archive mirror
 help / color / mirror / Atom feed
From: Joao Martins <>
To: Paolo Bonzini <>
	"Radim Krčmář" <>,
	"Sean Christopherson" <>,
	"Vitaly Kuznetsov" <>,
	"Wanpeng Li" <>,
	"Jim Mattson" <>,
	"Joerg Roedel" <>,
	"Liran Alon" <>,
	"Jag Raman" <>
Subject: Re: [PATCH v1 2/3] KVM: VMX: Do not change PID.NDST when loading a blocked vCPU
Date: Mon, 11 Nov 2019 14:48:44 +0000	[thread overview]
Message-ID: <> (raw)
In-Reply-To: <>

On 11/11/19 2:39 PM, Paolo Bonzini wrote:
> On 06/11/19 18:56, Joao Martins wrote:
>> When vCPU enters block phase, pi_pre_block() inserts vCPU to a per pCPU
>> linked list of all vCPUs that are blocked on this pCPU. Afterwards, it
>> changes PID.NV to POSTED_INTR_WAKEUP_VECTOR which its handler
>> (wakeup_handler()) is responsible to kick (unblock) any vCPU on that
>> linked list that now has pending posted interrupts.
>> While vCPU is blocked (in kvm_vcpu_block()), it may be preempted which
>> will cause vmx_vcpu_pi_put() to set PID.SN.  If later the vCPU will be
>> scheduled to run on a different pCPU, vmx_vcpu_pi_load() will clear
>> PID.SN but will also *overwrite PID.NDST to this different pCPU*.
>> Instead of keeping it with original pCPU which vCPU had entered block
>> phase on.
>> This results in an issue because when a posted interrupt is delivered,
>> the wakeup_handler() will be executed and fail to find blocked vCPU on
>> its per pCPU linked list of all vCPUs that are blocked on this pCPU.
>> Which is due to the vCPU being placed on a *different* per pCPU
>> linked list than the original pCPU that it had entered block phase.
>> The regression is introduced by commit c112b5f50232 ("KVM: x86:
>> Recompute PID.ON when clearing PID.SN"). Therefore, partially revert
>> it and reintroduce the condition in vmx_vcpu_pi_load() responsible for
>> avoiding changing PID.NDST when loading a blocked vCPU.
>> Fixes: c112b5f50232 ("KVM: x86: Recompute PID.ON when clearing PID.SN")
>> Signed-off-by: Joao Martins <>
>> Signed-off-by: Liran Alon <>
> Something wrong in the SoB line?
I can't spot any mistake; at least it looks chained correctly for me. What's the
issue you see with the Sob line?

The only thing I forgot was a:

Tested-by: Nathan Ni <>

> Otherwise looks good.

If you want I can resubmit the series with the Tb and Jag Rb, unless you think
it's OK doing on commit? Otherwise I can resubmit.


  reply	other threads:[~2019-11-11 14:49 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-06 17:55 [PATCH v1 0/3] KVM: VMX: Posted Interrupts fixes Joao Martins
2019-11-06 17:56 ` [PATCH v1 1/3] KVM: VMX: Consider PID.PIR to determine if vCPU has pending interrupts Joao Martins
2019-11-07 16:00   ` Jag Raman
2019-11-11 14:46   ` Paolo Bonzini
2019-11-11 14:59     ` Joao Martins
2019-11-11 15:58       ` Paolo Bonzini
2019-11-06 17:56 ` [PATCH v1 2/3] KVM: VMX: Do not change PID.NDST when loading a blocked vCPU Joao Martins
2019-11-06 21:54   ` Joao Martins
2019-11-11 14:39   ` Paolo Bonzini
2019-11-11 14:48     ` Joao Martins [this message]
2019-11-11 14:50       ` Paolo Bonzini
2019-11-11 14:56         ` Joao Martins
2019-11-11 14:59           ` Liran Alon
2019-11-11 15:53             ` Sean Christopherson
2019-11-11 17:27               ` Joao Martins
2019-11-06 17:56 ` [PATCH v1 3/3] KVM: VMX: Introduce pi_is_pir_empty() helper Joao Martins

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:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \ \ \ \ \ \ \ \ \ \ \ \ \ \

* 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).