Merge tag 'kvm-ppc-next-5.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD

PPC KVM update for 5.4

- Some prep for extending the uses of the rmap array
- Various minor fixes
- Commits from the powerpc topic/ppc-kvm branch, which fix a problem
  with interrupts arriving after free_irq, causing host hangs and crashes.

11 files changed, 140 insertions, 49 deletions

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 9524d92bc45d..d7fcdfa7fee4 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -1083,9 +1083,11 @@ static int kvmppc_book3s_init(void)
 	if (xics_on_xive()) {
 		kvmppc_xive_init_module();
 		kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
-		kvmppc_xive_native_init_module();
-		kvm_register_device_ops(&kvm_xive_native_ops,
-					KVM_DEV_TYPE_XIVE);
+		if (kvmppc_xive_native_supported()) {
+			kvmppc_xive_native_init_module();
+			kvm_register_device_ops(&kvm_xive_native_ops,
+						KVM_DEV_TYPE_XIVE);
+		}
 	} else
 #endif
 		kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index 653936177857..18f244aad7aa 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -239,6 +239,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 				case 2:
 				case 6:
 					pte->may_write = true;
+					/* fall through */
 				case 3:
 				case 5:
 				case 7:
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index ec1804f822af..f8975c620f41 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1678,7 +1678,14 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		*val = get_reg_val(id, vcpu->arch.pspb);
 		break;
 	case KVM_REG_PPC_DPDES:
-		*val = get_reg_val(id, vcpu->arch.vcore->dpdes);
+		/*
+		 * On POWER9, where we are emulating msgsndp etc.,
+		 * we return 1 bit for each vcpu, which can come from
+		 * either vcore->dpdes or doorbell_request.
+		 * On POWER8, doorbell_request is 0.
+		 */
+		*val = get_reg_val(id, vcpu->arch.vcore->dpdes |
+				   vcpu->arch.doorbell_request);
 		break;
 	case KVM_REG_PPC_VTB:
 		*val = get_reg_val(id, vcpu->arch.vcore->vtb);
@@ -2860,7 +2867,7 @@ static void collect_piggybacks(struct core_info *cip, int target_threads)
 		if (!spin_trylock(&pvc->lock))
 			continue;
 		prepare_threads(pvc);
-		if (!pvc->n_runnable) {
+		if (!pvc->n_runnable || !pvc->kvm->arch.mmu_ready) {
 			list_del_init(&pvc->preempt_list);
 			if (pvc->runner == NULL) {
 				pvc->vcore_state = VCORE_INACTIVE;
@@ -2881,15 +2888,20 @@ static void collect_piggybacks(struct core_info *cip, int target_threads)
 	spin_unlock(&lp->lock);
 }
 
-static bool recheck_signals(struct core_info *cip)
+static bool recheck_signals_and_mmu(struct core_info *cip)
 {
 	int sub, i;
 	struct kvm_vcpu *vcpu;
+	struct kvmppc_vcore *vc;
 
-	for (sub = 0; sub < cip->n_subcores; ++sub)
-		for_each_runnable_thread(i, vcpu, cip->vc[sub])
+	for (sub = 0; sub < cip->n_subcores; ++sub) {
+		vc = cip->vc[sub];
+		if (!vc->kvm->arch.mmu_ready)
+			return true;
+		for_each_runnable_thread(i, vcpu, vc)
 			if (signal_pending(vcpu->arch.run_task))
 				return true;
+	}
 	return false;
 }
 
@@ -3119,7 +3131,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	local_irq_disable();
 	hard_irq_disable();
 	if (lazy_irq_pending() || need_resched() ||
-	    recheck_signals(&core_info) || !vc->kvm->arch.mmu_ready) {
+	    recheck_signals_and_mmu(&core_info)) {
 		local_irq_enable();
 		vc->vcore_state = VCORE_INACTIVE;
 		/* Unlock all except the primary vcore */
@@ -3569,9 +3581,18 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb());
 
 	if (kvmhv_on_pseries()) {
+		/*
+		 * We need to save and restore the guest visible part of the
+		 * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor
+		 * doesn't do this for us. Note only required if pseries since
+		 * this is done in kvmhv_load_hv_regs_and_go() below otherwise.
+		 */
+		unsigned long host_psscr;
 		/* call our hypervisor to load up HV regs and go */
 		struct hv_guest_state hvregs;
 
+		host_psscr = mfspr(SPRN_PSSCR_PR);
+		mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr);
 		kvmhv_save_hv_regs(vcpu, &hvregs);
 		hvregs.lpcr = lpcr;
 		vcpu->arch.regs.msr = vcpu->arch.shregs.msr;
@@ -3590,6 +3611,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 		vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
 		vcpu->arch.shregs.dar = mfspr(SPRN_DAR);
 		vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR);
+		vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR);
+		mtspr(SPRN_PSSCR_PR, host_psscr);
 
 		/* H_CEDE has to be handled now, not later */
 		if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
@@ -3654,6 +3677,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 		vcpu->arch.vpa.dirty = 1;
 		save_pmu = lp->pmcregs_in_use;
 	}
+	/* Must save pmu if this guest is capable of running nested guests */
+	save_pmu |= nesting_enabled(vcpu->kvm);
 
 	kvmhv_save_guest_pmu(vcpu, save_pmu);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 63e0ce91e29d..7186c65c61c9 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -99,7 +99,7 @@ void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
 	} else {
 		rev->forw = rev->back = pte_index;
 		*rmap = (*rmap & ~KVMPPC_RMAP_INDEX) |
-			pte_index | KVMPPC_RMAP_PRESENT;
+			pte_index | KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_HPT;
 	}
 	unlock_rmap(rmap);
 }
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 337e64468d78..07181d0dfcb7 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -942,6 +942,8 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
 	li	r9, TM_QW1_OS
 	lwz	r8, VCPU_XIVE_CAM_WORD(r4)
+	cmpwi	r8, 0
+	beq	no_xive
 	li	r7, TM_QW1_OS + TM_WORD2
 	mfmsr	r0
 	andi.	r0, r0, MSR_DR		/* in real mode? */
@@ -2831,29 +2833,39 @@ kvm_cede_prodded:
 kvm_cede_exit:
 	ld	r9, HSTATE_KVM_VCPU(r13)
 #ifdef CONFIG_KVM_XICS
-	/* Abort if we still have a pending escalation */
+	/* are we using XIVE with single escalation? */
+	ld	r10, VCPU_XIVE_ESC_VADDR(r9)
+	cmpdi	r10, 0
+	beq	3f
+	li	r6, XIVE_ESB_SET_PQ_00
+	/*
+	 * If we still have a pending escalation, abort the cede,
+	 * and we must set PQ to 10 rather than 00 so that we don't
+	 * potentially end up with two entries for the escalation
+	 * interrupt in the XIVE interrupt queue.  In that case
+	 * we also don't want to set xive_esc_on to 1 here in
+	 * case we race with xive_esc_irq().
+	 */
 	lbz	r5, VCPU_XIVE_ESC_ON(r9)
 	cmpwi	r5, 0
-	beq	1f
+	beq	4f
 	li	r0, 0
 	stb	r0, VCPU_CEDED(r9)
-1:	/* Enable XIVE escalation */
-	li	r5, XIVE_ESB_SET_PQ_00
+	li	r6, XIVE_ESB_SET_PQ_10
+	b	5f
+4:	li	r0, 1
+	stb	r0, VCPU_XIVE_ESC_ON(r9)
+	/* make sure store to xive_esc_on is seen before xive_esc_irq runs */
+	sync
+5:	/* Enable XIVE escalation */
 	mfmsr	r0
 	andi.	r0, r0, MSR_DR		/* in real mode? */
 	beq	1f
-	ld	r10, VCPU_XIVE_ESC_VADDR(r9)
-	cmpdi	r10, 0
-	beq	3f
-	ldx	r0, r10, r5
+	ldx	r0, r10, r6
 	b	2f
 1:	ld	r10, VCPU_XIVE_ESC_RADDR(r9)
-	cmpdi	r10, 0
-	beq	3f
-	ldcix	r0, r10, r5
+	ldcix	r0, r10, r6
 2:	sync
-	li	r0, 1
-	stb	r0, VCPU_XIVE_ESC_ON(r9)
 #endif /* CONFIG_KVM_XICS */
 3:	b	guest_exit_cont
 
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 6ca0d7376a9f..591bfb4bfd0f 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -67,8 +67,14 @@ void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu)
 	void __iomem *tima = local_paca->kvm_hstate.xive_tima_virt;
 	u64 pq;
 
-	if (!tima)
+	/*
+	 * Nothing to do if the platform doesn't have a XIVE
+	 * or this vCPU doesn't have its own XIVE context
+	 * (e.g. because it's not using an in-kernel interrupt controller).
+	 */
+	if (!tima || !vcpu->arch.xive_cam_word)
 		return;
+
 	eieio();
 	__raw_writeq(vcpu->arch.xive_saved_state.w01, tima + TM_QW1_OS);
 	__raw_writel(vcpu->arch.xive_cam_word, tima + TM_QW1_OS + TM_WORD2);
@@ -160,6 +166,9 @@ static irqreturn_t xive_esc_irq(int irq, void *data)
 	 */
 	vcpu->arch.xive_esc_on = false;
 
+	/* This orders xive_esc_on = false vs. subsequent stale_p = true */
+	smp_wmb();	/* goes with smp_mb() in cleanup_single_escalation */
+
 	return IRQ_HANDLED;
 }
 
@@ -1113,6 +1122,31 @@ void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
 	vcpu->arch.xive_esc_raddr = 0;
 }
 
+/*
+ * In single escalation mode, the escalation interrupt is marked so
+ * that EOI doesn't re-enable it, but just sets the stale_p flag to
+ * indicate that the P bit has already been dealt with.  However, the
+ * assembly code that enters the guest sets PQ to 00 without clearing
+ * stale_p (because it has no easy way to address it).  Hence we have
+ * to adjust stale_p before shutting down the interrupt.
+ */
+void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu,
+				    struct kvmppc_xive_vcpu *xc, int irq)
+{
+	struct irq_data *d = irq_get_irq_data(irq);
+	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+
+	/*
+	 * This slightly odd sequence gives the right result
+	 * (i.e. stale_p set if xive_esc_on is false) even if
+	 * we race with xive_esc_irq() and xive_irq_eoi().
+	 */
+	xd->stale_p = false;
+	smp_mb();		/* paired with smb_wmb in xive_esc_irq */
+	if (!vcpu->arch.xive_esc_on)
+		xd->stale_p = true;
+}
+
 void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
@@ -1134,20 +1168,28 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
 	/* Mask the VP IPI */
 	xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_01);
 
-	/* Disable the VP */
-	xive_native_disable_vp(xc->vp_id);
-
-	/* Free the queues & associated interrupts */
+	/* Free escalations */
 	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
-		struct xive_q *q = &xc->queues[i];
-
-		/* Free the escalation irq */
 		if (xc->esc_virq[i]) {
+			if (xc->xive->single_escalation)
+				xive_cleanup_single_escalation(vcpu, xc,
+							xc->esc_virq[i]);
 			free_irq(xc->esc_virq[i], vcpu);
 			irq_dispose_mapping(xc->esc_virq[i]);
 			kfree(xc->esc_virq_names[i]);
 		}
-		/* Free the queue */
+	}
+
+	/* Disable the VP */
+	xive_native_disable_vp(xc->vp_id);
+
+	/* Clear the cam word so guest entry won't try to push context */
+	vcpu->arch.xive_cam_word = 0;
+
+	/* Free the queues */
+	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+		struct xive_q *q = &xc->queues[i];
+
 		xive_native_disable_queue(xc->vp_id, q, i);
 		if (q->qpage) {
 			free_pages((unsigned long)q->qpage,
@@ -1986,10 +2028,8 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 
 	xive->single_escalation = xive_native_has_single_escalation();
 
-	if (ret) {
-		kfree(xive);
+	if (ret)
 		return ret;
-	}
 
 	return 0;
 }
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index 50494d0ee375..955b820ffd6d 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -282,6 +282,8 @@ int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio);
 int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
 				  bool single_escalation);
 struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type);
+void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu,
+				    struct kvmppc_xive_vcpu *xc, int irq);
 
 #endif /* CONFIG_KVM_XICS */
 #endif /* _KVM_PPC_BOOK3S_XICS_H */
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index 5596c8ec221a..248c1ea9e788 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -67,20 +67,28 @@ void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu)
 	xc->valid = false;
 	kvmppc_xive_disable_vcpu_interrupts(vcpu);
 
-	/* Disable the VP */
-	xive_native_disable_vp(xc->vp_id);
-
-	/* Free the queues & associated interrupts */
+	/* Free escalations */
 	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
 		/* Free the escalation irq */
 		if (xc->esc_virq[i]) {
+			if (xc->xive->single_escalation)
+				xive_cleanup_single_escalation(vcpu, xc,
+							xc->esc_virq[i]);
 			free_irq(xc->esc_virq[i], vcpu);
 			irq_dispose_mapping(xc->esc_virq[i]);
 			kfree(xc->esc_virq_names[i]);
 			xc->esc_virq[i] = 0;
 		}
+	}
+
+	/* Disable the VP */
+	xive_native_disable_vp(xc->vp_id);
 
-		/* Free the queue */
+	/* Clear the cam word so guest entry won't try to push context */
+	vcpu->arch.xive_cam_word = 0;
+
+	/* Free the queues */
+	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
 		kvmppc_xive_native_cleanup_queue(vcpu, i);
 	}
 
@@ -1090,9 +1098,9 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
 	xive->ops = &kvmppc_xive_native_ops;
 
 	if (ret)
-		kfree(xive);
+		return ret;
 
-	return ret;
+	return 0;
 }
 
 /*
@@ -1171,6 +1179,11 @@ int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val)
 	return 0;
 }
 
+bool kvmppc_xive_native_supported(void)
+{
+	return xive_native_has_queue_state_support();
+}
+
 static int xive_native_debug_show(struct seq_file *m, void *private)
 {
 	struct kvmppc_xive *xive = m->private;
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index bb4d09c1ad56..6fca38ca791f 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -271,6 +271,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		 */
 		if (inst == KVMPPC_INST_SW_BREAKPOINT) {
 			run->exit_reason = KVM_EXIT_DEBUG;
+			run->debug.arch.status = 0;
 			run->debug.arch.address = kvmppc_get_pc(vcpu);
 			emulated = EMULATE_EXIT_USER;
 			advance = 0;
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 9208c82ed08d..2e496eb86e94 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -89,12 +89,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	rs = get_rs(inst);
 	rt = get_rt(inst);
 
-	/*
-	 * if mmio_vsx_tx_sx_enabled == 0, copy data between
-	 * VSR[0..31] and memory
-	 * if mmio_vsx_tx_sx_enabled == 1, copy data between
-	 * VSR[32..63] and memory
-	 */
 	vcpu->arch.mmio_vsx_copy_nums = 0;
 	vcpu->arch.mmio_vsx_offset = 0;
 	vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3e566c2e6066..3a77bb643452 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -561,7 +561,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 * a POWER9 processor) and the PowerNV platform, as
 		 * nested is not yet supported.
 		 */
-		r = xive_enabled() && !!cpu_has_feature(CPU_FTR_HVMODE);
+		r = xive_enabled() && !!cpu_has_feature(CPU_FTR_HVMODE) &&
+			kvmppc_xive_native_supported();
 		break;
 #endif