diff options
Diffstat (limited to 'fs/btrfs/block-group.c')
-rw-r--r-- | fs/btrfs/block-group.c | 82 |
1 files changed, 37 insertions, 45 deletions
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 0ef8b8926bfa..e97af2e510c3 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -160,15 +160,6 @@ void btrfs_put_block_group(struct btrfs_block_group *cache) btrfs_discard_cancel_work(&cache->fs_info->discard_ctl, cache); - /* - * If not empty, someone is still holding mutex of - * full_stripe_lock, which can only be released by caller. - * And it will definitely cause use-after-free when caller - * tries to release full stripe lock. - * - * No better way to resolve, but only to warn. - */ - WARN_ON(!RB_EMPTY_ROOT(&cache->full_stripe_locks_root.root)); kfree(cache->free_space_ctl); kfree(cache->physical_map); kfree(cache); @@ -1175,14 +1166,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, < block_group->zone_unusable); WARN_ON(block_group->space_info->disk_total < block_group->length * factor); - WARN_ON(test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, - &block_group->runtime_flags) && - block_group->space_info->active_total_bytes - < block_group->length); } block_group->space_info->total_bytes -= block_group->length; - if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) - block_group->space_info->active_total_bytes -= block_group->length; block_group->space_info->bytes_readonly -= (block_group->length - block_group->zone_unusable); block_group->space_info->bytes_zone_unusable -= @@ -1983,12 +1968,12 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, map = em->map_lookup; data_stripe_length = em->orig_block_len; - io_stripe_size = map->stripe_len; + io_stripe_size = BTRFS_STRIPE_LEN; chunk_start = em->start; /* For RAID5/6 adjust to a full IO stripe length */ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) - io_stripe_size = map->stripe_len * nr_data_stripes(map); + io_stripe_size = btrfs_stripe_nr_to_offset(nr_data_stripes(map)); buf = kcalloc(map->num_stripes, sizeof(u64), GFP_NOFS); if (!buf) { @@ -1998,28 +1983,28 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, for (i = 0; i < map->num_stripes; i++) { bool already_inserted = false; - u64 stripe_nr; - u64 offset; + u32 stripe_nr; + u32 offset; int j; if (!in_range(physical, map->stripes[i].physical, data_stripe_length)) continue; - stripe_nr = physical - map->stripes[i].physical; - stripe_nr = div64_u64_rem(stripe_nr, map->stripe_len, &offset); + stripe_nr = (physical - map->stripes[i].physical) >> + BTRFS_STRIPE_LEN_SHIFT; + offset = (physical - map->stripes[i].physical) & + BTRFS_STRIPE_LEN_MASK; if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | - BTRFS_BLOCK_GROUP_RAID10)) { - stripe_nr = stripe_nr * map->num_stripes + i; - stripe_nr = div_u64(stripe_nr, map->sub_stripes); - } + BTRFS_BLOCK_GROUP_RAID10)) + stripe_nr = div_u64(stripe_nr * map->num_stripes + i, + map->sub_stripes); /* * The remaining case would be for RAID56, multiply by * nr_data_stripes(). Alternatively, just use rmap_len below * instead of map->stripe_len */ - bytenr = chunk_start + stripe_nr * io_stripe_size + offset; /* Ensure we don't add duplicate addresses */ @@ -2130,8 +2115,6 @@ static struct btrfs_block_group *btrfs_create_block_group_cache( btrfs_init_free_space_ctl(cache, cache->free_space_ctl); atomic_set(&cache->frozen, 0); mutex_init(&cache->free_space_lock); - cache->full_stripe_locks_root.root = RB_ROOT; - mutex_init(&cache->full_stripe_locks_root.lock); return cache; } @@ -2678,7 +2661,7 @@ static u64 calculate_global_root_id(struct btrfs_fs_info *fs_info, u64 offset) } struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans, - u64 bytes_used, u64 type, + u64 type, u64 chunk_offset, u64 size) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -2693,7 +2676,6 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran cache->length = size; set_free_space_tree_thresholds(cache); - cache->used = bytes_used; cache->flags = type; cache->cached = BTRFS_CACHE_FINISHED; cache->global_root_id = calculate_global_root_id(fs_info, cache->start); @@ -2744,9 +2726,7 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran #ifdef CONFIG_BTRFS_DEBUG if (btrfs_should_fragment_free_space(cache)) { - u64 new_bytes_used = size - bytes_used; - - cache->space_info->bytes_used += new_bytes_used >> 1; + cache->space_info->bytes_used += size >> 1; fragment_free_space(cache); } #endif @@ -2838,10 +2818,20 @@ int btrfs_inc_block_group_ro(struct btrfs_block_group *cache, } ret = inc_block_group_ro(cache, 0); - if (!do_chunk_alloc || ret == -ETXTBSY) - goto unlock_out; if (!ret) goto out; + if (ret == -ETXTBSY) + goto unlock_out; + + /* + * Skip chunk alloction if the bg is SYSTEM, this is to avoid system + * chunk allocation storm to exhaust the system chunk array. Otherwise + * we still want to try our best to mark the block group read-only. + */ + if (!do_chunk_alloc && ret == -ENOSPC && + (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM)) + goto unlock_out; + alloc_flags = btrfs_get_alloc_profile(fs_info, cache->space_info->flags); ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); if (ret < 0) @@ -3476,6 +3466,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, spin_unlock(&info->delalloc_root_lock); while (total) { + struct btrfs_space_info *space_info; bool reclaim = false; cache = btrfs_lookup_block_group(info, bytenr); @@ -3483,6 +3474,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, ret = -ENOENT; break; } + space_info = cache->space_info; factor = btrfs_bg_type_to_factor(cache->flags); /* @@ -3497,7 +3489,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, byte_in_group = bytenr - cache->start; WARN_ON(byte_in_group > cache->length); - spin_lock(&cache->space_info->lock); + spin_lock(&space_info->lock); spin_lock(&cache->lock); if (btrfs_test_opt(info, SPACE_CACHE) && @@ -3510,24 +3502,24 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, old_val += num_bytes; cache->used = old_val; cache->reserved -= num_bytes; - cache->space_info->bytes_reserved -= num_bytes; - cache->space_info->bytes_used += num_bytes; - cache->space_info->disk_used += num_bytes * factor; + space_info->bytes_reserved -= num_bytes; + space_info->bytes_used += num_bytes; + space_info->disk_used += num_bytes * factor; spin_unlock(&cache->lock); - spin_unlock(&cache->space_info->lock); + spin_unlock(&space_info->lock); } else { old_val -= num_bytes; cache->used = old_val; cache->pinned += num_bytes; - btrfs_space_info_update_bytes_pinned(info, - cache->space_info, num_bytes); - cache->space_info->bytes_used -= num_bytes; - cache->space_info->disk_used -= num_bytes * factor; + btrfs_space_info_update_bytes_pinned(info, space_info, + num_bytes); + space_info->bytes_used -= num_bytes; + space_info->disk_used -= num_bytes * factor; reclaim = should_reclaim_block_group(cache, num_bytes); spin_unlock(&cache->lock); - spin_unlock(&cache->space_info->lock); + spin_unlock(&space_info->lock); set_extent_dirty(&trans->transaction->pinned_extents, bytenr, bytenr + num_bytes - 1, |