Merge remote-tracking branch 'qemu-kvm/uq/master' into staging

* qemu-kvm/uq/master:
  kvm: Activate in-kernel irqchip support
  kvm: x86: Add user space part for in-kernel IOAPIC
  kvm: x86: Add user space part for in-kernel i8259
  kvm: x86: Add user space part for in-kernel APIC
  kvm: x86: Establish IRQ0 override control
  kvm: Introduce core services for in-kernel irqchip support
  memory: Introduce memory_region_init_reservation
  ioapic: Factor out base class for KVM reuse
  ioapic: Drop post-load irr initialization
  i8259: Factor out base class for KVM reuse
  i8259: Completely privatize PicState
  apic: Open-code timer save/restore
  apic: Factor out base class for KVM reuse
  apic: Introduce apic_report_irq_delivered
  apic: Inject external NMI events via LINT1
  apic: Stop timer on reset
  kvm: Move kvmclock into hw/kvm folder
  msi: Generalize msix_supported to msi_supported
  hyper-v: initialize Hyper-V CPUID leaves.
  hyper-v: introduce Hyper-V support infrastructure.

Conflicts:
	Makefile.target

Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

5 files changed, 524 insertions, 0 deletions

diff --git a/hw/kvm/apic.c b/hw/kvm/apic.c
new file mode 100644
index 0000000000..6300695e86
--- /dev/null
+++ b/hw/kvm/apic.c
@@ -0,0 +1,138 @@
+/*
+ * KVM in-kernel APIC support
+ *
+ * Copyright (c) 2011 Siemens AG
+ *
+ * Authors:
+ *  Jan Kiszka          <jan.kiszka@siemens.com>
+ *
+ * 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)));
+}
+
+void kvm_put_apic_state(DeviceState *d, struct kvm_lapic_state *kapic)
+{
+    APICCommonState *s = DO_UPCAST(APICCommonState, busdev.qdev, d);
+    int i;
+
+    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);
+}
+
+void kvm_get_apic_state(DeviceState *d, struct kvm_lapic_state *kapic)
+{
+    APICCommonState *s = DO_UPCAST(APICCommonState, busdev.qdev, d);
+    int i, v;
+
+    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);
+}
+
+static void kvm_apic_set_base(APICCommonState *s, uint64_t val)
+{
+    s->apicbase = val;
+}
+
+static void kvm_apic_set_tpr(APICCommonState *s, uint8_t val)
+{
+    s->tpr = (val & 0x0f) << 4;
+}
+
+static void do_inject_external_nmi(void *data)
+{
+    APICCommonState *s = data;
+    CPUState *env = s->cpu_env;
+    uint32_t lvt;
+    int ret;
+
+    cpu_synchronize_state(env);
+
+    lvt = s->lvt[APIC_LVT_LINT1];
+    if (!(lvt & APIC_LVT_MASKED) && ((lvt >> 8) & 7) == APIC_DM_NMI) {
+        ret = kvm_vcpu_ioctl(env, KVM_NMI);
+        if (ret < 0) {
+            fprintf(stderr, "KVM: injection failed, NMI lost (%s)\n",
+                    strerror(-ret));
+        }
+    }
+}
+
+static void kvm_apic_external_nmi(APICCommonState *s)
+{
+    run_on_cpu(s->cpu_env, do_inject_external_nmi, s);
+}
+
+static void kvm_apic_init(APICCommonState *s)
+{
+    memory_region_init_reservation(&s->io_memory, "kvm-apic-msi",
+                                   MSI_SPACE_SIZE);
+}
+
+static APICCommonInfo kvm_apic_info = {
+    .busdev.qdev.name = "kvm-apic",
+    .init = kvm_apic_init,
+    .set_base = kvm_apic_set_base,
+    .set_tpr = kvm_apic_set_tpr,
+    .external_nmi = kvm_apic_external_nmi,
+};
+
+static void kvm_apic_register_device(void)
+{
+    apic_qdev_register(&kvm_apic_info);
+}
+
+device_init(kvm_apic_register_device)
diff --git a/hw/kvm/clock.c b/hw/kvm/clock.c
new file mode 100644
index 0000000000..bb28c088db
--- /dev/null
+++ b/hw/kvm/clock.c
@@ -0,0 +1,120 @@
+/*
+ * QEMU KVM support, paravirtual clock device
+ *
+ * Copyright (C) 2011 Siemens AG
+ *
+ * Authors:
+ *  Jan Kiszka        <jan.kiszka@siemens.com>
+ *
+ * This work is licensed under the terms of the GNU GPL version 2.
+ * See the COPYING file in the top-level directory.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "qemu-common.h"
+#include "sysemu.h"
+#include "kvm.h"
+#include "hw/sysbus.h"
+#include "hw/kvm/clock.h"
+
+#include <linux/kvm.h>
+#include <linux/kvm_para.h>
+
+typedef struct KVMClockState {
+    SysBusDevice busdev;
+    uint64_t clock;
+    bool clock_valid;
+} KVMClockState;
+
+static void kvmclock_pre_save(void *opaque)
+{
+    KVMClockState *s = opaque;
+    struct kvm_clock_data data;
+    int ret;
+
+    if (s->clock_valid) {
+        return;
+    }
+    ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
+    if (ret < 0) {
+        fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));
+        data.clock = 0;
+    }
+    s->clock = data.clock;
+    /*
+     * If the VM is stopped, declare the clock state valid to avoid re-reading
+     * it on next vmsave (which would return a different value). Will be reset
+     * when the VM is continued.
+     */
+    s->clock_valid = !runstate_is_running();
+}
+
+static int kvmclock_post_load(void *opaque, int version_id)
+{
+    KVMClockState *s = opaque;
+    struct kvm_clock_data data;
+
+    data.clock = s->clock;
+    data.flags = 0;
+    return kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data);
+}
+
+static void kvmclock_vm_state_change(void *opaque, int running,
+                                     RunState state)
+{
+    KVMClockState *s = opaque;
+
+    if (running) {
+        s->clock_valid = false;
+    }
+}
+
+static int kvmclock_init(SysBusDevice *dev)
+{
+    KVMClockState *s = FROM_SYSBUS(KVMClockState, dev);
+
+    qemu_add_vm_change_state_handler(kvmclock_vm_state_change, s);
+    return 0;
+}
+
+static const VMStateDescription kvmclock_vmsd = {
+    .name = "kvmclock",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .minimum_version_id_old = 1,
+    .pre_save = kvmclock_pre_save,
+    .post_load = kvmclock_post_load,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64(clock, KVMClockState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static SysBusDeviceInfo kvmclock_info = {
+    .qdev.name = "kvmclock",
+    .qdev.size = sizeof(KVMClockState),
+    .qdev.vmsd = &kvmclock_vmsd,
+    .qdev.no_user = 1,
+    .init = kvmclock_init,
+};
+
+/* Note: Must be called after VCPU initialization. */
+void kvmclock_create(void)
+{
+    if (kvm_enabled() &&
+        first_cpu->cpuid_kvm_features & ((1ULL << KVM_FEATURE_CLOCKSOURCE) |
+                                         (1ULL << KVM_FEATURE_CLOCKSOURCE2))) {
+        sysbus_create_simple("kvmclock", -1, NULL);
+    }
+}
+
+static void kvmclock_register_device(void)
+{
+    if (kvm_enabled()) {
+        sysbus_register_withprop(&kvmclock_info);
+    }
+}
+
+device_init(kvmclock_register_device);
diff --git a/hw/kvm/clock.h b/hw/kvm/clock.h
new file mode 100644
index 0000000000..252ea13461
--- /dev/null
+++ b/hw/kvm/clock.h
@@ -0,0 +1,24 @@
+/*
+ * QEMU KVM support, paravirtual clock device
+ *
+ * Copyright (C) 2011 Siemens AG
+ *
+ * Authors:
+ *  Jan Kiszka        <jan.kiszka@siemens.com>
+ *
+ * This work is licensed under the terms of the GNU GPL version 2.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifdef CONFIG_KVM
+
+void kvmclock_create(void);
+
+#else /* CONFIG_KVM */
+
+static inline void kvmclock_create(void)
+{
+}
+
+#endif /* !CONFIG_KVM */
diff --git a/hw/kvm/i8259.c b/hw/kvm/i8259.c
new file mode 100644
index 0000000000..64bb5c26e2
--- /dev/null
+++ b/hw/kvm/i8259.c
@@ -0,0 +1,128 @@
+/*
+ * KVM in-kernel PIC (i8259) support
+ *
+ * Copyright (c) 2011 Siemens AG
+ *
+ * Authors:
+ *  Jan Kiszka          <jan.kiszka@siemens.com>
+ *
+ * This work is licensed under the terms of the GNU GPL version 2.
+ * See the COPYING file in the top-level directory.
+ */
+#include "hw/i8259_internal.h"
+#include "hw/apic_internal.h"
+#include "kvm.h"
+
+static void kvm_pic_get(PICCommonState *s)
+{
+    struct kvm_irqchip chip;
+    struct kvm_pic_state *kpic;
+    int ret;
+
+    chip.chip_id = s->master ? KVM_IRQCHIP_PIC_MASTER : KVM_IRQCHIP_PIC_SLAVE;
+    ret = kvm_vm_ioctl(kvm_state, KVM_GET_IRQCHIP, &chip);
+    if (ret < 0) {
+        fprintf(stderr, "KVM_GET_IRQCHIP failed: %s\n", strerror(ret));
+        abort();
+    }
+
+    kpic = &chip.chip.pic;
+
+    s->last_irr = kpic->last_irr;
+    s->irr = kpic->irr;
+    s->imr = kpic->imr;
+    s->isr = kpic->isr;
+    s->priority_add = kpic->priority_add;
+    s->irq_base = kpic->irq_base;
+    s->read_reg_select = kpic->read_reg_select;
+    s->poll = kpic->poll;
+    s->special_mask = kpic->special_mask;
+    s->init_state = kpic->init_state;
+    s->auto_eoi = kpic->auto_eoi;
+    s->rotate_on_auto_eoi = kpic->rotate_on_auto_eoi;
+    s->special_fully_nested_mode = kpic->special_fully_nested_mode;
+    s->init4 = kpic->init4;
+    s->elcr = kpic->elcr;
+    s->elcr_mask = kpic->elcr_mask;
+}
+
+static void kvm_pic_put(PICCommonState *s)
+{
+    struct kvm_irqchip chip;
+    struct kvm_pic_state *kpic;
+    int ret;
+
+    chip.chip_id = s->master ? KVM_IRQCHIP_PIC_MASTER : KVM_IRQCHIP_PIC_SLAVE;
+
+    kpic = &chip.chip.pic;
+
+    kpic->last_irr = s->last_irr;
+    kpic->irr = s->irr;
+    kpic->imr = s->imr;
+    kpic->isr = s->isr;
+    kpic->priority_add = s->priority_add;
+    kpic->irq_base = s->irq_base;
+    kpic->read_reg_select = s->read_reg_select;
+    kpic->poll = s->poll;
+    kpic->special_mask = s->special_mask;
+    kpic->init_state = s->init_state;
+    kpic->auto_eoi = s->auto_eoi;
+    kpic->rotate_on_auto_eoi = s->rotate_on_auto_eoi;
+    kpic->special_fully_nested_mode = s->special_fully_nested_mode;
+    kpic->init4 = s->init4;
+    kpic->elcr = s->elcr;
+    kpic->elcr_mask = s->elcr_mask;
+
+    ret = kvm_vm_ioctl(kvm_state, KVM_SET_IRQCHIP, &chip);
+    if (ret < 0) {
+        fprintf(stderr, "KVM_GET_IRQCHIP failed: %s\n", strerror(ret));
+        abort();
+    }
+}
+
+static void kvm_pic_reset(DeviceState *dev)
+{
+    PICCommonState *s = DO_UPCAST(PICCommonState, dev.qdev, dev);
+
+    pic_reset_common(s);
+    s->elcr = 0;
+
+    kvm_pic_put(s);
+}
+
+static void kvm_pic_set_irq(void *opaque, int irq, int level)
+{
+    int delivered;
+
+    delivered = kvm_irqchip_set_irq(kvm_state, irq, level);
+    apic_report_irq_delivered(delivered);
+}
+
+static void kvm_pic_init(PICCommonState *s)
+{
+    memory_region_init_reservation(&s->base_io, "kvm-pic", 2);
+    memory_region_init_reservation(&s->elcr_io, "kvm-elcr", 1);
+}
+
+qemu_irq *kvm_i8259_init(ISABus *bus)
+{
+    i8259_init_chip("kvm-i8259", bus, true);
+    i8259_init_chip("kvm-i8259", bus, false);
+
+    return qemu_allocate_irqs(kvm_pic_set_irq, NULL, ISA_NUM_IRQS);
+}
+
+static PICCommonInfo kvm_i8259_info = {
+    .isadev.qdev.name  = "kvm-i8259",
+    .isadev.qdev.reset = kvm_pic_reset,
+    .init       = kvm_pic_init,
+    .pre_save   = kvm_pic_get,
+    .post_load  = kvm_pic_put,
+};
+
+static void kvm_pic_register(void)
+{
+    pic_qdev_register(&kvm_i8259_info);
+}
+
+device_init(kvm_pic_register)
diff --git a/hw/kvm/ioapic.c b/hw/kvm/ioapic.c
new file mode 100644
index 0000000000..10ffdd4b20
--- /dev/null
+++ b/hw/kvm/ioapic.c
@@ -0,0 +1,114 @@
+/*
+ * KVM in-kernel IOPIC support
+ *
+ * Copyright (c) 2011 Siemens AG
+ *
+ * Authors:
+ *  Jan Kiszka          <jan.kiszka@siemens.com>
+ *
+ * This work is licensed under the terms of the GNU GPL version 2.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "hw/pc.h"
+#include "hw/ioapic_internal.h"
+#include "hw/apic_internal.h"
+#include "kvm.h"
+
+typedef struct KVMIOAPICState KVMIOAPICState;
+
+struct KVMIOAPICState {
+    IOAPICCommonState ioapic;
+    uint32_t kvm_gsi_base;
+};
+
+static void kvm_ioapic_get(IOAPICCommonState *s)
+{
+    struct kvm_irqchip chip;
+    struct kvm_ioapic_state *kioapic;
+    int ret, i;
+
+    chip.chip_id = KVM_IRQCHIP_IOAPIC;
+    ret = kvm_vm_ioctl(kvm_state, KVM_GET_IRQCHIP, &chip);
+    if (ret < 0) {
+        fprintf(stderr, "KVM_GET_IRQCHIP failed: %s\n", strerror(ret));
+        abort();
+    }
+
+    kioapic = &chip.chip.ioapic;
+
+    s->id = kioapic->id;
+    s->ioregsel = kioapic->ioregsel;
+    s->irr = kioapic->irr;
+    for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+        s->ioredtbl[i] = kioapic->redirtbl[i].bits;
+    }
+}
+
+static void kvm_ioapic_put(IOAPICCommonState *s)
+{
+    struct kvm_irqchip chip;
+    struct kvm_ioapic_state *kioapic;
+    int ret, i;
+
+    chip.chip_id = KVM_IRQCHIP_IOAPIC;
+    kioapic = &chip.chip.ioapic;
+
+    kioapic->id = s->id;
+    kioapic->ioregsel = s->ioregsel;
+    kioapic->base_address = s->busdev.mmio[0].addr;
+    kioapic->irr = s->irr;
+    for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+        kioapic->redirtbl[i].bits = s->ioredtbl[i];
+    }
+
+    ret = kvm_vm_ioctl(kvm_state, KVM_SET_IRQCHIP, &chip);
+    if (ret < 0) {
+        fprintf(stderr, "KVM_GET_IRQCHIP failed: %s\n", strerror(ret));
+        abort();
+    }
+}
+
+static void kvm_ioapic_reset(DeviceState *dev)
+{
+    IOAPICCommonState *s = DO_UPCAST(IOAPICCommonState, busdev.qdev, dev);
+
+    ioapic_reset_common(dev);
+    kvm_ioapic_put(s);
+}
+
+static void kvm_ioapic_set_irq(void *opaque, int irq, int level)
+{
+    KVMIOAPICState *s = opaque;
+    int delivered;
+
+    delivered = kvm_irqchip_set_irq(kvm_state, s->kvm_gsi_base + irq, level);
+    apic_report_irq_delivered(delivered);
+}
+
+static void kvm_ioapic_init(IOAPICCommonState *s, int instance_no)
+{
+    memory_region_init_reservation(&s->io_memory, "kvm-ioapic", 0x1000);
+
+    qdev_init_gpio_in(&s->busdev.qdev, kvm_ioapic_set_irq, IOAPIC_NUM_PINS);
+}
+
+static IOAPICCommonInfo kvm_ioapic_info = {
+    .busdev.qdev.name  = "kvm-ioapic",
+    .busdev.qdev.size = sizeof(KVMIOAPICState),
+    .busdev.qdev.reset = kvm_ioapic_reset,
+    .busdev.qdev.props = (Property[]) {
+        DEFINE_PROP_UINT32("gsi_base", KVMIOAPICState, kvm_gsi_base, 0),
+        DEFINE_PROP_END_OF_LIST()
+    },
+    .init      = kvm_ioapic_init,
+    .pre_save  = kvm_ioapic_get,
+    .post_load = kvm_ioapic_put,
+};
+
+static void kvm_ioapic_register_device(void)
+{
+    ioapic_qdev_register(&kvm_ioapic_info);
+}
+
+device_init(kvm_ioapic_register_device)