From: Lorenzo Stoakes <lstoakes@gmail.com>
To: Uladzislau Rezki <urezki@gmail.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
linux-fsdevel@vger.kernel.org,
Andrew Morton <akpm@linux-foundation.org>,
Baoquan He <bhe@redhat.com>, Matthew Wilcox <willy@infradead.org>,
David Hildenbrand <david@redhat.com>,
Liu Shixin <liushixin2@huawei.com>, Jiri Olsa <jolsa@kernel.org>
Subject: Re: [PATCH v2 2/4] mm: vmalloc: use rwsem, mutex for vmap_area_lock and vmap_block->lock
Date: Mon, 20 Mar 2023 08:25:32 +0000 [thread overview]
Message-ID: <413e0dfe-5a68-4cd9-9036-bed741e4cd22@lucifer.local> (raw)
In-Reply-To: <ZBgROQ0uAfZCbScg@pc636>
On Mon, Mar 20, 2023 at 08:54:33AM +0100, Uladzislau Rezki wrote:
> > vmalloc() is, by design, not permitted to be used in atomic context and
> > already contains components which may sleep, so avoiding spin locks is not
> > a problem from the perspective of atomic context.
> >
> > The global vmap_area_lock is held when the red/black tree rooted in
> > vmap_are_root is accessed and thus is rather long-held and under
> > potentially high contention. It is likely to be under contention for reads
> > rather than write, so replace it with a rwsem.
> >
> > Each individual vmap_block->lock is likely to be held for less time but
> > under low contention, so a mutex is not an outrageous choice here.
> >
> > A subset of test_vmalloc.sh performance results:-
> >
> > fix_size_alloc_test 0.40%
> > full_fit_alloc_test 2.08%
> > long_busy_list_alloc_test 0.34%
> > random_size_alloc_test -0.25%
> > random_size_align_alloc_test 0.06%
> > ...
> > all tests cycles 0.2%
> >
> > This represents a tiny reduction in performance that sits barely above
> > noise.
> >
> How important to have many simultaneous users of vread()? I do not see a
> big reason to switch into mutexes due to performance impact and making it
> less atomic.
It's less about simultaneous users of vread() and more about being able to write
direct to user memory rather than via a bounce buffer and not hold a spinlock
over possible page faults.
The performance impact is barely above noise (I got fairly widely varying
results), so I don't think it's really much of a cost at all. I can't imagine
there are many users critically dependent on a sub-single digit % reduction in
speed in vmalloc() allocation.
As I was saying to Willy, the code is already not atomic, or rather needs rework
to become atomic-safe (there are a smattering of might_sleep()'s throughout)
However, given your objection alongside Willy's, let me examine Willy's
suggestion that we instead of doing this, prefault the user memory in advance of
the vread call.
>
> So, how important for you to have this change?
>
Personally, always very important :)
> --
> Uladzislau Rezki
next prev parent reply other threads:[~2023-03-20 8:25 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-19 7:09 [PATCH v2 0/4] convert read_kcore(), vread() to use iterators Lorenzo Stoakes
2023-03-19 7:09 ` [PATCH v2 1/4] fs/proc/kcore: Avoid bounce buffer for ktext data Lorenzo Stoakes
2023-03-20 9:58 ` David Hildenbrand
2023-03-19 7:09 ` [PATCH v2 2/4] mm: vmalloc: use rwsem, mutex for vmap_area_lock and vmap_block->lock Lorenzo Stoakes
2023-03-19 20:10 ` Andrew Morton
2023-03-19 20:29 ` Lorenzo Stoakes
2023-03-19 20:47 ` Matthew Wilcox
2023-03-19 21:16 ` Lorenzo Stoakes
2023-03-20 8:40 ` Lorenzo Stoakes
2023-03-20 7:54 ` Uladzislau Rezki
2023-03-20 8:25 ` Lorenzo Stoakes [this message]
2023-03-20 8:32 ` Uladzislau Rezki
2023-03-20 8:35 ` Lorenzo Stoakes
2023-03-20 11:20 ` Uladzislau Rezki
2023-03-21 1:09 ` Dave Chinner
2023-03-21 5:23 ` Uladzislau Rezki
2023-03-21 7:45 ` Lorenzo Stoakes
2023-03-21 8:54 ` Uladzislau Rezki
2023-03-21 10:05 ` Dave Chinner
2023-03-21 10:24 ` Uladzislau Rezki
2023-03-22 13:18 ` Uladzislau Rezki
2023-03-22 17:47 ` Matthew Wilcox
2023-03-22 18:01 ` Uladzislau Rezki
2023-03-22 19:15 ` Uladzislau Rezki
2023-03-23 12:47 ` Uladzislau Rezki
2023-03-24 5:25 ` Dave Chinner
2023-03-24 5:31 ` Matthew Wilcox
2023-03-27 0:38 ` Dave Chinner
2023-03-27 17:22 ` Uladzislau Rezki
2023-03-28 2:53 ` Dave Chinner
2023-03-28 12:40 ` Uladzislau Rezki
2023-03-19 7:09 ` [PATCH v2 3/4] fs/proc/kcore: convert read_kcore() to read_kcore_iter() Lorenzo Stoakes
2023-03-19 7:09 ` [PATCH v2 4/4] mm: vmalloc: convert vread() to vread_iter() Lorenzo Stoakes
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=413e0dfe-5a68-4cd9-9036-bed741e4cd22@lucifer.local \
--to=lstoakes@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=bhe@redhat.com \
--cc=david@redhat.com \
--cc=jolsa@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=liushixin2@huawei.com \
--cc=urezki@gmail.com \
--cc=willy@infradead.org \
/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;
as well as URLs for NNTP newsgroup(s).