Re: [PATCH v3 4/7] hugetlb: pass *next_nid_to_alloc directly to for_each_node_mask_to_alloc

[David Rientjes]

On Wed, 3 Jan 2024, Gang Li wrote:

> On 2024/1/3 09:32, David Rientjes wrote:
> > Same error as v2:
> > 
> > mm/hugetlb.c:3315:53: warning: variable 'node' is used uninitialized
> > whenever '&&' condition is false [-Wsometimes-uninitialized]
> >          for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node,
> > &node_states[N_MEMORY]) {
> >          ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> > mm/hugetlb.c:1501:3: note: expanded from macro 'for_each_node_mask_to_alloc'
> >                  nr_nodes > 0 &&                                         \
> >                  ^~~~~~~~~~~~
> > mm/hugetlb.c:3342:38: note: uninitialized use occurs here
> >          list_add(&m->list, &huge_boot_pages[node]);
> >                                              ^~~~
> > mm/hugetlb.c:3315:53: note: remove the '&&' if its condition is always true
> >          for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node,
> > &node_states[N_MEMORY]) {
> >                                                             ^
> > mm/hugetlb.c:3310:7: warning: variable 'node' is used uninitialized whenever
> > 'if' condition is false [-Wsometimes-uninitialized]
> >                  if (!m)
> >                      ^~
> > mm/hugetlb.c:3342:38: note: uninitialized use occurs here
> >          list_add(&m->list, &huge_boot_pages[node]);
> >                                              ^~~~
> > mm/hugetlb.c:3310:3: note: remove the 'if' if its condition is always true
> >                  if (!m)
> >                  ^~~~~~~
> > mm/hugetlb.c:3304:20: note: initialize the variable 'node' to silence this
> > warning
> >          int nr_nodes, node;
> >                            ^
> >                             = 0
> > 2 warnings generated.
> > 
> 
> How did you get those warnings? I got nothing in my compilation.
> 

I'm using clang.

You spotted the issue in your earlier reply about the potentially 
uninitialized use of "node" when adding to the list.