btrfs_load_block_group_zone_info(struct btrfs_fs_info *fs_info,
+ struct btrfs_block_group_cache *cache);
#else
static inline bool zone_is_sequential(struct btrfs_zone_info *zinfo,
u64 bytenr)
@@ -76,6 +78,11 @@ static int zero_zone_blocks(int fd, struct btrfs_zone_info *zinfo, off_t start,
{
return -EOPNOTSUPP;
}
+static inline int btrfs_load_block_group_zone_info(
+ struct btrfs_fs_info *fs_info, struct btrfs_block_group_cache *cache)
+{
+ return 0;
+}
#endif /* BTRFS_ZONED */
#endif /* __BTRFS_HMZONED_H__ */
@@ -1087,6 +1087,20 @@ struct btrfs_space_info {
struct list_head list;
};
+/* Block group allocation types */
+enum btrfs_alloc_type {
+
+ /* Regular first fit allocation */
+ BTRFS_ALLOC_FIT = 0,
+
+ /*
+ * Sequential allocation: this is for HMZONED mode and
+ * will result in ignoring free space before a block
+ * group allocation offset.
+ */
+ BTRFS_ALLOC_SEQ = 1,
+};
+
struct btrfs_block_group_cache {
struct cache_extent cache;
struct btrfs_key key;
@@ -1109,6 +1123,8 @@ struct btrfs_block_group_cache {
*/
u32 bitmap_low_thresh;
+ enum btrfs_alloc_type alloc_type;
+ u64 alloc_offset;
};
struct btrfs_device;
@@ -251,6 +251,14 @@ again:
if (cache->ro || !block_group_bits(cache, data))
goto new_group;
+ if (cache->alloc_type == BTRFS_ALLOC_SEQ) {
+ if (cache->key.offset - cache->alloc_offset < num)
+ goto new_group;
+ *start_ret = cache->key.objectid + cache->alloc_offset;
+ cache->alloc_offset += num;
+ return 0;
+ }
+
while(1) {
ret = find_first_extent_bit(&root->fs_info->free_space_cache,
last, &start, &end, EXTENT_DIRTY);
@@ -2724,6 +2732,10 @@ int btrfs_read_block_groups(struct btrfs_root *root)
BUG_ON(ret);
cache->space_info = space_info;
+ ret = btrfs_load_block_group_zone_info(info, cache);
+ if (ret)
+ goto error;
+
/* use EXTENT_LOCKED to prevent merging */
set_extent_bits(block_group_cache, found_key.objectid,
found_key.objectid + found_key.offset - 1,
@@ -2753,6 +2765,9 @@ btrfs_add_block_group(struct btrfs_fs_info *fs_info, u64 bytes_used, u64 type,
cache->key.objectid = chunk_offset;
cache->key.offset = size;
+ ret = btrfs_load_block_group_zone_info(fs_info, cache);
+ BUG_ON(ret);
+
cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
btrfs_set_block_group_used(&cache->item, bytes_used);
btrfs_set_block_group_chunk_objectid(&cache->item,
On HMZONED drives, writes must always be sequential and directed at a block group zone write pointer position. Thus, block allocation in a block group must also be done sequentially using an allocation pointer equal to the block group zone write pointer plus the number of blocks allocated but not yet written. Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com> --- common/hmzoned.c | 212 +++++++++++++++++++++++++++++++++++++++++++++++ common/hmzoned.h | 7 ++ ctree.h | 16 ++++ extent-tree.c | 15 ++++ 4 files changed, 250 insertions(+)