From: Avi Kivity <avi@redhat.com>
To: Peter Maydell <peter.maydell@linaro.org>
Cc: Christoffer Dall <c.dall@virtualopensystems.com>,
tech@virtualopensystems.com, kvm@vger.kernel.org,
android-virt@lists.cs.columbia.edu
Subject: Re: [Android-virt] [PATCH v9 16/16] ARM: KVM: Guest wait-for-interrupts (WFI) support
Date: Tue, 03 Jul 2012 18:57:13 +0300 [thread overview]
Message-ID: <4FF31659.40908@redhat.com> (raw)
In-Reply-To: <CAFEAcA_vDbvMom+A3Gb8ZnYJMT8DianrUoSWtHmx7C+y+6Cqpw@mail.gmail.com>
On 07/03/2012 04:49 PM, Peter Maydell wrote:
> On 3 July 2012 14:24, Avi Kivity <avi@redhat.com> wrote:
>> On 07/03/2012 04:14 PM, Peter Maydell wrote:
>>> You could just always wake the cpu when migrating: the
>>> architecture allows WFI to return early for any reason
>>> it likes including implementation convenience.
>>
>> Seems reasonable.
>>
>> I imagine wfi works with interrupts disabled, unlike the x86 silliness?
>
> Not sure exactly which bit of x86 silliness you're referring
> to, but WFI will wake up regardless of the interrupt mask
> bits in the CPSR. (If you've disabled interrupts in the GIC
> that's your own bad lookout I guess.)
On x86 HLT respects the interrupt enable flag, so to avoid races, you
have to use a feature of STI (enable interrupts instruction) that only
enables interrupts after another instruction has executed. So the
sequence STI; HLT atomically enables interrupts and waits for one (as
long as HLT didn't trigger an exception like a page fault).
The problem is that this "interrupt shadow" has to be tracked by
virtualization hardware, live migration, instruction emulation, etc. It
interacts with non-maskable interrupts as well. A horrible hack.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2012-07-03 15:57 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-07-03 8:59 [PATCH v9 00/16] KVM/ARM Implementation Christoffer Dall
2012-07-03 8:59 ` [PATCH v9 01/16] ARM: add mem_type prot_pte accessor Christoffer Dall
2012-07-20 14:54 ` Andreas Färber
2012-07-26 21:26 ` Christoffer Dall
2012-07-03 8:59 ` [PATCH v9 02/16] ARM: Add config option ARM_VIRT_EXT Christoffer Dall
2012-07-03 8:59 ` [PATCH v9 03/16] ARM: Section based HYP idmap Christoffer Dall
2012-07-03 8:59 ` [PATCH v9 04/16] KVM: Move KVM_IRQ_LINE to arch-generic code Christoffer Dall
2012-07-03 19:50 ` Marcelo Tosatti
2012-07-24 12:37 ` Christoffer Dall
2012-07-03 9:00 ` [PATCH v9 05/16] KVM: Guard mmu_notifier specific code with CONFIG_MMU_NOTIFIER Christoffer Dall
2012-07-03 9:00 ` [PATCH v9 06/16] ARM: KVM: Initial skeleton to compile KVM support Christoffer Dall
2012-07-03 9:00 ` [PATCH v9 07/16] ARM: KVM: Support Cortex-A15 VCPUs reset Christoffer Dall
2012-07-03 9:00 ` [PATCH v9 08/16] ARM: KVM: Hypervisor inititalization Christoffer Dall
2012-07-03 9:00 ` [PATCH v9 09/16] ARM: KVM: Module unloading support Christoffer Dall
2012-07-03 9:01 ` [PATCH v9 10/16] ARM: KVM: Memory virtualization setup Christoffer Dall
2012-07-03 9:01 ` [PATCH v9 11/16] ARM: KVM: Inject IRQs and FIQs from userspace Christoffer Dall
2012-08-06 17:20 ` [Android-virt] " Peter Maydell
2012-08-07 13:59 ` Avi Kivity
2012-08-07 14:12 ` Peter Maydell
2012-08-07 14:28 ` Avi Kivity
2012-08-07 14:36 ` Peter Maydell
2012-07-03 9:01 ` [PATCH v9 12/16] ARM: KVM: World-switch implementation Christoffer Dall
2012-07-03 10:07 ` Avi Kivity
2012-07-25 14:16 ` Christoffer Dall
2012-07-03 9:01 ` [PATCH v9 13/16] ARM: KVM: Emulation framework and CP15 emulation Christoffer Dall
2012-07-12 5:35 ` 김민규
2012-07-16 14:09 ` Christoffer Dall
2012-07-17 10:54 ` Min-gyu Kim
2012-07-03 9:01 ` [PATCH v9 14/16] ARM: KVM: Handle guest faults in KVM Christoffer Dall
2012-07-03 9:02 ` [PATCH v9 15/16] ARM: KVM: Handle I/O aborts Christoffer Dall
2012-07-03 9:02 ` [PATCH v9 16/16] ARM: KVM: Guest wait-for-interrupts (WFI) support Christoffer Dall
2012-07-03 13:10 ` Avi Kivity
2012-07-03 13:14 ` [Android-virt] " Peter Maydell
2012-07-03 13:24 ` Avi Kivity
2012-07-03 13:49 ` Peter Maydell
2012-07-03 15:57 ` Avi Kivity [this message]
2012-07-26 21:08 ` Christoffer Dall
2012-07-03 13:29 ` [PATCH v9 00/16] KVM/ARM Implementation Avi Kivity
2012-07-03 13:51 ` [Android-virt] " Peter Maydell
2012-07-26 21:15 ` Christoffer Dall
2012-07-26 21:21 ` Peter Maydell
2012-07-26 21:25 ` Christoffer Dall
2012-07-03 19:51 ` Marcelo Tosatti
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=4FF31659.40908@redhat.com \
--to=avi@redhat.com \
--cc=android-virt@lists.cs.columbia.edu \
--cc=c.dall@virtualopensystems.com \
--cc=kvm@vger.kernel.org \
--cc=peter.maydell@linaro.org \
--cc=tech@virtualopensystems.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).