From: Dietmar Eggemann <dietmar.eggemann@arm.com>
To: Will Deacon <will@kernel.org>, Juri Lelli <juri.lelli@redhat.com>
Cc: Quentin Perret <qperret@google.com>,
Daniel Bristot de Oliveira <bristot@redhat.com>,
linux-arm-kernel@lists.infradead.org, linux-arch@vger.kernel.org,
linux-kernel@vger.kernel.org,
Catalin Marinas <catalin.marinas@arm.com>,
Marc Zyngier <maz@kernel.org>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Peter Zijlstra <peterz@infradead.org>,
Morten Rasmussen <morten.rasmussen@arm.com>,
Qais Yousef <qais.yousef@arm.com>,
Suren Baghdasaryan <surenb@google.com>, Tejun Heo <tj@kernel.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Ingo Molnar <mingo@redhat.com>,
Vincent Guittot <vincent.guittot@linaro.org>,
"Rafael J. Wysocki" <rjw@rjwysocki.net>,
kernel-team@android.com
Subject: Re: [PATCH v6 13/21] sched: Admit forcefully-affined tasks into SCHED_DEADLINE
Date: Fri, 21 May 2021 13:23:55 +0200 [thread overview]
Message-ID: <3620bad5-2a27-0f9e-f1f0-70036997d33c@arm.com> (raw)
In-Reply-To: <20210521103724.GA11680@willie-the-truck>
On 21/05/2021 12:37, Will Deacon wrote:
> On Fri, May 21, 2021 at 10:39:32AM +0200, Juri Lelli wrote:
>> On 21/05/21 08:15, Quentin Perret wrote:
>>> On Friday 21 May 2021 at 07:25:51 (+0200), Juri Lelli wrote:
>>>> On 20/05/21 19:01, Will Deacon wrote:
>>>>> On Thu, May 20, 2021 at 02:38:55PM +0200, Daniel Bristot de Oliveira wrote:
>>>>>> On 5/20/21 12:33 PM, Quentin Perret wrote:
>>>>>>> On Thursday 20 May 2021 at 11:16:41 (+0100), Will Deacon wrote:
>>>>>>>> Ok, thanks for the insight. In which case, I'll go with what we discussed:
>>>>>>>> require admission control to be disabled for sched_setattr() but allow
>>>>>>>> execve() to a 32-bit task from a 64-bit deadline task with a warning (this
>>>>>>>> is probably similar to CPU hotplug?).
>>>>>>>
>>>>>>> Still not sure that we can let execve go through ... It will break AC
>>>>>>> all the same, so it should probably fail as well if AC is on IMO
>>>>>>>
>>>>>>
>>>>>> If the cpumask of the 32-bit task is != of the 64-bit task that is executing it,
>>>>>> the admission control needs to be re-executed, and it could fail. So I see this
>>>>>> operation equivalent to sched_setaffinity(). This will likely be true for future
>>>>>> schedulers that will allow arbitrary affinities (AC should run on affinity
>>>>>> change, and could fail).
>>>>>>
>>>>>> I would vote with Juri: "I'd go with fail hard if AC is on, let it
>>>>>> pass if AC is off (supposedly the user knows what to do)," (also hope nobody
>>>>>> complains until we add better support for affinity, and use this as a motivation
>>>>>> to get back on this front).
>>>>>
>>>>> I can have a go at implementing it, but I don't think it's a great solution
>>>>> and here's why:
>>>>>
>>>>> Failing an execve() is _very_ likely to be fatal to the application. It's
>>>>> also very likely that the task calling execve() doesn't know whether the
>>>>> program it's trying to execute is 32-bit or not. Consequently, if we go
>>>>> with failing execve() then all that will happen is that people will disable
>>>>> admission control altogether.
>>>
>>> Right, but only on these dumb 32bit asymmetric systems, and only if we
>>> care about running 32bits deadline tasks -- which I seriously doubt for
>>> the Android use-case.
>>>
>>> Note that running deadline tasks is also a privileged operation, it
>>> can't be done by random apps.
>>>
>>>>> That has a negative impact on "pure" 64-bit
>>>>> applications and so I think we end up with the tail wagging the dog because
>>>>> admission control will be disabled for everybody just because there is a
>>>>> handful of 32-bit programs which may get executed. I understand that it
>>>>> also means that RT throttling would be disabled.
>>>>
>>>> Completely understand your perplexity. But how can the kernel still give
>>>> guarantees to "pure" 64-bit applications if there are 32-bit
>>>> applications around that essentially broke admission control when they
>>>> were restricted to a subset of cores?
>>>>
>>>>> Allowing the execve() to continue with a warning is very similar to the
>>>>> case in which all the 64-bit CPUs are hot-unplugged at the point of
>>>>> execve(), and this is much closer to the illusion that this patch series
>>>>> intends to provide.
>>>>
>>>> So, for hotplug we currently have a check that would make hotplug
>>>> operations fail if removing a CPU would mean not enough bandwidth to run
>>>> the currently admitted set of DEADLINE tasks.
>>>
>>> Aha, wasn't aware. Any pointers to that check for my education?
>>
>> Hotplug ends up calling dl_cpu_busy() (after the cpu being hotplugged out
>> got removed), IIRC. So, if that fails the operation in undone.
>
> Interesting, thanks. Thinking about this some more, it strikes me that with
> these silly asymmetric systems there could be an interesting additional
> problem with hotplug and deadline tasks. Imagine the following sequence of
> events:
>
> 1. All online CPUs are 32-bit-capable
> 2. sched_setattr() admits a 32-bit deadline task
> 3. A 64-bit-only CPU is onlined
> 4. Some of the 32-bit-capable CPUs are offlined
>
> I wonder if we can get into a situation where we think we have enough
> bandwidth available, but in reality the 32-bit task is in trouble because
> it can't make use of the 64-bit-only CPU.
>
> If so, then it seems to me that admission control is really just
> "best-effort" for 32-bit deadline tasks on these systems because it's based
> on a snapshot in time of the available resources.
IMHO DL AC is per root domain (rd). So if we have e.g. an 8 CPU system
with aarch32_el0 eq. [0-3] then we would need 2 exclusive cpusets ([0-3]
and [4-7]) to admit 32-bit DL tasks into [0-3] (i.e. to pass the `if
(!cpumask_subset(span, p->cpus_ptr) ...` test in __sched_setscheduler().
Trying to admit too many 32-bit DL tasks or trying to hp out a CPU[0-3]
would lead to `Device or resource busy` in case the rd bw wouldn't be
sufficient anymore for the set of admitted tasks. But the [0-3] DL AC
wouldn't care about hp on CPU[4-7].
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2021-05-21 11:27 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-18 9:47 [PATCH v6 00/21] Add support for 32-bit tasks on asymmetric AArch32 systems Will Deacon
2021-05-18 9:47 ` [PATCH v6 01/21] arm64: cpuinfo: Split AArch32 registers out into a separate struct Will Deacon
2021-05-21 10:47 ` Catalin Marinas
2021-05-18 9:47 ` [PATCH v6 02/21] arm64: Allow mismatched 32-bit EL0 support Will Deacon
2021-05-21 10:25 ` Catalin Marinas
2021-05-24 12:05 ` Will Deacon
2021-05-24 13:49 ` Catalin Marinas
2021-05-21 10:41 ` Catalin Marinas
2021-05-24 12:09 ` Will Deacon
2021-05-24 13:46 ` Catalin Marinas
2021-05-21 15:22 ` Qais Yousef
2021-05-24 20:21 ` Will Deacon
2021-05-18 9:47 ` [PATCH v6 03/21] KVM: arm64: Kill 32-bit vCPUs on systems with mismatched " Will Deacon
2021-05-21 10:47 ` Catalin Marinas
2021-05-18 9:47 ` [PATCH v6 04/21] arm64: Kill 32-bit applications scheduled on 64-bit-only CPUs Will Deacon
2021-05-21 10:55 ` Catalin Marinas
2021-05-18 9:47 ` [PATCH v6 05/21] arm64: Advertise CPUs capable of running 32-bit applications in sysfs Will Deacon
2021-05-21 11:00 ` Catalin Marinas
2021-05-18 9:47 ` [PATCH v6 06/21] sched: Introduce task_cpu_possible_mask() to limit fallback rq selection Will Deacon
2021-05-21 16:03 ` Peter Zijlstra
2021-05-24 12:17 ` Will Deacon
2021-05-18 9:47 ` [PATCH v6 07/21] cpuset: Don't use the cpu_possible_mask as a last resort for cgroup v1 Will Deacon
2021-05-21 17:39 ` Qais Yousef
2021-05-24 20:21 ` Will Deacon
2021-05-18 9:47 ` [PATCH v6 08/21] cpuset: Honour task_cpu_possible_mask() in guarantee_online_cpus() Will Deacon
2021-05-21 16:25 ` Qais Yousef
2021-05-24 21:09 ` Will Deacon
2021-05-18 9:47 ` [PATCH v6 09/21] sched: Reject CPU affinity changes based on task_cpu_possible_mask() Will Deacon
2021-05-18 9:47 ` [PATCH v6 10/21] sched: Introduce task_struct::user_cpus_ptr to track requested affinity Will Deacon
2021-05-18 9:47 ` [PATCH v6 11/21] sched: Split the guts of sched_setaffinity() into a helper function Will Deacon
2021-05-21 16:41 ` Qais Yousef
2021-05-24 21:16 ` Will Deacon
2021-05-18 9:47 ` [PATCH v6 12/21] sched: Allow task CPU affinity to be restricted on asymmetric systems Will Deacon
2021-05-21 17:11 ` Qais Yousef
2021-05-24 21:43 ` Will Deacon
2021-05-18 9:47 ` [PATCH v6 13/21] sched: Admit forcefully-affined tasks into SCHED_DEADLINE Will Deacon
2021-05-18 10:20 ` Quentin Perret
2021-05-18 10:28 ` Will Deacon
2021-05-18 10:48 ` Quentin Perret
2021-05-18 10:59 ` Will Deacon
2021-05-18 13:19 ` Quentin Perret
2021-05-20 9:13 ` Juri Lelli
2021-05-20 10:16 ` Will Deacon
2021-05-20 10:33 ` Quentin Perret
2021-05-20 12:38 ` Juri Lelli
2021-05-20 12:38 ` Daniel Bristot de Oliveira
2021-05-20 15:06 ` Dietmar Eggemann
2021-05-20 16:00 ` Daniel Bristot de Oliveira
2021-05-20 17:55 ` Dietmar Eggemann
2021-05-20 18:03 ` Will Deacon
2021-05-21 11:26 ` Dietmar Eggemann
2021-05-20 18:01 ` Will Deacon
2021-05-21 5:25 ` Juri Lelli
2021-05-21 8:15 ` Quentin Perret
2021-05-21 8:39 ` Juri Lelli
2021-05-21 10:37 ` Will Deacon
2021-05-21 11:23 ` Dietmar Eggemann [this message]
2021-05-21 13:02 ` Quentin Perret
2021-05-21 14:04 ` Juri Lelli
2021-05-21 17:47 ` Dietmar Eggemann
2021-05-21 13:00 ` Daniel Bristot de Oliveira
2021-05-21 13:12 ` Quentin Perret
2021-05-24 20:47 ` Will Deacon
2021-05-18 9:47 ` [PATCH v6 14/21] freezer: Add frozen_or_skipped() helper function Will Deacon
2021-05-18 9:47 ` [PATCH v6 15/21] sched: Defer wakeup in ttwu() for unschedulable frozen tasks Will Deacon
2021-05-18 9:47 ` [PATCH v6 16/21] arm64: Implement task_cpu_possible_mask() Will Deacon
2021-05-24 14:57 ` Catalin Marinas
2021-05-18 9:47 ` [PATCH v6 17/21] arm64: exec: Adjust affinity for compat tasks with mismatched 32-bit EL0 Will Deacon
2021-05-24 15:02 ` Catalin Marinas
2021-05-18 9:47 ` [PATCH v6 18/21] arm64: Prevent offlining first CPU with 32-bit EL0 on mismatched system Will Deacon
2021-05-24 15:46 ` Catalin Marinas
2021-05-24 20:32 ` Will Deacon
2021-05-25 9:43 ` Catalin Marinas
2021-05-18 9:47 ` [PATCH v6 19/21] arm64: Hook up cmdline parameter to allow mismatched 32-bit EL0 Will Deacon
2021-05-24 15:47 ` Catalin Marinas
2021-05-18 9:47 ` [PATCH v6 20/21] arm64: Remove logic to kill 32-bit tasks on 64-bit-only cores Will Deacon
2021-05-24 15:47 ` Catalin Marinas
2021-05-18 9:47 ` [PATCH v6 21/21] Documentation: arm64: describe asymmetric 32-bit support Will Deacon
2021-05-21 17:37 ` Qais Yousef
2021-05-24 21:46 ` Will Deacon
2021-05-24 16:22 ` Catalin Marinas
2021-05-21 17:45 ` [PATCH v6 00/21] Add support for 32-bit tasks on asymmetric AArch32 systems Qais Yousef
2021-05-24 22:08 ` Will Deacon
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=3620bad5-2a27-0f9e-f1f0-70036997d33c@arm.com \
--to=dietmar.eggemann@arm.com \
--cc=bristot@redhat.com \
--cc=catalin.marinas@arm.com \
--cc=gregkh@linuxfoundation.org \
--cc=hannes@cmpxchg.org \
--cc=juri.lelli@redhat.com \
--cc=kernel-team@android.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=maz@kernel.org \
--cc=mingo@redhat.com \
--cc=morten.rasmussen@arm.com \
--cc=peterz@infradead.org \
--cc=qais.yousef@arm.com \
--cc=qperret@google.com \
--cc=rjw@rjwysocki.net \
--cc=surenb@google.com \
--cc=tj@kernel.org \
--cc=vincent.guittot@linaro.org \
--cc=will@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).