From: ALOK TIWARI <alok.a.tiwari@oracle.com>
To: Oscar Salvador <osalvador@suse.de>,
Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Vlastimil Babka <vbabka@suse.cz>,
Hyeonggon Yoo <42.hyeyoo@gmail.com>,
Jonathan Cameron <Jonathan.Cameron@huawei.com>,
Rakie Kim <rakie.kim@sk.com>, Harry Yoo <harry.yoo@oracle.com>
Subject: Re: [PATCH v3 2/3] mm,memory_hotplug: Implement numa node notifier
Date: Sat, 3 May 2025 00:39:58 +0530 [thread overview]
Message-ID: <348e5677-f7ed-4386-a5cf-38024dc23c8e@oracle.com> (raw)
In-Reply-To: <20250502083624.49849-3-osalvador@suse.de>
> - node_states_set_node(nid, &arg);
> + node_states_set_node(nid, &node_arg);
> if (need_zonelists_rebuild)
> build_all_zonelists(NULL);
>
> @@ -1245,16 +1252,26 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
> kswapd_run(nid);
> kcompactd_run(nid);
>
> + if (node_arg.status_change_nid >= 0)
> + /*
> + * Node went from memoryless to have memory. Notifiy interested
typo Notifiy -> Notify
"to have memory" /s "to having memory"
> + * consumers
> + */
> + node_notify(NODE_BECAME_MEM_AWARE, &node_arg);
> +
> writeback_set_ratelimit();
>
> - memory_notify(MEM_ONLINE, &arg);
> + memory_notify(MEM_ONLINE, &mem_arg);
> return 0;
>
> failed_addition:
> pr_debug("online_pages [mem %#010llx-%#010llx] failed\n",
> (unsigned long long) pfn << PAGE_SHIFT,
> (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
> - memory_notify(MEM_CANCEL_ONLINE, &arg);
> + if (cancel_mem_notifier_on_err)
> + memory_notify(MEM_CANCEL_ONLINE, &mem_arg);
> + if (cancel_node_notifier_on_err)
> + node_notify(NODE_CANCEL_MEM_AWARE, &node_arg);
> remove_pfn_range_from_zone(zone, pfn, nr_pages);
> return ret;
> }
> @@ -1888,48 +1905,29 @@ early_param("movable_node", cmdline_parse_movable_node);
>
> /* check which state of node_states will be changed when offline memory */
> static void node_states_check_changes_offline(unsigned long nr_pages,
> - struct zone *zone, struct memory_notify *arg)
> + struct zone *zone, struct node_notify *arg)
> {
> struct pglist_data *pgdat = zone->zone_pgdat;
> unsigned long present_pages = 0;
> enum zone_type zt;
>
> arg->status_change_nid = NUMA_NO_NODE;
> - arg->status_change_nid_normal = NUMA_NO_NODE;
>
> /*
> - * Check whether node_states[N_NORMAL_MEMORY] will be changed.
> - * If the memory to be offline is within the range
> - * [0..ZONE_NORMAL], and it is the last present memory there,
> - * the zones in that range will become empty after the offlining,
> - * thus we can determine that we need to clear the node from
> - * node_states[N_NORMAL_MEMORY].
> + * Here we count the possible pages within the range [0..ZONE_MOVABLE].
> + * If after having accounted all the pages, we see that the nr_pages to
> + * be offlined is over or equal to the accounted pages, we know that the
> + * node will become empty, ans so, we can clear it for N_MEMORY.
typo ans -> and
"over or equal to the accounted" -> "greater than or equal to the accounted"
> */
> - for (zt = 0; zt <= ZONE_NORMAL; zt++)
> + for (zt = 0; zt <= ZONE_MOVABLE; zt++)
> present_pages += pgdat->node_zones[zt].present_pages;
> - if (zone_idx(zone) <= ZONE_NORMAL && nr_pages >= present_pages)
> - arg->status_change_nid_normal = zone_to_nid(zone);
> -
> - /*
> - * We have accounted the pages from [0..ZONE_NORMAL); ZONE_HIGHMEM
> - * does not apply as we don't support 32bit.
> - * Here we count the possible pages from ZONE_MOVABLE.
> - * If after having accounted all the pages, we see that the nr_pages
> - * to be offlined is over or equal to the accounted pages,
> - * we know that the node will become empty, and so, we can clear
> - * it for N_MEMORY as well.
> - */
> - present_pages += pgdat->node_zones[ZONE_MOVABLE].present_pages;
>
> if (nr_pages >= present_pages)
> arg->status_change_nid = zone_to_nid(zone);
> }
>
> -static void node_states_clear_node(int node, struct memory_notify *arg)
> +static void node_states_clear_node(int node, struct node_notify *arg)
> {
> - if (arg->status_change_nid_normal >= 0)
> - node_clear_state(node, N_NORMAL_MEMORY);
> -
> if (arg->status_change_nid >= 0)
> node_clear_state(node, N_MEMORY);
> }
> @@ -1953,7 +1951,9 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
> unsigned long pfn, managed_pages, system_ram_pages = 0;
> const int node = zone_to_nid(zone);
> unsigned long flags;
> - struct memory_notify arg;
> + struct memory_notify mem_arg;
> + struct node_notify node_arg;
> + bool cancel_mem_notifier_on_err = false, cancel_node_notifier_on_err = false;
> char *reason;
> int ret;
>
> @@ -2012,11 +2012,21 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
> goto failed_removal_pcplists_disabled;
> }
>
> - arg.start_pfn = start_pfn;
> - arg.nr_pages = nr_pages;
> - node_states_check_changes_offline(nr_pages, zone, &arg);
> + mem_arg.start_pfn = start_pfn;
> + mem_arg.nr_pages = nr_pages;
> + node_states_check_changes_offline(nr_pages, zone, &node_arg);
> +
> + if (node_arg.status_change_nid >= 0) {
> + cancel_node_notifier_on_err = true;
> + ret = node_notify(NODE_BECOMING_MEMORYLESS, &node_arg);
> + ret = notifier_to_errno(ret);
> + if (ret)
> + goto failed_removal_isolated;
> + }
>
> - ret = memory_notify(MEM_GOING_OFFLINE, &arg);
> + cancel_mem_notifier_on_err = true;
> + mem_arg.status_change_nid = node_arg.status_change_nid;
> + ret = memory_notify(MEM_GOING_OFFLINE, &mem_arg);
> ret = notifier_to_errno(ret);
> if (ret) {
> reason = "notifier failure";
> @@ -2096,27 +2106,32 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
> * Make sure to mark the node as memory-less before rebuilding the zone
> * list. Otherwise this node would still appear in the fallback lists.
> */
> - node_states_clear_node(node, &arg);
> + node_states_clear_node(node, &node_arg);
> if (!populated_zone(zone)) {
> zone_pcp_reset(zone);
> build_all_zonelists(NULL);
> }
>
> - if (arg.status_change_nid >= 0) {
> + if (node_arg.status_change_nid >= 0) {
> kcompactd_stop(node);
> kswapd_stop(node);
> + /* Node went memoryless. Notifiy interested consumers */
typo Notifiy -> Notify
> + node_notify(NODE_BECAME_MEMORYLESS, &node_arg);
> }
>
> writeback_set_ratelimit();
>
> - memory_notify(MEM_OFFLINE, &arg);
> + memory_notify(MEM_OFFLINE, &mem_arg);
> remove_pfn_range_from_zone(zone, start_pfn, nr_pages);
> return 0;
>
> failed_removal_isolated:
> /* pushback to free area */
> undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
> - memory_notify(MEM_CANCEL_OFFLINE, &arg);
> + if (cancel_mem_notifier_on_err)
> + memory_notify(MEM_CANCEL_OFFLINE, &mem_arg);
> + if (cancel_node_notifier_on_err)
> + node_notify(NODE_CANCEL_MEMORYLESS, &node_arg);
> failed_removal_pcplists_disabled:
> lru_cache_enable();
> zone_pcp_enable(zone);
> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> index f43951668c41..b3ad63fb3a2b 100644
Thanks,
Alok
next prev parent reply other threads:[~2025-05-02 19:10 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-02 8:36 [PATCH v3 0/3] " Oscar Salvador
2025-05-02 8:36 ` [PATCH v3 1/3] mm,slub: Do not special case N_NORMAL nodes for slab_nodes Oscar Salvador
2025-05-05 13:43 ` Vlastimil Babka
2025-05-02 8:36 ` [PATCH v3 2/3] mm,memory_hotplug: Implement numa node notifier Oscar Salvador
2025-05-02 15:28 ` Gregory Price
2025-05-05 14:51 ` Dan Carpenter
2025-05-28 2:23 ` Honggyu Kim
2025-06-03 9:14 ` Oscar Salvador
2025-05-02 19:09 ` ALOK TIWARI [this message]
2025-05-05 13:58 ` Vlastimil Babka
2025-05-02 8:36 ` [PATCH v3 3/3] mm,memory_hotplug: Rename status_change_nid parameter in memory_notify Oscar Salvador
2025-05-02 19:15 ` ALOK TIWARI
2025-05-04 3:03 ` [PATCH v3 0/3] Implement numa node notifier Andrew Morton
2025-05-04 5:44 ` Oscar Salvador
2025-05-04 6:16 ` Andrew Morton
2025-05-05 17:07 ` Gregory Price
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=348e5677-f7ed-4386-a5cf-38024dc23c8e@oracle.com \
--to=alok.a.tiwari@oracle.com \
--cc=42.hyeyoo@gmail.com \
--cc=Jonathan.Cameron@huawei.com \
--cc=akpm@linux-foundation.org \
--cc=david@redhat.com \
--cc=harry.yoo@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=osalvador@suse.de \
--cc=rakie.kim@sk.com \
--cc=vbabka@suse.cz \
/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