mm/memplicy: add page allocation function for MPOL_PREFERRED_MANY policy

The semantics of MPOL_PREFERRED_MANY is similar to MPOL_PREFERRED, that it
will first try to allocate memory from the preferred node(s), and fallback
to all nodes in system when first try fails.

Add a dedicated function alloc_pages_preferred_many() for it just like for
'interleave' policy, which will be used by 2 general memoory allocation
APIs: alloc_pages() and alloc_pages_vma()

Link: https://lore.kernel.org/r/20200630212517.308045-9-ben.widawsky@intel.com
Link: https://lkml.kernel.org/r/1627970362-61305-3-git-send-email-feng.tang@intel.com
Suggested-by: Michal Hocko <mhocko@suse.com>
Originally-by: Ben Widawsky <ben.widawsky@intel.com>
Co-developed-by: Ben Widawsky <ben.widawsky@intel.com>
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 30 insertions, 0 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f8f2c18e61cb..64be3565ab7f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2166,6 +2166,27 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
 	return page;
 }
 
+static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
+						int nid, struct mempolicy *pol)
+{
+	struct page *page;
+	gfp_t preferred_gfp;
+
+	/*
+	 * This is a two pass approach. The first pass will only try the
+	 * preferred nodes but skip the direct reclaim and allow the
+	 * allocation to fail, while the second pass will try all the
+	 * nodes in system.
+	 */
+	preferred_gfp = gfp | __GFP_NOWARN;
+	preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
+	page = __alloc_pages(preferred_gfp, order, nid, &pol->nodes);
+	if (!page)
+		page = __alloc_pages(gfp, order, numa_node_id(), NULL);
+
+	return page;
+}
+
 /**
  * alloc_pages_vma - Allocate a page for a VMA.
  * @gfp: GFP flags.
@@ -2201,6 +2222,12 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		goto out;
 	}
 
+	if (pol->mode == MPOL_PREFERRED_MANY) {
+		page = alloc_pages_preferred_many(gfp, order, node, pol);
+		mpol_cond_put(pol);
+		goto out;
+	}
+
 	if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
 		int hpage_node = node;
 
@@ -2278,6 +2305,9 @@ struct page *alloc_pages(gfp_t gfp, unsigned order)
 	 */
 	if (pol->mode == MPOL_INTERLEAVE)
 		page = alloc_page_interleave(gfp, order, interleave_nodes(pol));
+	else if (pol->mode == MPOL_PREFERRED_MANY)
+		page = alloc_pages_preferred_many(gfp, order,
+				numa_node_id(), pol);
 	else
 		page = __alloc_pages(gfp, order,
 				policy_node(gfp, pol, numa_node_id()),