Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Mon, 29 Jul 2019 17:38:25 +0200
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
Message-ID: <20190729153825.GI31398@hirez.programming.kicks-ass.net>
References: <20190727171047.31610-1-longman@redhat.com>
 <20190729085235.GT31381@hirez.programming.kicks-ass.net>
 <20190729142756.GF31425@hirez.programming.kicks-ass.net>
 <2bc722b9-3eff-6d99-4ee7-1f4cab8b6c21@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <2bc722b9-3eff-6d99-4ee7-1f4cab8b6c21@redhat.com>
User-Agent: Mutt/1.10.1 (2018-07-13)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

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.