From patchwork Sun Jan 13 15:49:07 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiao Guangrong X-Patchwork-Id: 1970021 Return-Path: X-Original-To: patchwork-kvm@patchwork.kernel.org Delivered-To: patchwork-process-083081@patchwork1.kernel.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by patchwork1.kernel.org (Postfix) with ESMTP id B1F233FD86 for ; Sun, 13 Jan 2013 15:50:14 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755179Ab3AMPtx (ORCPT ); Sun, 13 Jan 2013 10:49:53 -0500 Received: from e23smtp04.au.ibm.com ([202.81.31.146]:49563 "EHLO e23smtp04.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755061Ab3AMPtw (ORCPT ); Sun, 13 Jan 2013 10:49:52 -0500 Received: from /spool/local by e23smtp04.au.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Mon, 14 Jan 2013 01:42:15 +1000 Received: from d23dlp01.au.ibm.com (202.81.31.203) by e23smtp04.au.ibm.com (202.81.31.210) with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted; Mon, 14 Jan 2013 01:42:14 +1000 Received: from d23relay05.au.ibm.com (d23relay05.au.ibm.com [9.190.235.152]) by d23dlp01.au.ibm.com (Postfix) with ESMTP id B41372CE804A; Mon, 14 Jan 2013 02:49:47 +1100 (EST) Received: from d23av04.au.ibm.com (d23av04.au.ibm.com [9.190.235.139]) by d23relay05.au.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id r0DFc3fP56099034; Mon, 14 Jan 2013 02:38:03 +1100 Received: from d23av04.au.ibm.com (loopback [127.0.0.1]) by d23av04.au.ibm.com (8.14.4/8.13.1/NCO v10.0 AVout) with ESMTP id r0DFnkuG002465; Mon, 14 Jan 2013 02:49:47 +1100 Received: from localhost.localdomain ([9.77.181.222]) by d23av04.au.ibm.com (8.14.4/8.13.1/NCO v10.0 AVin) with ESMTP id r0DFn8GN002190; Mon, 14 Jan 2013 02:49:20 +1100 Message-ID: <50F2D773.2070301@linux.vnet.ibm.com> Date: Sun, 13 Jan 2013 23:49:07 +0800 From: Xiao Guangrong User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:15.0) Gecko/20120911 Thunderbird/15.0.1 MIME-Version: 1.0 To: Xiao Guangrong CC: Marcelo Tosatti , Gleb Natapov , LKML , KVM Subject: [PATCH v6 3/3] KVM: x86: improve reexecute_instruction References: <50F2D64C.4030804@linux.vnet.ibm.com> In-Reply-To: <50F2D64C.4030804@linux.vnet.ibm.com> X-Content-Scanned: Fidelis XPS MAILER x-cbid: 13011315-9264-0000-0000-000002FC7BCE Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org The current reexecute_instruction can not well detect the failed instruction emulation. It allows guest to retry all the instructions except it accesses on error pfn For example, some cases are nested-write-protect - if the page we want to write is used as PDE but it chains to itself. Under this case, we should stop the emulation and report the case to userspace Signed-off-by: Xiao Guangrong --- arch/x86/include/asm/kvm_host.h | 7 +++++++ arch/x86/kvm/paging_tmpl.h | 27 ++++++++++++++++++++------- arch/x86/kvm/x86.c | 22 ++++++++++++++++++---- 3 files changed, 45 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c431b33..d6ab8d2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -502,6 +502,13 @@ struct kvm_vcpu_arch { u64 msr_val; struct gfn_to_hva_cache data; } pv_eoi; + + /* + * Indicate whether the access faults on its page table in guest + * which is set when fix page fault and used to detect unhandeable + * instruction. + */ + bool write_fault_to_shadow_pgtable; }; struct kvm_lpage_info { diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 3d1a352..ca69dcc 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -497,26 +497,34 @@ out_gpte_changed: * created when kvm establishes shadow page table that stop kvm using large * page size. Do it early can avoid unnecessary #PF and emulation. * + * @write_fault_to_shadow_pgtable will return true if the fault gfn is + * currently used as its page table. + * * Note: the PDPT page table is not checked for PAE-32 bit guest. It is ok * since the PDPT is always shadowed, that means, we can not use large page * size to map the gfn which is used as PDPT. */ static bool FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, - struct guest_walker *walker, int user_fault) + struct guest_walker *walker, int user_fault, + bool *write_fault_to_shadow_pgtable) { int level; gfn_t mask = ~(KVM_PAGES_PER_HPAGE(walker->level) - 1); + bool self_changed = false; if (!(walker->pte_access & ACC_WRITE_MASK || (!is_write_protection(vcpu) && !user_fault))) return false; - for (level = walker->level; level <= walker->max_level; level++) - if (!((walker->gfn ^ walker->table_gfn[level - 1]) & mask)) - return true; + for (level = walker->level; level <= walker->max_level; level++) { + gfn_t gfn = walker->gfn ^ walker->table_gfn[level - 1]; + + self_changed |= !(gfn & mask); + *write_fault_to_shadow_pgtable |= !gfn; + } - return false; + return self_changed; } /* @@ -544,7 +552,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int level = PT_PAGE_TABLE_LEVEL; int force_pt_level; unsigned long mmu_seq; - bool map_writable; + bool map_writable, is_self_change_mapping; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -572,9 +580,14 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, return 0; } + vcpu->arch.write_fault_to_shadow_pgtable = false; + + is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, + &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable); + if (walker.level >= PT_DIRECTORY_LEVEL) force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn) - || FNAME(is_self_change_mapping)(vcpu, &walker, user_fault); + || is_self_change_mapping; else force_pt_level = 1; if (!force_pt_level) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6f13e03..139a5f8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4753,7 +4753,8 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu) return r; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2) +static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, + bool write_fault_to_shadow_pgtable) { gpa_t gpa = cr2; pfn_t pfn; @@ -4810,7 +4811,13 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2) * guest to let CPU execute the instruction. */ kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); - return true; + + /* + * If the access faults on its page table, it can not + * be fixed by unprotecting shadow page and it should + * be reported to userspace. + */ + return !write_fault_to_shadow_pgtable; } static bool retry_instruction(struct x86_emulate_ctxt *ctxt, @@ -4869,7 +4876,13 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, int r; struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; bool writeback = true; + bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; + /* + * Clear write_fault_to_shadow_pgtable here to ensure it is + * never reused. + */ + vcpu->arch.write_fault_to_shadow_pgtable = false; kvm_clear_exception_queue(vcpu); if (!(emulation_type & EMULTYPE_NO_DECODE)) { @@ -4888,7 +4901,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, if (r != EMULATION_OK) { if (emulation_type & EMULTYPE_TRAP_UD) return EMULATE_FAIL; - if (reexecute_instruction(vcpu, cr2)) + if (reexecute_instruction(vcpu, cr2, + write_fault_to_spt)) return EMULATE_DONE; if (emulation_type & EMULTYPE_SKIP) return EMULATE_FAIL; @@ -4918,7 +4932,7 @@ restart: return EMULATE_DONE; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2)) + if (reexecute_instruction(vcpu, cr2, write_fault_to_spt)) return EMULATE_DONE; return handle_emulation_failure(vcpu);