[RFC PATCH 3/9] mm: default slub, oom_kill, compaction, and page_alloc to sysram

[Gregory Price <gourry@gourry.net>]

Constrain core users of nodemasks to the default_sysram_nodemask,
which is guaranteed to either be NULL or contain the set of nodes
with sysram memory blocks.

Signed-off-by: Gregory Price <gourry@gourry.net>
---
 mm/oom_kill.c   |  5 ++++-
 mm/page_alloc.c | 12 ++++++++----
 mm/slub.c       |  4 +++-
 3 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index c145b0feecc1..e0b6137835b2 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -34,6 +34,7 @@
 #include <linux/export.h>
 #include <linux/notifier.h>
 #include <linux/memcontrol.h>
+#include <linux/memory-tiers.h>
 #include <linux/mempolicy.h>
 #include <linux/security.h>
 #include <linux/ptrace.h>
@@ -1118,6 +1119,8 @@ EXPORT_SYMBOL_GPL(unregister_oom_notifier);
 bool out_of_memory(struct oom_control *oc)
 {
 	unsigned long freed = 0;
+	if (!oc->nodemask)
+		oc->nodemask = default_sysram_nodes;
 
 	if (oom_killer_disabled)
 		return false;
@@ -1154,7 +1157,7 @@ bool out_of_memory(struct oom_control *oc)
 	 */
 	oc->constraint = constrained_alloc(oc);
 	if (oc->constraint != CONSTRAINT_MEMORY_POLICY)
-		oc->nodemask = NULL;
+		oc->nodemask = default_sysram_nodes;
 	check_panic_on_oom(oc);
 
 	if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task &&
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fd5401fb5e00..18213eacf974 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -34,6 +34,7 @@
 #include <linux/cpuset.h>
 #include <linux/pagevec.h>
 #include <linux/memory_hotplug.h>
+#include <linux/memory-tiers.h>
 #include <linux/nodemask.h>
 #include <linux/vmstat.h>
 #include <linux/fault-inject.h>
@@ -4610,7 +4611,7 @@ check_retry_cpuset(int cpuset_mems_cookie, struct alloc_context *ac)
 	 */
 	if (cpusets_enabled() && ac->nodemask &&
 			!cpuset_nodemask_valid_mems_allowed(ac->nodemask)) {
-		ac->nodemask = NULL;
+		ac->nodemask = default_sysram_nodes;
 		return true;
 	}
 
@@ -4794,7 +4795,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	 * user oriented.
 	 */
 	if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
-		ac->nodemask = NULL;
+		ac->nodemask = default_sysram_nodes;
 		ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
 					ac->highest_zoneidx, ac->nodemask);
 	}
@@ -4946,7 +4947,8 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 			ac->nodemask = &cpuset_current_mems_allowed;
 		else
 			*alloc_flags |= ALLOC_CPUSET;
-	}
+	} else if (!ac->nodemask) /* sysram_nodes may be NULL during __init */
+		ac->nodemask = default_sysram_nodes;
 
 	might_alloc(gfp_mask);
 
@@ -5190,8 +5192,10 @@ struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order,
 	/*
 	 * Restore the original nodemask if it was potentially replaced with
 	 * &cpuset_current_mems_allowed to optimize the fast-path attempt.
+	 *
+	 * If not set, default to sysram nodes.
 	 */
-	ac.nodemask = nodemask;
+	ac.nodemask = nodemask ? nodemask : default_sysram_nodes;
 
 	page = __alloc_pages_slowpath(alloc_gfp, order, &ac);
 
diff --git a/mm/slub.c b/mm/slub.c
index d4367f25b20d..b8358a961c4c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -28,6 +28,7 @@
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/mempolicy.h>
+#include <linux/memory-tiers.h>
 #include <linux/ctype.h>
 #include <linux/stackdepot.h>
 #include <linux/debugobjects.h>
@@ -3570,7 +3571,8 @@ static struct slab *get_any_partial(struct kmem_cache *s,
 	do {
 		cpuset_mems_cookie = read_mems_allowed_begin();
 		zonelist = node_zonelist(mempolicy_slab_node(), pc->flags);
-		for_each_zone_zonelist(zone, z, zonelist, highest_zoneidx) {
+		for_each_zone_zonelist_nodemask(zone, z, zonelist, highest_zoneidx,
+						default_sysram_nodes) {
 			struct kmem_cache_node *n;
 
 			n = get_node(s, zone_to_nid(zone));
-- 
2.51.1