From mboxrd@z Thu Jan 1 00:00:00 1970 From: Scott Wood Date: Wed, 16 May 2012 22:07:20 +0000 Subject: Re: [PATCH] KVM: PPC: Not optimizing MSR_CE and MSR_DE with paravirt. Message-Id: <4FB42518.9060401@freescale.com> List-Id: References: <1337067442-26625-1-git-send-email-bharat.bhushan@freescale.com> In-Reply-To: <1337067442-26625-1-git-send-email-bharat.bhushan@freescale.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: kvm-ppc@vger.kernel.org On 05/16/2012 10:13 AM, Sethi Varun-B16395 wrote: >>> Why is MSR[CE] unsafe? >> >> MSR=0 >> * critical interrupt comes in * >> mtmsr(MSR_CE) >> --> MSR = MSR_CE >> * interrupt should be delivered, but host doesn't get notified that >> MSR_CE is changing * >> >> However, we completely ignore critical interrupts in KVM these days, no? Watchdog will use them. > Well, it's least likely that MSR_CE/MSR_ME would get changed directly. They would > mostly get changed via rfci/rfmci, which would trap. It being unlikely means that there's little performance downside to this patch -- it doesn't mean that this patch is unnecessary. FWIW, Topaz directly manipulates MSR[CE] extensively, since it uses critical interrupts as its main interrupts (to distinguish from EE interrupts which are delivered directly to the guest). -Scott