From b79f1c2caadc5c6251241977c7987fefdeadc2d9 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 25 Jul 2024 10:46:01 +0100 Subject: [PATCH] btrfs: reschedule when updating chunk maps at the end of a device replace At the end of a device replace we must go over all the chunk maps and update their stripes to point to the target device instead of the source device. We iterate over the chunk maps while holding a write lock and we never reschedule, which can result in monopolizing a CPU for too long and blocking readers for too long (it's a rw lock, non-blocking). So improve on this by rescheduling if necessary. This is safe because at this point we are holding the chunk mutex, which means no new chunks can be allocated and therefore we don't risk missing a new chunk map that covers a range behind the last one we processed before rescheduling. Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/dev-replace.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index f638c458d285..20cf5e95f2bc 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -827,6 +827,14 @@ static void btrfs_dev_replace_update_device_in_mapping_tree( u64 start = 0; int i; + /* + * The chunk mutex must be held so that no new chunks can be created + * while we are updating existing chunks. This guarantees we don't miss + * any new chunk that gets created for a range that falls before the + * range of the last chunk we processed. + */ + lockdep_assert_held(&fs_info->chunk_mutex); + write_lock(&fs_info->mapping_tree_lock); do { struct btrfs_chunk_map *map; @@ -839,6 +847,7 @@ static void btrfs_dev_replace_update_device_in_mapping_tree( map->stripes[i].dev = tgtdev; start = map->start + map->chunk_len; btrfs_free_chunk_map(map); + cond_resched_rwlock_write(&fs_info->mapping_tree_lock); } while (start); write_unlock(&fs_info->mapping_tree_lock); } -- 2.42.0