q35: ioapic: add support for emulated IOAPIC IR

This patch translates all IOAPIC interrupts into MSI ones. One pseudo
ioapic address space is added to transfer the MSI message. By default,
it will be system memory address space. When IR is enabled, it will be
IOMMU address space.

Currently, only emulated IOAPIC is supported.

Idea suggested by Jan Kiszka and Rita Sinha in the following patch:

https://lists.gnu.org/archive/html/qemu-devel/2016-03/msg01933.html

Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

6 files changed, 38 insertions, 5 deletions

diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index ccfcc69347..6ba5520283 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -28,6 +28,7 @@
 #include "hw/i386/pc.h"
 #include "hw/boards.h"
 #include "hw/i386/x86-iommu.h"
+#include "hw/pci-host/q35.h"
 
 /*#define DEBUG_INTEL_IOMMU*/
 #ifdef DEBUG_INTEL_IOMMU
@@ -2367,7 +2368,8 @@ static AddressSpace *vtd_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
 
 static void vtd_realize(DeviceState *dev, Error **errp)
 {
-    PCIBus *bus = PC_MACHINE(qdev_get_machine())->bus;
+    PCMachineState *pcms = PC_MACHINE(qdev_get_machine());
+    PCIBus *bus = pcms->bus;
     IntelIOMMUState *s = INTEL_IOMMU_DEVICE(dev);
 
     VTD_DPRINTF(GENERAL, "");
@@ -2383,6 +2385,8 @@ static void vtd_realize(DeviceState *dev, Error **errp)
     vtd_init(s);
     sysbus_mmio_map(SYS_BUS_DEVICE(s), 0, Q35_HOST_BRIDGE_IOMMU_ADDR);
     pci_setup_iommu(bus, vtd_host_dma_iommu, dev);
+    /* Pseudo address space under root PCI bus. */
+    pcms->ioapic_as = vtd_host_dma_iommu(bus, s, Q35_PSEUDO_DEVFN_IOAPIC);
 }
 
 static void vtd_class_init(ObjectClass *klass, void *data)
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 719884ff88..979f36d99f 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1475,6 +1475,9 @@ void pc_memory_init(PCMachineState *pcms,
         rom_add_option(option_rom[i].name, option_rom[i].bootindex);
     }
     pcms->fw_cfg = fw_cfg;
+
+    /* Init default IOAPIC address space */
+    pcms->ioapic_as = &address_space_memory;
 }
 
 qemu_irq pc_allocate_cpu_irq(void)
diff --git a/hw/intc/ioapic.c b/hw/intc/ioapic.c
index 273bb0854c..36dd42af20 100644
--- a/hw/intc/ioapic.c
+++ b/hw/intc/ioapic.c
@@ -29,6 +29,8 @@
 #include "hw/i386/ioapic_internal.h"
 #include "include/hw/pci/msi.h"
 #include "sysemu/kvm.h"
+#include "target-i386/cpu.h"
+#include "hw/i386/apic-msidef.h"
 
 //#define DEBUG_IOAPIC
 
@@ -50,13 +52,15 @@ extern int ioapic_no;
 
 static void ioapic_service(IOAPICCommonState *s)
 {
+    AddressSpace *ioapic_as = PC_MACHINE(qdev_get_machine())->ioapic_as;
+    uint32_t addr, data;
     uint8_t i;
     uint8_t trig_mode;
     uint8_t vector;
     uint8_t delivery_mode;
     uint32_t mask;
     uint64_t entry;
-    uint8_t dest;
+    uint16_t dest_idx;
     uint8_t dest_mode;
 
     for (i = 0; i < IOAPIC_NUM_PINS; i++) {
@@ -67,7 +71,14 @@ static void ioapic_service(IOAPICCommonState *s)
             entry = s->ioredtbl[i];
             if (!(entry & IOAPIC_LVT_MASKED)) {
                 trig_mode = ((entry >> IOAPIC_LVT_TRIGGER_MODE_SHIFT) & 1);
-                dest = entry >> IOAPIC_LVT_DEST_SHIFT;
+                /*
+                 * By default, this would be dest_id[8] +
+                 * reserved[8]. When IR is enabled, this would be
+                 * interrupt_index[15] + interrupt_format[1]. This
+                 * field never means anything, but only used to
+                 * generate corresponding MSI.
+                 */
+                dest_idx = entry >> IOAPIC_LVT_DEST_IDX_SHIFT;
                 dest_mode = (entry >> IOAPIC_LVT_DEST_MODE_SHIFT) & 1;
                 delivery_mode =
                     (entry >> IOAPIC_LVT_DELIV_MODE_SHIFT) & IOAPIC_DM_MASK;
@@ -97,8 +108,17 @@ static void ioapic_service(IOAPICCommonState *s)
 #else
                 (void)coalesce;
 #endif
-                apic_deliver_irq(dest, dest_mode, delivery_mode, vector,
-                                 trig_mode);
+                /* No matter whether IR is enabled, we translate
+                 * the IOAPIC message into a MSI one, and its
+                 * address space will decide whether we need a
+                 * translation. */
+                addr = APIC_DEFAULT_ADDRESS | \
+                    (dest_idx << MSI_ADDR_DEST_IDX_SHIFT) |
+                    (dest_mode << MSI_ADDR_DEST_MODE_SHIFT);
+                data = (vector << MSI_DATA_VECTOR_SHIFT) |
+                    (trig_mode << MSI_DATA_TRIGGER_SHIFT) |
+                    (delivery_mode << MSI_DATA_DELIVERY_MODE_SHIFT);
+                stl_le_phys(ioapic_as, addr, data);
             }
         }
     }
diff --git a/include/hw/i386/apic-msidef.h b/include/hw/i386/apic-msidef.h
index 6e2eb71f2f..8b4d4cca55 100644
--- a/include/hw/i386/apic-msidef.h
+++ b/include/hw/i386/apic-msidef.h
@@ -25,6 +25,7 @@
 #define MSI_ADDR_REDIRECTION_SHIFT      3
 
 #define MSI_ADDR_DEST_ID_SHIFT          12
+#define MSI_ADDR_DEST_IDX_SHIFT         4
 #define  MSI_ADDR_DEST_ID_MASK          0x00ffff0
 
 #endif /* HW_APIC_MSIDEF_H */
diff --git a/include/hw/i386/ioapic_internal.h b/include/hw/i386/ioapic_internal.h
index 0542aa1131..5c901ae78f 100644
--- a/include/hw/i386/ioapic_internal.h
+++ b/include/hw/i386/ioapic_internal.h
@@ -31,6 +31,7 @@
 #define IOAPIC_VERSION                  0x11
 
 #define IOAPIC_LVT_DEST_SHIFT           56
+#define IOAPIC_LVT_DEST_IDX_SHIFT       48
 #define IOAPIC_LVT_MASKED_SHIFT         16
 #define IOAPIC_LVT_TRIGGER_MODE_SHIFT   15
 #define IOAPIC_LVT_REMOTE_IRR_SHIFT     14
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index e38c95a4da..9811125492 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -72,6 +72,10 @@ struct PCMachineState {
     /* NUMA information: */
     uint64_t numa_nodes;
     uint64_t *node_mem;
+
+    /* Address space used by IOAPIC device. All IOAPIC interrupts
+     * will be translated to MSI messages in the address space. */
+    AddressSpace *ioapic_as;
 };
 
 #define PC_MACHINE_ACPI_DEVICE_PROP "acpi-device"