aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--include/linux/mempolicy.h2
-rw-r--r--include/linux/mmzone.h18
-rw-r--r--mm/mempolicy.c2
-rw-r--r--mm/page_alloc.c13
4 files changed, 33 insertions, 2 deletions
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index e147cf50529..5bdd656e88c 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -166,7 +166,7 @@ extern enum zone_type policy_zone;
static inline void check_highest_zone(enum zone_type k)
{
- if (k > policy_zone)
+ if (k > policy_zone && k != ZONE_MOVABLE)
policy_zone = k;
}
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3ea68cd3b61..4e5627379b0 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -410,6 +410,24 @@ struct zonelist {
#endif
};
+#ifdef CONFIG_NUMA
+/*
+ * Only custom zonelists like MPOL_BIND need to be filtered as part of
+ * policies. As described in the comment for struct zonelist_cache, these
+ * zonelists will not have a zlcache so zlcache_ptr will not be set. Use
+ * that to determine if the zonelists needs to be filtered or not.
+ */
+static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
+{
+ return !zonelist->zlcache_ptr;
+}
+#else
+static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
+{
+ return 0;
+}
+#endif /* CONFIG_NUMA */
+
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
struct node_active_region {
unsigned long start_pfn;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 71b84b45154..172abffeb2e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -149,7 +149,7 @@ static struct zonelist *bind_zonelist(nodemask_t *nodes)
lower zones etc. Avoid empty zones because the memory allocator
doesn't like them. If you implement node hot removal you
have to fix that. */
- k = policy_zone;
+ k = MAX_NR_ZONES - 1;
while (1) {
for_each_node_mask(nd, *nodes) {
struct zone *z = &NODE_DATA(nd)->node_zones[k];
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3da85b81dab..6427653023a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1157,6 +1157,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
int zlc_active = 0; /* set if using zonelist_cache */
int did_zlc_setup = 0; /* just call zlc_setup() one time */
+ enum zone_type highest_zoneidx = -1; /* Gets set for policy zonelists */
zonelist_scan:
/*
@@ -1166,6 +1167,18 @@ zonelist_scan:
z = zonelist->zones;
do {
+ /*
+ * In NUMA, this could be a policy zonelist which contains
+ * zones that may not be allowed by the current gfp_mask.
+ * Check the zone is allowed by the current flags
+ */
+ if (unlikely(alloc_should_filter_zonelist(zonelist))) {
+ if (highest_zoneidx == -1)
+ highest_zoneidx = gfp_zone(gfp_mask);
+ if (zone_idx(*z) > highest_zoneidx)
+ continue;
+ }
+
if (NUMA_BUILD && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;