Merge tag 'kvm-x86-svm-6.6' of https://github.com/kvm-x86/linux into HEAD

KVM: x86: SVM changes for 6.6:

 - Add support for SEV-ES DebugSwap, i.e. allow SEV-ES guests to use debug
   registers and generate/handle #DBs

 - Clean up LBR virtualization code

 - Fix a bug where KVM fails to set the target pCPU during an IRTE update

 - Fix fatal bugs in SEV-ES intrahost migration

 - Fix a bug where the recent (architecturally correct) change to reinject
   #BP and skip INT3 broke SEV guests (can't decode INT3 to skip it)

1 files changed, 112 insertions, 67 deletions

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d4bfdc607fe7..488814e919ca 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -203,7 +203,7 @@ static int nested = true;
 module_param(nested, int, S_IRUGO);
 
 /* enable/disable Next RIP Save */
-static int nrips = true;
+int nrips = true;
 module_param(nrips, int, 0444);
 
 /* enable/disable Virtual VMLOAD VMSAVE */
@@ -365,6 +365,8 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 		svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK;
 
 }
+static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
+					void *insn, int insn_len);
 
 static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu,
 					   bool commit_side_effects)
@@ -385,6 +387,14 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu,
 	}
 
 	if (!svm->next_rip) {
+		/*
+		 * FIXME: Drop this when kvm_emulate_instruction() does the
+		 * right thing and treats "can't emulate" as outright failure
+		 * for EMULTYPE_SKIP.
+		 */
+		if (!svm_can_emulate_instruction(vcpu, EMULTYPE_SKIP, NULL, 0))
+			return 0;
+
 		if (unlikely(!commit_side_effects))
 			old_rflags = svm->vmcb->save.rflags;
 
@@ -677,6 +687,39 @@ free_save_area:
 
 }
 
+static void set_dr_intercepts(struct vcpu_svm *svm)
+{
+	struct vmcb *vmcb = svm->vmcb01.ptr;
+
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
+
+	recalc_intercepts(svm);
+}
+
+static void clr_dr_intercepts(struct vcpu_svm *svm)
+{
+	struct vmcb *vmcb = svm->vmcb01.ptr;
+
+	vmcb->control.intercepts[INTERCEPT_DR] = 0;
+
+	recalc_intercepts(svm);
+}
+
 static int direct_access_msr_slot(u32 msr)
 {
 	u32 i;
@@ -947,50 +990,24 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
 		svm_copy_lbrs(svm->vmcb01.ptr, svm->vmcb);
 }
 
-static int svm_get_lbr_msr(struct vcpu_svm *svm, u32 index)
+static struct vmcb *svm_get_lbr_vmcb(struct vcpu_svm *svm)
 {
 	/*
-	 * If the LBR virtualization is disabled, the LBR msrs are always
-	 * kept in the vmcb01 to avoid copying them on nested guest entries.
-	 *
-	 * If nested, and the LBR virtualization is enabled/disabled, the msrs
-	 * are moved between the vmcb01 and vmcb02 as needed.
+	 * If LBR virtualization is disabled, the LBR MSRs are always kept in
+	 * vmcb01.  If LBR virtualization is enabled and L1 is running VMs of
+	 * its own, the MSRs are moved between vmcb01 and vmcb02 as needed.
 	 */
-	struct vmcb *vmcb =
-		(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) ?
-			svm->vmcb : svm->vmcb01.ptr;
-
-	switch (index) {
-	case MSR_IA32_DEBUGCTLMSR:
-		return vmcb->save.dbgctl;
-	case MSR_IA32_LASTBRANCHFROMIP:
-		return vmcb->save.br_from;
-	case MSR_IA32_LASTBRANCHTOIP:
-		return vmcb->save.br_to;
-	case MSR_IA32_LASTINTFROMIP:
-		return vmcb->save.last_excp_from;
-	case MSR_IA32_LASTINTTOIP:
-		return vmcb->save.last_excp_to;
-	default:
-		KVM_BUG(false, svm->vcpu.kvm,
-			"%s: Unknown MSR 0x%x", __func__, index);
-		return 0;
-	}
+	return svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK ? svm->vmcb :
+								   svm->vmcb01.ptr;
 }
 
 void svm_update_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-
-	bool enable_lbrv = svm_get_lbr_msr(svm, MSR_IA32_DEBUGCTLMSR) &
-					   DEBUGCTLMSR_LBR;
-
-	bool current_enable_lbrv = !!(svm->vmcb->control.virt_ext &
-				      LBR_CTL_ENABLE_MASK);
-
-	if (unlikely(is_guest_mode(vcpu) && svm->lbrv_enabled))
-		if (unlikely(svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))
-			enable_lbrv = true;
+	bool current_enable_lbrv = svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK;
+	bool enable_lbrv = (svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR) ||
+			   (is_guest_mode(vcpu) && svm->lbrv_enabled &&
+			    (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK));
 
 	if (enable_lbrv == current_enable_lbrv)
 		return;
@@ -1201,10 +1218,9 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 	 * Guest access to VMware backdoor ports could legitimately
 	 * trigger #GP because of TSS I/O permission bitmap.
 	 * We intercept those #GP and allow access to them anyway
-	 * as VMware does.  Don't intercept #GP for SEV guests as KVM can't
-	 * decrypt guest memory to decode the faulting instruction.
+	 * as VMware does.
 	 */
-	if (enable_vmware_backdoor && !sev_guest(vcpu->kvm))
+	if (enable_vmware_backdoor)
 		set_exception_intercept(svm, GP_VECTOR);
 
 	svm_set_intercept(svm, INTERCEPT_INTR);
@@ -1949,7 +1965,7 @@ static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (vcpu->arch.guest_state_protected)
+	if (WARN_ON_ONCE(sev_es_guest(vcpu->kvm)))
 		return;
 
 	get_debugreg(vcpu->arch.db[0], 0);
@@ -2510,12 +2526,13 @@ static int iret_interception(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	WARN_ON_ONCE(sev_es_guest(vcpu->kvm));
+
 	++vcpu->stat.nmi_window_exits;
 	svm->awaiting_iret_completion = true;
 
 	svm_clr_iret_intercept(svm);
-	if (!sev_es_guest(vcpu->kvm))
-		svm->nmi_iret_rip = kvm_rip_read(vcpu);
+	svm->nmi_iret_rip = kvm_rip_read(vcpu);
 
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	return 1;
@@ -2680,6 +2697,13 @@ static int dr_interception(struct kvm_vcpu *vcpu)
 	unsigned long val;
 	int err = 0;
 
+	/*
+	 * SEV-ES intercepts DR7 only to disable guest debugging and the guest issues a VMGEXIT
+	 * for DR7 write only. KVM cannot change DR7 (always swapped as type 'A') so return early.
+	 */
+	if (sev_es_guest(vcpu->kvm))
+		return 1;
+
 	if (vcpu->guest_debug == 0) {
 		/*
 		 * No more DR vmexits; force a reload of the debug registers
@@ -2802,11 +2826,19 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = svm->tsc_aux;
 		break;
 	case MSR_IA32_DEBUGCTLMSR:
+		msr_info->data = svm_get_lbr_vmcb(svm)->save.dbgctl;
+		break;
 	case MSR_IA32_LASTBRANCHFROMIP:
+		msr_info->data = svm_get_lbr_vmcb(svm)->save.br_from;
+		break;
 	case MSR_IA32_LASTBRANCHTOIP:
+		msr_info->data = svm_get_lbr_vmcb(svm)->save.br_to;
+		break;
 	case MSR_IA32_LASTINTFROMIP:
+		msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_from;
+		break;
 	case MSR_IA32_LASTINTTOIP:
-		msr_info->data = svm_get_lbr_msr(svm, msr_info->index);
+		msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_to;
 		break;
 	case MSR_VM_HSAVE_PA:
 		msr_info->data = svm->nested.hsave_msr;
@@ -3037,13 +3069,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
-		if (svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK)
-			svm->vmcb->save.dbgctl = data;
-		else
-			svm->vmcb01.ptr->save.dbgctl = data;
-
+		svm_get_lbr_vmcb(svm)->save.dbgctl = data;
 		svm_update_lbrv(vcpu);
-
 		break;
 	case MSR_VM_HSAVE_PA:
 		/*
@@ -3769,6 +3796,19 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu)
 	if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion)
 		return; /* IRET will cause a vm exit */
 
+	/*
+	 * SEV-ES guests are responsible for signaling when a vCPU is ready to
+	 * receive a new NMI, as SEV-ES guests can't be single-stepped, i.e.
+	 * KVM can't intercept and single-step IRET to detect when NMIs are
+	 * unblocked (architecturally speaking).  See SVM_VMGEXIT_NMI_COMPLETE.
+	 *
+	 * Note, GIF is guaranteed to be '1' for SEV-ES guests as hardware
+	 * ignores SEV-ES guest writes to EFER.SVME *and* CLGI/STGI are not
+	 * supported NAEs in the GHCB protocol.
+	 */
+	if (sev_es_guest(vcpu->kvm))
+		return;
+
 	if (!gif_set(svm)) {
 		if (vgif)
 			svm_set_intercept(svm, INTERCEPT_STGI);
@@ -3918,12 +3958,11 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu)
 	svm->soft_int_injected = false;
 
 	/*
-	 * If we've made progress since setting HF_IRET_MASK, we've
+	 * If we've made progress since setting awaiting_iret_completion, we've
 	 * executed an IRET and can allow NMI injection.
 	 */
 	if (svm->awaiting_iret_completion &&
-	    (sev_es_guest(vcpu->kvm) ||
-	     kvm_rip_read(vcpu) != svm->nmi_iret_rip)) {
+	    kvm_rip_read(vcpu) != svm->nmi_iret_rip) {
 		svm->awaiting_iret_completion = false;
 		svm->nmi_masked = false;
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
@@ -4651,16 +4690,25 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 	 * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and
 	 * decode garbage.
 	 *
-	 * Inject #UD if KVM reached this point without an instruction buffer.
-	 * In practice, this path should never be hit by a well-behaved guest,
-	 * e.g. KVM doesn't intercept #UD or #GP for SEV guests, but this path
-	 * is still theoretically reachable, e.g. via unaccelerated fault-like
-	 * AVIC access, and needs to be handled by KVM to avoid putting the
-	 * guest into an infinite loop.   Injecting #UD is somewhat arbitrary,
-	 * but its the least awful option given lack of insight into the guest.
+	 * If KVM is NOT trying to simply skip an instruction, inject #UD if
+	 * KVM reached this point without an instruction buffer.  In practice,
+	 * this path should never be hit by a well-behaved guest, e.g. KVM
+	 * doesn't intercept #UD or #GP for SEV guests, but this path is still
+	 * theoretically reachable, e.g. via unaccelerated fault-like AVIC
+	 * access, and needs to be handled by KVM to avoid putting the guest
+	 * into an infinite loop.   Injecting #UD is somewhat arbitrary, but
+	 * its the least awful option given lack of insight into the guest.
+	 *
+	 * If KVM is trying to skip an instruction, simply resume the guest.
+	 * If a #NPF occurs while the guest is vectoring an INT3/INTO, then KVM
+	 * will attempt to re-inject the INT3/INTO and skip the instruction.
+	 * In that scenario, retrying the INT3/INTO and hoping the guest will
+	 * make forward progress is the only option that has a chance of
+	 * success (and in practice it will work the vast majority of the time).
 	 */
 	if (unlikely(!insn)) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
+		if (!(emul_type & EMULTYPE_SKIP))
+			kvm_queue_exception(vcpu, UD_VECTOR);
 		return false;
 	}
 
@@ -5112,9 +5160,11 @@ static __init int svm_hardware_setup(void)
 
 	svm_adjust_mmio_mask();
 
+	nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS);
+
 	/*
 	 * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which
-	 * may be modified by svm_adjust_mmio_mask()).
+	 * may be modified by svm_adjust_mmio_mask()), as well as nrips.
 	 */
 	sev_hardware_setup();
 
@@ -5126,11 +5176,6 @@ static __init int svm_hardware_setup(void)
 			goto err;
 	}
 
-	if (nrips) {
-		if (!boot_cpu_has(X86_FEATURE_NRIPS))
-			nrips = false;
-	}
-
 	enable_apicv = avic = avic && avic_hardware_setup();
 
 	if (!enable_apicv) {