There is no need to acquire pcpu_lock for pcpu_chunk_addr_search():
1) both pcpu_first_chunk & pcpu_reserved_chunk must have been
   initialized before the invocation of free_percpu().
2) The dynamically-created chunk must be valid before the per-cpu
   pointers allocated from it are freed.
So acquire pcpu_lock() after the invocation of pcpu_chunk_addr_search().
Acked-by: Dennis Zhou <dennis@kernel.org>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20231020133202.4043247-2-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
        kmemleak_free_percpu(ptr);
 
        addr = __pcpu_ptr_to_addr(ptr);
-
-       spin_lock_irqsave(&pcpu_lock, flags);
-
        chunk = pcpu_chunk_addr_search(addr);
        off = addr - chunk->base_addr;
 
+       spin_lock_irqsave(&pcpu_lock, flags);
        size = pcpu_free_area(chunk, off);
 
        pcpu_memcg_free_hook(chunk, off, size);