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 v13 6/9] mm/demotion: Add pg_data_t member to track node memory tier details
Date: Mon,  8 Aug 2022 11:55:58 +0530	[thread overview]
Message-ID: <20220808062601.836025-7-aneesh.kumar@linux.ibm.com> (raw)
In-Reply-To: <20220808062601.836025-1-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/mmzone.h |  3 +++
 mm/memory-tiers.c      | 38 ++++++++++++++++++++++++++++++++------
 2 files changed, 35 insertions(+), 6 deletions(-)

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 02e514e87d5c..3778ac6a44a1 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -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"
@@ -137,12 +138,18 @@ 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 && node_isset(node, memtype->nodes))
-		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
@@ -295,6 +302,8 @@ static struct memory_tier *set_node_memory_tier(int node)
 {
 	struct memory_tier *memtier;
 	struct memory_dev_type *memtype;
+	pg_data_t *pgdat = NODE_DATA(node);
+
 
 	lockdep_assert_held_once(&memory_tier_lock);
 
@@ -307,6 +316,8 @@ static struct memory_tier *set_node_memory_tier(int node)
 	memtype = node_memory_types[node];
 	node_set(node, memtype->nodes);
 	memtier = find_create_memory_tier(memtype);
+	if (!IS_ERR(memtier))
+		rcu_assign_pointer(pgdat->memtier, memtier);
 	return memtier;
 }
 
@@ -319,12 +330,25 @@ static void destroy_memory_tier(struct memory_tier *memtier)
 static bool clear_node_memory_tier(int node)
 {
 	bool cleared = false;
+	pg_data_t *pgdat;
 	struct memory_tier *memtier;
 
+	pgdat = NODE_DATA(node);
+	if (!pgdat)
+		return false;
+
+	/*
+	 * 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.
+	 */
 	memtier = __node_get_memory_tier(node);
 	if (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)) {
@@ -422,8 +446,10 @@ 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) {
 		__init_node_memory_type(node, default_dram_type);
+		rcu_assign_pointer(NODE_DATA(node)->memtier, memtier);
+	}
 
 	mutex_unlock(&memory_tier_lock);
 #ifdef CONFIG_MIGRATION
-- 
2.37.1



  parent reply	other threads:[~2022-08-08  6:27 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-08  6:25 [PATCH v13 0/9] mm/demotion: Memory tiers and demotion Aneesh Kumar K.V
2022-08-08  6:25 ` [PATCH v13 1/9] mm/demotion: Add support for explicit memory tiers Aneesh Kumar K.V
2022-08-09  1:58   ` Huang, Ying
2022-08-09  5:34     ` Aneesh Kumar K V
2022-08-08  6:25 ` [PATCH v13 2/9] mm/demotion: Move memory demotion related code Aneesh Kumar K.V
2022-08-08  6:25 ` [PATCH v13 3/9] mm/demotion: Add hotplug callbacks to handle new numa node onlined Aneesh Kumar K.V
2022-08-08  6:25 ` [PATCH v13 4/9] mm/demotion/dax/kmem: Set node's abstract distance to MEMTIER_DEFAULT_DAX_ADISTANCE Aneesh Kumar K.V
2022-08-09  3:04   ` Huang, Ying
2022-08-09  5:33     ` Aneesh Kumar K V
2022-08-10  1:09       ` Huang, Ying
2022-08-08  6:25 ` [PATCH v13 5/9] mm/demotion: Build demotion targets based on explicit memory tiers Aneesh Kumar K.V
2022-08-08  6:25 ` Aneesh Kumar K.V [this message]
2022-08-09  3:07   ` [PATCH v13 6/9] mm/demotion: Add pg_data_t member to track node memory tier details Huang, Ying
2022-08-09  5:21   ` Huang, Ying
2022-08-09  5:41     ` Aneesh Kumar K V
2022-08-10  1:03       ` Huang, Ying
2022-08-08  6:25 ` [PATCH v13 7/9] mm/demotion: Demote pages according to allocation fallback order Aneesh Kumar K.V
2022-08-08  6:26 ` [PATCH v13 8/9] mm/demotion: Update node_is_toptier to work with memory tiers Aneesh Kumar K.V
2022-08-08  6:26 ` [PATCH v13 9/9] lib/nodemask: Optimize node_random for nodemask with single NUMA node Aneesh Kumar K.V
2022-08-09  3:13   ` Huang, Ying
2022-08-09  5:43     ` 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=20220808062601.836025-7-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).