From patchwork Wed Nov 16 05:43:28 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paul Mackerras X-Patchwork-Id: 695446 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 3tJY8Y2f5cz9t1Q for ; Wed, 16 Nov 2016 16:43:41 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752030AbcKPFni (ORCPT ); Wed, 16 Nov 2016 00:43:38 -0500 Received: from ozlabs.org ([103.22.144.67]:47153 "EHLO ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751900AbcKPFni (ORCPT ); Wed, 16 Nov 2016 00:43:38 -0500 Received: by ozlabs.org (Postfix, from userid 1003) id 3tJY8R4fZjz9t1C; Wed, 16 Nov 2016 16:43:35 +1100 (AEDT) Date: Wed, 16 Nov 2016 16:43:28 +1100 From: Paul Mackerras To: kvm@vger.kernel.org, kvm-ppc@vger.kernel.org Subject: [PATCH] KVM: PPC: Book3S HV: Don't lose hardware R/C bit updates in H_PROTECT Message-ID: <20161116054328.ik74cdnkvd37yxej@oak.ozlabs.ibm.com> MIME-Version: 1.0 Content-Disposition: inline User-Agent: NeoMutt/20161104 (1.7.1) Sender: kvm-ppc-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm-ppc@vger.kernel.org The hashed page table MMU in POWER processors can update the R (reference) and C (change) bits in a HPTE at any time until the HPTE has been invalidated and the TLB invalidation sequence has completed. In kvmppc_h_protect, which implements the H_PROTECT hypercall, we read the HPTE, modify the second doubleword, invalidate the HPTE in memory, do the TLB invalidation sequence, and then write the modified value of the second doubleword back to memory. In doing so we could overwrite an R/C bit update done by hardware between when we read the HPTE and when the TLB invalidation completed. To fix this we re-read the second doubleword after the TLB invalidation and OR in the (possibly) new values of R and C. We can use an OR since hardware only ever sets R and C, never clears them. This race was found by code inspection. In principle this bug could cause occasional guest memory corruption under host memory pressure. Fixes: a8606e20e41a ("KVM: PPC: Handle some PAPR hcalls in the kernel", 2011-06-29) Cc: stable@vger.kernel.org # v3.19+ Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 752451f3..02786b3 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -670,6 +670,8 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, HPTE_V_ABSENT); do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true); + /* Don't lose R/C bit updates done by hardware */ + r |= be64_to_cpu(hpte[1]) & (HPTE_R_R | HPTE_R_C); hpte[1] = cpu_to_be64(r); } }