With memory tiers support we can have memory only NUMA nodes
in the top tier from which we want to avoid promotion tracking NUMA
faults. Update node_is_toptier to work with memory tiers.
All NUMA nodes are by default top tier nodes. With lower memory
tiers added we consider all memory tiers above a memory tier having
CPU NUMA nodes as a top memory tier
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
---
include/linux/memory-tiers.h | 11 ++++++++++
include/linux/node.h | 5 -----
mm/huge_memory.c | 1 +
mm/memory-tiers.c | 42 ++++++++++++++++++++++++++++++++++++
mm/migrate.c | 1 +
mm/mprotect.c | 1 +
6 files changed, 56 insertions(+), 5 deletions(-)
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index f8dbeda617a7..bc9fb9d39b2c 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -35,6 +35,7 @@ struct memory_dev_type *init_node_memory_type(int node, struct memory_dev_type *
#ifdef CONFIG_MIGRATION
int next_demotion_node(int node);
void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
+bool node_is_toptier(int node);
#else
static inline int next_demotion_node(int node)
{
@@ -45,6 +46,11 @@ static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *target
{
*targets = NODE_MASK_NONE;
}
+
+static inline bool node_is_toptier(int node)
+{
+ return true;
+}
#endif
#else
@@ -64,5 +70,10 @@ static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *target
{
*targets = NODE_MASK_NONE;
}
+
+static inline bool node_is_toptier(int node)
+{
+ return true;
+}
#endif /* CONFIG_NUMA */
#endif /* _LINUX_MEMORY_TIERS_H */
diff --git a/include/linux/node.h b/include/linux/node.h
index 40d641a8bfb0..9ec680dd607f 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -185,9 +185,4 @@ static inline void register_hugetlbfs_with_node(node_registration_func_t reg,
#define to_node(device) container_of(device, struct node, dev)
-static inline bool node_is_toptier(int node)
-{
- return node_state(node, N_CPU);
-}
-
#endif /* _LINUX_NODE_H_ */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 834f288b3769..8405662646e9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -35,6 +35,7 @@
#include <linux/numa.h>
#include <linux/page_owner.h>
#include <linux/sched/sysctl.h>
+#include <linux/memory-tiers.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 84e2be31a853..36d87dc422ab 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -30,6 +30,7 @@ static DEFINE_MUTEX(memory_tier_lock);
static LIST_HEAD(memory_tiers);
struct memory_dev_type *node_memory_types[MAX_NUMNODES];
#ifdef CONFIG_MIGRATION
+static int top_tier_adistance;
/*
* node_demotion[] examples:
*
@@ -159,6 +160,31 @@ static struct memory_tier *__node_get_memory_tier(int node)
}
#ifdef CONFIG_MIGRATION
+bool node_is_toptier(int node)
+{
+ bool toptier;
+ pg_data_t *pgdat;
+ struct memory_tier *memtier;
+
+ pgdat = NODE_DATA(node);
+ if (!pgdat)
+ return false;
+
+ rcu_read_lock();
+ memtier = rcu_dereference(pgdat->memtier);
+ if (!memtier) {
+ toptier = true;
+ goto out;
+ }
+ if (memtier->adistance_start >= top_tier_adistance)
+ toptier = true;
+ else
+ toptier = false;
+out:
+ rcu_read_unlock();
+ return toptier;
+}
+
void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets)
{
struct memory_tier *memtier;
@@ -315,6 +341,22 @@ static void establish_demotion_targets(void)
}
} while (1);
}
+ /*
+ * Promotion is allowed from a memory tier to higher
+ * memory tier only if the memory tier doesn't include
+ * compute. We want to skip promotion from a memory tier,
+ * if any node that is part of the memory tier have CPUs.
+ * Once we detect such a memory tier, we consider that tier
+ * as top tiper from which promotion on is not allowed.
+ */
+ list_for_each_entry(memtier, &memory_tiers, list) {
+ tier_nodes = get_memtier_nodemask(memtier);
+ nodes_and(tier_nodes, node_states[N_CPU], tier_nodes);
+ if (!nodes_empty(tier_nodes)) {
+ top_tier_adistance = memtier->adistance_start;
+ break;
+ }
+ }
/*
* Now build the lower_tier mask for each node collecting node mask from
* all memory tier below it. This allows us to fallback demotion page
diff --git a/mm/migrate.c b/mm/migrate.c
index c758c9c21d7d..1da81136eaaa 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -50,6 +50,7 @@
#include <linux/memory.h>
#include <linux/random.h>
#include <linux/sched/sysctl.h>
+#include <linux/memory-tiers.h>
#include <asm/tlbflush.h>
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ba5592655ee3..92a2fc0fa88b 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -31,6 +31,7 @@
#include <linux/pgtable.h>
#include <linux/sched/sysctl.h>
#include <linux/userfaultfd_k.h>
+#include <linux/memory-tiers.h>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
--
2.37.1
