From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Date: Thu, 18 Aug 2022 18:40:41 +0530
Subject: mm/demotion: update node_is_toptier to work with memory tiers
Git-commit: 467b171af881282fc627328e6c164f044a6df888
Patch-mainline: v6.1-rc1
References: jsc#PED-1248
With memory tier 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(slower) memory tiers added we consider all
memory tiers above a memory tier having CPU NUMA nodes as a top memory
tier
[sj@kernel.org: include missed header file, memory-tiers.h]
Link: https://lkml.kernel.org/r/20220820190720.248704-1-sj@kernel.org
[akpm@linux-foundation.org: mm/memory.c needs linux/memory-tiers.h]
[aneesh.kumar@linux.ibm.com: make toptier_distance inclusive upper bound of toptiers]
Link: https://lkml.kernel.org/r/20220830081457.118960-1-aneesh.kumar@linux.ibm.com
Link: https://lkml.kernel.org/r/20220818131042.113280-10-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Wei Xu <weixugc@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Bharata B Rao <bharata@amd.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hesham Almatary <hesham.almatary@huawei.com>
Cc: Jagdish Gediya <jvgediya.oss@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/memory-tiers.h | 11 ++++++++++
include/linux/node.h | 5 ----
mm/huge_memory.c | 1
mm/memory-tiers.c | 47 +++++++++++++++++++++++++++++++++++++++++++
mm/memory.c | 1
mm/migrate.c | 1
mm/mprotect.c | 1
7 files changed, 62 insertions(+), 5 deletions(-)
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -40,6 +40,7 @@ void clear_node_memory_type(int node, st
#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)
{
@@ -50,6 +51,11 @@ static inline void node_get_allowed_targ
{
*targets = NODE_MASK_NONE;
}
+
+static inline bool node_is_toptier(int node)
+{
+ return true;
+}
#endif
#else
@@ -87,5 +93,10 @@ static inline void node_get_allowed_targ
{
*targets = NODE_MASK_NONE;
}
+
+static inline bool node_is_toptier(int node)
+{
+ return true;
+}
#endif /* CONFIG_NUMA */
#endif /* _LINUX_MEMORY_TIERS_H */
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -181,9 +181,4 @@ static inline void register_hugetlbfs_wi
#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_ */
--- 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>
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -37,6 +37,7 @@ static LIST_HEAD(memory_tiers);
static struct node_memory_type_map node_memory_types[MAX_NUMNODES];
static struct memory_dev_type *default_dram_type;
#ifdef CONFIG_MIGRATION
+static int top_tier_adistance;
/*
* node_demotion[] examples:
*
@@ -162,6 +163,31 @@ static struct memory_tier *__node_get_me
}
#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;
@@ -320,6 +346,27 @@ static void establish_demotion_targets(v
} 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 is not allowed.
+ */
+ list_for_each_entry_reverse(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)) {
+ /*
+ * abstract distance below the max value of this memtier
+ * is considered toptier.
+ */
+ top_tier_adistance = memtier->adistance_start +
+ MEMTIER_CHUNK_SIZE - 1;
+ 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
* allocation to a set of nodes that is closer the above selected
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -65,6 +65,7 @@
#include <linux/gfp.h>
#include <linux/migrate.h>
#include <linux/string.h>
+#include <linux/memory-tiers.h>
#include <linux/debugfs.h>
#include <linux/userfaultfd_k.h>
#include <linux/dax.h>
--- 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>
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -30,6 +30,7 @@
#include <linux/mm_inline.h>
#include <linux/pgtable.h>
#include <linux/sched/sysctl.h>
+#include <linux/memory-tiers.h>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>