Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
From:   "Huang, Ying" <ying.huang@intel.com>
To:     Oscar Salvador <osalvador@suse.de>
Cc:     Andrew Morton <akpm@linux-foundation.org>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Abhishek Goel <huntbag@linux.vnet.ibm.com>,
        Baolin Wang <baolin.wang@linux.alibaba.com>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3] mm: Only re-generate demotion targets when a numa
 node changes its N_CPU state
References: <20220314150945.12694-1-osalvador@suse.de>
Date:   Tue, 15 Mar 2022 14:40:53 +0800
In-Reply-To: <20220314150945.12694-1-osalvador@suse.de> (Oscar Salvador's
        message of "Mon, 14 Mar 2022 16:09:45 +0100")
Message-ID: <87pmmn3eh6.fsf@yhuang6-desk2.ccr.corp.intel.com>
User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/27.1 (gnu/linux)
MIME-Version: 1.0
Content-Type: text/plain; charset=ascii
Precedence: bulk

Oscar Salvador <osalvador@suse.de> writes:

> Abhishek reported that after patch [1], hotplug operations are
> taking ~double the expected time. [2]
>
> The reason behind is that the CPU callbacks that migrate_on_reclaim_init()
> sets always call set_migration_target_nodes() whenever a CPU is brought
> up/down.
> But we only care about numa nodes going from having cpus to become
> cpuless, and vice versa, as that influences the demotion_target order.
>
> We do already have two CPU callbacks (vmstat_cpu_online() and vmstat_cpu_dead())
> that check exactly that, so get rid of the CPU callbacks in
> migrate_on_reclaim_init() and only call set_migration_target_nodes() from
> vmstat_cpu_{dead,online}() whenever a numa node change its N_CPU state.
>
> [1] https://lore.kernel.org/linux-mm/20210721063926.3024591-2-ying.huang@intel.com/
> [2] https://lore.kernel.org/linux-mm/eb438ddd-2919-73d4-bd9f-b7eecdd9577a@linux.vnet.ibm.com/
>
> Fixes: 884a6e5d1f93b ("mm/migrate: update node demotion order on hotplug events")
> Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> Reported-by: Abhishek Goel <huntbag@linux.vnet.ibm.com>
> Signed-off-by: Oscar Salvador <osalvador@suse.de>
> ---
>  v2 -> v3:
>            - Add feedback from Huang Ying
> 	   - Add tags
>  v1 -> v2:
>            - Add fedback from Huang Ying
>            - Add feedback from Baolin Wang
> ---
>  include/linux/migrate.h |  8 +++++++
>  mm/migrate.c            | 47 +++++++++--------------------------------
>  mm/vmstat.c             | 13 +++++++++++-
>  3 files changed, 30 insertions(+), 38 deletions(-)
>
> diff --git a/include/linux/migrate.h b/include/linux/migrate.h
> index db96e10eb8da..90e75d5a54d6 100644
> --- a/include/linux/migrate.h
> +++ b/include/linux/migrate.h
> @@ -48,7 +48,15 @@ int folio_migrate_mapping(struct address_space *mapping,
>  		struct folio *newfolio, struct folio *folio, int extra_count);
>  
>  extern bool numa_demotion_enabled;
> +extern void migrate_on_reclaim_init(void);
> +#ifdef CONFIG_HOTPLUG_CPU
> +extern void set_migration_target_nodes(void);
>  #else
> +static inline void set_migration_target_nodes(void) {}
> +#endif
> +#else
> +
> +static inline void set_migration_target_nodes(void) {}
>  
>  static inline void putback_movable_pages(struct list_head *l) {}
>  static inline int migrate_pages(struct list_head *l, new_page_t new,
> diff --git a/mm/migrate.c b/mm/migrate.c
> index e8a6933af68d..2561881f03b2 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -3193,7 +3193,7 @@ static void __set_migration_target_nodes(void)
>  /*
>   * For callers that do not hold get_online_mems() already.
>   */
> -static void set_migration_target_nodes(void)
> +void set_migration_target_nodes(void)
>  {
>  	get_online_mems();
>  	__set_migration_target_nodes();
> @@ -3257,51 +3257,24 @@ static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
>  	return notifier_from_errno(0);
>  }
>  
> -/*
> - * React to hotplug events that might affect the migration targets
> - * like events that online or offline NUMA nodes.
> - *
> - * The ordering is also currently dependent on which nodes have
> - * CPUs.  That means we need CPU on/offline notification too.
> - */
> -static int migration_online_cpu(unsigned int cpu)
> -{
> -	set_migration_target_nodes();
> -	return 0;
> -}
> -
> -static int migration_offline_cpu(unsigned int cpu)
> +void __init migrate_on_reclaim_init(void)
>  {
> -	set_migration_target_nodes();
> -	return 0;
> -}
> -
> -static int __init migrate_on_reclaim_init(void)
> -{
> -	int ret;
> -
>  	node_demotion = kmalloc_array(nr_node_ids,
>  				      sizeof(struct demotion_nodes),
>  				      GFP_KERNEL);
>  	WARN_ON(!node_demotion);
>  
> -	ret = cpuhp_setup_state_nocalls(CPUHP_MM_DEMOTION_DEAD, "mm/demotion:offline",

CPUHP_MM_DEMOTION_DEAD and CPUHP_AP_MM_DEMOTION_ONLINE needs to be
deleted from include/linux/cpuhotplug.h too.

Best Regards,
Huang, Ying

> -					NULL, migration_offline_cpu);
> +	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
>  	/*
> -	 * In the unlikely case that this fails, the automatic
> -	 * migration targets may become suboptimal for nodes
> -	 * where N_CPU changes.  With such a small impact in a
> -	 * rare case, do not bother trying to do anything special.
> +	 * At this point, all numa nodes with memory/CPus have their state
> +	 * properly set, so we can build the demotion order now.
> +	 * Let us hold the cpu_hotplug lock just, as we could possibily have
> +	 * CPU hotplug events during boot.
>  	 */
> -	WARN_ON(ret < 0);
> -	ret = cpuhp_setup_state(CPUHP_AP_MM_DEMOTION_ONLINE, "mm/demotion:online",
> -				migration_online_cpu, NULL);
> -	WARN_ON(ret < 0);
> -
> -	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
> -	return 0;
> +	cpus_read_lock();
> +	set_migration_target_nodes();
> +	cpus_read_unlock();
>  }
> -late_initcall(migrate_on_reclaim_init);
>  #endif /* CONFIG_HOTPLUG_CPU */
>  
>  bool numa_demotion_enabled = false;

[snip]