From: Peter Zijlstra <peterz@infradead.org>
To: Waiman Long <longman@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Andrew Morton <akpm@linux-foundation.org>,
Phil Auld <pauld@redhat.com>,
Will Deacon <will.deacon@kernel.org>,
Rik van Riel <riel@surriel.com>,
Andy Lutomirski <luto@kernel.org>
Subject: Re: [PATCH v2] sched/core: Don't use dying mm as active_mm of kthreads
Date: Mon, 29 Jul 2019 17:38:25 +0200 [thread overview]
Message-ID: <20190729153825.GI31398@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <2bc722b9-3eff-6d99-4ee7-1f4cab8b6c21@redhat.com>
On Mon, Jul 29, 2019 at 11:22:16AM -0400, Waiman Long wrote:
> On 7/29/19 10:27 AM, Peter Zijlstra wrote:
> > Also; why then not key off that owner tracking to free the resources
> > (and leave the struct mm around) and avoid touching this scheduling
> > hot-path ?
>
> The resources are pinned by the reference count. Making a special case
> will certainly mess up the existing code.
>
> It is actually a problem for systems that are mostly idle. Only the
> kernel->kernel case needs to be updated. If the CPUs isn't busy running
> user tasks, a little bit more overhead shouldn't really hurt IMHO.
But when you cannot find a new owner; you can start to strip mm_struct.
That is, what's stopping you from freeing swap reservations when that
happens?
That is; I think the moment mm_users drops to 0, you can destroy the
actual addres space. But you have to keep mm_struct around until
mm_count goes to 0.
This is going on the comments with mmget() and mmgrab(); they forever
confuse me.
next prev parent reply other threads:[~2019-07-29 15:38 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-27 17:10 [PATCH v2] sched/core: Don't use dying mm as active_mm of kthreads Waiman Long
2019-07-29 8:18 ` Qais Yousef
2019-07-29 21:06 ` Waiman Long
2019-07-29 21:33 ` Qais Yousef
2019-07-29 8:52 ` Peter Zijlstra
2019-07-29 14:24 ` [PATCH] sched: Clean up active_mm reference counting Peter Zijlstra
2019-07-29 15:01 ` Mathieu Desnoyers
2019-07-29 15:16 ` Waiman Long
2019-07-29 15:22 ` Peter Zijlstra
2019-07-29 15:29 ` Rik van Riel
2019-07-29 14:27 ` [PATCH v2] sched/core: Don't use dying mm as active_mm of kthreads Peter Zijlstra
2019-07-29 15:22 ` Waiman Long
2019-07-29 15:38 ` Peter Zijlstra [this message]
2019-07-29 14:51 ` Waiman Long
2019-07-29 15:03 ` Peter Zijlstra
2019-07-29 15:28 ` Rik van Riel
2019-07-29 15:44 ` Peter Zijlstra
2019-07-29 16:10 ` Rik van Riel
2019-07-29 16:26 ` Peter Zijlstra
2019-07-29 15:37 ` Waiman Long
2019-07-29 16:12 ` Rik van Riel
2019-07-29 16:22 ` Andy Lutomirski
2019-07-29 9:12 ` Michal Hocko
2019-07-29 15:27 ` Waiman Long
2019-07-29 18:58 ` Michal Hocko
2019-07-29 20:41 ` Waiman Long
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=20190729153825.GI31398@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=longman@redhat.com \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=pauld@redhat.com \
--cc=riel@surriel.com \
--cc=will.deacon@kernel.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).