From mboxrd@z Thu Jan  1 00:00:00 1970
From: Avi Kivity <avi@redhat.com>
Subject: Re: [PATCH RFC V2 3/5] kvm hypervisor : Add two hypercalls to support
 pv-ticketlock
Date: Mon, 24 Oct 2011 15:09:25 +0200
Message-ID: <4EA56385.9040302@redhat.com>
References: <20111023190307.16364.35381.sendpatchset@oc5400248562.ibm.com> <20111023190558.16364.2136.sendpatchset@oc5400248562.ibm.com> <4EA53A7D.300@redhat.com> <20111024122734.GA10634@linux.vnet.ibm.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>,
	Greg Kroah-Hartman <gregkh@suse.de>,
	"H. Peter Anvin" <hpa@zytor.com>, Gleb Natapov <gleb@redhat.com>,
	Virtualization <virtualization@lists.linux-foundation.org>,
	Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>,
	x86@kernel.org, KVM <kvm@vger.kernel.org>,
	Dave Jiang <dave.jiang@intel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Stefano Stabellini <stefano.stabellini@eu.citrix.com>,
	Xen <xen-devel@lists.xensource.com>,
	Sedat Dilek <sedat.dilek@gmail.com>,
	Yinghai Lu <yinghai@kernel.org>,
	Marcelo Tosatti <mtosatti@redhat.com>,
	Ingo Molnar <mingo@redhat.com>, Rik van Riel <riel@redhat.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	LKML <linux-kernel@vger.kernel.org>,
	Suzuki Poulose <suzuki@linux.vnet.ibm.com>,
	Peter Zijlstra <peterz@infradead.org>
To: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Return-path: <linux-kernel-owner@vger.kernel.org>
In-Reply-To: <20111024122734.GA10634@linux.vnet.ibm.com>
Sender: linux-kernel-owner@vger.kernel.org
List-Id: kvm.vger.kernel.org

On 10/24/2011 02:27 PM, Srivatsa Vaddagiri wrote:
> Good point. Assuming yield_on_hlt=1, that would allow the vcpu to be put
> to sleep and let other vcpus make progress.
>
> I guess with that change, we can also dropthe need for other hypercall
> introduced in this patch (kvm_pv_kick_cpu_op()). Essentially a vcpu sleeping 
> because of HLT instruction can be woken up by a IPI issued by vcpu releasing a
> lock.

Not if interrupts are disabled.  My original plan was to use NMIs for
wakeups, but it turns out NMIs can be coalesced under certain rare
circumstances; this requires workarounds by the generic NMI code that
make NMIs too slow.

-- 
I have a truly marvellous patch that fixes the bug which this
signature is too narrow to contain.