Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
To:     linux-mm@kvack.org, akpm@linux-foundation.org
Cc:     Wei Xu <weixugc@google.com>, Huang Ying <ying.huang@intel.com>,
        Yang Shi <shy828301@gmail.com>,
        Davidlohr Bueso <dave@stgolabs.net>,
        Tim C Chen <tim.c.chen@intel.com>,
        Michal Hocko <mhocko@kernel.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Hesham Almatary <hesham.almatary@huawei.com>,
        Dave Hansen <dave.hansen@intel.com>,
        Jonathan Cameron <Jonathan.Cameron@huawei.com>,
        Alistair Popple <apopple@nvidia.com>,
        Dan Williams <dan.j.williams@intel.com>,
        Johannes Weiner <hannes@cmpxchg.org>, jvgediya.oss@gmail.com,
        Bharata B Rao <bharata@amd.com>,
        "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: [PATCH v14 09/10] mm/demotion: Update node_is_toptier to work with memory tiers
Date:   Fri, 12 Aug 2022 11:27:08 +0530
Message-Id: <20220812055710.357820-10-aneesh.kumar@linux.ibm.com>
In-Reply-To: <20220812055710.357820-1-aneesh.kumar@linux.ibm.com>
References: <20220812055710.357820-1-aneesh.kumar@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 include/linux/memory-tiers.h | 11 +++++++++
 include/linux/node.h         |  5 ----
 mm/huge_memory.c             |  1 +
 mm/memory-tiers.c            | 46 ++++++++++++++++++++++++++++++++++++
 mm/migrate.c                 |  1 +
 mm/mprotect.c                |  1 +
 6 files changed, 60 insertions(+), 5 deletions(-)

diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 6fdff436c205..9198d69afaa9 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -37,6 +37,7 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype);
 #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)
 {
@@ -47,6 +48,11 @@ 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
@@ -84,5 +90,10 @@ 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 8a7c1b344abe..1e9357576f2d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -36,6 +36,7 @@
 #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 2db4b4116a28..165ebbbac30d 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -32,6 +32,7 @@ static LIST_HEAD(memory_tiers);
 static struct memory_dev_type *node_memory_types[MAX_NUMNODES];
 static struct memory_dev_type *default_dram_type;
 #ifdef CONFIG_MIGRATION
+static int top_tier_adistance;
 /*
  * node_demotion[] examples:
  *
@@ -157,6 +158,31 @@ 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;
@@ -314,6 +340,26 @@ 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 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;
+			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 ea86594f4bc5..55e7718cfe45 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 3a23dde73723..61cd80831b04 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