diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 0ef8b8926bfa..5fc670c27f86 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1175,14 +1175,8 @@ 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 -= @@ -3476,6 +3470,7 @@ 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 +3478,7 @@ 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 +3493,7 @@ 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 +3506,24 @@ 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, diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 0d250d052487..d84cef89cdff 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2693,8 +2693,13 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold); spin_lock(&ctl->tree_lock); + /* Count initial region as zone_unusable until it gets activated. */ if (!used) to_free = size; + else if (initial && + test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &block_group->fs_info->flags) && + (block_group->flags & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM))) + to_free = 0; else if (initial) to_free = block_group->zone_capacity; else if (offset >= block_group->alloc_offset) @@ -2722,7 +2727,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, reclaimable_unusable = block_group->zone_unusable - (block_group->length - block_group->zone_capacity); /* All the region is now unusable. Mark it as unused and reclaim */ - if (block_group->zone_unusable == block_group->length) { + if (block_group->zone_unusable == block_group->length && + block_group->alloc_offset) { btrfs_mark_bg_unused(block_group); } else if (bg_reclaim_threshold && reclaimable_unusable >= diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 4c477eae6891..24cd49229408 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -120,11 +120,8 @@ enum { /* Indicate that we want to commit the transaction. */ BTRFS_FS_NEED_TRANS_COMMIT, - /* - * Indicate metadata over-commit is disabled. This is set when active - * zone tracking is needed. - */ - BTRFS_FS_NO_OVERCOMMIT, + /* This is set when active zone tracking is needed. */ + BTRFS_FS_ACTIVE_ZONE_TRACKING, /* * Indicate if we have some features changed, this is mostly for diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6c18dc9a1831..957e4d76a7b6 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5421,8 +5421,13 @@ static int btrfs_inode_by_name(struct btrfs_inode *dir, struct dentry *dentry, return -ENOMEM; ret = fscrypt_setup_filename(&dir->vfs_inode, &dentry->d_name, 1, &fname); - if (ret) + if (ret < 0) goto out; + /* + * fscrypt_setup_filename() should never return a positive value, but + * gcc on sparc/parisc thinks it can, so assert that doesn't happen. + */ + ASSERT(ret == 0); /* This needs to handle no-key deletions later on */ diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 69c09508afb5..3eecce86f63f 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -308,8 +308,6 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, ASSERT(found); spin_lock(&found->lock); found->total_bytes += block_group->length; - if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) - found->active_total_bytes += block_group->length; found->disk_total += block_group->length * factor; found->bytes_used += block_group->used; found->disk_used += block_group->used * factor; @@ -379,22 +377,6 @@ static u64 calc_available_free_space(struct btrfs_fs_info *fs_info, return avail; } -static inline u64 writable_total_bytes(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info) -{ - /* - * On regular filesystem, all total_bytes are always writable. On zoned - * filesystem, there may be a limitation imposed by max_active_zones. - * For metadata allocation, we cannot finish an existing active block - * group to avoid a deadlock. Thus, we need to consider only the active - * groups to be writable for metadata space. - */ - if (!btrfs_is_zoned(fs_info) || (space_info->flags & BTRFS_BLOCK_GROUP_DATA)) - return space_info->total_bytes; - - return space_info->active_total_bytes; -} - int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 bytes, enum btrfs_reserve_flush_enum flush) @@ -407,13 +389,13 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, return 0; used = btrfs_space_info_used(space_info, true); - if (test_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags) && + if (test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &fs_info->flags) && (space_info->flags & BTRFS_BLOCK_GROUP_METADATA)) avail = 0; else avail = calc_available_free_space(fs_info, space_info, flush); - if (used + bytes < writable_total_bytes(fs_info, space_info) + avail) + if (used + bytes < space_info->total_bytes + avail) return 1; return 0; } @@ -449,7 +431,7 @@ again: ticket = list_first_entry(head, struct reserve_ticket, list); /* Check and see if our ticket can be satisfied now. */ - if ((used + ticket->bytes <= writable_total_bytes(fs_info, space_info)) || + if ((used + ticket->bytes <= space_info->total_bytes) || btrfs_can_overcommit(fs_info, space_info, ticket->bytes, flush)) { btrfs_space_info_update_bytes_may_use(fs_info, @@ -829,7 +811,6 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, { u64 used; u64 avail; - u64 total; u64 to_reclaim = space_info->reclaim_size; lockdep_assert_held(&space_info->lock); @@ -844,9 +825,8 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, * space. If that's the case add in our overage so we make sure to put * appropriate pressure on the flushing state machine. */ - total = writable_total_bytes(fs_info, space_info); - if (total + avail < used) - to_reclaim += used - (total + avail); + if (space_info->total_bytes + avail < used) + to_reclaim += used - (space_info->total_bytes + avail); return to_reclaim; } @@ -856,11 +836,10 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, { u64 global_rsv_size = fs_info->global_block_rsv.reserved; u64 ordered, delalloc; - u64 total = writable_total_bytes(fs_info, space_info); u64 thresh; u64 used; - thresh = mult_perc(total, 90); + thresh = mult_perc(space_info->total_bytes, 90); lockdep_assert_held(&space_info->lock); @@ -923,8 +902,8 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, BTRFS_RESERVE_FLUSH_ALL); used = space_info->bytes_used + space_info->bytes_reserved + space_info->bytes_readonly + global_rsv_size; - if (used < total) - thresh += total - used; + if (used < space_info->total_bytes) + thresh += space_info->total_bytes - used; thresh >>= space_info->clamp; used = space_info->bytes_pinned; @@ -1651,7 +1630,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, * can_overcommit() to ensure we can overcommit to continue. */ if (!pending_tickets && - ((used + orig_bytes <= writable_total_bytes(fs_info, space_info)) || + ((used + orig_bytes <= space_info->total_bytes) || btrfs_can_overcommit(fs_info, space_info, orig_bytes, flush))) { btrfs_space_info_update_bytes_may_use(fs_info, space_info, orig_bytes); @@ -1665,8 +1644,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, */ if (ret && unlikely(flush == BTRFS_RESERVE_FLUSH_EMERGENCY)) { used = btrfs_space_info_used(space_info, false); - if (used + orig_bytes <= - writable_total_bytes(fs_info, space_info)) { + if (used + orig_bytes <= space_info->total_bytes) { btrfs_space_info_update_bytes_may_use(fs_info, space_info, orig_bytes); ret = 0; diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index fc99ea2b0c34..2033b71b18ce 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -96,8 +96,6 @@ struct btrfs_space_info { u64 bytes_may_use; /* number of bytes that may be used for delalloc/allocations */ u64 bytes_readonly; /* total bytes that are read only */ - /* Total bytes in the space, but only accounts active block groups. */ - u64 active_total_bytes; u64 bytes_zone_unusable; /* total bytes that are unusable until resetting the device zone */ diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 7823168c08a6..6d0124b6e79e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6363,7 +6363,8 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, ASSERT(op != BTRFS_MAP_DISCARD); em = btrfs_get_chunk_map(fs_info, logical, *length); - ASSERT(!IS_ERR(em)); + if (IS_ERR(em)) + return PTR_ERR(em); map = em->map_lookup; data_stripes = nr_data_stripes(map); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index f95b2c94d619..45d04092f2f8 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -524,8 +524,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) } atomic_set(&zone_info->active_zones_left, max_active_zones - nactive); - /* Overcommit does not work well with active zone tacking. */ - set_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags); + set_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &fs_info->flags); } /* Validate superblock log */ @@ -1581,9 +1580,19 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) return; WARN_ON(cache->bytes_super != 0); - unusable = (cache->alloc_offset - cache->used) + - (cache->length - cache->zone_capacity); - free = cache->zone_capacity - cache->alloc_offset; + + /* Check for block groups never get activated */ + if (test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &cache->fs_info->flags) && + cache->flags & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM) && + !test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &cache->runtime_flags) && + cache->alloc_offset == 0) { + unusable = cache->length; + free = 0; + } else { + unusable = (cache->alloc_offset - cache->used) + + (cache->length - cache->zone_capacity); + free = cache->zone_capacity - cache->alloc_offset; + } /* We only need ->free_space in ALLOC_SEQ block groups */ cache->cached = BTRFS_CACHE_FINISHED; @@ -1902,7 +1911,11 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) /* Successfully activated all the zones */ set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags); - space_info->active_total_bytes += block_group->length; + WARN_ON(block_group->alloc_offset != 0); + if (block_group->zone_unusable == block_group->length) { + block_group->zone_unusable = block_group->length - block_group->zone_capacity; + space_info->bytes_zone_unusable -= block_group->zone_capacity; + } spin_unlock(&block_group->lock); btrfs_try_granting_tickets(fs_info, space_info); spin_unlock(&space_info->lock); @@ -2086,11 +2099,21 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) if (!device->bdev) continue; - if (!zinfo->max_active_zones || - atomic_read(&zinfo->active_zones_left)) { + if (!zinfo->max_active_zones) { ret = true; break; } + + switch (flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) { + case 0: /* single */ + ret = (atomic_read(&zinfo->active_zones_left) >= 1); + break; + case BTRFS_BLOCK_GROUP_DUP: + ret = (atomic_read(&zinfo->active_zones_left) >= 2); + break; + } + if (ret) + break; } mutex_unlock(&fs_info->chunk_mutex); @@ -2256,7 +2279,7 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info) u64 avail; spin_lock(&block_group->lock); - if (block_group->reserved || + if (block_group->reserved || block_group->alloc_offset == 0 || (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM)) { spin_unlock(&block_group->lock); continue; @@ -2293,10 +2316,6 @@ int btrfs_zoned_activate_one_bg(struct btrfs_fs_info *fs_info, if (!btrfs_is_zoned(fs_info) || (space_info->flags & BTRFS_BLOCK_GROUP_DATA)) return 0; - /* No more block groups to activate */ - if (space_info->active_total_bytes == space_info->total_bytes) - return 0; - for (;;) { int ret; bool need_finish = false;