linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
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,
	"Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: [PATCH v8 08/12] mm/demotion: Add pg_data_t member to track node memory tier details
Date: Mon,  4 Jul 2022 12:36:08 +0530	[thread overview]
Message-ID: <20220704070612.299585-9-aneesh.kumar@linux.ibm.com> (raw)
In-Reply-To: <20220704070612.299585-1-aneesh.kumar@linux.ibm.com>

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/memory-tiers.h |  11 ++++
 include/linux/mmzone.h       |   3 +
 mm/memory-tiers.c            | 104 +++++++++++++++++++++++++----------
 3 files changed, 89 insertions(+), 29 deletions(-)

diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 453f6e5d357c..705b63ee31d5 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -6,6 +6,9 @@
 
 #ifdef CONFIG_NUMA
 
+#include <linux/device.h>
+#include <linux/nodemask.h>
+
 #define MEMORY_TIER_HBM_GPU	300
 #define MEMORY_TIER_DRAM	200
 #define MEMORY_TIER_PMEM	100
@@ -13,6 +16,12 @@
 #define DEFAULT_MEMORY_TIER	MEMORY_TIER_DRAM
 #define MAX_MEMORY_TIER_ID	400
 
+struct memory_tier {
+	struct list_head list;
+	struct device dev;
+	nodemask_t nodelist;
+};
+
 extern bool numa_demotion_enabled;
 int node_create_and_set_memory_tier(int node, int tier);
 #ifdef CONFIG_MIGRATION
@@ -25,6 +34,8 @@ static inline int next_demotion_node(int node)
 #endif
 int node_get_memory_tier_id(int node);
 int node_update_memory_tier(int node, int tier);
+struct memory_tier *node_get_memory_tier(int node);
+void node_put_memory_tier(struct memory_tier *memtier);
 
 #else
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index aab70355d64f..353812495a70 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -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)
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index b7cb368cb9c0..6a2476faf13a 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -1,22 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
-#include <linux/device.h>
-#include <linux/nodemask.h>
 #include <linux/slab.h>
 #include <linux/lockdep.h>
 #include <linux/moduleparam.h>
 #include <linux/memory.h>
 #include <linux/random.h>
+#include <linux/rcupdate.h>
 #include <linux/memory-tiers.h>
 
 #include "internal.h"
 
-struct memory_tier {
-	struct list_head list;
-	struct device dev;
-	nodemask_t nodelist;
-};
-
 struct demotion_nodes {
 	nodemask_t preferred;
 };
@@ -120,7 +113,7 @@ static void memory_tier_device_release(struct device *dev)
 {
 	struct memory_tier *tier = to_memory_tier(dev);
 
-	kfree(tier);
+	kfree_rcu(tier);
 }
 
 static void insert_memory_tier(struct memory_tier *memtier)
@@ -176,13 +169,18 @@ static void unregister_memory_tier(struct memory_tier *memtier)
 
 static struct memory_tier *__node_get_memory_tier(int node)
 {
-	struct memory_tier *memtier;
+	pg_data_t *pgdat;
 
-	list_for_each_entry(memtier, &memory_tiers, list) {
-		if (node_isset(node, memtier->nodelist))
-			return 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));
 }
 
 static struct memory_tier *__get_memory_tier_from_id(int id)
@@ -196,6 +194,33 @@ static struct memory_tier *__get_memory_tier_from_id(int id)
 	return NULL;
 }
 
+/*
+ * Called with memory_tier_lock. Hence the device references cannot
+ * be dropped during this function.
+ */
+static void memtier_node_set(int node, struct memory_tier *memtier)
+{
+	pg_data_t *pgdat;
+	struct memory_tier *current_memtier;
+
+	pgdat = NODE_DATA(node);
+	if (!pgdat)
+		return;
+	/*
+	 * Make sure we mark the memtier NULL before we assign the new memory tier
+	 * to the NUMA node. This make sure that anybody looking at NODE_DATA
+	 * finds a NULL memtier or the one which is still valid.
+	 */
+	current_memtier = rcu_dereference_check(pgdat->memtier,
+						lockdep_is_held(&memory_tier_lock));
+	rcu_assign_pointer(pgdat->memtier, NULL);
+	if (current_memtier)
+		node_clear(node, current_memtier->nodelist);
+	synchronize_rcu();
+	node_set(node, memtier->nodelist);
+	rcu_assign_pointer(pgdat->memtier, memtier);
+}
+
 static int __node_create_and_set_memory_tier(int node, int tier)
 {
 	int ret = 0;
@@ -209,7 +234,7 @@ static int __node_create_and_set_memory_tier(int node, int tier)
 			goto out;
 		}
 	}
-	node_set(node, memtier->nodelist);
+	memtier_node_set(node, memtier);
 out:
 	return ret;
 }
@@ -231,14 +256,7 @@ int node_create_and_set_memory_tier(int node, int tier)
 	if (current_tier->dev.id == tier)
 		goto out;
 
-	node_clear(node, current_tier->nodelist);
-
 	ret = __node_create_and_set_memory_tier(node, tier);
-	if (ret) {
-		/* reset it back to older tier */
-		node_set(node, current_tier->nodelist);
-		goto out;
-	}
 	if (nodes_empty(current_tier->nodelist))
 		unregister_memory_tier(current_tier);
 
@@ -260,7 +278,7 @@ static int __node_set_memory_tier(int node, int tier)
 		ret = -EINVAL;
 		goto out;
 	}
-	node_set(node, memtier->nodelist);
+	memtier_node_set(node, memtier);
 out:
 	return ret;
 }
@@ -316,10 +334,7 @@ int node_update_memory_tier(int node, int tier)
 	if (!current_tier || current_tier->dev.id == tier)
 		goto out;
 
-	node_clear(node, current_tier->nodelist);
-
 	ret = __node_create_and_set_memory_tier(node, tier);
-
 	if (nodes_empty(current_tier->nodelist))
 		unregister_memory_tier(current_tier);
 
@@ -330,6 +345,34 @@ int node_update_memory_tier(int node, int tier)
 	return ret;
 }
 
+/*
+ * lockless access to memory tier of a NUMA node.
+ */
+struct memory_tier *node_get_memory_tier(int node)
+{
+	pg_data_t *pgdat;
+	struct memory_tier *memtier;
+
+	pgdat = NODE_DATA(node);
+	if (!pgdat)
+		return NULL;
+
+	rcu_read_lock();
+	memtier = rcu_dereference(pgdat->memtier);
+	if (!memtier)
+		goto out;
+
+	get_device(&memtier->dev);
+out:
+	rcu_read_unlock();
+	return memtier;
+}
+
+void node_put_memory_tier(struct memory_tier *memtier)
+{
+	put_device(&memtier->dev);
+}
+
 #ifdef CONFIG_MIGRATION
 /**
  * next_demotion_node() - Get the next node in the demotion path
@@ -546,7 +589,7 @@ static const struct attribute_group *memory_tier_attr_groups[] = {
 
 static int __init memory_tier_init(void)
 {
-	int ret;
+	int ret, node;
 	struct memory_tier *memtier;
 
 	ret = subsys_system_register(&memory_tier_subsys, memory_tier_attr_groups);
@@ -567,7 +610,10 @@ static int __init memory_tier_init(void)
 		      __func__, PTR_ERR(memtier));
 
 	/* CPU only nodes are not part of memory tiers. */
-	memtier->nodelist = node_states[N_MEMORY];
+	for_each_node_state(node, N_MEMORY) {
+		rcu_assign_pointer(NODE_DATA(node)->memtier, memtier);
+		node_set(node, memtier->nodelist);
+	}
 	mutex_unlock(&memory_tier_lock);
 
 	migrate_on_reclaim_init();
-- 
2.36.1



  parent reply	other threads:[~2022-07-04  7:11 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-04  7:06 [PATCH v8 00/12] mm/demotion: Memory tiers and demotion Aneesh Kumar K.V
2022-07-04  7:06 ` [PATCH v8 01/12] mm/demotion: Add support for explicit memory tiers Aneesh Kumar K.V
2022-07-04  7:06 ` [PATCH v8 02/12] mm/demotion: Move memory demotion related code Aneesh Kumar K.V
2022-07-04  7:06 ` [PATCH v8 03/12] mm/demotion/dax/kmem: Set node's memory tier to MEMORY_TIER_PMEM Aneesh Kumar K.V
2022-07-04  7:06 ` [PATCH v8 04/12] mm/demotion: Add hotplug callbacks to handle new numa node onlined Aneesh Kumar K.V
2022-07-04  7:06 ` [PATCH v8 05/12] mm/demotion: Build demotion targets based on explicit memory tiers Aneesh Kumar K.V
2022-07-04  7:06 ` [PATCH v8 06/12] mm/demotion: Expose memory tier details via sysfs Aneesh Kumar K.V
2022-07-04  7:06 ` [PATCH v8 07/12] mm/demotion: Add per node memory tier attribute to sysfs Aneesh Kumar K.V
2022-07-04  7:06 ` Aneesh Kumar K.V [this message]
2022-07-04  7:06 ` [PATCH v8 09/12] mm/demotion: Demote pages according to allocation fallback order Aneesh Kumar K.V
2022-07-04  7:06 ` [PATCH v8 10/12] mm/demotion: Update node_is_toptier to work with memory tiers Aneesh Kumar K.V
2022-07-04  7:06 ` [PATCH v8 11/12] mm/demotion: Add documentation for memory tiering Aneesh Kumar K.V
2022-07-04  7:06 ` [PATCH v8 12/12] mm/demotion: Add sysfs ABI documentation Aneesh Kumar K.V
2022-07-04 15:00 ` [PATCH v8 00/12] mm/demotion: Memory tiers and demotion Matthew Wilcox
2022-07-05  3:45   ` Alistair Popple
2022-07-05  4:17   ` Aneesh Kumar K V
2022-07-05  4:29 ` Huang, Ying
2022-07-05  5:22   ` Aneesh Kumar K V
2022-07-12  1:16     ` Huang, Ying
2022-07-12  4:42       ` Aneesh Kumar K V
2022-07-12  5:09         ` Aneesh Kumar K V
2022-07-12 18:02           ` Yang Shi
2022-07-13  3:42             ` Huang, Ying
2022-07-13  6:38               ` Wei Xu
2022-07-13  6:39               ` Wei Xu
2022-07-13  7:25               ` Aneesh Kumar K V
2022-07-13  8:20                 ` Huang, Ying
2022-07-12  6:59         ` Huang, Ying
2022-07-12  7:31           ` Aneesh Kumar K V
2022-07-12  8:48             ` Huang, Ying
2022-07-12  9:17               ` Aneesh Kumar K V
2022-07-13  2:59                 ` Huang, Ying
2022-07-13  6:46                   ` Wei Xu
2022-07-13  8:17                     ` Huang, Ying
2022-07-19 14:00                       ` Jonathan Cameron
2022-07-25  6:02                         ` Huang, Ying
2022-07-13  9:44                     ` Aneesh Kumar K.V
2022-07-13  9:40                   ` Aneesh Kumar K.V
2022-07-14  4:56                     ` Huang, Ying
2022-07-14  5:29                       ` Aneesh Kumar K V
2022-07-14  7:21                         ` Huang, Ying
2022-07-11 15:29 ` Aneesh Kumar K.V

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220704070612.299585-9-aneesh.kumar@linux.ibm.com \
    --to=aneesh.kumar@linux.ibm.com \
    --cc=Jonathan.Cameron@huawei.com \
    --cc=akpm@linux-foundation.org \
    --cc=apopple@nvidia.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=dave@stgolabs.net \
    --cc=hannes@cmpxchg.org \
    --cc=hesham.almatary@huawei.com \
    --cc=jvgediya.oss@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=shy828301@gmail.com \
    --cc=tim.c.chen@intel.com \
    --cc=weixugc@google.com \
    --cc=ying.huang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).