3.16.45-rc1 review patch. If anyone has any objections, please let me know. ------------------ From: Paolo Bonzini <pbonzini@xxxxxxxxxx> commit c8401dda2f0a00cd25c0af6a95ed50e478d25de4 upstream. TF is handled a bit differently for syscall and sysret, compared to the other instructions: TF is checked after the instruction completes, so that the OS can disable #DB at a syscall by adding TF to FMASK. When the sysret is executed the #DB is taken "as if" the syscall insn just completed. KVM emulates syscall so that it can trap 32-bit syscall on Intel processors. Fix the behavior, otherwise you could get #DB on a user stack which is not nice. This does not affect Linux guests, as they use an IST or task gate for #DB. This fixes CVE-2017-7518. Reported-by: Andy Lutomirski <luto@xxxxxxxxxx> Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx> Signed-off-by: Radim Krčmář <rkrcmar@xxxxxxxxxx> [bwh: Backported to 3.16: - kvm_vcpu_check_singlestep() did not take an rflags parameter but called get_rflags() itself; delete that code - kvm_vcpu_check_singlestep() sets some flags differently - Drop changes to kvm_skip_emulated_instruction()] Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx> --- --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -274,6 +274,7 @@ struct x86_emulate_ctxt { bool guest_mode; /* guest running a nested guest */ bool perm_ok; /* do not check permissions if true */ bool ud; /* inject an #UD if host doesn't support insn */ + bool tf; /* TF value before instruction (after for syscall/sysret) */ bool have_exception; struct x86_exception exception; --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2310,6 +2310,7 @@ static int em_syscall(struct x86_emulate ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF); } + ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; return X86EMUL_CONTINUE; } --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4942,6 +4942,8 @@ static void init_emulate_ctxt(struct kvm kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); ctxt->eflags = kvm_get_rflags(vcpu); + ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; + ctxt->eip = kvm_rip_read(vcpu); ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : (ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : @@ -5132,38 +5134,26 @@ static int kvm_vcpu_check_hw_bp(unsigned return dr6; } -static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, int *r) +static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r) { struct kvm_run *kvm_run = vcpu->run; - /* - * Use the "raw" value to see if TF was passed to the processor. - * Note that the new value of the flags has not been saved yet. - * - * This is correct even for TF set by the guest, because "the - * processor will not generate this exception after the instruction - * that sets the TF flag". - */ - unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); - - if (unlikely(rflags & X86_EFLAGS_TF)) { - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1; - kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; - kvm_run->debug.arch.exception = DB_VECTOR; - kvm_run->exit_reason = KVM_EXIT_DEBUG; - *r = EMULATE_USER_EXIT; - } else { - vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF; - /* - * "Certain debug exceptions may clear bit 0-3. The - * remaining contents of the DR6 register are never - * cleared by the processor". - */ - vcpu->arch.dr6 &= ~15; - vcpu->arch.dr6 |= DR6_BS; - kvm_queue_exception(vcpu, DB_VECTOR); - } + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1; + kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + *r = EMULATE_USER_EXIT; + } else { + vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF; + /* + * "Certain debug exceptions may clear bit 0-3. The + * remaining contents of the DR6 register are never + * cleared by the processor". + */ + vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 |= DR6_BS; + kvm_queue_exception(vcpu, DB_VECTOR); } } @@ -5316,8 +5306,9 @@ restart: kvm_make_request(KVM_REQ_EVENT, vcpu); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; kvm_rip_write(vcpu, ctxt->eip); - if (r == EMULATE_DONE) - kvm_vcpu_check_singlestep(vcpu, &r); + if (r == EMULATE_DONE && + (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) + kvm_vcpu_do_singlestep(vcpu, &r); kvm_set_rflags(vcpu, ctxt->eflags); } else vcpu->arch.emulate_regs_need_sync_to_vcpu = true;