This patch allows HVM guests to remap interrupts and MSIs into pirqs;
once the mapping is in place the guest will receive the interrupt (or
the MSI) as an event.
The interrupt to be remapped can either be an interrupt of an emulated
device or an interrupt of a passthrough device and we keep track of
that.
Signed-off-by: Stefano Stabellini <stefano.stabellini@xxxxxxxxxxxxx>
diff -r 5218db847b58 xen/arch/x86/domain.c
--- a/xen/arch/x86/domain.c Tue Aug 17 19:32:37 2010 +0100
+++ b/xen/arch/x86/domain.c Fri Aug 20 16:47:36 2010 +0100
@@ -490,6 +490,16 @@ int arch_domain_create(struct domain *d,
if ( !IO_APIC_IRQ(i) )
d->arch.irq_pirq[i] = d->arch.pirq_irq[i] = i;
+ d->arch.pirq_emuirq = xmalloc_array(int, d->nr_pirqs);
+ d->arch.emuirq_pirq = xmalloc_array(int, nr_irqs);
+ if ( !d->arch.pirq_emuirq || !d->arch.emuirq_pirq )
+ goto fail;
+ memset(d->arch.pirq_emuirq, IRQ_UNBOUND,
+ d->nr_pirqs * sizeof(*d->arch.pirq_emuirq));
+ memset(d->arch.emuirq_pirq, IRQ_UNBOUND,
+ d->nr_pirqs * sizeof(*d->arch.emuirq_pirq));
+
+
if ( (rc = iommu_domain_init(d)) != 0 )
goto fail;
diff -r 5218db847b58 xen/arch/x86/hvm/hvm.c
--- a/xen/arch/x86/hvm/hvm.c Tue Aug 17 19:32:37 2010 +0100
+++ b/xen/arch/x86/hvm/hvm.c Fri Aug 20 16:47:36 2010 +0100
@@ -2281,6 +2281,20 @@ static long hvm_memory_op(int cmd, XEN_G
return rc;
}
+static long hvm_physdev_op(int cmd, XEN_GUEST_HANDLE(void) arg)
+{
+ switch ( cmd )
+ {
+ case PHYSDEVOP_map_pirq:
+ case PHYSDEVOP_unmap_pirq:
+ case PHYSDEVOP_eoi:
+ case PHYSDEVOP_irq_status_query:
+ return do_physdev_op(cmd, arg);
+ default:
+ return -ENOSYS;
+ }
+}
+
static long hvm_vcpu_op(
int cmd, int vcpuid, XEN_GUEST_HANDLE(void) arg)
{
@@ -2316,6 +2330,7 @@ static hvm_hypercall_t *hvm_hypercall32_
[ __HYPERVISOR_memory_op ] = (hvm_hypercall_t *)hvm_memory_op,
[ __HYPERVISOR_grant_table_op ] = (hvm_hypercall_t *)hvm_grant_table_op,
[ __HYPERVISOR_vcpu_op ] = (hvm_hypercall_t *)hvm_vcpu_op,
+ [ __HYPERVISOR_physdev_op ] = (hvm_hypercall_t *)hvm_physdev_op,
HYPERCALL(xen_version),
HYPERCALL(event_channel_op),
HYPERCALL(sched_op),
@@ -2366,10 +2381,28 @@ static long hvm_vcpu_op_compat32(
return rc;
}
+static long hvm_physdev_op_compat32(
+ int cmd, XEN_GUEST_HANDLE(void) arg)
+{
+ switch ( cmd )
+ {
+ case PHYSDEVOP_map_pirq:
+ case PHYSDEVOP_unmap_pirq:
+ case PHYSDEVOP_eoi:
+ case PHYSDEVOP_irq_status_query:
+ return compat_physdev_op(cmd, arg);
+ break;
+ default:
+ return -ENOSYS;
+ break;
+ }
+}
+
static hvm_hypercall_t *hvm_hypercall64_table[NR_hypercalls] = {
[ __HYPERVISOR_memory_op ] = (hvm_hypercall_t *)hvm_memory_op,
[ __HYPERVISOR_grant_table_op ] = (hvm_hypercall_t *)hvm_grant_table_op,
[ __HYPERVISOR_vcpu_op ] = (hvm_hypercall_t *)hvm_vcpu_op,
+ [ __HYPERVISOR_physdev_op ] = (hvm_hypercall_t *)hvm_physdev_op,
HYPERCALL(xen_version),
HYPERCALL(event_channel_op),
HYPERCALL(sched_op),
@@ -2382,6 +2415,7 @@ static hvm_hypercall_t *hvm_hypercall32_
[ __HYPERVISOR_memory_op ] = (hvm_hypercall_t *)hvm_memory_op_compat32,
[ __HYPERVISOR_grant_table_op ] = (hvm_hypercall_t
*)hvm_grant_table_op_compat32,
[ __HYPERVISOR_vcpu_op ] = (hvm_hypercall_t *)hvm_vcpu_op_compat32,
+ [ __HYPERVISOR_physdev_op ] = (hvm_hypercall_t *)hvm_physdev_op_compat32,
HYPERCALL(xen_version),
HYPERCALL(event_channel_op),
HYPERCALL(sched_op),
diff -r 5218db847b58 xen/arch/x86/hvm/irq.c
--- a/xen/arch/x86/hvm/irq.c Tue Aug 17 19:32:37 2010 +0100
+++ b/xen/arch/x86/hvm/irq.c Fri Aug 20 16:47:36 2010 +0100
@@ -23,9 +23,30 @@
#include <xen/types.h>
#include <xen/event.h>
#include <xen/sched.h>
+#include <xen/irq.h>
#include <asm/hvm/domain.h>
#include <asm/hvm/support.h>
+/* Must be called with hvm_domain->irq_lock hold */
+static void assert_irq(struct domain *d, unsigned ioapic_gsi, unsigned pic_irq)
+{
+ int pirq = domain_emuirq_to_pirq(d, ioapic_gsi);
+ if ( pirq != IRQ_UNBOUND )
+ {
+ send_guest_pirq(d, pirq);
+ return;
+ }
+ vioapic_irq_positive_edge(d, ioapic_gsi);
+ vpic_irq_positive_edge(d, pic_irq);
+}
+
+/* Must be called with hvm_domain->irq_lock hold */
+static void deassert_irq(struct domain *d, unsigned isa_irq)
+{
+ if ( domain_emuirq_to_pirq(d, isa_irq) != IRQ_UNBOUND )
+ vpic_irq_negative_edge(d, isa_irq);
+}
+
static void __hvm_pci_intx_assert(
struct domain *d, unsigned int device, unsigned int intx)
{
@@ -45,10 +66,7 @@ static void __hvm_pci_intx_assert(
isa_irq = hvm_irq->pci_link.route[link];
if ( (hvm_irq->pci_link_assert_count[link]++ == 0) && isa_irq &&
(hvm_irq->gsi_assert_count[isa_irq]++ == 0) )
- {
- vioapic_irq_positive_edge(d, isa_irq);
- vpic_irq_positive_edge(d, isa_irq);
- }
+ assert_irq(d, isa_irq, isa_irq);
}
void hvm_pci_intx_assert(
@@ -77,7 +95,7 @@ static void __hvm_pci_intx_deassert(
isa_irq = hvm_irq->pci_link.route[link];
if ( (--hvm_irq->pci_link_assert_count[link] == 0) && isa_irq &&
(--hvm_irq->gsi_assert_count[isa_irq] == 0) )
- vpic_irq_negative_edge(d, isa_irq);
+ deassert_irq(d, isa_irq);
}
void hvm_pci_intx_deassert(
@@ -100,10 +118,7 @@ void hvm_isa_irq_assert(
if ( !__test_and_set_bit(isa_irq, &hvm_irq->isa_irq.i) &&
(hvm_irq->gsi_assert_count[gsi]++ == 0) )
- {
- vioapic_irq_positive_edge(d, gsi);
- vpic_irq_positive_edge(d, isa_irq);
- }
+ assert_irq(d, gsi, isa_irq);
spin_unlock(&d->arch.hvm_domain.irq_lock);
}
@@ -120,7 +135,7 @@ void hvm_isa_irq_deassert(
if ( __test_and_clear_bit(isa_irq, &hvm_irq->isa_irq.i) &&
(--hvm_irq->gsi_assert_count[gsi] == 0) )
- vpic_irq_negative_edge(d, isa_irq);
+ deassert_irq(d, isa_irq);
spin_unlock(&d->arch.hvm_domain.irq_lock);
}
diff -r 5218db847b58 xen/arch/x86/irq.c
--- a/xen/arch/x86/irq.c Tue Aug 17 19:32:37 2010 +0100
+++ b/xen/arch/x86/irq.c Fri Aug 20 16:47:36 2010 +0100
@@ -1404,7 +1404,11 @@ int get_free_pirq(struct domain *d, int
{
for ( i = 16; i < nr_irqs_gsi; i++ )
if ( !d->arch.pirq_irq[i] )
- break;
+ {
+ if ( !is_hvm_domain(d) ||
+ d->arch.pirq_emuirq[i] == IRQ_UNBOUND )
+ break;
+ }
if ( i == nr_irqs_gsi )
return -ENOSPC;
}
@@ -1412,7 +1416,11 @@ int get_free_pirq(struct domain *d, int
{
for ( i = d->nr_pirqs - 1; i >= nr_irqs_gsi; i-- )
if ( !d->arch.pirq_irq[i] )
- break;
+ {
+ if ( !is_hvm_domain(d) ||
+ d->arch.pirq_emuirq[i] == IRQ_UNBOUND )
+ break;
+ }
if ( i < nr_irqs_gsi )
return -ENOSPC;
}
@@ -1743,3 +1751,82 @@ void fixup_irqs(void)
peoi[sp].ready = 1;
flush_ready_eoi();
}
+
+int map_domain_emuirq_pirq(struct domain *d, int pirq, int emuirq)
+{
+ int old_emuirq = IRQ_UNBOUND, old_pirq = IRQ_UNBOUND;
+
+ ASSERT(spin_is_locked(&d->event_lock));
+
+ if ( !is_hvm_domain(d) )
+ return -EINVAL;
+
+ if ( pirq < 0 || pirq >= d->nr_pirqs ||
+ emuirq == IRQ_UNBOUND || emuirq >= (int) nr_irqs )
+ {
+ dprintk(XENLOG_G_ERR, "dom%d: invalid pirq %d or emuirq %d\n",
+ d->domain_id, pirq, emuirq);
+ return -EINVAL;
+ }
+
+ old_emuirq = domain_pirq_to_emuirq(d, pirq);
+ if ( emuirq != IRQ_PT )
+ old_pirq = domain_emuirq_to_pirq(d, emuirq);
+
+ if ( (old_emuirq != IRQ_UNBOUND && (old_emuirq != emuirq) ) ||
+ (old_pirq != IRQ_UNBOUND && (old_pirq != pirq)) )
+ {
+ dprintk(XENLOG_G_WARNING, "dom%d: pirq %d or emuirq %d already
mapped\n",
+ d->domain_id, pirq, emuirq);
+ return 0;
+ }
+
+ d->arch.pirq_emuirq[pirq] = emuirq;
+ /* do not store emuirq mappings for pt devices */
+ if ( emuirq != IRQ_PT )
+ d->arch.emuirq_pirq[emuirq] = pirq;
+
+ return 0;
+}
+
+int unmap_domain_pirq_emuirq(struct domain *d, int pirq)
+{
+ int emuirq, ret = 0;
+
+ if ( !is_hvm_domain(d) )
+ return -EINVAL;
+
+ if ( (pirq < 0) || (pirq >= d->nr_pirqs) )
+ return -EINVAL;
+
+ ASSERT(spin_is_locked(&d->event_lock));
+
+ emuirq = domain_pirq_to_emuirq(d, pirq);
+ if ( emuirq == IRQ_UNBOUND )
+ {
+ dprintk(XENLOG_G_ERR, "dom%d: pirq %d not mapped\n",
+ d->domain_id, pirq);
+ ret = -EINVAL;
+ goto done;
+ }
+
+ d->arch.pirq_emuirq[pirq] = IRQ_UNBOUND;
+ d->arch.emuirq_pirq[emuirq] = IRQ_UNBOUND;
+
+ done:
+ return ret;
+}
+
+int hvm_domain_use_pirq(struct domain *d, int pirq)
+{
+ int emuirq;
+
+ if ( !is_hvm_domain(d) )
+ return 0;
+
+ emuirq = domain_pirq_to_emuirq(d, pirq);
+ if ( emuirq != IRQ_UNBOUND && d->pirq_to_evtchn[pirq] != 0 )
+ return 1;
+ else
+ return 0;
+}
diff -r 5218db847b58 xen/arch/x86/physdev.c
--- a/xen/arch/x86/physdev.c Tue Aug 17 19:32:37 2010 +0100
+++ b/xen/arch/x86/physdev.c Fri Aug 20 16:47:36 2010 +0100
@@ -45,6 +45,60 @@ static int physdev_map_pirq(struct physd
if ( d == NULL )
return -ESRCH;
+ if ( map->domid == DOMID_SELF && is_hvm_domain(d) )
+ {
+ spin_lock(&d->event_lock);
+ switch ( map->type )
+ {
+ case MAP_PIRQ_TYPE_GSI :
+ {
+ struct hvm_irq_dpci *hvm_irq_dpci;
+ struct hvm_girq_dpci_mapping *girq;
+ uint32_t machine_gsi = 0;
+
+ /* find the machine gsi corresponding to the
+ * emulated gsi */
+ hvm_irq_dpci = domain_get_irq_dpci(d);
+ if (hvm_irq_dpci) {
+ list_for_each_entry ( girq,
+ &hvm_irq_dpci->girq[map->index],
+ list ) {
+ machine_gsi = girq->machine_gsi;
+ }
+ }
+ /* found one, this mean we are dealing with a pt device */
+ if ( machine_gsi )
+ {
+ map->index = domain_pirq_to_irq(d, machine_gsi);
+ pirq = machine_gsi;
+ if ( pirq > 0 )
+ ret = 0;
+ else
+ ret = pirq;
+ }
+ /* we didn't find any, this means we are dealing
+ * with an emulated device */
+ else
+ {
+ pirq = map->pirq;
+ if ( pirq < 0 )
+ {
+ pirq = get_free_pirq(d, map->type, map->index);
+ }
+ ret = map_domain_emuirq_pirq(d, pirq, map->index);
+ }
+ map->pirq = pirq;
+ }
+ break;
+ default :
+ ret = -EINVAL;
+ dprintk(XENLOG_G_WARNING, "map type %d not supported yet\n",
map->type);
+ break;
+ }
+ spin_unlock(&d->event_lock);
+ return ret;
+ }
+
if ( !IS_PRIV_FOR(current->domain, d) )
{
ret = -EPERM;
@@ -150,6 +204,9 @@ static int physdev_map_pirq(struct physd
if ( ret == 0 )
map->pirq = pirq;
+ if ( !ret && is_hvm_domain(d) )
+ map_domain_emuirq_pirq(d, pirq, IRQ_PT);
+
done:
spin_unlock(&d->event_lock);
spin_unlock(&pcidevs_lock);
@@ -173,6 +230,14 @@ static int physdev_unmap_pirq(struct phy
if ( d == NULL )
return -ESRCH;
+ if ( is_hvm_domain(d) )
+ {
+ spin_lock(&d->event_lock);
+ ret = unmap_domain_pirq_emuirq(d, unmap->pirq);
+ spin_unlock(&d->event_lock);
+ goto free_domain;
+ }
+
ret = -EPERM;
if ( !IS_PRIV_FOR(current->domain, d) )
goto free_domain;
@@ -206,7 +271,11 @@ ret_t do_physdev_op(int cmd, XEN_GUEST_H
break;
if ( v->domain->arch.pirq_eoi_map )
evtchn_unmask(v->domain->pirq_to_evtchn[eoi.irq]);
- ret = pirq_guest_eoi(v->domain, eoi.irq);
+ if ( !is_hvm_domain(v->domain) ||
+ domain_pirq_to_emuirq(v->domain, eoi.irq) == IRQ_PT )
+ ret = pirq_guest_eoi(v->domain, eoi.irq);
+ else
+ ret = 0;
break;
}
@@ -261,6 +330,13 @@ ret_t do_physdev_op(int cmd, XEN_GUEST_H
if ( (irq < 0) || (irq >= v->domain->nr_pirqs) )
break;
irq_status_query.flags = 0;
+ if ( is_hvm_domain(v->domain) &&
+ domain_pirq_to_emuirq(v->domain, irq) != IRQ_PT )
+ {
+ ret = copy_to_guest(arg, &irq_status_query, 1) ? -EFAULT : 0;
+ break;
+ }
+
/*
* Even edge-triggered or message-based IRQs can need masking from
* time to time. If teh guest is not dynamically checking for this
diff -r 5218db847b58 xen/common/event_channel.c
--- a/xen/common/event_channel.c Tue Aug 17 19:32:37 2010 +0100
+++ b/xen/common/event_channel.c Fri Aug 20 16:47:36 2010 +0100
@@ -331,7 +331,7 @@ static long evtchn_bind_pirq(evtchn_bind
if ( (pirq < 0) || (pirq >= d->nr_pirqs) )
return -EINVAL;
- if ( !irq_access_permitted(d, pirq) )
+ if ( !is_hvm_domain(d) && !irq_access_permitted(d, pirq) )
return -EPERM;
spin_lock(&d->event_lock);
@@ -345,12 +345,15 @@ static long evtchn_bind_pirq(evtchn_bind
chn = evtchn_from_port(d, port);
d->pirq_to_evtchn[pirq] = port;
- rc = pirq_guest_bind(v, pirq,
- !!(bind->flags & BIND_PIRQ__WILL_SHARE));
- if ( rc != 0 )
+ if ( !is_hvm_domain(d) )
{
- d->pirq_to_evtchn[pirq] = 0;
- goto out;
+ rc = pirq_guest_bind(v, pirq,
+ !!(bind->flags & BIND_PIRQ__WILL_SHARE));
+ if ( rc != 0 )
+ {
+ d->pirq_to_evtchn[pirq] = 0;
+ goto out;
+ }
}
chn->state = ECS_PIRQ;
@@ -403,7 +406,8 @@ static long __evtchn_close(struct domain
break;
case ECS_PIRQ:
- pirq_guest_unbind(d1, chn1->u.pirq.irq);
+ if ( !is_hvm_domain(d1) )
+ pirq_guest_unbind(d1, chn1->u.pirq.irq);
d1->pirq_to_evtchn[chn1->u.pirq.irq] = 0;
unlink_pirq_port(chn1, d1->vcpu[chn1->notify_vcpu_id]);
break;
@@ -664,8 +668,17 @@ int send_guest_pirq(struct domain *d, in
/*
* It should not be possible to race with __evtchn_close():
* The caller of this function must synchronise with pirq_guest_unbind().
+ *
+ * In the HVM case port is 0 when the guest disable the
+ * emulated interrupt\evtchn.
*/
- ASSERT(port != 0);
+ if (!port)
+ {
+ if ( is_hvm_domain(d) )
+ return 0;
+ else
+ return -EINVAL;
+ }
chn = evtchn_from_port(d, port);
return evtchn_set_pending(d->vcpu[chn->notify_vcpu_id], port);
diff -r 5218db847b58 xen/common/kernel.c
--- a/xen/common/kernel.c Tue Aug 17 19:32:37 2010 +0100
+++ b/xen/common/kernel.c Fri Aug 20 16:47:36 2010 +0100
@@ -261,7 +261,8 @@ DO(xen_version)(int cmd, XEN_GUEST_HANDL
(1U << XENFEAT_gnttab_map_avail_bits);
else
fi.submap |= (1U << XENFEAT_hvm_safe_pvclock) |
- (1U << XENFEAT_hvm_callback_vector);
+ (1U << XENFEAT_hvm_callback_vector) |
+ (1U << XENFEAT_hvm_pirqs);
#endif
break;
default:
diff -r 5218db847b58 xen/drivers/passthrough/io.c
--- a/xen/drivers/passthrough/io.c Tue Aug 17 19:32:37 2010 +0100
+++ b/xen/drivers/passthrough/io.c Fri Aug 20 16:47:36 2010 +0100
@@ -373,6 +373,7 @@ int pt_irq_destroy_bind_vtd(
hvm_irq_dpci->mirq[machine_gsi].dom = NULL;
hvm_irq_dpci->mirq[machine_gsi].flags = 0;
clear_bit(machine_gsi, hvm_irq_dpci->mapping);
+ unmap_domain_pirq_emuirq(d, machine_gsi);
}
}
spin_unlock(&d->event_lock);
@@ -452,7 +453,10 @@ void hvm_dpci_msi_eoi(struct domain *d,
extern int vmsi_deliver(struct domain *d, int pirq);
static int hvm_pci_msi_assert(struct domain *d, int pirq)
{
- return vmsi_deliver(d, pirq);
+ if ( hvm_domain_use_pirq(d, pirq) )
+ return send_guest_pirq(d, pirq);
+ else
+ return vmsi_deliver(d, pirq);
}
#endif
@@ -486,7 +490,10 @@ static void hvm_dirq_assist(unsigned lon
{
device = digl->device;
intx = digl->intx;
- hvm_pci_intx_assert(d, device, intx);
+ if ( hvm_domain_use_pirq(d, pirq) )
+ send_guest_pirq(d, pirq);
+ else
+ hvm_pci_intx_assert(d, device, intx);
hvm_irq_dpci->mirq[pirq].pending++;
#ifdef SUPPORT_MSI_REMAPPING
diff -r 5218db847b58 xen/include/asm-x86/domain.h
--- a/xen/include/asm-x86/domain.h Tue Aug 17 19:32:37 2010 +0100
+++ b/xen/include/asm-x86/domain.h Fri Aug 20 16:47:36 2010 +0100
@@ -258,6 +258,9 @@ struct arch_domain
/* NB. protected by d->event_lock and by irq_desc[irq].lock */
int *irq_pirq;
int *pirq_irq;
+ /* pirq to emulated irq and vice versa */
+ int *emuirq_pirq;
+ int *pirq_emuirq;
/* Shared page for notifying that explicit PIRQ EOI is required. */
unsigned long *pirq_eoi_map;
diff -r 5218db847b58 xen/include/asm-x86/irq.h
--- a/xen/include/asm-x86/irq.h Tue Aug 17 19:32:37 2010 +0100
+++ b/xen/include/asm-x86/irq.h Fri Aug 20 16:47:36 2010 +0100
@@ -113,6 +113,9 @@ int map_domain_pirq(struct domain *d, in
int unmap_domain_pirq(struct domain *d, int pirq);
int get_free_pirq(struct domain *d, int type, int index);
void free_domain_pirqs(struct domain *d);
+int map_domain_emuirq_pirq(struct domain *d, int pirq, int irq);
+int unmap_domain_pirq_emuirq(struct domain *d, int pirq);
+int hvm_domain_use_pirq(struct domain *d, int irq);
int init_irq_data(void);
@@ -146,5 +149,9 @@ void irq_set_affinity(struct irq_desc *,
#define domain_pirq_to_irq(d, pirq) ((d)->arch.pirq_irq[pirq])
#define domain_irq_to_pirq(d, irq) ((d)->arch.irq_pirq[irq])
+#define domain_pirq_to_emuirq(d, pirq) ((d)->arch.pirq_emuirq[pirq])
+#define domain_emuirq_to_pirq(d, emuirq) ((d)->arch.emuirq_pirq[emuirq])
+#define IRQ_UNBOUND -1
+#define IRQ_PT -2
#endif /* _ASM_HW_IRQ_H */
diff -r 5218db847b58 xen/include/public/features.h
--- a/xen/include/public/features.h Tue Aug 17 19:32:37 2010 +0100
+++ b/xen/include/public/features.h Fri Aug 20 16:47:36 2010 +0100
@@ -74,6 +74,9 @@
/* x86: pvclock algorithm is safe to use on HVM */
#define XENFEAT_hvm_safe_pvclock 9
+/* x86: pirq can be used by HVM guests */
+#define XENFEAT_hvm_pirqs 10
+
#define XENFEAT_NR_SUBMAPS 1
#endif /* __XEN_PUBLIC_FEATURES_H__ */
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
Home