thp: add numa awareness to hugepage allocations

It's mostly a matter of replacing alloc_pages with alloc_pages_vma after
introducing alloc_pages_vma.  khugepaged needs special handling as the
allocation has to happen inside collapse_huge_page where the vma is known
and an error has to be returned to the outer loop to sleep
alloc_sleep_millisecs in case of failure.  But it retains the more
efficient logic of handling allocation failures in khugepaged in case of
CONFIG_NUMA=n.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 8 insertions, 5 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 83b7df309fc4..368fc9d23610 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1796,7 +1796,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
 }
 
 /**
- *      alloc_page_vma  - Allocate a page for a VMA.
+ *      alloc_pages_vma - Allocate a page for a VMA.
  *
  *      @gfp:
  *      %GFP_USER    user allocation.
@@ -1805,6 +1805,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  *      %GFP_FS      allocation should not call back into a file system.
  *      %GFP_ATOMIC  don't sleep.
  *
+ *      @order:Order of the GFP allocation.
  *      @vma:  Pointer to VMA or NULL if not available.
  *      @addr: Virtual Address of the allocation. Must be inside the VMA.
  *
@@ -1818,7 +1819,8 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  *      Should be called with the mm_sem of the vma hold.
  */
 struct page *
-alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
+alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
+                unsigned long addr)
 {
         struct mempolicy *pol = get_vma_policy(current, vma, addr);
         struct zonelist *zl;
@@ -1830,7 +1832,7 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
 
                 nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
                 mpol_cond_put(pol);
-                page = alloc_page_interleave(gfp, 0, nid);
+                page = alloc_page_interleave(gfp, order, nid);
                 put_mems_allowed();
                 return page;
         }
@@ -1839,7 +1841,7 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
                 /*
                  * slow path: ref counted shared policy
                  */
-                struct page *page =  __alloc_pages_nodemask(gfp, 0,
+                struct page *page =  __alloc_pages_nodemask(gfp, order,
                                                 zl, policy_nodemask(gfp, pol));
                 __mpol_put(pol);
                 put_mems_allowed();
@@ -1848,7 +1850,8 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
         /*
          * fast path:  default or task policy
          */
-        page = __alloc_pages_nodemask(gfp, 0, zl, policy_nodemask(gfp, pol));
+        page = __alloc_pages_nodemask(gfp, order, zl,
+                                      policy_nodemask(gfp, pol));
         put_mems_allowed();
         return page;
 }