linux-kernel - Re: [PATCH v13 6/9] mm/demotion: Add pg_data_t member to track node memory tier details

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 09 Aug 2022 11:07:17 +0800
From:   "Huang, Ying" <ying.huang@...el.com>
To:     "Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>
Cc:     linux-mm@...ck.org, akpm@...ux-foundation.org,
        Wei Xu <weixugc@...gle.com>, Yang Shi <shy828301@...il.com>,
        Davidlohr Bueso <dave@...olabs.net>,
        Tim C Chen <tim.c.chen@...el.com>,
        Michal Hocko <mhocko@...nel.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Hesham Almatary <hesham.almatary@...wei.com>,
        Dave Hansen <dave.hansen@...el.com>,
        Jonathan Cameron <Jonathan.Cameron@...wei.com>,
        Alistair Popple <apopple@...dia.com>,
        Dan Williams <dan.j.williams@...el.com>,
        Johannes Weiner <hannes@...xchg.org>, jvgediya.oss@...il.com
Subject: Re: [PATCH v13 6/9] mm/demotion: Add pg_data_t member to track node
 memory tier details

"Aneesh Kumar K.V" <aneesh.kumar@...ux.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@...ux.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.
> +	 */

The synchronize_rcu() is also needed because we may free the memory
tier.

Best Regards,
Huang, Ying

>  	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