From: Matthew Wilcox <willy@infradead.org>
To: Minchan Kim <minchan@kernel.org>
Cc: "Yu Zhao" <yuzhao@google.com>,
"Yin, Fengwei" <fengwei.yin@intel.com>,
"Yang Shi" <shy828301@gmail.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
Linux-MM <linux-mm@kvack.org>, 韩天硕 <hantianshuo@iie.ac.cn>,
mawupeng <mawupeng1@huawei.com>
Subject: Re: (resend)WARNING: trying to isolate tail page in isolate_lru_page
Date: Fri, 26 Aug 2022 19:02:48 +0100 [thread overview]
Message-ID: <YwkKyBPeDbZc3r8J@casper.infradead.org> (raw)
In-Reply-To: <YwkIqt3T6y/jJizP@google.com>
On Fri, Aug 26, 2022 at 10:53:46AM -0700, Minchan Kim wrote:
> Long term, that's better idea(For stable backport, I'd like to go with
> simple PageLRU check).
>
> I wonder it's possible to mix LRU pages and non-struct pages together
> in a VMA. Otherwise, could we reuse(abuse) VM_MIXEDMAP?
On a bit of a tangent, I'm not sure that we should be allowing this for
file pages at all. I see that we only allow it if mapcount is 1, but page
cache is also used by applications that don't mmap it. So if some other
application is using /tmp/bigfile with read() and write(), I can force
that memory out of the page cache by mmaping it and calling MADV_PAGEOUT.
That could be used as an exfiltration side-channel, for example.
next prev parent reply other threads:[~2022-08-26 18:03 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-25 14:40 韩天硕
2022-08-25 16:50 ` Yu Zhao
2022-08-25 18:23 ` Matthew Wilcox
2022-08-25 18:37 ` Yu Zhao
2022-08-25 18:40 ` Yang Shi
2022-08-25 18:46 ` Matthew Wilcox
2022-08-26 3:20 ` Yin, Fengwei
2022-08-26 16:56 ` Minchan Kim
2022-08-26 18:23 ` Yang Shi
2022-08-26 22:58 ` Minchan Kim
2022-08-27 0:48 ` Yin, Fengwei
2022-08-26 17:15 ` Matthew Wilcox
2022-08-26 17:27 ` Yu Zhao
2022-08-26 17:53 ` Minchan Kim
2022-08-26 17:58 ` Yu Zhao
2022-08-26 18:02 ` Matthew Wilcox [this message]
2022-08-26 18:19 ` Yang Shi
2022-08-26 23:12 ` Minchan Kim
2022-08-27 0:24 ` Yin, Fengwei
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=YwkKyBPeDbZc3r8J@casper.infradead.org \
--to=willy@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=fengwei.yin@intel.com \
--cc=hantianshuo@iie.ac.cn \
--cc=linux-mm@kvack.org \
--cc=mawupeng1@huawei.com \
--cc=minchan@kernel.org \
--cc=shy828301@gmail.com \
--cc=yuzhao@google.com \
/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