Revert "Revert "Revert "mm, thp: consolidate THP gfp handling into alloc_hugepage_dir...

[linux-2.6-block.git] / mm / mempolicy.c

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 9c9877a43d5832eb93c5694f36faf3afc0d8663e..547cd403ed020eb17f260829942be7b0c35d5e47 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1180,8 +1180,8 @@ static struct page *new_page(struct page *page, unsigned long start)
        } else if (PageTransHuge(page)) {
                struct page *thp;
 
-               thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma,
-                               address, numa_node_id());
+               thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
+                                        HPAGE_PMD_ORDER);
                if (!thp)
                        return NULL;
                prep_transhuge_page(thp);
@@ -2083,6 +2083,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  *     @vma:  Pointer to VMA or NULL if not available.
  *     @addr: Virtual Address of the allocation. Must be inside the VMA.
  *     @node: Which node to prefer for allocation (modulo policy).
+ *     @hugepage: for hugepages try only the preferred node if possible
  *
  *     This function allocates a page from the kernel page pool and applies
  *     a NUMA policy associated with the VMA or the current process.
@@ -2093,7 +2094,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  */
 struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
-               unsigned long addr, int node)
+               unsigned long addr, int node, bool hugepage)
 {
        struct mempolicy *pol;
        struct page *page;
@@ -2111,6 +2112,31 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
                goto out;
        }
 
+       if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
+               int hpage_node = node;
+
+               /*
+                * For hugepage allocation and non-interleave policy which
+                * allows the current node (or other explicitly preferred
+                * node) we only try to allocate from the current/preferred
+                * node and don't fall back to other nodes, as the cost of
+                * remote accesses would likely offset THP benefits.
+                *
+                * If the policy is interleave, or does not allow the current
+                * node in its nodemask, we allocate the standard way.
+                */
+               if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL))
+                       hpage_node = pol->v.preferred_node;
+
+               nmask = policy_nodemask(gfp, pol);
+               if (!nmask || node_isset(hpage_node, *nmask)) {
+                       mpol_cond_put(pol);
+                       page = __alloc_pages_node(hpage_node,
+                                               gfp | __GFP_THISNODE, order);
+                       goto out;
+               }
+       }
+
        nmask = policy_nodemask(gfp, pol);
        preferred_nid = policy_node(gfp, pol, node);
        page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);