Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20220421165137.306101-1-posk@google.com> <b1b04160-1604-8281-4c82-09b1f84ba86c@redhat.com>
In-Reply-To: <b1b04160-1604-8281-4c82-09b1f84ba86c@redhat.com>
From:   Peter Oskolkov <posk@google.com>
Date:   Thu, 28 Apr 2022 12:13:26 -0700
Message-ID: <CAPNVh5eTzpK6QpJumegoN4_7r56ZHsi6hFCG-Mqt+R8ngrCitw@mail.gmail.com>
Subject: Re: [PATCH] KVM: x86: add HC_VMM_CUSTOM hypercall
To:     Paolo Bonzini <pbonzini@redhat.com>
Cc:     Sean Christopherson <seanjc@google.com>,
        Vitaly Kuznetsov <vkuznets@redhat.com>,
        Wanpeng Li <wanpengli@tencent.com>,
        Jim Mattson <jmattson@google.com>,
        Joerg Roedel <joro@8bytes.org>, kvm@vger.kernel.org,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        Dave Hansen <dave.hansen@linux.intel.com>, x86@kernel.org,
        "H . Peter Anvin" <hpa@zytor.com>, linux-kernel@vger.kernel.org,
        Paul Turner <pjt@google.com>, Peter Oskolkov <posk@posk.io>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Thu, Apr 21, 2022 at 10:14 AM Paolo Bonzini <pbonzini@redhat.com> wrote:
>
> On 4/21/22 18:51, Peter Oskolkov wrote:
> > Allow kvm-based VMMs to request KVM to pass a custom vmcall
> > from the guest to the VMM in the host.
> >
> > Quite often, operating systems research projects and/or specialized
> > paravirtualized workloads would benefit from a extra-low-overhead,
> > extra-low-latency guest-host communication channel.
>
> You can use a memory page and an I/O port.  It should be as fast as a
> hypercall.  You can even change it to use ioeventfd if an asynchronous
> channel is enough, and then it's going to be less than 1 us latency.

So this function:

uint8_t hyperchannel_ping(uint8_t arg)
{
        uint8_t inb;
        uint16_t port = PORT;

        asm(
                "outb %[arg] , %[port]  \n\t"  // write arg
                "inb  %[port], %[inb]   \n\t"  // read  res
                : [inb] "=r"(inb)
                : [arg] "r"(arg), [port] "r"(port)
        );
        return inb;
}

takes about 5.5usec vs 2.5usec for a vmcall on the same
hardware/kernel/etc. I've also tried AF_VSOCK, and a roundtrip there
is 30-50usec.

The main problem of port I/O vs a vmcall is that with port I/O a
second VM exit is needed to return any result to the guest. Am I
missing something?

I'll try now using ioeventfd, but I suspect that building a
synchronous request/response channel on top of it will not match a
direct vmcall in terms of latency.

Are there any other alternatives I should look at?

Thanks,
Peter

>
> Paolo
>
> > With cloud-hypervisor modified to handle the new hypercall (simply
> > return the sum of the received arguments), the following function in
> > guest_userspace_  completes, on average, in 2.5 microseconds (walltime)
> > on a relatively modern Intel Xeon processor:
>