On Fri, Dec 02, 2016 at 03:03:30PM +0100, Michal Hocko wrote:

On Wed 16-11-16 14:55:04, Huang Shijie wrote:

quoted

There are three ways we can allocate a new gigantic page:

1. When the NUMA is not enabled, use alloc_gigantic_page() to get
   the gigantic page.

2. The NUMA is enabled, but the vma is NULL.
   There is no memory policy we can refer to.
   So create a @nodes_allowed, initialize it with init_nodemask_of_mempolicy()
   or init_nodemask_of_node(). Then use alloc_fresh_gigantic_page() to get
   the gigantic page.

3. The NUMA is enabled, and the vma is valid.
   We can follow the memory policy of the @vma.

   Get @nodes_allowed by huge_nodemask(), and use alloc_fresh_gigantic_page()
   to get the gigantic page.

Again __hugetlb_alloc_gigantic_page is not used and it is hard to deduce
its usage from this commit. The above shouldn't be really much different from

Okay, I will merge it into the later patch.

what we do in alloc_pages_vma so please make sure to check it before
coming up with something hugetlb specific.

No problem. Thanks for the hint.

Thanks
Huang Shijie