From: Herbert Xu <herbert@gondor.apana.org.au>
To: Yosry Ahmed <yosry.ahmed@linux.dev>
Cc: Vitaly Wool <vitaly.wool@konsulko.se>,
linux-mm@kvack.org, akpm@linux-foundation.org,
linux-kernel@vger.kernel.org, Nhat Pham <nphamcs@gmail.com>,
Shakeel Butt <shakeel.butt@linux.dev>,
Johannes Weiner <hannes@cmpxchg.org>,
Minchan Kim <minchan@kernel.org>,
Sergey Senozhatsky <senozhatsky@chromium.org>,
Igor Belousov <igor.b@beldev.am>, Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH] mm/zblock: use vmalloc for page allocations
Date: Tue, 6 May 2025 21:27:49 +0800 [thread overview]
Message-ID: <aBoOVajBDXkFNUBI@gondor.apana.org.au> (raw)
In-Reply-To: <aBoK7f7rtfbPFGap@google.com>
On Tue, May 06, 2025 at 01:13:17PM +0000, Yosry Ahmed wrote:
>
> Keep in mind that zswap_decompress() will always do an extra copy if the
> address returned by zpool_obj_read_begin() is a vmalloc address. To
> avoid this we need to enlighten the scatterlist API to work with vmalloc
> addresses.
>
> (CC'ing Herbert as he was looking into this)
acomp now supports linear addresses so vmalloc can be sent through
directly. It will fail if you use hardware offload though since
you can't DMA directly to vmalloc virtual addresses.
If you wish to support hardware offload, then you'll need to break
the vmalloc memory down page-by-page to create an SG list.
Adding Christoph to the cc list in case he knows of any updates in
this area (using vmalloc memory with DMA).
Cheers,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
next prev parent reply other threads:[~2025-05-06 13:28 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-02 8:01 Vitaly Wool
2025-05-02 8:07 ` Igor Belousov
2025-05-03 18:46 ` Vitaly Wool
2025-05-04 5:02 ` Sergey Senozhatsky
2025-05-04 6:14 ` Sergey Senozhatsky
2025-05-05 14:08 ` Johannes Weiner
2025-05-06 2:13 ` Sergey Senozhatsky
2025-05-05 14:29 ` Johannes Weiner
2025-05-06 9:42 ` Uladzislau Rezki
2025-05-06 13:13 ` Yosry Ahmed
2025-05-06 13:27 ` Herbert Xu [this message]
2025-05-06 13:37 ` Christoph Hellwig
2025-05-07 5:57 ` Sergey Senozhatsky
2025-05-07 6:08 ` Sergey Senozhatsky
2025-05-07 6:14 ` Sergey Senozhatsky
2025-05-07 6:54 ` Christoph Hellwig
2025-05-08 5:58 ` Sergey Senozhatsky
2025-05-08 6:00 ` Christoph Hellwig
2025-05-08 6:17 ` Sergey Senozhatsky
2025-05-08 6:33 ` Sergey Senozhatsky
2025-05-07 8:50 ` Uladzislau Rezki
2025-05-08 6:07 ` Sergey Senozhatsky
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=aBoOVajBDXkFNUBI@gondor.apana.org.au \
--to=herbert@gondor.apana.org.au \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=hch@lst.de \
--cc=igor.b@beldev.am \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=minchan@kernel.org \
--cc=nphamcs@gmail.com \
--cc=senozhatsky@chromium.org \
--cc=shakeel.butt@linux.dev \
--cc=vitaly.wool@konsulko.se \
--cc=yosry.ahmed@linux.dev \
/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