@@ -928,6 +928,9 @@ typedef struct pglist_data {
/* Per-node vmstats */
struct per_cpu_nodestat __percpu *per_cpu_nodestats;
atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS];
+#ifdef CONFIG_NUMA
+ struct memory_tier __rcu *memtier;
+#endif
} pg_data_t;
#define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages)
@@ -5,6 +5,7 @@
#include <linux/kobject.h>
#include <linux/memory.h>
#include <linux/random.h>
+#include <linux/mmzone.h>
#include <linux/memory-tiers.h>
#include "internal.h"
@@ -144,12 +145,18 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty
static struct memory_tier *__node_get_memory_tier(int node)
{
- struct memory_dev_type *memtype;
+ pg_data_t *pgdat;
- memtype = node_memory_types[node];
- if (memtype)
- return memtype->memtier;
- return NULL;
+ pgdat = NODE_DATA(node);
+ if (!pgdat)
+ return NULL;
+ /*
+ * Since we hold memory_tier_lock, we can avoid
+ * RCU read locks when accessing the details. No
+ * parallel updates are possible here.
+ */
+ return rcu_dereference_check(pgdat->memtier,
+ lockdep_is_held(&memory_tier_lock));
}
#ifdef CONFIG_MIGRATION
@@ -292,6 +299,7 @@ static inline void establish_demotion_targets(void) {}
static void init_node_memory_tier(int node)
{
+ pg_data_t *pgdat = NODE_DATA(node);
struct memory_tier *memtier;
mutex_lock(&memory_tier_lock);
@@ -313,8 +321,12 @@ static void init_node_memory_tier(int node)
}
memtype = node_memory_types[node];
memtier = find_create_memory_tier(memtype);
+ if (IS_ERR(memtier))
+ goto err_out;
+ rcu_assign_pointer(pgdat->memtier, memtier);
}
establish_demotion_targets();
+err_out:
mutex_unlock(&memory_tier_lock);
}
@@ -326,13 +338,26 @@ static void destroy_memory_tier(struct memory_tier *memtier)
static void clear_node_memory_tier(int node)
{
+ pg_data_t *pgdat;
struct memory_tier *current_memtier;
+ pgdat = NODE_DATA(node);
+ if (!pgdat)
+ return;
+
mutex_lock(&memory_tier_lock);
+ /*
+ * Make sure that anybody looking at NODE_DATA who finds
+ * a valid memtier finds memory_dev_types with nodes still
+ * linked to the memtier. We achieve this by waiting for
+ * rcu read section to finish using synchronize_rcu.
+ */
current_memtier = __node_get_memory_tier(node);
if (current_memtier) {
struct memory_dev_type *memtype;
+ rcu_assign_pointer(pgdat->memtier, NULL);
+ synchronize_rcu();
memtype = node_memory_types[node];
node_clear(node, memtype->nodes);
if (nodes_empty(memtype->nodes)) {
@@ -400,8 +425,10 @@ static int __init memory_tier_init(void)
panic("%s() failed to register memory tier: %ld\n",
__func__, PTR_ERR(memtier));
- for_each_node_state(node, N_MEMORY)
+ for_each_node_state(node, N_MEMORY) {
node_memory_types[node] = &default_dram_type;
+ rcu_assign_pointer(NODE_DATA(node)->memtier, memtier);
+ }
mutex_unlock(&memory_tier_lock);
#ifdef CONFIG_MIGRATION
Also update different helpes to use NODE_DATA()->memtier. Since node specific memtier can change based on the reassignment of NUMA node to a different memory tiers, accessing NODE_DATA()->memtier needs to happen under an rcu read lock or memory_tier_lock. Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> --- include/linux/mmzone.h | 3 +++ mm/memory-tiers.c | 39 +++++++++++++++++++++++++++++++++------ 2 files changed, 36 insertions(+), 6 deletions(-)