From: "Radim Krčmář" <rkrcmar@redhat.com>
To: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Cc: pbonzini@redhat.com, joro@8bytes.org, bp@alien8.de,
gleb@kernel.org, alex.williamson@redhat.com, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org, wei@redhat.com,
sherry.hurwitz@amd.com
Subject: Re: [PART1 RFC v2 10/10] svm: Manage vcpu load/unload when enable AVIC
Date: Mon, 14 Mar 2016 17:40:36 +0100 [thread overview]
Message-ID: <20160314164035.GB4120@potion.brq.redhat.com> (raw)
In-Reply-To: <56E6A523.7040701@amd.com>
2016-03-14 18:48+0700, Suravee Suthikulpanit:
> On 03/10/2016 04:46 AM, Radim Krčmář wrote:
>>2016-03-04 14:46-0600, Suravee Suthikulpanit:
>>>From: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
>>>
>>>When a vcpu is loaded/unloaded to a physical core, we need to update
>>>information in the Physical APIC-ID table accordingly.
>>>
>>>Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
>>>---
>>>diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
>>>@@ -1508,6 +1510,146 @@ static int avic_vcpu_init(struct kvm *kvm, struct vcpu_svm *svm, int id)
>>>+static inline int
>>>+avic_update_iommu(struct kvm_vcpu *vcpu, int cpu, phys_addr_t pa, bool r)
>>>+{
>>>+ if (!kvm_arch_has_assigned_device(vcpu->kvm))
>>>+ return 0;
>>>+
>>>+ /* TODO: We will hook up with IOMMU API at later time */
>>
>>(It'd be best to drop avic_update_iommu from this series and introduce
>> it when merging iommu support.)
>>
>
> I just kept it there to make code merging b/w part1 and 2 that I have been
> testing simpler. I didn't think it would cause much confusion. But if you
> think that might be the case, I can drop it for now.
The iommu part might end up having different requirements for this
function, so this husk can only add work when compared to waiting.
And avic_update_iommu is logically separable, so it would be nicer as a
short separate patch anyway. (It's not a problem if you leave it.)
>>>+static int avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu, bool is_load)
>>
>>This function does a lot and there is only one thing that must be done
>>in svm_vcpu_load: change host physical APIC ID if the CPU changed.
>>The rest can be done elsewhere:
>> - is_running when blocking.
>
> I added the logic here to track if the is_running is set when unloading
> since I noticed the case when the vCPU is busy doing some work for the
> guest, then get unloaded and later on get loaded w/o blocking/unblocking.
> So, in theory, it should be be set to running during unloaded period, and it
> should restore this flag if it is loaded again.
(A second mail will be related to this.)
>> - kb_pg_ptr when the pointer changes = only on initialization?
>
> The reason I put this here mainly because it is a convenient place to set
> the vAPIC bakcing page address since we already have to set up the host
> physical APIC id. I guess I can try setting this separately during vcpu
> create. But I don't think it would make much difference.
vcpu_load isn't as hot vcpu_run, but it's still called often and the
most useful optimization is to avoid unnecessary operations ...
(I think the split code is going to be easier to understand as well.)
>> - valid when the kb_pg_ptr is valid = always for existing VCPUs?
>
> According to the programming manual, the valid bit is set when we set the
> host physical APIC ID.
(Physical APIC ID doesn't affect the valid bit at all.)
> However, in theory, the vAPIC backing page address is
> required for AVIC hardware to set bits in IRR register, while the host
> physical APIC ID is needed for sending doorbell to the target physical core.
> So, I would actually interpret the valid bit as it should be set when the
> vAPIC backing address is set.
Yes, APM (rev 3.23, vol 2, table 15-24):
Valid bit. When set, indicates that this entry contains a valid vAPIC
backing page pointer. If cleared, this table entry contains no
information.
> In the current implementation, the valid bit is set during vcpu load, but is
> not unset it when unload. This actually reflect the interpretation of the
> description above.
>
> If we decide to move the setting of vAPIC backing page address to the vcpu
> create phrase, we would set the valid bit at that point as well.
>
> Please let me know if you think differently.
I agree with your analysis and setting the backing page and valid bit on
LAPIC creation seems better to me.
Thanks.
prev parent reply other threads:[~2016-03-14 16:40 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-03-04 20:45 [PART1 RFC v2 00/10] KVM: x86: Introduce SVM AVIC support Suravee Suthikulpanit
2016-03-04 20:45 ` [PART1 RFC v2 01/10] KVM: x86: Misc LAPIC changes to exposes helper functions Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 02/10] KVM: x86: Introducing kvm_x86_ops VCPU blocking/unblocking Suravee Suthikulpanit
2016-03-07 15:42 ` Paolo Bonzini
2016-03-14 6:19 ` Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 03/10] svm: Introduce new AVIC VMCB registers Suravee Suthikulpanit
2016-03-07 15:44 ` Paolo Bonzini
2016-03-14 7:41 ` Suravee Suthikulpanit
2016-03-14 12:25 ` Paolo Bonzini
2016-03-15 12:51 ` Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 04/10] svm: clean up V_TPR, V_IRQ, V_INTR_PRIO, and V_INTR_MASKING Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 05/10] KVM: x86: Detect and Initialize AVIC support Suravee Suthikulpanit
2016-03-07 16:41 ` Paolo Bonzini
2016-03-15 17:09 ` Suravee Suthikulpanit
2016-03-15 17:22 ` Paolo Bonzini
2016-03-16 6:22 ` Suravee Suthikulpanit
2016-03-16 7:20 ` Paolo Bonzini
2016-03-16 8:21 ` Suravee Suthikulpanit
2016-03-16 11:12 ` Paolo Bonzini
2016-03-04 20:46 ` [PART1 RFC v2 06/10] svm: Add interrupt injection via AVIC Suravee Suthikulpanit
2016-03-07 15:36 ` Paolo Bonzini
2016-03-08 21:54 ` Radim Krčmář
2016-03-09 11:10 ` Paolo Bonzini
2016-03-09 16:00 ` Radim Krčmář
2016-03-14 9:41 ` Suravee Suthikulpanit
2016-03-14 12:27 ` Paolo Bonzini
2016-03-14 9:50 ` Suravee Suthikulpanit
2016-03-14 5:25 ` Suravee Suthikulpanit
2016-03-14 8:54 ` Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 07/10] svm: Add VMEXIT handlers for AVIC Suravee Suthikulpanit
2016-03-07 15:58 ` Paolo Bonzini
2016-03-08 22:05 ` Radim Krčmář
2016-03-09 10:56 ` Paolo Bonzini
2016-03-09 20:55 ` Radim Krčmář
2016-03-10 19:34 ` Radim Krčmář
2016-03-10 19:54 ` Paolo Bonzini
2016-03-10 20:44 ` Radim Krčmář
2016-03-17 3:58 ` Suravee Suthikulpanit
2016-03-17 9:35 ` Paolo Bonzini
2016-03-17 19:44 ` Suravee Suthikulpanit
2016-03-17 20:27 ` [PATCH] KVM: split kvm_vcpu_wake_up from kvm_vcpu_kick Radim Krčmář
2016-03-18 5:13 ` Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 08/10] svm: Do not expose x2APIC when enable AVIC Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 09/10] svm: Do not intercept CR8 " Suravee Suthikulpanit
2016-03-07 15:39 ` Paolo Bonzini
2016-03-14 6:09 ` Suravee Suthikulpanit
2016-03-14 12:28 ` Paolo Bonzini
2016-03-04 20:46 ` [PART1 RFC v2 10/10] svm: Manage vcpu load/unload " Suravee Suthikulpanit
2016-03-09 21:46 ` Radim Krčmář
2016-03-10 14:01 ` Radim Krčmář
2016-03-14 11:58 ` Suravee Suthikulpanit
2016-03-14 16:54 ` Radim Krčmář
2016-03-14 11:48 ` Suravee Suthikulpanit
2016-03-14 16:40 ` Radim Krčmář [this message]
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=20160314164035.GB4120@potion.brq.redhat.com \
--to=rkrcmar@redhat.com \
--cc=Suravee.Suthikulpanit@amd.com \
--cc=alex.williamson@redhat.com \
--cc=bp@alien8.de \
--cc=gleb@kernel.org \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=sherry.hurwitz@amd.com \
--cc=wei@redhat.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).