linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "Huang, Ying" <ying.huang@intel.com>
To: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: linux-mm@kvack.org,  akpm@linux-foundation.org,
	 Wei Xu <weixugc@google.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
Subject: Re: [PATCH v10 6/8] mm/demotion: Add pg_data_t member to track node memory tier details
Date: Tue, 26 Jul 2022 16:02:33 +0800	[thread overview]
Message-ID: <87wnc0uwrq.fsf@yhuang6-desk2.ccr.corp.intel.com> (raw)
In-Reply-To: <20220720025920.1373558-7-aneesh.kumar@linux.ibm.com> (Aneesh Kumar K. V.'s message of "Wed, 20 Jul 2022 08:29:18 +0530")

"Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> writes:

> 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      | 65 +++++++++++++++++++++++++++++++++++-------
>  2 files changed, 57 insertions(+), 11 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 a8cfe2ca3903..4715f9b96a44 100644
> --- a/mm/memory-tiers.c
> +++ b/mm/memory-tiers.c
> @@ -138,13 +138,18 @@ static struct memory_tier *find_create_memory_tier(unsigned int perf_level)
>  
>  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));
>  }
>  
>  #ifdef CONFIG_MIGRATION
> @@ -277,6 +282,29 @@ static inline void disable_all_migrate_targets(void) {}
>  static inline void establish_migration_targets(void) {}
>  #endif /* CONFIG_MIGRATION */
>  
> +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);
> +	synchronize_rcu();
> +	if (current_memtier)
> +		node_clear(node, current_memtier->nodelist);

If pgdat->memtier == NULL, we don't need to set it to NULL and call
synchronize_rcu().  That is,

+	current_memtier = rcu_dereference_check(pgdat->memtier,
+						lockdep_is_held(&memory_tier_lock));
+	if (current_memtier) {
+               rcu_assign_pointer(pgdat->memtier, NULL);
+               synchronize_rcu();
+		node_clear(node, current_memtier->nodelist);
+       }

Same for clear_node_memory_tier().

Best Regards,
Huang, Ying

> +	node_set(node, memtier->nodelist);
> +	rcu_assign_pointer(pgdat->memtier, memtier);
> +}
> +
>  static void init_node_memory_tier(int node)
>  {
>  	int perf_level;
> @@ -295,7 +323,7 @@ static void init_node_memory_tier(int node)
>  	if (!memtier) {
>  		perf_level = node_devices[node]->perf_level;
>  		memtier = find_create_memory_tier(perf_level);
> -		node_set(node, memtier->nodelist);
> +		memtier_node_set(node, memtier);
>  	}
>  	establish_migration_targets();
>  	mutex_unlock(&memory_tier_lock);
> @@ -303,12 +331,25 @@ static void init_node_memory_tier(int node)
>  
>  static void clear_node_memory_tier(int node)
>  {
> -	struct memory_tier *memtier;
> +	pg_data_t *pgdat;
> +	struct memory_tier *current_memtier;
> +
> +	pgdat = NODE_DATA(node);
> +	if (!pgdat)
> +		return;
>  
>  	mutex_lock(&memory_tier_lock);
> -	memtier = __node_get_memory_tier(node);
> -	if (memtier) {
> -		node_clear(node, memtier->nodelist);
> +	/*
> +	 * 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);
> +	synchronize_rcu();
> +	if (current_memtier) {
> +		node_clear(node, current_memtier->nodelist);
>  		establish_migration_targets();
>  	}
>  	mutex_unlock(&memory_tier_lock);
> @@ -383,6 +424,8 @@ static int __init memory_tier_init(void)
>  
>  		if (!node_property->perf_level)
>  			node_property->perf_level = default_memtier_perf_level;
> +
> +		rcu_assign_pointer(NODE_DATA(node)->memtier, memtier);
>  	}
>  	mutex_unlock(&memory_tier_lock);


  reply	other threads:[~2022-07-26  8:02 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-20  2:59 [PATCH v10 0/8] mm/demotion: Memory tiers and demotion Aneesh Kumar K.V
2022-07-20  2:59 ` [PATCH v10 1/8] mm/demotion: Add support for explicit memory tiers Aneesh Kumar K.V
2022-07-26  3:53   ` Huang, Ying
2022-07-26 11:59     ` Aneesh Kumar K V
2022-07-27  1:16       ` Huang, Ying
2022-07-28 17:23         ` Johannes Weiner
2022-07-20  2:59 ` [PATCH v10 2/8] mm/demotion: Move memory demotion related code Aneesh Kumar K.V
2022-07-20  2:59 ` [PATCH v10 3/8] mm/demotion: Add hotplug callbacks to handle new numa node onlined Aneesh Kumar K.V
2022-07-26  4:03   ` Huang, Ying
2022-07-26 12:03     ` Aneesh Kumar K V
2022-07-27  1:53       ` Huang, Ying
2022-07-27  4:38         ` Aneesh Kumar K.V
2022-07-28  6:42           ` Huang, Ying
2022-07-20  2:59 ` [PATCH v10 4/8] mm/demotion/dax/kmem: Set node's performance level to MEMTIER_PERF_LEVEL_PMEM Aneesh Kumar K.V
2022-07-21  6:07   ` kernel test robot
2022-07-25  6:37   ` Huang, Ying
2022-07-25  6:48     ` Aneesh Kumar K V
2022-07-25  8:35       ` Huang, Ying
2022-07-25  8:42         ` Aneesh Kumar K V
2022-07-26  2:13           ` Huang, Ying
2022-07-27  4:31             ` Aneesh Kumar K.V
2022-07-28  6:39               ` Huang, Ying
2022-07-20  2:59 ` [PATCH v10 5/8] mm/demotion: Build demotion targets based on explicit memory tiers Aneesh Kumar K.V
2022-07-20  3:38   ` Aneesh Kumar K.V
2022-07-21  0:02   ` kernel test robot
2022-07-26  7:44   ` Huang, Ying
2022-07-26 12:30     ` Aneesh Kumar K V
2022-07-27  1:40       ` Huang, Ying
2022-07-27  4:35         ` Aneesh Kumar K.V
2022-07-28  6:51           ` Huang, Ying
2022-08-03  3:18         ` Aneesh Kumar K.V
2022-08-04  4:19           ` Huang, Ying
2022-07-20  2:59 ` [PATCH v10 6/8] mm/demotion: Add pg_data_t member to track node memory tier details Aneesh Kumar K.V
2022-07-26  8:02   ` Huang, Ying [this message]
2022-07-20  2:59 ` [PATCH v10 7/8] mm/demotion: Demote pages according to allocation fallback order Aneesh Kumar K.V
2022-07-26  8:24   ` Huang, Ying
2022-07-20  2:59 ` [PATCH v10 8/8] mm/demotion: Update node_is_toptier to work with memory tiers Aneesh Kumar K.V
2022-07-25  8:54   ` Huang, Ying
2022-07-25  8:56     ` 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=87wnc0uwrq.fsf@yhuang6-desk2.ccr.corp.intel.com \
    --to=ying.huang@intel.com \
    --cc=Jonathan.Cameron@huawei.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.ibm.com \
    --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 \
    /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