Revert "mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask"

This reverts commit 89c83fb539f95491be80cdd5158e6f0ce329e317.

This should have been done as part of 2f0799a0ffc0 ("mm, thp: restore
node-local hugepage allocations").  The movement of the thp allocation
policy from alloc_pages_vma() to alloc_hugepage_direct_gfpmask() was
intended to only set __GFP_THISNODE for mempolicies that are not
MPOL_BIND whereas the revert could set this regardless of mempolicy.

While the check for MPOL_BIND between alloc_hugepage_direct_gfpmask()
and alloc_pages_vma() was racy, that has since been removed since the
revert.  What is left is the possibility to use __GFP_THISNODE in
policy_node() when it is unexpected because the special handling for
hugepages in alloc_pages_vma()  was removed as part of the consolidation.

Secondly, prior to 89c83fb539f9, alloc_pages_vma() implemented a somewhat
different policy for hugepage allocations, which were allocated through
alloc_hugepage_vma().  For hugepage allocations, if the allocating
process's node is in the set of allowed nodes, allocate with
__GFP_THISNODE for that node (for MPOL_PREFERRED, use that node with
__GFP_THISNODE instead).  This was changed for shmem_alloc_hugepage() to
allow fallback to other nodes in 89c83fb539f9 as it did for new_page() in
mm/mempolicy.c which is functionally different behavior and removes the
requirement to only allocate hugepages locally.

So this commit does a full revert of 89c83fb539f9 instead of the partial
revert that was done in 2f0799a0ffc0.  The result is the same thp
allocation policy for 4.20 that was in 4.19.

Fixes: 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask")
Fixes: 2f0799a0ffc0 ("mm, thp: restore node-local hugepage allocations")
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 29 insertions, 3 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 69e278b469ef..d4496d9d34f5 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1116,8 +1116,8 @@ 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);
@@ -2011,6 +2011,7 @@ 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.
@@ -2021,7 +2022,7 @@ 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;
@@ -2039,6 +2040,31 @@ 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);