diff mbox series

[09/12] mm/mempolicy: Thread allocation for many preferred

Message ID 20200630212517.308045-10-ben.widawsky@intel.com (mailing list archive)
State New, archived
Headers show
Series Introduced multi-preference mempolicy | expand

Commit Message

Ben Widawsky June 30, 2020, 9:25 p.m. UTC 
In order to support MPOL_PREFERRED_MANY as the mode used by
set_mempolicy(2), alloc_pages_current() needs to support it. This patch
does that by using the new helper function to allocate properly based on
policy.

All the actual machinery to make this work was part of
("mm/mempolicy: Create a page allocator for policy")

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
---
 mm/mempolicy.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)
diff mbox series

Patch

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 1009cf90ad37..5fb70e6599a6 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2365,7 +2365,7 @@  EXPORT_SYMBOL(alloc_pages_vma);
 struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
 	struct mempolicy *pol = &default_policy;
-	struct page *page;
+	int nid = NUMA_NO_NODE;
 
 	if (!in_interrupt() && !(gfp & __GFP_THISNODE))
 		pol = get_task_policy(current);
@@ -2375,13 +2375,10 @@  struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 	 * nor system default_policy
 	 */
 	if (pol->mode == MPOL_INTERLEAVE)
-		page = alloc_pages_policy(pol, gfp, order, interleave_nodes(pol));
-	else
-		page = __alloc_pages_nodemask(gfp, order,
-				policy_node(gfp, pol, numa_node_id()),
-				policy_nodemask(gfp, pol));
+		nid = interleave_nodes(pol);
+
+	return alloc_pages_policy(pol, gfp, order, nid);
 
-	return page;
 }
 EXPORT_SYMBOL(alloc_pages_current);