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>

4 files changed, 233 insertions, 2 deletions

diff --git a/target-i386/cpuid.c b/target-i386/cpuid.c
index 91a104b..b9bfeaf 100644
--- a/target-i386/cpuid.c
+++ b/target-i386/cpuid.c
@@ -27,6 +27,8 @@
 #include "qemu-option.h"
 #include "qemu-config.h"
 
+#include "hyperv.h"
+
 /* feature flags taken from "Intel Processor Identification and the CPUID
  * Instruction" and AMD's "CPUID Specification".  In cases of disagreement
  * between feature naming conventions, aliases may be added.
@@ -716,6 +718,14 @@ static int cpu_x86_find_by_name(x86_def_t *x86_cpu_def, const char *cpu_model)
                     goto error;
                 }
                 x86_cpu_def->tsc_khz = tsc_freq / 1000;
+            } else if (!strcmp(featurestr, "hv_spinlocks")) {
+                char *err;
+                numvalue = strtoul(val, &err, 0);
+                if (!*val || *err) {
+                    fprintf(stderr, "bad numerical value %s\n", val);
+                    goto error;
+                }
+                hyperv_set_spinlock_retries(numvalue);
             } else {
                 fprintf(stderr, "unrecognized feature %s\n", featurestr);
                 goto error;
@@ -724,6 +734,10 @@ static int cpu_x86_find_by_name(x86_def_t *x86_cpu_def, const char *cpu_model)
             check_cpuid = 1;
         } else if (!strcmp(featurestr, "enforce")) {
             check_cpuid = enforce_cpuid = 1;
+        } else if (!strcmp(featurestr, "hv_relaxed")) {
+            hyperv_enable_relaxed_timing(true);
+        } else if (!strcmp(featurestr, "hv_vapic")) {
+            hyperv_enable_vapic_recommended(true);
         } else {
             fprintf(stderr, "feature string `%s' not in format (+feature|-feature|feature=xyz)\n", featurestr);
             goto error;
diff --git a/target-i386/hyperv.c b/target-i386/hyperv.c
new file mode 100644
index 0000000..f284e99
--- /dev/null
+++ b/target-i386/hyperv.c
@@ -0,0 +1,64 @@
+/*
+ * QEMU Hyper-V support
+ *
+ * Copyright Red Hat, Inc. 2011
+ *
+ * Author: Vadim Rozenfeld     <vrozenfe@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "hyperv.h"
+
+static bool hyperv_vapic;
+static bool hyperv_relaxed_timing;
+static int hyperv_spinlock_attempts = HYPERV_SPINLOCK_NEVER_RETRY;
+
+void hyperv_enable_vapic_recommended(bool val)
+{
+    hyperv_vapic = val;
+}
+
+void hyperv_enable_relaxed_timing(bool val)
+{
+    hyperv_relaxed_timing = val;
+}
+
+void hyperv_set_spinlock_retries(int val)
+{
+    hyperv_spinlock_attempts = val;
+    if (hyperv_spinlock_attempts < 0xFFF) {
+        hyperv_spinlock_attempts = 0xFFF;
+    }
+}
+
+bool hyperv_enabled(void)
+{
+    return hyperv_hypercall_available() || hyperv_relaxed_timing_enabled();
+}
+
+bool hyperv_hypercall_available(void)
+{
+    if (hyperv_vapic ||
+        (hyperv_spinlock_attempts != HYPERV_SPINLOCK_NEVER_RETRY)) {
+      return true;
+    }
+    return false;
+}
+
+bool hyperv_vapic_recommended(void)
+{
+    return hyperv_vapic;
+}
+
+bool hyperv_relaxed_timing_enabled(void)
+{
+    return hyperv_relaxed_timing;
+}
+
+int hyperv_get_spinlock_retries(void)
+{
+    return hyperv_spinlock_attempts;
+}
diff --git a/target-i386/hyperv.h b/target-i386/hyperv.h
new file mode 100644
index 0000000..15467bf
--- /dev/null
+++ b/target-i386/hyperv.h
@@ -0,0 +1,43 @@
+/*
+ * QEMU Hyper-V support
+ *
+ * Copyright Red Hat, Inc. 2011
+ *
+ * Author: Vadim Rozenfeld     <vrozenfe@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_HW_HYPERV_H
+#define QEMU_HW_HYPERV_H 1
+
+#include "qemu-common.h"
+#include <asm/hyperv.h>
+
+#ifndef HYPERV_SPINLOCK_NEVER_RETRY
+#define HYPERV_SPINLOCK_NEVER_RETRY             0xFFFFFFFF
+#endif
+
+#ifndef KVM_CPUID_SIGNATURE_NEXT
+#define KVM_CPUID_SIGNATURE_NEXT                0x40000100
+#endif
+
+#ifndef CONFIG_USER_ONLY
+void hyperv_enable_vapic_recommended(bool val);
+void hyperv_enable_relaxed_timing(bool val);
+void hyperv_set_spinlock_retries(int val);
+#else
+static inline void hyperv_enable_vapic_recommended(bool val) { }
+static inline void hyperv_enable_relaxed_timing(bool val) { }
+static inline void hyperv_set_spinlock_retries(int val) { }
+#endif
+
+bool hyperv_enabled(void);
+bool hyperv_hypercall_available(void);
+bool hyperv_vapic_recommended(void);
+bool hyperv_relaxed_timing_enabled(void);
+int hyperv_get_spinlock_retries(void);
+
+#endif /* QEMU_HW_HYPERV_H */
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 04e65c5..e41de39 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -29,6 +29,7 @@
 #include "hw/pc.h"
 #include "hw/apic.h"
 #include "ioport.h"
+#include "hyperv.h"
 
 //#define DEBUG_KVM
 
@@ -373,11 +374,16 @@ int kvm_arch_init_vcpu(CPUState *env)
     cpuid_i = 0;
 
     /* Paravirtualization CPUIDs */
-    memcpy(signature, "KVMKVMKVM\0\0\0", 12);
     c = &cpuid_data.entries[cpuid_i++];
     memset(c, 0, sizeof(*c));
     c->function = KVM_CPUID_SIGNATURE;
-    c->eax = 0;
+    if (!hyperv_enabled()) {
+        memcpy(signature, "KVMKVMKVM\0\0\0", 12);
+        c->eax = 0;
+    } else {
+        memcpy(signature, "Microsoft Hv", 12);
+        c->eax = HYPERV_CPUID_MIN;
+    }
     c->ebx = signature[0];
     c->ecx = signature[1];
     c->edx = signature[2];
@@ -388,6 +394,54 @@ int kvm_arch_init_vcpu(CPUState *env)
     c->eax = env->cpuid_kvm_features &
         kvm_arch_get_supported_cpuid(s, KVM_CPUID_FEATURES, 0, R_EAX);
 
+    if (hyperv_enabled()) {
+        memcpy(signature, "Hv#1\0\0\0\0\0\0\0\0", 12);
+        c->eax = signature[0];
+
+        c = &cpuid_data.entries[cpuid_i++];
+        memset(c, 0, sizeof(*c));
+        c->function = HYPERV_CPUID_VERSION;
+        c->eax = 0x00001bbc;
+        c->ebx = 0x00060001;
+
+        c = &cpuid_data.entries[cpuid_i++];
+        memset(c, 0, sizeof(*c));
+        c->function = HYPERV_CPUID_FEATURES;
+        if (hyperv_relaxed_timing_enabled()) {
+            c->eax |= HV_X64_MSR_HYPERCALL_AVAILABLE;
+        }
+        if (hyperv_vapic_recommended()) {
+            c->eax |= HV_X64_MSR_HYPERCALL_AVAILABLE;
+            c->eax |= HV_X64_MSR_APIC_ACCESS_AVAILABLE;
+        }
+
+        c = &cpuid_data.entries[cpuid_i++];
+        memset(c, 0, sizeof(*c));
+        c->function = HYPERV_CPUID_ENLIGHTMENT_INFO;
+        if (hyperv_relaxed_timing_enabled()) {
+            c->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED;
+        }
+        if (hyperv_vapic_recommended()) {
+            c->eax |= HV_X64_APIC_ACCESS_RECOMMENDED;
+        }
+        c->ebx = hyperv_get_spinlock_retries();
+
+        c = &cpuid_data.entries[cpuid_i++];
+        memset(c, 0, sizeof(*c));
+        c->function = HYPERV_CPUID_IMPLEMENT_LIMITS;
+        c->eax = 0x40;
+        c->ebx = 0x40;
+
+        c = &cpuid_data.entries[cpuid_i++];
+        memset(c, 0, sizeof(*c));
+        c->function = KVM_CPUID_SIGNATURE_NEXT;
+        memcpy(signature, "KVMKVMKVM\0\0\0", 12);
+        c->eax = 0;
+        c->ebx = signature[0];
+        c->ecx = signature[1];
+        c->edx = signature[2];
+    }
+
     has_msr_async_pf_en = c->eax & (1 << KVM_FEATURE_ASYNC_PF);
 
     cpu_x86_cpuid(env, 0, 0, &limit, &unused, &unused, &unused);
@@ -933,6 +987,13 @@ static int kvm_put_msrs(CPUState *env, int level)
             kvm_msr_entry_set(&msrs[n++], MSR_KVM_ASYNC_PF_EN,
                               env->async_pf_en_msr);
         }
+        if (hyperv_hypercall_available()) {
+            kvm_msr_entry_set(&msrs[n++], HV_X64_MSR_GUEST_OS_ID, 0);
+            kvm_msr_entry_set(&msrs[n++], HV_X64_MSR_HYPERCALL, 0);
+        }
+        if (hyperv_vapic_recommended()) {
+            kvm_msr_entry_set(&msrs[n++], HV_X64_MSR_APIC_ASSIST_PAGE, 0);
+        }
     }
     if (env->mcg_cap) {
         int i;
@@ -1276,6 +1337,36 @@ static int kvm_get_mp_state(CPUState *env)
     return 0;
 }
 
+static int kvm_get_apic(CPUState *env)
+{
+    DeviceState *apic = env->apic_state;
+    struct kvm_lapic_state kapic;
+    int ret;
+
+    if (apic && kvm_enabled() && kvm_irqchip_in_kernel()) {
+        ret = kvm_vcpu_ioctl(env, KVM_GET_LAPIC, &kapic);
+        if (ret < 0) {
+            return ret;
+        }
+
+        kvm_get_apic_state(apic, &kapic);
+    }
+    return 0;
+}
+
+static int kvm_put_apic(CPUState *env)
+{
+    DeviceState *apic = env->apic_state;
+    struct kvm_lapic_state kapic;
+
+    if (apic && kvm_enabled() && kvm_irqchip_in_kernel()) {
+        kvm_put_apic_state(apic, &kapic);
+
+        return kvm_vcpu_ioctl(env, KVM_SET_LAPIC, &kapic);
+    }
+    return 0;
+}
+
 static int kvm_put_vcpu_events(CPUState *env, int level)
 {
     struct kvm_vcpu_events events;
@@ -1449,6 +1540,10 @@ 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) {
@@ -1496,6 +1591,10 @@ 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;
@@ -1878,3 +1977,14 @@ bool kvm_arch_stop_on_emulation_error(CPUState *env)
     return !(env->cr[0] & CR0_PE_MASK) ||
            ((env->segs[R_CS].selector  & 3) != 3);
 }
+
+void kvm_arch_init_irq_routing(KVMState *s)
+{
+    if (!kvm_check_extension(s, KVM_CAP_IRQ_ROUTING)) {
+        /* If kernel can't do irq routing, interrupt source
+         * override 0->2 cannot be set up as required by HPET.
+         * So we have to disable it.
+         */
+        no_hpet = 1;
+    }
+}