1 files changed, 62 insertions, 45 deletions

diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index a998823f68a3..6ef0151ff70a 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -50,6 +50,24 @@ static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio)
 	}
 }
 
+static int kvmppc_xive_native_configure_queue(u32 vp_id, struct xive_q *q,
+					      u8 prio, __be32 *qpage,
+					      u32 order, bool can_escalate)
+{
+	int rc;
+	__be32 *qpage_prev = q->qpage;
+
+	rc = xive_native_configure_queue(vp_id, q, prio, qpage, order,
+					 can_escalate);
+	if (rc)
+		return rc;
+
+	if (qpage_prev)
+		put_page(virt_to_page(qpage_prev));
+
+	return rc;
+}
+
 void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
@@ -67,20 +85,28 @@ 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);
 	}
 
@@ -98,6 +124,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 	struct kvmppc_xive *xive = dev->private;
 	struct kvmppc_xive_vcpu *xc = NULL;
 	int rc;
+	u32 vp_id;
 
 	pr_devel("native_connect_vcpu(server=%d)\n", server_num);
 
@@ -109,18 +136,12 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 		return -EPERM;
 	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
 		return -EBUSY;
-	if (server_num >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) {
-		pr_devel("Out of bounds !\n");
-		return -EINVAL;
-	}
 
 	mutex_lock(&xive->lock);
 
-	if (kvmppc_xive_find_server(vcpu->kvm, server_num)) {
-		pr_devel("Duplicate !\n");
-		rc = -EEXIST;
+	rc = kvmppc_xive_compute_vp_id(xive, server_num, &vp_id);
+	if (rc)
 		goto bail;
-	}
 
 	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
 	if (!xc) {
@@ -133,7 +154,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 	xc->vcpu = vcpu;
 	xc->server_num = server_num;
 
-	xc->vp_id = kvmppc_xive_vp(xive, server_num);
+	xc->vp_id = vp_id;
 	xc->valid = true;
 	vcpu->arch.irq_type = KVMPPC_IRQ_XIVE;
 
@@ -572,19 +593,14 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 		q->guest_qaddr  = 0;
 		q->guest_qshift = 0;
 
-		rc = xive_native_configure_queue(xc->vp_id, q, priority,
-						 NULL, 0, true);
+		rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority,
+							NULL, 0, true);
 		if (rc) {
 			pr_err("Failed to reset queue %d for VCPU %d: %d\n",
 			       priority, xc->server_num, rc);
 			return rc;
 		}
 
-		if (q->qpage) {
-			put_page(virt_to_page(q->qpage));
-			q->qpage = NULL;
-		}
-
 		return 0;
 	}
 
@@ -614,17 +630,18 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	gfn = gpa_to_gfn(kvm_eq.qaddr);
-	page = gfn_to_page(kvm, gfn);
-	if (is_error_page(page)) {
+
+	page_size = kvm_host_page_size(vcpu, gfn);
+	if (1ull << kvm_eq.qshift > page_size) {
 		srcu_read_unlock(&kvm->srcu, srcu_idx);
-		pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
+		pr_warn("Incompatible host page size %lx!\n", page_size);
 		return -EINVAL;
 	}
 
-	page_size = kvm_host_page_size(kvm, gfn);
-	if (1ull << kvm_eq.qshift > page_size) {
+	page = gfn_to_page(kvm, gfn);
+	if (is_error_page(page)) {
 		srcu_read_unlock(&kvm->srcu, srcu_idx);
-		pr_warn("Incompatible host page size %lx!\n", page_size);
+		pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
 		return -EINVAL;
 	}
 
@@ -643,8 +660,8 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 	  * OPAL level because the use of END ESBs is not supported by
 	  * Linux.
 	  */
-	rc = xive_native_configure_queue(xc->vp_id, q, priority,
-					 (__be32 *) qaddr, kvm_eq.qshift, true);
+	rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority,
+					(__be32 *) qaddr, kvm_eq.qshift, true);
 	if (rc) {
 		pr_err("Failed to configure queue %d for VCPU %d: %d\n",
 		       priority, xc->server_num, rc);
@@ -918,6 +935,8 @@ static int kvmppc_xive_native_set_attr(struct kvm_device *dev,
 			return kvmppc_xive_reset(xive);
 		case KVM_DEV_XIVE_EQ_SYNC:
 			return kvmppc_xive_native_eq_sync(xive);
+		case KVM_DEV_XIVE_NR_SERVERS:
+			return kvmppc_xive_set_nr_servers(xive, attr->addr);
 		}
 		break;
 	case KVM_DEV_XIVE_GRP_SOURCE:
@@ -957,6 +976,7 @@ static int kvmppc_xive_native_has_attr(struct kvm_device *dev,
 		switch (attr->attr) {
 		case KVM_DEV_XIVE_RESET:
 		case KVM_DEV_XIVE_EQ_SYNC:
+		case KVM_DEV_XIVE_NR_SERVERS:
 			return 0;
 		}
 		break;
@@ -1057,7 +1077,6 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
 {
 	struct kvmppc_xive *xive;
 	struct kvm *kvm = dev->kvm;
-	int ret = 0;
 
 	pr_devel("Creating xive native device\n");
 
@@ -1071,27 +1090,20 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
 	dev->private = xive;
 	xive->dev = dev;
 	xive->kvm = kvm;
-	kvm->arch.xive = xive;
 	mutex_init(&xive->mapping_lock);
 	mutex_init(&xive->lock);
 
-	/*
-	 * Allocate a bunch of VPs. KVM_MAX_VCPUS is a large value for
-	 * a default. Getting the max number of CPUs the VM was
-	 * configured with would improve our usage of the XIVE VP space.
+	/* VP allocation is delayed to the first call to connect_vcpu */
+	xive->vp_base = XIVE_INVALID_VP;
+	/* KVM_MAX_VCPUS limits the number of VMs to roughly 64 per sockets
+	 * on a POWER9 system.
 	 */
-	xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS);
-	pr_devel("VP_Base=%x\n", xive->vp_base);
-
-	if (xive->vp_base == XIVE_INVALID_VP)
-		ret = -ENXIO;
+	xive->nr_servers = KVM_MAX_VCPUS;
 
 	xive->single_escalation = xive_native_has_single_escalation();
 	xive->ops = &kvmppc_xive_native_ops;
 
-	if (ret)
-		return ret;
-
+	kvm->arch.xive = xive;
 	return 0;
 }
 
@@ -1171,6 +1183,11 @@ 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;
@@ -1189,8 +1206,8 @@ static int xive_native_debug_show(struct seq_file *m, void *private)
 		if (!xc)
 			continue;
 
-		seq_printf(m, "cpu server %#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n",
-			   xc->server_num,
+		seq_printf(m, "cpu server %#x VP=%#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n",
+			   xc->server_num, xc->vp_id,
 			   vcpu->arch.xive_saved_state.nsr,
 			   vcpu->arch.xive_saved_state.cppr,
 			   vcpu->arch.xive_saved_state.ipb,