From: Marc Zyngier <maz@kernel.org>
To: Zenghui Yu <yuzenghui@huawei.com>
Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>,
Jason Cooper <jason@lakedaemon.net>,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Robert Richter <rrichter@marvell.com>,
Thomas Gleixner <tglx@linutronix.de>,
kvmarm@lists.cs.columbia.edu,
linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH v4 08/20] irqchip/gic-v4.1: Plumb get/set_irqchip_state SGI callbacks
Date: Mon, 02 Mar 2020 12:09:33 +0000 [thread overview]
Message-ID: <db819547d4be8daa458bcd56aac2efcd@kernel.org> (raw)
In-Reply-To: <4f8f3958-2976-b0a7-8d17-440ecaba0fc8@huawei.com>
Hi Zenghui,
On 2020-03-02 08:18, Zenghui Yu wrote:
> On 2020/3/2 3:00, Marc Zyngier wrote:
>> On 2020-02-28 19:37, Marc Zyngier wrote:
>>> On 2020-02-20 03:11, Zenghui Yu wrote:
>>
>>>> Do we really need to grab the vpe_lock for those which are belong to
>>>> the same irqchip with its_vpe_set_affinity()? The IRQ core code
>>>> should
>>>> already ensure the mutual exclusion among them, wrong?
>>>
>>> I've been trying to think about that, but jet-lag keeps getting in
>>> the way.
>>> I empirically think that you are right, but I need to go and check
>>> the various
>>> code paths to be sure. Hopefully I'll have a bit more brain space
>>> next week.
>>
>> So I slept on it and came back to my senses. The only case we actually
>> need
>> to deal with is when an affinity change impacts *another* interrupt.
>>
>> There is only two instances of this issue:
>>
>> - vLPIs have their *physical* affinity impacted by the affinity of the
>> vPE. Their virtual affinity is of course unchanged, but the
>> physical
>> one becomes important with direct invalidation. Taking a per-VPE
>> lock
>> in such context should address the issue.
>>
>> - vSGIs have the exact same issue, plus the matter of requiring some
>> *extra* one when reading the pending state, which requires a RMW
>> on two different registers. This requires an extra per-RD lock.
>
> Agreed with both!
>
>>
>> My original patch was stupidly complex, and the irq_desc lock is
>> perfectly enough to deal with anything that only affects the interrupt
>> state itself.
>>
>> GICv4 + direct invalidation for vLPIs breaks this by bypassing the
>> serialization initially provided by the ITS, as the RD is completely
>> out of band. The per-vPE lock brings back this serialization.
>>
>> I've updated the branch, which seems to run OK on D05. I still need
>> to run the usual tests on the FVP model though.
>
> I have pulled the latest branch and it looks good to me, except for
> one remaining concern:
>
> GICR_INV{LPI, ALL}R + GICR_SYNCR can also be accessed concurrently
> by multiple direct invalidation, should we also use the per-RD lock
> to ensure mutual exclusion? It looks not so harmful though, as this
> will only increase one's polling time against the Busy bit (in my
> view).
>
> But I point it out again for confirmation.
I was about to say that it doesn't really matter because it is only a
performance optimisation (and we're noty quite there yet), until I
spotted
this great nugget in the spec:
<quote>
Writing GICR_INVLPIR or GICR_INVALLR when GICR_SYNCR.Busy==1 is
CONSTRAINED
UNPREDICTABLE:
- The write is IGNORED .
- The invalidate specified by the write is performed.
</quote>
So we really need some form of mutual exclusion on a per-RD basis to
ensure
that no two invalidations occur at the same time, ensuring that Busy
clears
between the two.
Thanks for the heads up,
M.
--
Jazz is not dead. It just smells funny...
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
next prev parent reply other threads:[~2020-03-02 12:09 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-14 14:57 [PATCH v4 00/20] irqchip/gic-v4: GICv4.1 architecture support Marc Zyngier
2020-02-14 14:57 ` [PATCH v4 01/20] irqchip/gic-v4.1: Skip absent CPUs while iterating over redistributors Marc Zyngier
2020-02-17 9:11 ` Zenghui Yu
2020-02-14 14:57 ` [PATCH v4 02/20] irqchip/gic-v3: Use SGIs without active state if offered Marc Zyngier
2020-02-17 9:18 ` Zenghui Yu
2020-02-14 14:57 ` [PATCH v4 03/20] irqchip/gic-v4.1: Advertise support v4.1 to KVM Marc Zyngier
2020-02-17 9:09 ` Zenghui Yu
2020-02-14 14:57 ` [PATCH v4 04/20] irqchip/gic-v4.1: Map the ITS SGIR register page Marc Zyngier
2020-02-20 3:17 ` Zenghui Yu
2020-02-14 14:57 ` [PATCH v4 05/20] irqchip/gic-v4.1: Plumb skeletal VSGI irqchip Marc Zyngier
2020-02-20 3:21 ` Zenghui Yu
2020-02-14 14:57 ` [PATCH v4 06/20] irqchip/gic-v4.1: Add initial SGI configuration Marc Zyngier
2020-02-18 7:25 ` Zenghui Yu
2020-02-18 9:46 ` Marc Zyngier
2020-02-20 3:25 ` Zenghui Yu
2020-02-14 14:57 ` [PATCH v4 07/20] irqchip/gic-v4.1: Plumb mask/unmask SGI callbacks Marc Zyngier
2020-02-20 3:32 ` Zenghui Yu
2020-02-14 14:57 ` [PATCH v4 08/20] irqchip/gic-v4.1: Plumb get/set_irqchip_state " Marc Zyngier
2020-02-18 7:00 ` Zenghui Yu
2020-02-18 9:27 ` Marc Zyngier
2020-02-18 15:31 ` Marc Zyngier
2020-02-19 11:50 ` Zenghui Yu
2020-02-19 15:18 ` Zenghui Yu
2020-02-20 3:11 ` Zenghui Yu
2020-02-28 19:37 ` Marc Zyngier
2020-03-01 19:00 ` Marc Zyngier
2020-03-02 8:18 ` Zenghui Yu
2020-03-02 12:09 ` Marc Zyngier [this message]
2020-03-02 14:21 ` Bill Barrow
2020-02-14 14:57 ` [PATCH v4 09/20] irqchip/gic-v4.1: Plumb set_vcpu_affinity " Marc Zyngier
2020-02-20 3:37 ` Zenghui Yu
2020-02-28 19:00 ` Marc Zyngier
2020-02-14 14:57 ` [PATCH v4 10/20] irqchip/gic-v4.1: Move doorbell management to the GICv4 abstraction layer Marc Zyngier
2020-02-14 14:57 ` [PATCH v4 11/20] irqchip/gic-v4.1: Add VSGI allocation/teardown Marc Zyngier
2020-02-14 14:57 ` [PATCH v4 12/20] irqchip/gic-v4.1: Add VSGI property setup Marc Zyngier
2020-02-14 14:57 ` [PATCH v4 13/20] irqchip/gic-v4.1: Eagerly vmap vPEs Marc Zyngier
2020-02-14 14:57 ` [PATCH v4 14/20] KVM: arm64: GICv4.1: Let doorbells be auto-enabled Marc Zyngier
2020-02-14 14:57 ` [PATCH v4 15/20] KVM: arm64: GICv4.1: Add direct injection capability to SGI registers Marc Zyngier
2020-02-18 8:46 ` Zenghui Yu
2020-02-18 9:41 ` Marc Zyngier
2020-02-14 14:57 ` [PATCH v4 16/20] KVM: arm64: GICv4.1: Allow SGIs to switch between HW and SW interrupts Marc Zyngier
2020-02-20 3:55 ` Zenghui Yu
2020-02-28 19:16 ` Marc Zyngier
2020-03-02 2:40 ` Zenghui Yu
2020-02-14 14:57 ` [PATCH v4 17/20] KVM: arm64: GICv4.1: Plumb SGI implementation selection in the distributor Marc Zyngier
2020-02-14 14:57 ` [PATCH v4 18/20] KVM: arm64: GICv4.1: Reload VLPI configuration on distributor enable/disable Marc Zyngier
2020-02-14 14:57 ` [PATCH v4 19/20] KVM: arm64: GICv4.1: Allow non-trapping WFI when using HW SGIs Marc Zyngier
2020-02-14 14:57 ` [PATCH v4 20/20] KVM: arm64: GICv4.1: Expose HW-based SGIs in debugfs Marc Zyngier
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=db819547d4be8daa458bcd56aac2efcd@kernel.org \
--to=maz@kernel.org \
--cc=jason@lakedaemon.net \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lorenzo.pieralisi@arm.com \
--cc=rrichter@marvell.com \
--cc=tglx@linutronix.de \
--cc=yuzenghui@huawei.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;
as well as URLs for NNTP newsgroup(s).