[Qemu-devel] [RFC][PATCH 13/16] kvm: x86: Add user space part for in-kernel APIC

[Jan Kiszka]

From: Jan Kiszka <address@hidden>

This introduces the alternative APIC model 'kvm-apic' which makes use of
KVM's in-kernel device model. MSI is not yet supported, so we disable
this when the in-kernel model is in use.

Signed-off-by: Jan Kiszka <address@hidden>
---
 Makefile.target   |    2 +-
 hw/kvm/apic.c     |  147 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 hw/pc.c           |   15 ++++--
 kvm.h             |    3 +
 target-i386/kvm.c |    8 +++
 5 files changed, 169 insertions(+), 6 deletions(-)
 create mode 100644 hw/kvm/apic.c

diff --git a/Makefile.target b/Makefile.target
index 4cd3c0e..66b42d5 100644
--- a/Makefile.target
+++ b/Makefile.target
@@ -231,7 +231,7 @@ obj-i386-y += vmport.o
 obj-i386-y += device-hotplug.o pci-hotplug.o smbios.o wdt_ib700.o
 obj-i386-y += debugcon.o multiboot.o
 obj-i386-y += pc_piix.o
-obj-i386-$(CONFIG_KVM) += kvm/clock.o
+obj-i386-$(CONFIG_KVM) += kvm/clock.o kvm/apic.o
 obj-i386-$(CONFIG_SPICE) += qxl.o qxl-logger.o qxl-render.o
 
 # shared objects
diff --git a/hw/kvm/apic.c b/hw/kvm/apic.c
new file mode 100644
index 0000000..fe811b6
--- /dev/null
+++ b/hw/kvm/apic.c
@@ -0,0 +1,147 @@
+/*
+ * KVM in-kernel APIC support
+ *
+ * Copyright (c) 2011 Siemens AG
+ *
+ * Authors:
+ *  Jan Kiszka          <address@hidden>
+ *
+ * This work is licensed under the terms of the GNU GPL version 2.
+ * See the COPYING file in the top-level directory.
+ */
+#include <hw/apic_internal.h>
+#include <kvm.h>
+
+static inline void kvm_apic_set_reg(struct kvm_lapic_state *kapic,
+                                   int reg_id, uint32_t val)
+{
+    *((uint32_t *)(kapic->regs + (reg_id << 4))) = val;
+}
+
+static inline uint32_t kvm_apic_get_reg(struct kvm_lapic_state *kapic,
+                                       int reg_id)
+{
+    return *((uint32_t *)(kapic->regs + (reg_id << 4)));
+}
+
+int kvm_put_apic(CPUState *env)
+{
+    APICState *s = DO_UPCAST(APICState, busdev.qdev, env->apic_state);
+    struct kvm_lapic_state kapic;
+    int i;
+
+    if (s && kvm_enabled() && kvm_irqchip_in_kernel()) {
+        memset(&kapic, 0, sizeof(kapic));
+        kvm_apic_set_reg(&kapic, 0x2, s->id << 24);
+        kvm_apic_set_reg(&kapic, 0x8, s->tpr);
+        kvm_apic_set_reg(&kapic, 0xd, s->log_dest << 24);
+        kvm_apic_set_reg(&kapic, 0xe, s->dest_mode << 28 | 0x0fffffff);
+        kvm_apic_set_reg(&kapic, 0xf, s->spurious_vec);
+        for (i = 0; i < 8; i++) {
+            kvm_apic_set_reg(&kapic, 0x10 + i, s->isr[i]);
+            kvm_apic_set_reg(&kapic, 0x18 + i, s->tmr[i]);
+            kvm_apic_set_reg(&kapic, 0x20 + i, s->irr[i]);
+        }
+        kvm_apic_set_reg(&kapic, 0x28, s->esr);
+        kvm_apic_set_reg(&kapic, 0x30, s->icr[0]);
+        kvm_apic_set_reg(&kapic, 0x31, s->icr[1]);
+        for (i = 0; i < APIC_LVT_NB; i++) {
+            kvm_apic_set_reg(&kapic, 0x32 + i, s->lvt[i]);
+        }
+        kvm_apic_set_reg(&kapic, 0x38, s->initial_count);
+        kvm_apic_set_reg(&kapic, 0x3e, s->divide_conf);
+
+        return kvm_vcpu_ioctl(env, KVM_SET_LAPIC, &kapic);
+    }
+
+    return 0;
+}
+
+int kvm_get_apic(CPUState *env)
+{
+    APICState *s = DO_UPCAST(APICState, busdev.qdev, env->apic_state);
+    struct kvm_lapic_state kapic;
+    int ret, i, v;
+
+    if (s && kvm_enabled() && kvm_irqchip_in_kernel()) {
+        ret = kvm_vcpu_ioctl(env, KVM_GET_LAPIC, &kapic);
+        if (ret < 0) {
+            return ret;
+        }
+
+        s->id = kvm_apic_get_reg(&kapic, 0x2) >> 24;
+        s->tpr = kvm_apic_get_reg(&kapic, 0x8);
+        s->arb_id = kvm_apic_get_reg(&kapic, 0x9);
+        s->log_dest = kvm_apic_get_reg(&kapic, 0xd) >> 24;
+        s->dest_mode = kvm_apic_get_reg(&kapic, 0xe) >> 28;
+        s->spurious_vec = kvm_apic_get_reg(&kapic, 0xf);
+        for (i = 0; i < 8; i++) {
+            s->isr[i] = kvm_apic_get_reg(&kapic, 0x10 + i);
+            s->tmr[i] = kvm_apic_get_reg(&kapic, 0x18 + i);
+            s->irr[i] = kvm_apic_get_reg(&kapic, 0x20 + i);
+        }
+        s->esr = kvm_apic_get_reg(&kapic, 0x28);
+        s->icr[0] = kvm_apic_get_reg(&kapic, 0x30);
+        s->icr[1] = kvm_apic_get_reg(&kapic, 0x31);
+        for (i = 0; i < APIC_LVT_NB; i++) {
+            s->lvt[i] = kvm_apic_get_reg(&kapic, 0x32 + i);
+        }
+        s->initial_count = kvm_apic_get_reg(&kapic, 0x38);
+        s->divide_conf = kvm_apic_get_reg(&kapic, 0x3e);
+
+        v = (s->divide_conf & 3) | ((s->divide_conf >> 1) & 4);
+        s->count_shift = (v + 1) & 7;
+
+        s->initial_count_load_time = qemu_get_clock_ns(vm_clock);
+        apic_next_timer(s, s->initial_count_load_time);
+    }
+    return 0;
+}
+
+static void kvm_apic_set_base(APICState *s, uint64_t val)
+{
+    s->apicbase = val;
+}
+
+static void kvm_apic_set_tpr(APICState *s, uint8_t val)
+{
+    s->tpr = (val & 0x0f) << 4;
+}
+
+static int kvm_apic_init(SysBusDevice *dev)
+{
+    APICState *s = FROM_SYSBUS(APICState, dev);
+
+    memory_region_init_reservation(&s->io_memory, "kvm-apic-msi",
+                                   MSI_SPACE_SIZE);
+
+    if (apic_init_common(s) < 0) {
+        memory_region_destroy(&s->io_memory);
+        return -1;
+    }
+
+    s->set_base = kvm_apic_set_base;
+    s->set_tpr = kvm_apic_set_tpr;
+    return 0;
+}
+
+static SysBusDeviceInfo kvm_apic_info = {
+    .init = kvm_apic_init,
+    .qdev.name = "kvm-apic",
+    .qdev.size = sizeof(APICState),
+    .qdev.vmsd = &vmstate_apic,
+    .qdev.reset = apic_reset,
+    .qdev.no_user = 1,
+    .qdev.props = (Property[]) {
+        DEFINE_PROP_UINT8("id", APICState, id, -1),
+        DEFINE_PROP_PTR("cpu_env", APICState, cpu_env),
+        DEFINE_PROP_END_OF_LIST(),
+    }
+};
+
+static void kvm_apic_register_devices(void)
+{
+    sysbus_register_withprop(&kvm_apic_info);
+}
+
+device_init(kvm_apic_register_devices)
diff --git a/hw/pc.c b/hw/pc.c
index 715cc63..0a1e51c 100644
--- a/hw/pc.c
+++ b/hw/pc.c
@@ -879,25 +879,30 @@ DeviceState *cpu_get_current_apic(void)
 static DeviceState *apic_init(void *env, uint8_t apic_id)
 {
     DeviceState *dev;
-    SysBusDevice *d;
     static int apic_mapped;
 
-    dev = qdev_create(NULL, "apic");
+    if (kvm_enabled() && kvm_irqchip_in_kernel()) {
+        dev = qdev_create(NULL, "kvm-apic");
+    } else {
+        dev = qdev_create(NULL, "apic");
+    }
     qdev_prop_set_uint8(dev, "id", apic_id);
     qdev_prop_set_ptr(dev, "cpu_env", env);
     qdev_init_nofail(dev);
-    d = sysbus_from_qdev(dev);
 
     /* XXX: mapping more APICs at the same memory location */
     if (apic_mapped == 0) {
         /* NOTE: the APIC is directly connected to the CPU - it is not
            on the global memory bus. */
         /* XXX: what if the base changes? */
-        sysbus_mmio_map(d, 0, MSI_ADDR_BASE);
+        sysbus_mmio_map(sysbus_from_qdev(dev), 0, MSI_ADDR_BASE);
         apic_mapped = 1;
     }
 
-    msi_supported = true;
+    /* KVM does not support MSI yet. */
+    if (!kvm_enabled() || !kvm_irqchip_in_kernel()) {
+        msi_supported = true;
+    }
 
     return dev;
 }
diff --git a/kvm.h b/kvm.h
index a3c87af..446360a 100644
--- a/kvm.h
+++ b/kvm.h
@@ -134,6 +134,9 @@ int kvm_irqchip_set_irq(KVMState *s, int irq, int level);
 void kvm_irqchip_add_route(KVMState *s, int gsi, int irqchip, int pin);
 int kvm_irqchip_commit_routes(KVMState *s);
 
+int kvm_put_apic(CPUState *env);
+int kvm_get_apic(CPUState *env);
+
 struct kvm_guest_debug;
 struct kvm_debug_exit_arch;
 
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 232c897..537b61f 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -1435,6 +1435,10 @@ int kvm_arch_put_registers(CPUState *env, int level)
         if (ret < 0) {
             return ret;
         }
+        ret = kvm_put_apic(env);
+        if (ret < 0) {
+            return ret;
+        }
     }
     ret = kvm_put_vcpu_events(env, level);
     if (ret < 0) {
@@ -1482,6 +1486,10 @@ int kvm_arch_get_registers(CPUState *env)
     if (ret < 0) {
         return ret;
     }
+    ret = kvm_get_apic(env);
+    if (ret < 0) {
+        return ret;
+    }
     ret = kvm_get_vcpu_events(env);
     if (ret < 0) {
         return ret;
-- 
1.7.3.4