Subject: Re: [PATCH v3 2/5] KVM: add KVM_REQ_EXIT request for userspace exit
To: Wanpeng Li <wanpeng.li@hotmail.com>,
        =?UTF-8?B?UmFkaW0gS3LEjW3DocWZ?= <rkrcmar@redhat.com>,
        linux-kernel@vger.kernel.org
References: <1439546917-17391-1-git-send-email-rkrcmar@redhat.com>
 <1439546917-17391-3-git-send-email-rkrcmar@redhat.com>
 <BLU436-SMTP2157250AAE5CAE1E256309080660@phx.gbl>
Cc: kvm@vger.kernel.org, Christian Borntraeger <borntraeger@de.ibm.com>
From: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <55D81F17.8000907@redhat.com>
Date: Sat, 22 Aug 2015 00:04:55 -0700
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101
 Thunderbird/38.1.0
MIME-Version: 1.0
In-Reply-To: <BLU436-SMTP2157250AAE5CAE1E256309080660@phx.gbl>
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1076
Lines: 24


On 19/08/2015 20:55, Wanpeng Li wrote:
>> The disadvantage is that it adds an overhead of one bit check for all
>> kernel exits.  A quick tracing shows that the ratio of userspace exits
>> after boot is about 1/5 and in subsequent run of nmap and kernel compile
>> has about 1/60, so the check should not regress global performance.
>>
>> All signal_pending() calls are userspace exit requests, so we add a
>> check for KVM_REQ_EXIT there.  There is one omitted call in kvm_vcpu_run
>> because KVM_REQ_EXIT is implied in earlier check for requests.
> 
> Actually I see more SIGUSR1 signals are intercepted by signal_pending()
> in vcpu_enter_guest() and vcpu_run() w/ win7 guest and kernel_irqchip=off.

You need more patches on the QEMU side.  I tested a version that is
mostly okay but not ready for upstream inclusion.

Paolo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/