From: marc.zyngier@arm.com (Marc Zyngier)
To: linux-arm-kernel@lists.infradead.org
Subject: [kvmarm] [PATCH 10/15] KVM: ARM: World-switch implementation
Date: Tue, 25 Sep 2012 19:42:21 +0200 [thread overview]
Message-ID: <2f4c4963f36aabf6e5f48ad42bf145f2@localhost> (raw)
In-Reply-To: <CAFEAcA-69tmRdZkZ9dsSk9ck-AC7tKmYvxyxGGVA6ocKDRB25A@mail.gmail.com>
On Tue, 25 Sep 2012 18:15:50 +0100, Peter Maydell
<peter.maydell@linaro.org> wrote:
> On 25 September 2012 18:00, Will Deacon <will.deacon@arm.com> wrote:
>> On Sat, Sep 15, 2012 at 04:35:33PM +0100, Christoffer Dall wrote:
>>> ENTRY(__kvm_tlb_flush_vmid)
>>> + hvc #0 @ Switch to Hyp mode
>>> + push {r2, r3}
>>> +
>>> + add r0, r0, #KVM_VTTBR
>>> + ldrd r2, r3, [r0]
>>> + mcrr p15, 6, r2, r3, c2 @ Write VTTBR
>>> + isb
>>> + mcr p15, 0, r0, c8, c3, 0 @ TLBIALLIS (rt ignored)
>>> + dsb
>>> + isb
>>> + mov r2, #0
>>> + mov r3, #0
>>> + mcrr p15, 6, r2, r3, c2 @ Back to VMID #0
>>> + isb
>>
>> Do you need this isb, given that you're about to do an hvc?
>>
>>> + pop {r2, r3}
>>> + hvc #0 @ Back to SVC
>>> bx lr
>
> ...you probably don't want to do the memory accesses involved
> in the 'pop' under the wrong VMID ?
Well, we're still in HYP mode when performing the pop, so the VMID is
pretty much irrelevant. Same for the initial push, actually. As long as
we're sure VTTBR has been updated when we do the exception return, I think
we're safe.
M.
--
Fast, cheap, reliable. Pick two.
next prev parent reply other threads:[~2012-09-25 17:42 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-09-15 15:34 [PATCH 00/15] KVM/ARM Implementation Christoffer Dall
2012-09-15 15:34 ` [PATCH 01/15] ARM: add mem_type prot_pte accessor Christoffer Dall
2012-09-18 12:23 ` Will Deacon
2012-09-18 19:18 ` Christoffer Dall
2012-09-18 21:04 ` Russell King - ARM Linux
2012-09-18 21:53 ` Christoffer Dall
2012-09-20 10:01 ` Marc Zyngier
2012-09-20 13:21 ` Christoffer Dall
2012-09-15 15:34 ` [PATCH 02/15] ARM: Add page table and page defines needed by KVM Christoffer Dall
2012-09-18 12:47 ` Will Deacon
2012-09-18 14:06 ` Catalin Marinas
2012-09-18 15:05 ` Christoffer Dall
2012-09-18 15:07 ` Catalin Marinas
2012-09-18 15:10 ` Christoffer Dall
2012-09-18 22:01 ` Christoffer Dall
2012-09-19 9:21 ` Will Deacon
2012-09-20 0:10 ` Christoffer Dall
2012-09-15 15:34 ` [PATCH 03/15] ARM: Section based HYP idmap Christoffer Dall
2012-09-18 13:00 ` Will Deacon
2012-10-01 2:19 ` Christoffer Dall
2012-09-15 15:34 ` [PATCH 04/15] ARM: idmap: only initialize HYP idmap when HYP mode is available Christoffer Dall
2012-09-18 13:03 ` Will Deacon
2012-09-20 0:11 ` Christoffer Dall
2012-09-15 15:35 ` [PATCH 05/15] ARM: Expose PMNC bitfields for KVM use Christoffer Dall
2012-09-18 13:08 ` Will Deacon
2012-09-18 22:13 ` Christoffer Dall
2012-09-19 4:09 ` [kvmarm] " Rusty Russell
2012-09-19 9:30 ` Will Deacon
2012-09-15 15:35 ` [PATCH 06/15] KVM: ARM: Initial skeleton to compile KVM support Christoffer Dall
2012-09-25 15:20 ` Will Deacon
2012-09-26 1:43 ` Christoffer Dall
2012-09-27 14:13 ` Will Deacon
2012-09-27 14:39 ` Marc Zyngier
2012-09-27 14:45 ` [kvmarm] " Peter Maydell
2012-09-27 15:20 ` Will Deacon
2012-09-30 19:21 ` Christoffer Dall
2012-10-01 13:03 ` [kvmarm] " Marc Zyngier
2012-10-04 13:02 ` Min-gyu Kim
2012-10-04 13:35 ` Christoffer Dall
2012-10-05 6:28 ` Rusty Russell
2012-10-04 13:44 ` [kvmarm] " Avi Kivity
2012-09-15 15:35 ` [PATCH 07/15] KVM: ARM: Hypervisor inititalization Christoffer Dall
2012-09-15 15:35 ` [PATCH 08/15] KVM: ARM: Memory virtualization setup Christoffer Dall
2012-09-15 15:35 ` [PATCH 09/15] KVM: ARM: Inject IRQs and FIQs from userspace Christoffer Dall
2012-09-25 15:55 ` Will Deacon
2012-09-29 15:50 ` Christoffer Dall
2012-09-30 12:48 ` Will Deacon
2012-09-30 14:34 ` Christoffer Dall
2012-09-15 15:35 ` [PATCH 10/15] KVM: ARM: World-switch implementation Christoffer Dall
2012-09-25 17:00 ` Will Deacon
2012-09-25 17:15 ` [kvmarm] " Peter Maydell
2012-09-25 17:42 ` Marc Zyngier [this message]
2012-09-30 0:33 ` Christoffer Dall
2012-09-30 9:48 ` Peter Maydell
2012-09-30 14:31 ` Christoffer Dall
2012-09-30 17:47 ` Christoffer Dall
2012-09-15 15:35 ` [PATCH 11/15] KVM: ARM: Emulation framework and CP15 emulation Christoffer Dall
2012-09-15 15:35 ` [PATCH 12/15] KVM: ARM: User space API for getting/setting co-proc registers Christoffer Dall
2012-09-15 15:35 ` [PATCH 13/15] KVM: ARM: Handle guest faults in KVM Christoffer Dall
2012-09-25 11:11 ` Min-gyu Kim
2012-09-25 12:38 ` Christoffer Dall
2012-09-27 3:11 ` Min-gyu Kim
2012-09-27 5:35 ` Christoffer Dall
2012-09-27 15:26 ` [kvmarm] " Marc Zyngier
2012-09-27 12:39 ` Catalin Marinas
2012-09-27 17:15 ` Christoffer Dall
2012-09-27 17:21 ` Catalin Marinas
2012-09-15 15:35 ` [PATCH 14/15] KVM: ARM: Handle I/O aborts Christoffer Dall
2012-09-27 15:11 ` Will Deacon
2012-09-30 21:49 ` Christoffer Dall
2012-10-01 12:53 ` Dave Martin
2012-10-01 15:12 ` Jon Medhurst (Tixy)
2012-10-01 16:07 ` Dave Martin
2012-10-05 9:00 ` Russell King - ARM Linux
2012-10-08 10:04 ` Dave Martin
2012-10-08 21:52 ` Christoffer Dall
2012-09-15 15:36 ` [PATCH 15/15] KVM: ARM: Guest wait-for-interrupts (WFI) support Christoffer Dall
2012-09-25 17:04 ` Will Deacon
2012-09-29 23:00 ` Christoffer Dall
2012-09-18 12:21 ` [PATCH 00/15] KVM/ARM Implementation Will Deacon
2012-09-18 12:32 ` Christoffer Dall
2012-09-19 12:44 ` Avi Kivity
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=2f4c4963f36aabf6e5f48ad42bf145f2@localhost \
--to=marc.zyngier@arm.com \
--cc=linux-arm-kernel@lists.infradead.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).