kvmvapic: Introduce TPR access optimization for Windows guests

This enables acceleration for MMIO-based TPR registers accesses of
32-bit Windows guest systems. It is mostly useful with KVM enabled,
either on older Intel CPUs (without flexpriority feature, can also be
manually disabled for testing) or any current AMD processor.

The approach introduced here is derived from the original version of
qemu-kvm. It was refactored, documented, and extended by support for
user space APIC emulation, both with and without KVM acceleration. The
VMState format was kept compatible, so was the ABI to the option ROM
that implements the guest-side para-virtualized driver service. This
enables seamless migration from qemu-kvm to upstream or, one day,
between KVM and TCG mode.

The basic concept goes like this:
 - VAPIC PV interface consisting of I/O port 0x7e and (for KVM in-kernel
   irqchip) a vmcall hypercall is registered
 - VAPIC option ROM is loaded into guest
 - option ROM activates TPR MMIO access reporting via port 0x7e
 - TPR accesses are trapped and patched in the guest to call into option
   ROM instead, VAPIC support is enabled
 - option ROM TPR helpers track state in memory and invoke hypercall to
   poll for pending IRQs if required

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

1 files changed, 62 insertions, 2 deletions

diff --git a/hw/apic_common.c b/hw/apic_common.c
index 340d793..60b8259 100644
--- a/hw/apic_common.c
+++ b/hw/apic_common.c
@@ -20,8 +20,10 @@
 #include "apic.h"
 #include "apic_internal.h"
 #include "trace.h"
+#include "kvm.h"
 
 static int apic_irq_delivered;
+bool apic_report_tpr_access;
 
 void cpu_set_apic_base(DeviceState *d, uint64_t val)
 {
@@ -63,14 +65,45 @@ void cpu_set_apic_tpr(DeviceState *d, uint8_t val)
 
 uint8_t cpu_get_apic_tpr(DeviceState *d)
 {
+    APICCommonState *s;
+    APICCommonClass *info;
+
+    if (!d) {
+        return 0;
+    }
+
+    s = APIC_COMMON(d);
+    info = APIC_COMMON_GET_CLASS(s);
+
+    return info->get_tpr(s);
+}
+
+void apic_enable_tpr_access_reporting(DeviceState *d, bool enable)
+{
+    APICCommonState *s = DO_UPCAST(APICCommonState, busdev.qdev, d);
+    APICCommonClass *info = APIC_COMMON_GET_CLASS(s);
+
+    apic_report_tpr_access = enable;
+    if (info->enable_tpr_reporting) {
+        info->enable_tpr_reporting(s, enable);
+    }
+}
+
+void apic_enable_vapic(DeviceState *d, target_phys_addr_t paddr)
+{
     APICCommonState *s = DO_UPCAST(APICCommonState, busdev.qdev, d);
+    APICCommonClass *info = APIC_COMMON_GET_CLASS(s);
 
-    return s ? s->tpr >> 4 : 0;
+    s->vapic_paddr = paddr;
+    info->vapic_base_update(s);
 }
 
 void apic_handle_tpr_access_report(DeviceState *d, target_ulong ip,
                                    TPRAccess access)
 {
+    APICCommonState *s = DO_UPCAST(APICCommonState, busdev.qdev, d);
+
+    vapic_report_tpr_access(s->vapic, s->cpu_env, ip, access);
 }
 
 void apic_report_irq_delivered(int delivered)
@@ -171,12 +204,16 @@ void apic_init_reset(DeviceState *d)
 static void apic_reset_common(DeviceState *d)
 {
     APICCommonState *s = DO_UPCAST(APICCommonState, busdev.qdev, d);
+    APICCommonClass *info = APIC_COMMON_GET_CLASS(s);
     bool bsp;
 
     bsp = cpu_is_bsp(s->cpu_env);
     s->apicbase = 0xfee00000 |
         (bsp ? MSR_IA32_APICBASE_BSP : 0) | MSR_IA32_APICBASE_ENABLE;
 
+    s->vapic_paddr = 0;
+    info->vapic_base_update(s);
+
     apic_init_reset(d);
 
     if (bsp) {
@@ -239,6 +276,7 @@ static int apic_init_common(SysBusDevice *dev)
 {
     APICCommonState *s = APIC_COMMON(dev);
     APICCommonClass *info;
+    static DeviceState *vapic;
     static int apic_no;
 
     if (apic_no >= MAX_APICS) {
@@ -249,10 +287,29 @@ static int apic_init_common(SysBusDevice *dev)
     info = APIC_COMMON_GET_CLASS(s);
     info->init(s);
 
-    sysbus_init_mmio(&s->busdev, &s->io_memory);
+    sysbus_init_mmio(dev, &s->io_memory);
+
+    if (!vapic && s->vapic_control & VAPIC_ENABLE_MASK) {
+        vapic = sysbus_create_simple("kvmvapic", -1, NULL);
+    }
+    s->vapic = vapic;
+    if (apic_report_tpr_access && info->enable_tpr_reporting) {
+        info->enable_tpr_reporting(s, true);
+    }
+
     return 0;
 }
 
+static void apic_dispatch_pre_save(void *opaque)
+{
+    APICCommonState *s = APIC_COMMON(opaque);
+    APICCommonClass *info = APIC_COMMON_GET_CLASS(s);
+
+    if (info->pre_save) {
+        info->pre_save(s);
+    }
+}
+
 static int apic_dispatch_post_load(void *opaque, int version_id)
 {
     APICCommonState *s = APIC_COMMON(opaque);
@@ -270,6 +327,7 @@ static const VMStateDescription vmstate_apic_common = {
     .minimum_version_id = 3,
     .minimum_version_id_old = 1,
     .load_state_old = apic_load_old,
+    .pre_save = apic_dispatch_pre_save,
     .post_load = apic_dispatch_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINT32(apicbase, APICCommonState),
@@ -299,6 +357,8 @@ static const VMStateDescription vmstate_apic_common = {
 static Property apic_properties_common[] = {
     DEFINE_PROP_UINT8("id", APICCommonState, id, -1),
     DEFINE_PROP_PTR("cpu_env", APICCommonState, cpu_env),
+    DEFINE_PROP_BIT("vapic", APICCommonState, vapic_control, VAPIC_ENABLE_BIT,
+                    true),
     DEFINE_PROP_END_OF_LIST(),
 };