>> @@ -61,7 +61,7 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node) >> table_group = kzalloc_node(sizeof(*table_group), GFP_KERNEL, >> node); if (!table_group) >> - goto fail_exit; >> + return NULL; >> >> tbl = kzalloc_node(sizeof(*tbl), GFP_KERNEL, node); >> if (!tbl) > > I have seen quite a few fixes that do inverse of this patch after a > piece of code allocating some extra piece of memory was added before > code that just returns on fail because it is the first allocation in > the function. > > This is not useful. How do you think about an information from the section “7) Centralized exiting of functions” in the document “coding-style.rst” then? “… If there is no cleanup needed then just return directly. …” > A final fail_exit that frees everything that could have been allocated > is much better. I got an other software development opinion for such use cases. I prefer only required function calls there. Regards, Markus -- To unsubscribe from this list: send the line "unsubscribe kernel-janitors" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html