*/
#include <linux/kvm_host.h>
+#include <trace/events/kvm.h>
+
+#include <asm/msidef.h>
+#ifdef CONFIG_IA64
+#include <asm/iosapic.h>
+#endif
+
#include "irq.h"
#include "ioapic.h"
-static void kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
- struct kvm *kvm, int level)
+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 irq_source_id, int level)
{
#ifdef CONFIG_X86
- 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 irq_source_id, int 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)
+{
+#ifdef CONFIG_IA64
+ return irq->delivery_mode ==
+ (IOSAPIC_LOWEST_PRIORITY << IOSAPIC_DELIVERY_SHIFT);
+#else
+ return irq->delivery_mode == APIC_DM_LOWEST;
#endif
}
-static void kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
- struct kvm *kvm, int level)
+int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
+ struct kvm_lapic_irq *irq)
{
- kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level);
+ 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))
+ printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!kvm_apic_present(vcpu))
+ continue;
+
+ if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
+ irq->dest_id, irq->dest_mode))
+ continue;
+
+ if (!kvm_is_dm_lowest_prio(irq)) {
+ if (r < 0)
+ r = 0;
+ r += kvm_apic_set_irq(vcpu, irq);
+ } else {
+ if (!lowest)
+ lowest = vcpu;
+ else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
+ lowest = vcpu;
+ }
+ }
+
+ if (lowest)
+ r = kvm_apic_set_irq(lowest, irq);
+
+ return r;
}
-/* This should be called with the kvm->lock mutex held */
-void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level)
+static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level)
{
- struct kvm_kernel_irq_routing_entry *e;
- unsigned long *irq_state = (unsigned long *)&kvm->arch.irq_states[irq];
+ struct kvm_lapic_irq irq;
- /* Logical OR for level trig interrupt */
- if (level)
- set_bit(irq_source_id, irq_state);
- else
- clear_bit(irq_source_id, irq_state);
+ if (!level)
+ return -1;
+
+ trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+
+ irq.dest_id = (e->msi.address_lo &
+ MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+ 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;
+
+ /* TODO Deal with RH bit of MSI message address */
+ return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
+}
+
+/*
+ * 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, u32 irq, int level)
+{
+ 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);
/* 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)
- e->set(e, kvm, !!(*irq_state));
+ 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);
+ }
+
+ return ret;
}
-void kvm_notify_acked_irq(struct kvm *kvm, unsigned gsi)
+void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
{
struct kvm_irq_ack_notifier *kian;
struct hlist_node *n;
-
- hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link)
- if (kian->gsi == gsi)
- kian->irq_acked(kian);
+ int gsi;
+
+ trace_kvm_ack_irq(irqchip, pin);
+
+ 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)
{
- hlist_add_head(&kian->link, &kvm->arch.irq_ack_notifier_list);
+ mutex_lock(&kvm->irq_lock);
+ hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
+ mutex_unlock(&kvm->irq_lock);
}
-void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian)
+void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
+ struct kvm_irq_ack_notifier *kian)
{
- hlist_del_init(&kian->link);
+ mutex_lock(&kvm->irq_lock);
+ hlist_del_init_rcu(&kian->link);
+ mutex_unlock(&kvm->irq_lock);
+ synchronize_rcu();
}
-/* 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,
+ int irq_source_id;
+
+ mutex_lock(&kvm->irq_lock);
+ irq_source_id = find_first_zero_bit(bitmap,
sizeof(kvm->arch.irq_sources_bitmap));
if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
set_bit(irq_source_id, bitmap);
+ mutex_unlock(&kvm->irq_lock);
return irq_source_id;
}
ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
+ mutex_lock(&kvm->irq_lock);
if (irq_source_id < 0 ||
irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
printk(KERN_ERR "kvm: IRQ source ID out of range!\n");
return;
}
- for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
- clear_bit(irq_source_id, &kvm->arch.irq_states[i]);
+ 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
+ }
clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
+ 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_rcu();
}
void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
struct kvm_irq_mask_notifier *kimn;
struct hlist_node *n;
- 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)
{
- __kvm_free_irq_routing(&kvm->irq_routing);
+ /* Called only during vm destruction. Nobody can use the pointer
+ at this stage */
+ kfree(kvm->irq_routing);
}
-int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
- const struct kvm_irq_routing_entry *ue)
+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;
switch (ue->type) {
case KVM_IRQ_ROUTING_IRQCHIP:
delta = 0;
e->set = kvm_set_pic_irq;
break;
case KVM_IRQCHIP_PIC_SLAVE:
- e->set = kvm_set_pic_irq;
+ e->set = kvm_set_pic_irq;
delta = 8;
break;
case KVM_IRQCHIP_IOAPIC:
- e->set = kvm_set_ioapic_irq;
+ e->set = kvm_set_ioapic_irq;
break;
default:
goto out;
}
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;
+ e->msi.address_lo = ue->u.msi.address_lo;
+ e->msi.address_hi = ue->u.msi.address_hi;
+ e->msi.data = ue->u.msi.data;
break;
default:
goto out;
}
+
+ hlist_add_head(&e->link, &rt->map[e->gsi]);
r = 0;
out:
return r;
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->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);
+ mutex_lock(&kvm->irq_lock);
+ 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;
}
#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)
#ifdef CONFIG_X86
-#define SELECT_PIC(irq) \
- ((irq) < 8 ? KVM_IRQCHIP_PIC_MASTER : KVM_IRQCHIP_PIC_SLAVE)
# define PIC_ROUTING_ENTRY(irq) \
{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \
.u.irqchip.irqchip = SELECT_PIC(irq), .u.irqchip.pin = (irq) % 8 }
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff