linux-kernel - Re: [PATCH 0/2] Implement numa node notifier

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 for Android: free password hash cracker in your pocket

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

Message-ID: <Z--uHnqP_GRnt1TK@harry>
Date: Fri, 4 Apr 2025 19:02:06 +0900
From: Harry Yoo <harry.yoo@...cle.com>
To: Vlastimil Babka <vbabka@...e.cz>
Cc: David Hildenbrand <david@...hat.com>, Oscar Salvador <osalvador@...e.de>,
        Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org, Hyeonggon Yoo <42.hyeyoo@...il.com>,
        mkoutny@...e.com, Dan Williams <dan.j.williams@...el.com>,
        Jonathan Cameron <Jonathan.Cameron@...wei.com>
Subject: Re: [PATCH 0/2] Implement numa node notifier

On Fri, Apr 04, 2025 at 10:50:49AM +0200, Vlastimil Babka wrote:
> On 4/4/25 00:06, Harry Yoo wrote:
> > On Thu, Apr 03, 2025 at 03:02:25PM +0200, David Hildenbrand wrote:
> >> On 02.04.25 19:03, Oscar Salvador wrote:
> >> > On Wed, Apr 02, 2025 at 06:06:51PM +0200, Vlastimil Babka wrote:
> >> > > What if we had two chains:
> >> > > 
> >> > > register_node_notifier()
> >> > > register_node_normal_notifier()
> >> > > 
> >> > > I think they could have shared the state #defines and struct node_notify
> >> > > would have just one nid and be always >= 0.
> >> > > 
> >> > > Or would it add too much extra boilerplate and only slab cares?
> >> > 
> >> > We could indeed go on that direction to try to decouple
> >> > status_change_nid from status_change_nid_normal.
> >> > 
> >> > Although as you said, slub is the only user of status_change_nid_normal
> >> > for the time beign, so I am not sure of adding a second chain for only
> >> > one user.
> >> > 
> >> > Might look cleaner though, and the advantatge is that slub would not get
> >> > notified for nodes adquiring only ZONE_MOVABLE.
> >> > 
> >> > Let us see what David thinks about it.
> >> 
> >> I'd hope we'd be able to get rid of the _normal stuff completely, it's seems
> >> way to specialized.
> > 
> > Hmm, perhaps we can remove it with as part of this patch series?
> > 
> > status_change_nid_normal has been used to indicate both 'There is a
> > status change' AND 'The node id when the NUMA node has normal memory'.
> > 
> > But since NUMA node notifier triggers only when there is a state change,
> > it can simply pass nid, like patch 2 does. SLUB can then check whether the
> > node has normal memory.
> 
> Well the state change could be adding movable memory, SLUB checks that
> there's no normal memory and thus does nothing. Then normal memory is added
> to the node, but there's no new notification and SLUB is left without
> supporting the node forever.

You're right. I thought it still notifies state changes from
N_NORMAL_MEMORY || N_MEMORY, but if you don't even want to notify state
change from N_NORMAL_MEMORY... yes. It won't work.

> But with David's suggestion we avoid that problem.

David's suggestion looks good to me too!

> > Or am I missing something?
> > 
> >> We added that in
> >> 
> >> commit b9d5ab2562eceeada5e4837a621b6260574dd11d
> >> Author: Lai Jiangshan <laijs@...fujitsu.com>
> >> Date:   Tue Dec 11 16:01:05 2012 -0800
> >> 
> >>     slub, hotplug: ignore unrelated node's hot-adding and hot-removing
> >>     SLUB only focuses on the nodes which have normal memory and it ignores the
> >>     other node's hot-adding and hot-removing.
> >>     Aka: if some memory of a node which has no onlined memory is online, but
> >>     this new memory onlined is not normal memory (for example, highmem), we
> >>     should not allocate kmem_cache_node for SLUB.
> >>     And if the last normal memory is offlined, but the node still has memory,
> >>     we should remove kmem_cache_node for that node.  (The current code delays
> >>     it when all of the memory is offlined)
> >>     So we only do something when marg->status_change_nid_normal > 0.
> >>     marg->status_change_nid is not suitable here.
> >>     The same problem doesn't exist in SLAB, because SLAB allocates kmem_list3
> >>     for every node even the node don't have normal memory, SLAB tolerates
> >>     kmem_list3 on alien nodes.  SLUB only focuses on the nodes which have
> >>     normal memory, it don't tolerate alien kmem_cache_node.  The patch makes
> >>     SLUB become self-compatible and avoids WARNs and BUGs in rare conditions.
> >> 
> >> 
> >> How "bad" would it be if we do the slab_mem_going_online_callback() etc even
> >> for completely-movable nodes? I assume one kmem_cache_alloc() per slab_caches.
> >>
> >> slab_mem_going_offline_callback() only does shrinking, #dontcare
> >> 
> >> Looking at slab_mem_offline_callback(), we never even free the caches either
> >> way when offlining. So the implication would be that we would have movable-only nodes
> >> set in slab_nodes.
> >> 
> >> 
> >> We don't expect many such nodes, so ... do we care?
> >> 
> >> -- 
> >> Cheers,
> >> 
> >> David / dhildenb
> >> 
> >> 
> > 
> 

-- 
Cheers,
Harry (formerly known as Hyeonggon)