kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sean Christopherson <sean.j.christopherson@intel.com>
To: Wanpeng Li <kernellwp@gmail.com>
Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	Paolo Bonzini <pbonzini@redhat.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	Haiwei Li <lihaiwei@tencent.com>
Subject: Re: [PATCH v3 1/5] KVM: VMX: Introduce generic fastpath handler
Date: Mon, 27 Apr 2020 11:26:31 -0700	[thread overview]
Message-ID: <20200427182631.GM14870@linux.intel.com> (raw)
In-Reply-To: <1587709364-19090-2-git-send-email-wanpengli@tencent.com>

On Fri, Apr 24, 2020 at 02:22:40PM +0800, Wanpeng Li wrote:
> From: Wanpeng Li <wanpengli@tencent.com>
> 
> Introduce generic fastpath handler to handle MSR fastpath, VMX-preemption 
> timer fastpath etc. In addition, we can't observe benefit from single 
> target IPI fastpath when APICv is disabled, let's just enable IPI and 
> Timer fastpath when APICv is enabled for now.

There are three different changes being squished into a single patch:

  - Refactor code to add helper
  - Change !APICv behavior for WRMSR fastpath
  - Introduce EXIT_FASTPATH_CONT_RUN

I don't think you necessarily need to break this into three separate
patches, but's the !APICv change needs to be a standalone patch, especially
given the shortlog.  E.g. the refactoring could be introduced along with
the second fastpath case, and CONT_RUN could be introduced with its first
usage.

> 
> Tested-by: Haiwei Li <lihaiwei@tencent.com>
> Cc: Haiwei Li <lihaiwei@tencent.com>
> Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
> ---
>  arch/x86/include/asm/kvm_host.h |  1 +
>  arch/x86/kvm/vmx/vmx.c          | 25 ++++++++++++++++++++-----
>  2 files changed, 21 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index f26df2c..6397723 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -188,6 +188,7 @@ enum {
>  enum exit_fastpath_completion {
>  	EXIT_FASTPATH_NONE,
>  	EXIT_FASTPATH_SKIP_EMUL_INS,
> +	EXIT_FASTPATH_CONT_RUN,
>  };
>  
>  struct x86_emulate_ctxt;
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index 766303b..f1f6638 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -6559,6 +6559,20 @@ void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp)
>  	}
>  }
>  
> +static enum exit_fastpath_completion vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
> +{
> +	if (!is_guest_mode(vcpu) && vcpu->arch.apicv_active) {
> +		switch (to_vmx(vcpu)->exit_reason) {
> +		case EXIT_REASON_MSR_WRITE:
> +			return handle_fastpath_set_msr_irqoff(vcpu);
> +		default:
> +			return EXIT_FASTPATH_NONE;
> +		}
> +	}
> +
> +	return EXIT_FASTPATH_NONE;
> +}
> +
>  bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched);
>  
>  static enum exit_fastpath_completion vmx_vcpu_run(struct kvm_vcpu *vcpu)
> @@ -6567,6 +6581,7 @@ static enum exit_fastpath_completion vmx_vcpu_run(struct kvm_vcpu *vcpu)
>  	struct vcpu_vmx *vmx = to_vmx(vcpu);
>  	unsigned long cr3, cr4;
>  
> +cont_run:
>  	/* Record the guest's net vcpu time for enforced NMI injections. */
>  	if (unlikely(!enable_vnmi &&
>  		     vmx->loaded_vmcs->soft_vnmi_blocked))
> @@ -6733,17 +6748,17 @@ static enum exit_fastpath_completion vmx_vcpu_run(struct kvm_vcpu *vcpu)
>  	if (unlikely(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
>  		return EXIT_FASTPATH_NONE;
>  
> -	if (!is_guest_mode(vcpu) && vmx->exit_reason == EXIT_REASON_MSR_WRITE)
> -		exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu);
> -	else
> -		exit_fastpath = EXIT_FASTPATH_NONE;
> -
>  	vmx->loaded_vmcs->launched = 1;
>  	vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
>  
>  	vmx_recover_nmi_blocking(vmx);
>  	vmx_complete_interrupts(vmx);
>  
> +	exit_fastpath = vmx_exit_handlers_fastpath(vcpu);
> +	/* static call is better with retpolines */
> +	if (exit_fastpath == EXIT_FASTPATH_CONT_RUN)
> +		goto cont_run;
> +
>  	return exit_fastpath;
>  }
>  
> -- 
> 2.7.4
> 

  reply	other threads:[~2020-04-27 18:26 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-24  6:22 [PATCH v3 0/5] KVM: VMX: Tscdeadline timer emulation fastpath Wanpeng Li
2020-04-24  6:22 ` [PATCH v3 1/5] KVM: VMX: Introduce generic fastpath handler Wanpeng Li
2020-04-27 18:26   ` Sean Christopherson [this message]
2020-04-28  0:47     ` Wanpeng Li
2020-04-24  6:22 ` [PATCH v3 2/5] KVM: X86: Introduce need_cancel_enter_guest helper Wanpeng Li
2020-04-26  2:05   ` Wanpeng Li
2020-04-27 18:36     ` Sean Christopherson
2020-04-28  0:44       ` Wanpeng Li
2020-04-28  1:03         ` Sean Christopherson
2020-04-27 18:30   ` Sean Christopherson
2020-04-28  7:17     ` Wanpeng Li
2020-04-24  6:22 ` [PATCH v3 3/5] KVM: VMX: Optimize posted-interrupt delivery for timer fastpath Wanpeng Li
2020-04-27 18:37   ` Sean Christopherson
2020-04-24  6:22 ` [PATCH v3 4/5] KVM: X86: TSCDEADLINE MSR emulation fastpath Wanpeng Li
2020-04-27 18:38   ` Sean Christopherson
2020-04-24  6:22 ` [PATCH v3 5/5] KVM: VMX: Handle preemption timer fastpath Wanpeng Li
2020-04-27 18:42   ` Sean Christopherson
2020-04-28  0:45     ` Wanpeng Li

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=20200427182631.GM14870@linux.intel.com \
    --to=sean.j.christopherson@intel.com \
    --cc=jmattson@google.com \
    --cc=joro@8bytes.org \
    --cc=kernellwp@gmail.com \
    --cc=kvm@vger.kernel.org \
    --cc=lihaiwei@tencent.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.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).