linux-kernel - Re: [RFC PATCH v2] mm/zswap: store <PAGE

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]

Message-Id: <20250806212859.51259-1-sj@kernel.org>
Date: Wed,  6 Aug 2025 14:28:59 -0700
From: SeongJae Park <sj@...nel.org>
To: David Hildenbrand <david@...hat.com>
Cc: SeongJae Park <sj@...nel.org>,
	Nhat Pham <nphamcs@...il.com>,
	"Liam R. Howlett" <Liam.Howlett@...cle.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Chengming Zhou <chengming.zhou@...ux.dev>,
	Johannes Weiner <hannes@...xchg.org>,
	Jonathan Corbet <corbet@....net>,
	Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
	Michal Hocko <mhocko@...e.com>,
	Mike Rapoport <rppt@...nel.org>,
	Suren Baghdasaryan <surenb@...gle.com>,
	Vlastimil Babka <vbabka@...e.cz>,
	Yosry Ahmed <yosry.ahmed@...ux.dev>,
	kernel-team@...a.com,
	linux-doc@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-mm@...ck.org,
	Takero Funaki <flintglass@...il.com>
Subject: Re: [RFC PATCH v2] mm/zswap: store <PAGE_SIZE compression failed page as-is

On Wed, 6 Aug 2025 22:14:39 +0200 David Hildenbrand <david@...hat.com> wrote:

> On 05.08.25 18:56, Nhat Pham wrote:
> > On Tue, Aug 5, 2025 at 3:47 AM David Hildenbrand <david@...hat.com> wrote:
> >>
> >> On 05.08.25 02:29, SeongJae Park wrote:
> >>> When zswap writeback is enabled and it fails compressing a given page,
> >>> the page is swapped out to the backing swap device.  This behavior
> >>> breaks the zswap's writeback LRU order, and hence users can experience
> >>> unexpected latency spikes.  If the page is compressed without failure,
> >>> but results in a size of PAGE_SIZE, the LRU order is kept, but the
> >>> decompression overhead for loading the page back on the later access is
> >>> unnecessary.
> >>>
> >>> Keep the LRU order and optimize unnecessary decompression overheads in
> >>> the cases, by storing the original content in zpool as-is.
> >>
> >> Does this have any effect on the movability of the given page? IOW, does
> >> page migration etc. still work when we store an ordinary page of an
> >> shmem/anon folio here?
> > 
> > Good question. This depends on the backend allocator of zswap, but the
> > only backend allocator remaining (zsmalloc) does implement page
> > migration.
> 
> Right, but migration of these pages works completely different than 
> folio migration.
> 
> But I think the part I was missing: we are still performing a copy to 
> another page, it's just that we don't perform any compression.
> 
> So I guess *breaking* movability of folios is not a concern.
> 
> But yeah, whether these "as is" pages are movable or not is a good 
> question as well -- in particular when zsmalloc supports page migration 
> and the "as is" pages would not.

Maybe I'm missing some of your points.  But there is no difference for "as is"
pages.

Before this patch, zswap asks zpool (backed by zsmalloc) to allocate memoy and
store the content of the page in the "compressed" form, if the content was able
to be compressed.  After that, the original page becomes same to any pages
that swapped out.

After this patch, if the content was unable to be compressed, the content is
saved "as is" _in_ the zpool, in a way same to those "compressible" case,
except the content is not changed.  After the saving is done, the original page
becomes same to any pages that swapped out.

Zsmalloc will support migration of pages that backing the internal contents,
regardless of whether those are compressed or saved "as is".  From perspectives
other than that of zsmalloc, hence, I think no difference is introduced by this
patch.

Again, I'm not sure if I'm really understanding your points.  If so, please let
me know.


Thanks,
SJ

[...]