@@ -2232,6 +2232,48 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
return page;
}
+static struct page *alloc_pages_vma_thp(gfp_t gfp, struct mempolicy *pol,
+ int order, int node)
+{
+ nodemask_t *nmask;
+ struct page *page;
+ 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 multiple preferred nodes, 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 = first_node(pol->v.preferred_nodes);
+
+ nmask = policy_nodemask(gfp, pol);
+
+ /*
+ * First, try to allocate THP only on local node, but don't reclaim
+ * unnecessarily, just compact.
+ */
+ page = __alloc_pages_nodemask(gfp | __GFP_THISNODE | __GFP_NORETRY,
+ order, hpage_node, nmask);
+
+ /*
+ * If hugepage allocations are configured to always synchronous compact
+ * or the vma has been madvised to prefer hugepage backing, retry
+ * allowing remote memory with both reclaim and compact as well.
+ */
+ if (!page && (gfp & __GFP_DIRECT_RECLAIM))
+ page = __alloc_pages_nodemask(gfp, order, hpage_node, nmask);
+
+ VM_BUG_ON(page && nmask && !node_isset(page_to_nid(page), *nmask));
+
+ return page;
+}
+
/**
* alloc_pages_vma - Allocate a page for a VMA.
*
@@ -2272,57 +2314,17 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
mpol_cond_put(pol);
page = alloc_page_interleave(gfp, order, nid);
- 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 multiple preferred nodes, 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 = first_node(pol->v.preferred_nodes);
-
+ } else if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+ hugepage)) {
+ page = alloc_pages_vma_thp(gfp, pol, order, node);
+ mpol_cond_put(pol);
+ } else {
nmask = policy_nodemask(gfp, pol);
+ preferred_nid = policy_node(gfp, pol, node);
+ page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);
mpol_cond_put(pol);
-
- /*
- * First, try to allocate THP only on local node, but
- * don't reclaim unnecessarily, just compact.
- */
- page = __alloc_pages_nodemask(gfp | __GFP_THISNODE |
- __GFP_NORETRY,
- order, hpage_node, nmask);
-
- /*
- * If hugepage allocations are configured to always synchronous
- * compact or the vma has been madvised to prefer hugepage
- * backing, retry allowing remote memory with both reclaim and
- * compact as well.
- */
- if (!page && (gfp & __GFP_DIRECT_RECLAIM))
- page = __alloc_pages_nodemask(gfp, order, hpage_node,
- nmask);
-
- VM_BUG_ON(page && nmask &&
- !node_isset(page_to_nid(page), *nmask));
- goto out;
}
- nmask = policy_nodemask(gfp, pol);
- preferred_nid = policy_node(gfp, pol, node);
- page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);
- mpol_cond_put(pol);
-out:
return page;
}
EXPORT_SYMBOL(alloc_pages_vma);
The next patch is going to rework this code to support MPOL_PREFERRED_MANY. This refactor makes the that change much more readable. After the extraction, the resulting code makes it apparent that this can be converted to a simple if ladder and thus allows removing the goto. There is not meant to be any functional or behavioral changes. Note that still at this point MPOL_PREFERRED_MANY isn't specially handled for huge pages. Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Ben Widawsky <ben.widawsky@intel.com> --- mm/mempolicy.c | 96 ++++++++++++++++++++++++++------------------------ 1 file changed, 49 insertions(+), 47 deletions(-)