diff options
| -rw-r--r-- | fs/btrfs/block-group.c | 15 | ||||
| -rw-r--r-- | fs/btrfs/block-group.h | 6 | ||||
| -rw-r--r-- | fs/btrfs/zoned.c | 151 | ||||
| -rw-r--r-- | fs/btrfs/zoned.h | 7 |
4 files changed, 179 insertions, 0 deletions
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index b8fbee70a897..e6bf728496eb 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -15,6 +15,7 @@ #include "delalloc-space.h" #include "discard.h" #include "raid56.h" +#include "zoned.h" /* * Return target flags in extended format or 0 if restripe for this chunk_type @@ -1855,6 +1856,13 @@ static int read_one_block_group(struct btrfs_fs_info *info, goto error; } + ret = btrfs_load_block_group_zone_info(cache); + if (ret) { + btrfs_err(info, "zoned: failed to load zone info of bg %llu", + cache->start); + goto error; + } + /* * We need to exclude the super stripes now so that the space info has * super bytes accounted for, otherwise we'll think we have more space @@ -2141,6 +2149,13 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, cache->cached = BTRFS_CACHE_FINISHED; if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) cache->needs_free_space = 1; + + ret = btrfs_load_block_group_zone_info(cache); + if (ret) { + btrfs_put_block_group(cache); + return ret; + } + ret = exclude_super_stripes(cache); if (ret) { /* We may have excluded something, so call this just in case */ diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 8f74a96074f7..224946fa9bed 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -183,6 +183,12 @@ struct btrfs_block_group { /* Record locked full stripes for RAID5/6 block group */ struct btrfs_full_stripe_locks_tree full_stripe_locks_root; + + /* + * Allocation offset for the block group to implement sequential + * allocation. This is used only on a zoned filesystem. + */ + u64 alloc_offset; }; static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) 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; +} diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 6c8f83c48c2e..4f3152d7b98f 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -41,6 +41,7 @@ u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start, int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical, u64 length, u64 *bytes); int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size); +int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache); #else /* CONFIG_BLK_DEV_ZONED */ static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone) @@ -116,6 +117,12 @@ static inline int btrfs_ensure_empty_zones(struct btrfs_device *device, return 0; } +static inline int btrfs_load_block_group_zone_info( + struct btrfs_block_group *cache) +{ + return 0; +} + #endif static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos) |