Merge commit 'origin/master' into next

Conflicts:
	include/linux/kvm.h

1 files changed, 136 insertions, 95 deletions

diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 001663ff401a..9b077342ab54 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -31,20 +31,39 @@
 
 #include "ioapic.h"
 
+static inline int kvm_irq_line_state(unsigned long *irq_state,
+				     int irq_source_id, int level)
+{
+	/* Logical OR for level trig interrupt */
+	if (level)
+		set_bit(irq_source_id, irq_state);
+	else
+		clear_bit(irq_source_id, irq_state);
+
+	return !!(*irq_state);
+}
+
 static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
-			   struct kvm *kvm, int level)
+			   struct kvm *kvm, int irq_source_id, int level)
 {
 #ifdef CONFIG_X86
-	return kvm_pic_set_irq(pic_irqchip(kvm), e->irqchip.pin, level);
+	struct kvm_pic *pic = pic_irqchip(kvm);
+	level = kvm_irq_line_state(&pic->irq_states[e->irqchip.pin],
+				   irq_source_id, level);
+	return kvm_pic_set_irq(pic, e->irqchip.pin, level);
 #else
 	return -1;
 #endif
 }
 
 static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
-			      struct kvm *kvm, int level)
+			      struct kvm *kvm, int irq_source_id, int level)
 {
-	return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level);
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+	level = kvm_irq_line_state(&ioapic->irq_states[e->irqchip.pin],
+				   irq_source_id, level);
+
+	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, level);
 }
 
 inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
@@ -63,8 +82,6 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	int i, r = -1;
 	struct kvm_vcpu *vcpu, *lowest = NULL;
 
-	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
-
 	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
 			kvm_is_dm_lowest_prio(irq))
 		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
@@ -96,10 +113,13 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 }
 
 static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
-		       struct kvm *kvm, int level)
+		       struct kvm *kvm, int irq_source_id, int level)
 {
 	struct kvm_lapic_irq irq;
 
+	if (!level)
+		return -1;
+
 	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
 
 	irq.dest_id = (e->msi.address_lo &
@@ -116,78 +136,67 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
-/* This should be called with the kvm->irq_lock mutex held
+/*
  * Return value:
  *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
  *  = 0   Interrupt was coalesced (previous irq is still pending)
  *  > 0   Number of CPUs interrupt was delivered to
  */
-int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level)
+int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 {
-	struct kvm_kernel_irq_routing_entry *e;
-	unsigned long *irq_state, sig_level;
-	int ret = -1;
+	struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS];
+	int ret = -1, i = 0;
+	struct kvm_irq_routing_table *irq_rt;
+	struct hlist_node *n;
 
 	trace_kvm_set_irq(irq, level, irq_source_id);
 
-	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
-
-	if (irq < KVM_IOAPIC_NUM_PINS) {
-		irq_state = (unsigned long *)&kvm->arch.irq_states[irq];
-
-		/* Logical OR for level trig interrupt */
-		if (level)
-			set_bit(irq_source_id, irq_state);
-		else
-			clear_bit(irq_source_id, irq_state);
-		sig_level = !!(*irq_state);
-	} else if (!level)
-		return ret;
-	else /* Deal with MSI/MSI-X */
-		sig_level = 1;
-
 	/* Not possible to detect if the guest uses the PIC or the
 	 * IOAPIC.  So set the bit in both. The guest will ignore
 	 * writes to the unused one.
 	 */
-	list_for_each_entry(e, &kvm->irq_routing, link)
-		if (e->gsi == irq) {
-			int r = e->set(e, kvm, sig_level);
-			if (r < 0)
-				continue;
+	rcu_read_lock();
+	irq_rt = rcu_dereference(kvm->irq_routing);
+	if (irq < irq_rt->nr_rt_entries)
+		hlist_for_each_entry(e, n, &irq_rt->map[irq], link)
+			irq_set[i++] = *e;
+	rcu_read_unlock();
+
+	while(i--) {
+		int r;
+		r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level);
+		if (r < 0)
+			continue;
+
+		ret = r + ((ret < 0) ? 0 : ret);
+	}
 
-			ret = r + ((ret < 0) ? 0 : ret);
-		}
 	return ret;
 }
 
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
-	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_ack_notifier *kian;
 	struct hlist_node *n;
-	unsigned gsi = pin;
+	int gsi;
 
 	trace_kvm_ack_irq(irqchip, pin);
 
-	list_for_each_entry(e, &kvm->irq_routing, link)
-		if (e->type == KVM_IRQ_ROUTING_IRQCHIP &&
-		    e->irqchip.irqchip == irqchip &&
-		    e->irqchip.pin == pin) {
-			gsi = e->gsi;
-			break;
-		}
-
-	hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link)
-		if (kian->gsi == gsi)
-			kian->irq_acked(kian);
+	rcu_read_lock();
+	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+	if (gsi != -1)
+		hlist_for_each_entry_rcu(kian, n, &kvm->irq_ack_notifier_list,
+					 link)
+			if (kian->gsi == gsi)
+				kian->irq_acked(kian);
+	rcu_read_unlock();
 }
 
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian)
 {
 	mutex_lock(&kvm->irq_lock);
-	hlist_add_head(&kian->link, &kvm->arch.irq_ack_notifier_list);
+	hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
 	mutex_unlock(&kvm->irq_lock);
 }
 
@@ -195,8 +204,9 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 				    struct kvm_irq_ack_notifier *kian)
 {
 	mutex_lock(&kvm->irq_lock);
-	hlist_del_init(&kian->link);
+	hlist_del_init_rcu(&kian->link);
 	mutex_unlock(&kvm->irq_lock);
+	synchronize_rcu();
 }
 
 int kvm_request_irq_source_id(struct kvm *kvm)
@@ -205,16 +215,17 @@ int kvm_request_irq_source_id(struct kvm *kvm)
 	int irq_source_id;
 
 	mutex_lock(&kvm->irq_lock);
-	irq_source_id = find_first_zero_bit(bitmap,
-				sizeof(kvm->arch.irq_sources_bitmap));
+	irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);
 
-	if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
+	if (irq_source_id >= BITS_PER_LONG) {
 		printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n");
-		return -EFAULT;
+		irq_source_id = -EFAULT;
+		goto unlock;
 	}
 
 	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
 	set_bit(irq_source_id, bitmap);
+unlock:
 	mutex_unlock(&kvm->irq_lock);
 
 	return irq_source_id;
@@ -228,13 +239,23 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 
 	mutex_lock(&kvm->irq_lock);
 	if (irq_source_id < 0 ||
-	    irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
+	    irq_source_id >= BITS_PER_LONG) {
 		printk(KERN_ERR "kvm: IRQ source ID out of range!\n");
-		return;
+		goto unlock;
 	}
-	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
-		clear_bit(irq_source_id, &kvm->arch.irq_states[i]);
 	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
+	if (!irqchip_in_kernel(kvm))
+		goto unlock;
+
+	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) {
+		clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]);
+		if (i >= 16)
+			continue;
+#ifdef CONFIG_X86
+		clear_bit(irq_source_id, &pic_irqchip(kvm)->irq_states[i]);
+#endif
+	}
+unlock:
 	mutex_unlock(&kvm->irq_lock);
 }
 
@@ -243,7 +264,7 @@ void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
 {
 	mutex_lock(&kvm->irq_lock);
 	kimn->irq = irq;
-	hlist_add_head(&kimn->link, &kvm->mask_notifier_list);
+	hlist_add_head_rcu(&kimn->link, &kvm->mask_notifier_list);
 	mutex_unlock(&kvm->irq_lock);
 }
 
@@ -251,8 +272,9 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 				      struct kvm_irq_mask_notifier *kimn)
 {
 	mutex_lock(&kvm->irq_lock);
-	hlist_del(&kimn->link);
+	hlist_del_rcu(&kimn->link);
 	mutex_unlock(&kvm->irq_lock);
+	synchronize_rcu();
 }
 
 void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
@@ -260,33 +282,37 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
 	struct kvm_irq_mask_notifier *kimn;
 	struct hlist_node *n;
 
-	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
-
-	hlist_for_each_entry(kimn, n, &kvm->mask_notifier_list, link)
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(kimn, n, &kvm->mask_notifier_list, link)
 		if (kimn->irq == irq)
 			kimn->func(kimn, mask);
-}
-
-static void __kvm_free_irq_routing(struct list_head *irq_routing)
-{
-	struct kvm_kernel_irq_routing_entry *e, *n;
-
-	list_for_each_entry_safe(e, n, irq_routing, link)
-		kfree(e);
+	rcu_read_unlock();
 }
 
 void kvm_free_irq_routing(struct kvm *kvm)
 {
-	mutex_lock(&kvm->irq_lock);
-	__kvm_free_irq_routing(&kvm->irq_routing);
-	mutex_unlock(&kvm->irq_lock);
+	/* Called only during vm destruction. Nobody can use the pointer
+	   at this stage */
+	kfree(kvm->irq_routing);
 }
 
-static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
+static int setup_routing_entry(struct kvm_irq_routing_table *rt,
+			       struct kvm_kernel_irq_routing_entry *e,
 			       const struct kvm_irq_routing_entry *ue)
 {
 	int r = -EINVAL;
 	int delta;
+	struct kvm_kernel_irq_routing_entry *ei;
+	struct hlist_node *n;
+
+	/*
+	 * Do not allow GSI to be mapped to the same irqchip more than once.
+	 * Allow only one to one mapping between GSI and MSI.
+	 */
+	hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link)
+		if (ei->type == KVM_IRQ_ROUTING_MSI ||
+		    ue->u.irqchip.irqchip == ei->irqchip.irqchip)
+			return r;
 
 	e->gsi = ue->gsi;
 	e->type = ue->type;
@@ -309,6 +335,9 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 		}
 		e->irqchip.irqchip = ue->u.irqchip.irqchip;
 		e->irqchip.pin = ue->u.irqchip.pin + delta;
+		if (e->irqchip.pin >= KVM_IOAPIC_NUM_PINS)
+			goto out;
+		rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi;
 		break;
 	case KVM_IRQ_ROUTING_MSI:
 		e->set = kvm_set_msi;
@@ -319,6 +348,8 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 	default:
 		goto out;
 	}
+
+	hlist_add_head(&e->link, &rt->map[e->gsi]);
 	r = 0;
 out:
 	return r;
@@ -330,43 +361,53 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			unsigned nr,
 			unsigned flags)
 {
-	struct list_head irq_list = LIST_HEAD_INIT(irq_list);
-	struct list_head tmp = LIST_HEAD_INIT(tmp);
-	struct kvm_kernel_irq_routing_entry *e = NULL;
-	unsigned i;
+	struct kvm_irq_routing_table *new, *old;
+	u32 i, j, nr_rt_entries = 0;
 	int r;
 
 	for (i = 0; i < nr; ++i) {
+		if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES)
+			return -EINVAL;
+		nr_rt_entries = max(nr_rt_entries, ue[i].gsi);
+	}
+
+	nr_rt_entries += 1;
+
+	new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head))
+		      + (nr * sizeof(struct kvm_kernel_irq_routing_entry)),
+		      GFP_KERNEL);
+
+	if (!new)
+		return -ENOMEM;
+
+	new->rt_entries = (void *)&new->map[nr_rt_entries];
+
+	new->nr_rt_entries = nr_rt_entries;
+	for (i = 0; i < 3; i++)
+		for (j = 0; j < KVM_IOAPIC_NUM_PINS; j++)
+			new->chip[i][j] = -1;
+
+	for (i = 0; i < nr; ++i) {
 		r = -EINVAL;
-		if (ue->gsi >= KVM_MAX_IRQ_ROUTES)
-			goto out;
 		if (ue->flags)
 			goto out;
-		r = -ENOMEM;
-		e = kzalloc(sizeof(*e), GFP_KERNEL);
-		if (!e)
-			goto out;
-		r = setup_routing_entry(e, ue);
+		r = setup_routing_entry(new, &new->rt_entries[i], ue);
 		if (r)
 			goto out;
 		++ue;
-		list_add(&e->link, &irq_list);
-		e = NULL;
 	}
 
 	mutex_lock(&kvm->irq_lock);
-	list_splice(&kvm->irq_routing, &tmp);
-	INIT_LIST_HEAD(&kvm->irq_routing);
-	list_splice(&irq_list, &kvm->irq_routing);
-	INIT_LIST_HEAD(&irq_list);
-	list_splice(&tmp, &irq_list);
+	old = kvm->irq_routing;
+	rcu_assign_pointer(kvm->irq_routing, new);
 	mutex_unlock(&kvm->irq_lock);
+	synchronize_rcu();
 
+	new = old;
 	r = 0;
 
 out:
-	kfree(e);
-	__kvm_free_irq_routing(&irq_list);
+	kfree(new);
 	return r;
 }