All of lore.kernel.org
 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 v12 6/8] mm/demotion: Add pg_data_t member to track node memory tier details
Date: Fri, 29 Jul 2022 11:43:47 +0530	[thread overview]
Message-ID: <20220729061349.968148-7-aneesh.kumar@linux.ibm.com> (raw)
In-Reply-To: <20220729061349.968148-1-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      | 39 +++++++++++++++++++++++++++++++++------
 2 files changed, 36 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 97634337803c..44f6676bc2c8 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"
@@ -144,12 +145,18 @@ 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)
-		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
@@ -292,6 +299,7 @@ static inline void establish_demotion_targets(void) {}
 
 static void init_node_memory_tier(int node)
 {
+	pg_data_t *pgdat = NODE_DATA(node);
 	struct memory_tier *memtier;
 
 	mutex_lock(&memory_tier_lock);
@@ -313,8 +321,12 @@ static void init_node_memory_tier(int node)
 		}
 		memtype = node_memory_types[node];
 		memtier = find_create_memory_tier(memtype);
+		if (IS_ERR(memtier))
+			goto err_out;
+		rcu_assign_pointer(pgdat->memtier, memtier);
 	}
 	establish_demotion_targets();
+err_out:
 	mutex_unlock(&memory_tier_lock);
 }
 
@@ -326,13 +338,26 @@ static void destroy_memory_tier(struct memory_tier *memtier)
 
 static void clear_node_memory_tier(int node)
 {
+	pg_data_t *pgdat;
 	struct memory_tier *current_memtier;
 
+	pgdat = NODE_DATA(node);
+	if (!pgdat)
+		return;
+
 	mutex_lock(&memory_tier_lock);
+	/*
+	 * 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.
+	 */
 	current_memtier = __node_get_memory_tier(node);
 	if (current_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)) {
@@ -400,8 +425,10 @@ 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) {
 		node_memory_types[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:[~2022-07-29  6:15 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-29  6:13 [PATCH v12 0/8] mm/demotion: Memory tiers and demotion Aneesh Kumar K.V
2022-07-29  6:13 ` [PATCH v12 1/8] mm/demotion: Add support for explicit memory tiers Aneesh Kumar K.V
2022-07-31  9:54   ` kernel test robot
2022-08-01  2:37   ` Huang, Ying
2022-08-01  4:47     ` Aneesh Kumar K V
2022-07-29  6:13 ` [PATCH v12 2/8] mm/demotion: Move memory demotion related code Aneesh Kumar K.V
2022-07-29  6:13 ` [PATCH v12 3/8] mm/demotion: Add hotplug callbacks to handle new numa node onlined Aneesh Kumar K.V
2022-07-29  6:13 ` [PATCH v12 4/8] mm/demotion/dax/kmem: Set node's abstract distance to MEMTIER_ADISTANCE_PMEM Aneesh Kumar K.V
2022-07-29  6:13 ` [PATCH v12 5/8] mm/demotion: Build demotion targets based on explicit memory tiers Aneesh Kumar K.V
2022-07-29  6:13 ` Aneesh Kumar K.V [this message]
2022-07-29  6:13 ` [PATCH v12 7/8] mm/demotion: Demote pages according to allocation fallback order Aneesh Kumar K.V
2022-07-29  6:13 ` [PATCH v12 8/8] mm/demotion: Update node_is_toptier to work with memory tiers 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=20220729061349.968148-7-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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.