1 files changed, 143 insertions, 161 deletions

diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index a8bd466d00c..ced4a542a03 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -17,9 +17,13 @@
  * Authors:
  *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
  *
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
  */
 
 #include <linux/kvm_host.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <trace/events/kvm.h>
 
 #include <asm/msidef.h>
 #ifdef CONFIG_IA64
@@ -31,19 +35,24 @@
 #include "ioapic.h"
 
 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,
+			   bool line_status)
 {
 #ifdef CONFIG_X86
-	return kvm_pic_set_irq(pic_irqchip(kvm), e->irqchip.pin, level);
+	struct kvm_pic *pic = pic_irqchip(kvm);
+	return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, 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,
+			      bool line_status)
 {
-	return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level);
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
+				line_status);
 }
 
 inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
@@ -57,19 +66,22 @@ inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
 }
 
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
-		struct kvm_lapic_irq *irq)
+		struct kvm_lapic_irq *irq, unsigned long *dest_map)
 {
 	int i, r = -1;
 	struct kvm_vcpu *vcpu, *lowest = NULL;
 
 	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
-			kvm_is_dm_lowest_prio(irq))
+			kvm_is_dm_lowest_prio(irq)) {
 		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
+		irq->delivery_mode = APIC_DM_FIXED;
+	}
 
-	for (i = 0; i < KVM_MAX_VCPUS; i++) {
-		vcpu = kvm->vcpus[i];
+	if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
+		return r;
 
-		if (!vcpu || !kvm_apic_present(vcpu))
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_apic_present(vcpu))
 			continue;
 
 		if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
@@ -79,8 +91,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 		if (!kvm_is_dm_lowest_prio(irq)) {
 			if (r < 0)
 				r = 0;
-			r += kvm_apic_set_irq(vcpu, irq);
-		} else {
+			r += kvm_apic_set_irq(vcpu, irq, dest_map);
+		} else if (kvm_lapic_enabled(vcpu)) {
 			if (!lowest)
 				lowest = vcpu;
 			else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
@@ -89,188 +101,200 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	}
 
 	if (lowest)
-		r = kvm_apic_set_irq(lowest, irq);
+		r = kvm_apic_set_irq(lowest, irq, dest_map);
 
 	return r;
 }
 
-static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
-		       struct kvm *kvm, int level)
+static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+				   struct kvm_lapic_irq *irq)
 {
-	struct kvm_lapic_irq irq;
+	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
 
-	irq.dest_id = (e->msi.address_lo &
+	irq->dest_id = (e->msi.address_lo &
 			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
-	irq.vector = (e->msi.data &
+	irq->vector = (e->msi.data &
 			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
-	irq.dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
-	irq.trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
-	irq.delivery_mode = e->msi.data & 0x700;
-	irq.level = 1;
-	irq.shorthand = 0;
-
+	irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
+	irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
+	irq->delivery_mode = e->msi.data & 0x700;
+	irq->level = 1;
+	irq->shorthand = 0;
 	/* TODO Deal with RH bit of MSI message address */
-	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
-/* This should be called with the kvm->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_msi(struct kvm_kernel_irq_routing_entry *e,
+		struct kvm *kvm, int irq_source_id, int level, bool line_status)
 {
-	struct kvm_kernel_irq_routing_entry *e;
-	unsigned long *irq_state, sig_level;
-	int ret = -1;
-
-	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 /* 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;
+	struct kvm_lapic_irq irq;
 
-			ret = r + ((ret < 0) ? 0 : ret);
-		}
-	return ret;
-}
+	if (!level)
+		return -1;
 
-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;
-
-	list_for_each_entry(e, &kvm->irq_routing, link)
-		if (e->irqchip.irqchip == irqchip &&
-		    e->irqchip.pin == pin) {
-			gsi = e->gsi;
-			break;
-		}
+	kvm_set_msi_irq(e, &irq);
 
-	hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link)
-		if (kian->gsi == gsi)
-			kian->irq_acked(kian);
+	return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
 }
 
-void kvm_register_irq_ack_notifier(struct kvm *kvm,
-				   struct kvm_irq_ack_notifier *kian)
+
+static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
+			 struct kvm *kvm)
 {
-	hlist_add_head(&kian->link, &kvm->arch.irq_ack_notifier_list);
+	struct kvm_lapic_irq irq;
+	int r;
+
+	kvm_set_msi_irq(e, &irq);
+
+	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
+		return r;
+	else
+		return -EWOULDBLOCK;
 }
 
-void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian)
+/*
+ * Deliver an IRQ in an atomic context if we can, or return a failure,
+ * user can retry in a process context.
+ * Return value:
+ *  -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context.
+ *  Other values - No need to retry.
+ */
+int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 {
-	hlist_del_init(&kian->link);
+	struct kvm_kernel_irq_routing_entry *e;
+	int ret = -EINVAL;
+	struct kvm_irq_routing_table *irq_rt;
+	int idx;
+
+	trace_kvm_set_irq(irq, level, irq_source_id);
+
+	/*
+	 * Injection into either PIC or IOAPIC might need to scan all CPUs,
+	 * which would need to be retried from thread context;  when same GSI
+	 * is connected to both PIC and IOAPIC, we'd have to report a
+	 * partial failure here.
+	 * Since there's no easy way to do this, we only support injecting MSI
+	 * which is limited to 1:1 GSI mapping.
+	 */
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+	if (irq < irq_rt->nr_rt_entries)
+		hlist_for_each_entry(e, &irq_rt->map[irq], link) {
+			if (likely(e->type == KVM_IRQ_ROUTING_MSI))
+				ret = kvm_set_msi_inatomic(e, kvm);
+			else
+				ret = -EWOULDBLOCK;
+			break;
+		}
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+	return ret;
 }
 
-/* The caller must hold kvm->lock mutex */
 int kvm_request_irq_source_id(struct kvm *kvm)
 {
 	unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
-	int irq_source_id = find_first_zero_bit(bitmap,
-				sizeof(kvm->arch.irq_sources_bitmap));
+	int irq_source_id;
+
+	mutex_lock(&kvm->irq_lock);
+	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);
+#ifdef CONFIG_X86
+	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
+#endif
 	set_bit(irq_source_id, bitmap);
+unlock:
+	mutex_unlock(&kvm->irq_lock);
 
 	return irq_source_id;
 }
 
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 {
-	int i;
-
 	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
+#ifdef CONFIG_X86
+	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
+#endif
 
+	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;
+
+	kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
+#ifdef CONFIG_X86
+	kvm_pic_clear_all(pic_irqchip(kvm), irq_source_id);
+#endif
+unlock:
+	mutex_unlock(&kvm->irq_lock);
 }
 
 void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
 				    struct kvm_irq_mask_notifier *kimn)
 {
+	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);
 }
 
 void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 				      struct kvm_irq_mask_notifier *kimn)
 {
-	hlist_del(&kimn->link);
+	mutex_lock(&kvm->irq_lock);
+	hlist_del_rcu(&kimn->link);
+	mutex_unlock(&kvm->irq_lock);
+	synchronize_srcu(&kvm->irq_srcu);
 }
 
-void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
+void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
+			     bool mask)
 {
 	struct kvm_irq_mask_notifier *kimn;
-	struct hlist_node *n;
-
-	hlist_for_each_entry(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);
-}
-
-void kvm_free_irq_routing(struct kvm *kvm)
-{
-	__kvm_free_irq_routing(&kvm->irq_routing);
+	int idx, gsi;
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin];
+	if (gsi != -1)
+		hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link)
+			if (kimn->irq == gsi)
+				kimn->func(kimn, mask);
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
-static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
-			       const struct kvm_irq_routing_entry *ue)
+int kvm_set_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;
+	unsigned max_pin;
 
-	e->gsi = ue->gsi;
 	switch (ue->type) {
 	case KVM_IRQ_ROUTING_IRQCHIP:
 		delta = 0;
 		switch (ue->u.irqchip.irqchip) {
 		case KVM_IRQCHIP_PIC_MASTER:
 			e->set = kvm_set_pic_irq;
+			max_pin = PIC_NUM_PINS;
 			break;
 		case KVM_IRQCHIP_PIC_SLAVE:
 			e->set = kvm_set_pic_irq;
+			max_pin = PIC_NUM_PINS;
 			delta = 8;
 			break;
 		case KVM_IRQCHIP_IOAPIC:
+			max_pin = KVM_IOAPIC_NUM_PINS;
 			e->set = kvm_set_ioapic_irq;
 			break;
 		default:
@@ -278,6 +302,9 @@ 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 >= max_pin)
+			goto out;
+		rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi;
 		break;
 	case KVM_IRQ_ROUTING_MSI:
 		e->set = kvm_set_msi;
@@ -288,54 +315,9 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 	default:
 		goto out;
 	}
-	r = 0;
-out:
-	return r;
-}
-
-
-int kvm_set_irq_routing(struct kvm *kvm,
-			const struct kvm_irq_routing_entry *ue,
-			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;
-	int r;
-
-	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);
-		if (r)
-			goto out;
-		++ue;
-		list_add(&e->link, &irq_list);
-		e = NULL;
-	}
-
-	mutex_lock(&kvm->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);
-	mutex_unlock(&kvm->lock);
 
 	r = 0;
-
 out:
-	kfree(e);
-	__kvm_free_irq_routing(&irq_list);
 	return r;
 }