@@ -2149,6 +2149,12 @@ do_not_translate:
return 0;
}
+static int vtd_int_remap(X86IOMMUState *iommu, MSIMessage *src,
+ MSIMessage *dst, uint16_t sid)
+{
+ return vtd_interrupt_remap_msi(INTEL_IOMMU_DEVICE(iommu), src, dst);
+}
+
static MemTxResult vtd_mem_ir_read(void *opaque, hwaddr addr,
uint64_t *data, unsigned size,
MemTxAttrs attrs)
@@ -2393,6 +2399,7 @@ static void vtd_class_init(ObjectClass *klass, void *data)
dc->props = vtd_properties;
x86_class->realize = vtd_realize;
x86_class->find_add_as = vtd_find_add_as;
+ x86_class->int_remap = vtd_int_remap;
}
static const TypeInfo vtd_info = {
@@ -26,6 +26,7 @@
#include "hw/i386/x86-iommu.h"
#include "hw/i386/ioapic.h"
#include "hw/pci/msi.h"
+#include "hw/sysbus.h"
#define TYPE_INTEL_IOMMU_DEVICE "intel-iommu"
#define INTEL_IOMMU_DEVICE(obj) \
@@ -22,6 +22,7 @@
#include "hw/sysbus.h"
#include "exec/memory.h"
+#include "hw/pci/pci.h"
#define TYPE_X86_IOMMU_DEVICE ("x86-iommu")
#define X86_IOMMU_DEVICE(obj) \
@@ -43,6 +44,9 @@ struct X86IOMMUClass {
DeviceRealize realize;
/* Find/Add IOMMU address space for specific PCI device */
AddressSpace *(*find_add_as)(X86IOMMUState *s, PCIBus *bus, int devfn);
+ /* MSI-based interrupt remapping */
+ int (*int_remap)(X86IOMMUState *iommu, MSIMessage *src,
+ MSIMessage *dst, uint16_t sid);
};
struct X86IOMMUState {
@@ -36,6 +36,7 @@
#include "hw/i386/apic.h"
#include "hw/i386/apic_internal.h"
#include "hw/i386/apic-msidef.h"
+#include "hw/i386/intel_iommu.h"
#include "exec/ioport.h"
#include "standard-headers/asm-x86/hyperv.h"
@@ -43,6 +44,7 @@
#include "hw/pci/msi.h"
#include "migration/migration.h"
#include "exec/memattrs.h"
+#include "trace.h"
//#define DEBUG_KVM
@@ -3320,6 +3322,31 @@ int kvm_device_msix_deassign(KVMState *s, uint32_t dev_id)
int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route,
uint64_t address, uint32_t data, PCIDevice *dev)
{
+ X86IOMMUState *iommu = x86_iommu_get_default();
+
+ if (iommu) {
+ int ret;
+ MSIMessage src, dst;
+ X86IOMMUClass *class = X86_IOMMU_GET_CLASS(iommu);
+
+ src.address = route->u.msi.address_hi;
+ src.address <<= VTD_MSI_ADDR_HI_SHIFT;
+ src.address |= route->u.msi.address_lo;
+ src.data = route->u.msi.data;
+
+ ret = class->int_remap(iommu, &src, &dst, dev ? \
+ pci_requester_id(dev) : \
+ X86_IOMMU_SID_INVALID);
+ if (ret) {
+ trace_kvm_x86_fixup_msi_error(route->gsi);
+ return 1;
+ }
+
+ route->u.msi.address_hi = dst.address >> VTD_MSI_ADDR_HI_SHIFT;
+ route->u.msi.address_lo = dst.address & VTD_MSI_ADDR_LO_MASK;
+ route->u.msi.data = dst.data;
+ }
+
return 0;
}
@@ -2163,3 +2163,6 @@ e1000e_cfg_support_virtio(bool support) "Virtio header supported: %d"
e1000e_vm_state_running(void) "VM state is running"
e1000e_vm_state_stopped(void) "VM state is stopped"
+
+# target-i386/kvm.c
+kvm_x86_fixup_msi_error(uint32_t gsi) "VT-d failed to remap interrupt for GSI %" PRIu32
In split irqchip mode, IOAPIC is working in user space, only update kernel irq routes when entry changed. When IR is enabled, we directly update the kernel with translated messages. It works just like a kernel cache for the remapping entries. Since KVM irqfd is using kernel gsi routes to deliver interrupts, as long as we can support split irqchip, we will support irqfd as well. Also, since kernel gsi routes will cache translated interrupts, irqfd delivery will not suffer from any performance impact due to IR. And, since we supported irqfd, vhost devices will be able to work seamlessly with IR now. Logically this should contain both vhost-net and vhost-user case. Signed-off-by: Peter Xu <peterx@redhat.com> --- hw/i386/intel_iommu.c | 7 +++++++ include/hw/i386/intel_iommu.h | 1 + include/hw/i386/x86-iommu.h | 4 ++++ target-i386/kvm.c | 27 +++++++++++++++++++++++++++ trace-events | 3 +++ 5 files changed, 42 insertions(+)