From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tom Lendacky Subject: Re: [PATCH v3 59/75] x86/sev-es: Handle MONITOR/MONITORX Events Date: Thu, 11 Jun 2020 14:33:12 -0500 Message-ID: References: <20200428151725.31091-1-joro@8bytes.org> <20200428151725.31091-60-joro@8bytes.org> <20200520063845.GC17090@linux.intel.com> <20200611131045.GE11924@8bytes.org> <20200611171305.GJ29918@linux.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20200611171305.GJ29918@linux.intel.com> Content-Language: en-US Sender: linux-kernel-owner@vger.kernel.org To: Sean Christopherson , Joerg Roedel Cc: x86@kernel.org, hpa@zytor.com, Andy Lutomirski , Dave Hansen , Peter Zijlstra , Thomas Hellstrom , Jiri Slaby , Dan Williams , Juergen Gross , Kees Cook , David Rientjes , Cfir Cohen , Erdem Aktas , Masami Hiramatsu , Mike Stunes , Joerg Roedel , linux-kernel@vger.kernel.org, kvm@vger.kernel.org, virtualization@lists.linux-foundation.org List-Id: virtualization@lists.linuxfoundation.org On 6/11/20 12:13 PM, Sean Christopherson wrote: > On Thu, Jun 11, 2020 at 03:10:45PM +0200, Joerg Roedel wrote: >> On Tue, May 19, 2020 at 11:38:45PM -0700, Sean Christopherson wrote: >>> On Tue, Apr 28, 2020 at 05:17:09PM +0200, Joerg Roedel wrote: >>>> +static enum es_result vc_handle_monitor(struct ghcb *ghcb, >>>> + struct es_em_ctxt *ctxt) >>>> +{ >>>> + phys_addr_t monitor_pa; >>>> + pgd_t *pgd; >>>> + >>>> + pgd = __va(read_cr3_pa()); >>>> + monitor_pa = vc_slow_virt_to_phys(ghcb, ctxt->regs->ax); >>>> + >>>> + ghcb_set_rax(ghcb, monitor_pa); >>>> + ghcb_set_rcx(ghcb, ctxt->regs->cx); >>>> + ghcb_set_rdx(ghcb, ctxt->regs->dx); >>>> + >>>> + return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MONITOR, 0, 0); >>> >>> Why? If SVM has the same behavior as VMX, the MONITOR will be disarmed on >>> VM-Enter, i.e. the VMM can't do anything useful for MONITOR/MWAIT. I >>> assume that's the case given that KVM emulates MONITOR/MWAIT as NOPs on >>> SVM. >> >> Not sure if it is disarmed on VMRUN, but the MONITOR/MWAIT instructions >> are part of the GHCB spec, so they are implemented here. > > Even if MONITOR/MWAIT somehow works across VMRUN I'm not sure it's something > the guest should enable by default as it leaks GPAs to the untrusted host, > with no benefit to the guest except in specific configurations. Yeah, the > VMM can muck with page tables to trace guest to the some extent, but the > guest shouldn't be unnecessarily volunteering information to the host. > > If MONITOR/MWAIT is effectively a NOP then removing this code is a no > brainer. > > Can someone from AMD chime in? I don't think there is any guarantee that MONITOR/MWAIT would work within a guest (I'd have to dig some more on that to get a definitive answer, but probably not necessary to do). As you say, if KVM emulates it as a NOP, there's no sense in exposing the GPA - make it a NOP in the handler. I just need to poke some other hypervisor vendors and hear what they have to say. Thanks, Tom >