haraldwolff/qemu-patch-raspberry4
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

Initial support for the HVF accelerator

Browse source 
-----BEGIN PGP SIGNATURE-----
 
 iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAlo+CvYUHHBib256aW5p
 QHJlZGhhdC5jb20ACgkQv/vSX3jHroPZpAf9E93cRgy+l7EyjLYp1jNrRVbE/57N
 g3Z0l9VN3QIErtVpvysp3nrfwSlPCrNdc2tFNq58HHUIrwqTsi2dQeBMXv1zLLUp
 BscjBF6XgG35lVZG/mUngYeUlZMI+ERhkMa8clYcW7zPEbmGRQB5fhvsR4eak3Ub
 j3b1ydZiQF6sooJIOJq/7Qpn2YkPaNOYOKV+VkEZQJhQkJMV9BzEEbjzbrzmBN/u
 xsUBwIJRHfdiyHKv6VwxdMvH9bB1LE7X6hpfXmsep71PYA4YJM7GmotbwjODGszq
 PKNOnrVqHfdvxBKkgfGypuEI4D9tczDgducfq0hcpjpNF+x3lMgPXS/qtg==
 =+nhI
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream-hvf' into staging

Initial support for the HVF accelerator

# gpg: Signature made Sat 23 Dec 2017 07:51:18 GMT
# gpg:                using RSA key 0xBFFBD25F78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini/tags/for-upstream-hvf:
  i386: hvf: cleanup x86_gen.h
  i386: hvf: remove VM_PANIC from "in"
  i386: hvf: remove addr_t
  i386: hvf: simplify flag handling
  i386: hvf: abort on decoding error
  i386: hvf: remove ZERO_INIT macro
  i386: hvf: remove more dead emulator code
  i386: hvf: unify register enums between HVF and the rest
  i386: hvf: header cleanup
  i386: hvf: move all hvf files in the same directory
  i386: hvf: inject General Protection Fault when vmexit through vmcall
  i386: hvf: refactor event injection code for hvf
  i386: hvf: implement vga dirty page tracking
  i386: refactor KVM cpuid code so that it applies to hvf as well
  i386: hvf: implement hvf_get_supported_cpuid
  i386: hvf: use new helper functions for put/get xsave
  i386: hvf: fix licensing issues; isolate task handling code (GPL v2-only)
  i386: hvf: add code base from Google's QEMU repository
  apic: add function to apic that will be used by hvf

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Peter Maydell 2018-01-08 11:39:50 +00:00
parent b1e513ae33 895f9fdf3a
commit 1e10eb532c
39 changed files with 8472 additions and 57 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
accel/stubs/Makefile.objs
View file

@ -1,3 +1,4 @@
obj-$(call lnot,$(CONFIG_HAX)) += hax-stub.o
obj-$(call lnot,$(CONFIG_HVF)) += hvf-stub.o
obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o
obj-$(call lnot,$(CONFIG_TCG)) += tcg-stub.o

31
accel/stubs/hvf-stub.c Normal file
View file

@ -0,0 +1,31 @@
/*
* QEMU HVF support
*
* Copyright 2017 Red Hat, Inc.
*
* This software is licensed under the terms of the GNU General Public
* License version 2 or later, as published by the Free Software Foundation,
* and may be copied, distributed, and modified under those terms.
*
* See the COPYING file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "cpu.h"
#include "sysemu/hvf.h"
int hvf_init_vcpu(CPUState *cpu)
{
return -ENOSYS;
}
int hvf_vcpu_exec(CPUState *cpu)
{
return -ENOSYS;
}
void hvf_vcpu_destroy(CPUState *cpu)
{
}

38
configure vendored
View file

@ -211,6 +211,17 @@ supported_xen_target() {
return 1
}
supported_hvf_target() {
test "$hvf" = "yes" || return 1
glob "$1" "*-softmmu" || return 1
case "${1%-softmmu}" in
x86_64)
return 0
;;
esac
return 1
}
supported_target() {
case "$1" in
*-softmmu)
@ -236,6 +247,7 @@ supported_target() {
supported_kvm_target "$1" && return 0
supported_xen_target "$1" && return 0
supported_hax_target "$1" && return 0
supported_hvf_target "$1" && return 0
print_error "TCG disabled, but hardware accelerator not available for '$target'"
return 1
}
@ -325,6 +337,7 @@ vhost_vsock="no"
vhost_user=""
kvm="no"
hax="no"
hvf="no"
rdma=""
gprof="no"
debug_tcg="no"
@ -741,6 +754,7 @@ Darwin)
bsd="yes"
darwin="yes"
hax="yes"
hvf="yes"
LDFLAGS_SHARED="-bundle -undefined dynamic_lookup"
if [ "$cpu" = "x86_64" ] ; then
QEMU_CFLAGS="-arch x86_64 $QEMU_CFLAGS"
@ -1036,6 +1050,10 @@ for opt do
;;
--enable-hax) hax="yes"
;;
--disable-hvf) hvf="no"
;;
--enable-hvf) hvf="yes"
;;
--disable-tcg-interpreter) tcg_interpreter="no"
;;
--enable-tcg-interpreter) tcg_interpreter="yes"
@ -1529,6 +1547,7 @@ disabled with --disable-FEATURE, default is enabled if available:
bluez bluez stack connectivity
kvm KVM acceleration support
hax HAX acceleration support
hvf Hypervisor.framework acceleration support
rdma RDMA-based migration support
vde support for vde network
netmap support for netmap network
@ -5055,6 +5074,21 @@ then
fi
#################################################
# Check to see if we have the Hypervisor framework
if [ "$darwin" == "yes" ] ; then
cat > $TMPC << EOF
#include <Hypervisor/hv.h>
int main() { return 0;}
EOF
if ! compile_object ""; then
hvf='no'
else
hvf='yes'
LDFLAGS="-framework Hypervisor $LDFLAGS"
fi
fi
#################################################
# Sparc implicitly links with --relax, which is
# incompatible with -r, so --no-relax should be
@ -5530,6 +5564,7 @@ echo "ATTR/XATTR support $attr"
echo "Install blobs $blobs"
echo "KVM support $kvm"
echo "HAX support $hax"
echo "HVF support $hvf"
echo "TCG support $tcg"
if test "$tcg" = "yes" ; then
echo "TCG debug enabled $debug_tcg"
@ -6602,6 +6637,9 @@ fi
if supported_hax_target $target; then
echo "CONFIG_HAX=y" >> $config_target_mak
fi
if supported_hvf_target $target; then
echo "CONFIG_HVF=y" >> $config_target_mak
fi
if test "$target_bigendian" = "yes" ; then
echo "TARGET_WORDS_BIGENDIAN=y" >> $config_target_mak
fi

86
cpus.c
View file

@ -37,6 +37,7 @@
#include "sysemu/hw_accel.h"
#include "sysemu/kvm.h"
#include "sysemu/hax.h"
#include "sysemu/hvf.h"
#include "qmp-commands.h"
#include "exec/exec-all.h"
@ -900,6 +901,10 @@ void cpu_synchronize_all_states(void)
CPU_FOREACH(cpu) {
cpu_synchronize_state(cpu);
/* TODO: move to cpu_synchronize_state() */
if (hvf_enabled()) {
hvf_cpu_synchronize_state(cpu);
}
}
}
@ -909,6 +914,10 @@ void cpu_synchronize_all_post_reset(void)
CPU_FOREACH(cpu) {
cpu_synchronize_post_reset(cpu);
/* TODO: move to cpu_synchronize_post_reset() */
if (hvf_enabled()) {
hvf_cpu_synchronize_post_reset(cpu);
}
}
}
@ -918,6 +927,10 @@ void cpu_synchronize_all_post_init(void)
CPU_FOREACH(cpu) {
cpu_synchronize_post_init(cpu);
/* TODO: move to cpu_synchronize_post_init() */
if (hvf_enabled()) {
hvf_cpu_synchronize_post_init(cpu);
}
}
}
@ -1107,6 +1120,14 @@ static void qemu_kvm_wait_io_event(CPUState *cpu)
qemu_wait_io_event_common(cpu);
}
static void qemu_hvf_wait_io_event(CPUState *cpu)
{
while (cpu_thread_is_idle(cpu)) {
qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex);
}
qemu_wait_io_event_common(cpu);
}
static void *qemu_kvm_cpu_thread_fn(void *arg)
{
CPUState *cpu = arg;
@ -1444,6 +1465,48 @@ static void *qemu_hax_cpu_thread_fn(void *arg)
return NULL;
}
/* The HVF-specific vCPU thread function. This one should only run when the host
* CPU supports the VMX "unrestricted guest" feature. */
static void *qemu_hvf_cpu_thread_fn(void *arg)
{
CPUState *cpu = arg;
int r;
assert(hvf_enabled());
rcu_register_thread();
qemu_mutex_lock_iothread();
qemu_thread_get_self(cpu->thread);
cpu->thread_id = qemu_get_thread_id();
cpu->can_do_io = 1;
current_cpu = cpu;
hvf_init_vcpu(cpu);
/* signal CPU creation */
cpu->created = true;
qemu_cond_signal(&qemu_cpu_cond);
do {
if (cpu_can_run(cpu)) {
r = hvf_vcpu_exec(cpu);
if (r == EXCP_DEBUG) {
cpu_handle_guest_debug(cpu);
}
}
qemu_hvf_wait_io_event(cpu);
} while (!cpu->unplug || cpu_can_run(cpu));
hvf_vcpu_destroy(cpu);
cpu->created = false;
qemu_cond_signal(&qemu_cpu_cond);
qemu_mutex_unlock_iothread();
return NULL;
}
#ifdef _WIN32
static void CALLBACK dummy_apc_func(ULONG_PTR unused)
{
@ -1761,6 +1824,27 @@ static void qemu_kvm_start_vcpu(CPUState *cpu)
}
}
static void qemu_hvf_start_vcpu(CPUState *cpu)
{
char thread_name[VCPU_THREAD_NAME_SIZE];
/* HVF currently does not support TCG, and only runs in
* unrestricted-guest mode. */
assert(hvf_enabled());
cpu->thread = g_malloc0(sizeof(QemuThread));
cpu->halt_cond = g_malloc0(sizeof(QemuCond));
qemu_cond_init(cpu->halt_cond);
snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/HVF",
cpu->cpu_index);
qemu_thread_create(cpu->thread, thread_name, qemu_hvf_cpu_thread_fn,
cpu, QEMU_THREAD_JOINABLE);
while (!cpu->created) {
qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
}
}
static void qemu_dummy_start_vcpu(CPUState *cpu)
{
char thread_name[VCPU_THREAD_NAME_SIZE];
@ -1795,6 +1879,8 @@ void qemu_init_vcpu(CPUState *cpu)
qemu_kvm_start_vcpu(cpu);
} else if (hax_enabled()) {
qemu_hax_start_vcpu(cpu);
} else if (hvf_enabled()) {
qemu_hvf_start_vcpu(cpu);
} else if (tcg_enabled()) {
qemu_tcg_init_vcpu(cpu);
} else {

12
hw/intc/apic.c
View file

@ -305,6 +305,18 @@ static void apic_set_tpr(APICCommonState *s, uint8_t val)
}
}
int apic_get_highest_priority_irr(DeviceState *dev)
{
APICCommonState *s;
if (!dev) {
/* no interrupts */
return -1;
}
s = APIC_COMMON(dev);
return get_highest_priority_int(s->irr);
}
static uint8_t apic_get_tpr(APICCommonState *s)
{
apic_sync_vapic(s, SYNC_FROM_VAPIC);

1
include/hw/i386/apic.h
View file

@ -20,6 +20,7 @@ void apic_init_reset(DeviceState *s);
void apic_sipi(DeviceState *s);
void apic_poll_irq(DeviceState *d);
void apic_designate_bsp(DeviceState *d, bool bsp);
int apic_get_highest_priority_irr(DeviceState *dev);
/* pc.c */
DeviceState *cpu_get_current_apic(void);

1
include/qemu/typedefs.h
View file

@ -36,6 +36,7 @@ typedef struct FWCfgIoState FWCfgIoState;
typedef struct FWCfgMemState FWCfgMemState;
typedef struct FWCfgState FWCfgState;
typedef struct HCIInfo HCIInfo;
typedef struct HVFX86EmulatorState HVFX86EmulatorState;
typedef struct I2CBus I2CBus;
typedef struct I2SCodec I2SCodec;
typedef struct ISABus ISABus;

2
include/qom/cpu.h
View file

@ -423,6 +423,8 @@ struct CPUState {
* unnecessary flushes.
*/
uint16_t pending_tlb_flush;
int hvf_fd;
};
QTAILQ_HEAD(CPUTailQ, CPUState);

107
include/sysemu/hvf.h Normal file
View file

@ -0,0 +1,107 @@
/*
* QEMU Hypervisor.framework (HVF) support
*
* Copyright Google Inc., 2017
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
/* header to be included in non-HVF-specific code */
#ifndef _HVF_H
#define _HVF_H
#include "config-host.h"
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/bitops.h"
#include "exec/memory.h"
#include "sysemu/accel.h"
extern int hvf_disabled;
#ifdef CONFIG_HVF
#include <Hypervisor/hv.h>
#include <Hypervisor/hv_vmx.h>
#include <Hypervisor/hv_error.h>
#include "target/i386/cpu.h"
#include "hw/hw.h"
uint32_t hvf_get_supported_cpuid(uint32_t func, uint32_t idx,
int reg);
#define hvf_enabled() !hvf_disabled
#else
#define hvf_enabled() 0
#define hvf_get_supported_cpuid(func, idx, reg) 0
#endif
/* hvf_slot flags */
#define HVF_SLOT_LOG (1 << 0)
typedef struct hvf_slot {
uint64_t start;
uint64_t size;
uint8_t *mem;
int slot_id;
uint32_t flags;
MemoryRegion *region;
} hvf_slot;
typedef struct hvf_vcpu_caps {
uint64_t vmx_cap_pinbased;
uint64_t vmx_cap_procbased;
uint64_t vmx_cap_procbased2;
uint64_t vmx_cap_entry;
uint64_t vmx_cap_exit;
uint64_t vmx_cap_preemption_timer;
} hvf_vcpu_caps;
typedef struct HVFState {
AccelState parent;
hvf_slot slots[32];
int num_slots;
hvf_vcpu_caps *hvf_caps;
} HVFState;
extern HVFState *hvf_state;
void hvf_set_phys_mem(MemoryRegionSection *, bool);
void hvf_handle_io(CPUArchState *, uint16_t, void *,
int, int, int);
hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t);
/* Disable HVF if |disable| is 1, otherwise, enable it iff it is supported by
* the host CPU. Use hvf_enabled() after this to get the result. */
void hvf_disable(int disable);
/* Returns non-0 if the host CPU supports the VMX "unrestricted guest" feature
* which allows the virtual CPU to directly run in "real mode". If true, this
* allows QEMU to run several vCPU threads in parallel (see cpus.c). Otherwise,
* only a a single TCG thread can run, and it will call HVF to run the current
* instructions, except in case of "real mode" (paging disabled, typically at
* boot time), or MMIO operations. */
int hvf_sync_vcpus(void);
int hvf_init_vcpu(CPUState *);
int hvf_vcpu_exec(CPUState *);
int hvf_smp_cpu_exec(CPUState *);
void hvf_cpu_synchronize_state(CPUState *);
void hvf_cpu_synchronize_post_reset(CPUState *);
void hvf_cpu_synchronize_post_init(CPUState *);
void _hvf_cpu_synchronize_post_init(CPUState *, run_on_cpu_data);
void hvf_vcpu_destroy(CPUState *);
void hvf_raise_event(CPUState *);
/* void hvf_reset_vcpu_state(void *opaque); */
void hvf_reset_vcpu(CPUState *);
void vmx_update_tpr(CPUState *);
void update_apic_tpr(CPUState *);
int hvf_put_registers(CPUState *);
void vmx_clear_int_window_exiting(CPUState *cpu);
#define TYPE_HVF_ACCEL ACCEL_CLASS_NAME("hvf")
#define HVF_STATE(obj) \
OBJECT_CHECK(HVFState, (obj), TYPE_HVF_ACCEL)
#endif

10
qemu-options.hx
View file

@ -31,7 +31,7 @@ DEF("machine", HAS_ARG, QEMU_OPTION_machine, \
"-machine [type=]name[,prop[=value][,...]]\n"
" selects emulated machine ('-machine help' for list)\n"
" property accel=accel1[:accel2[:...]] selects accelerator\n"
" supported accelerators are kvm, xen, hax or tcg (default: tcg)\n"
" supported accelerators are kvm, xen, hax, hvf or tcg (default: tcg)\n"
" kernel_irqchip=on|off|split controls accelerated irqchip support (default=off)\n"
" vmport=on|off|auto controls emulation of vmport (default: auto)\n"
" kvm_shadow_mem=size of KVM shadow MMU in bytes\n"
@ -66,7 +66,7 @@ Supported machine properties are:
@table @option
@item accel=@var{accels1}[:@var{accels2}[:...]]
This is used to enable an accelerator. Depending on the target architecture,
kvm, xen, hax or tcg can be available. By default, tcg is used. If there is
kvm, xen, hax, hvf or tcg can be available. By default, tcg is used. If there is
more than one accelerator specified, the next one is used if the previous one
fails to initialize.
@item kernel_irqchip=on|off
@ -126,13 +126,13 @@ ETEXI
DEF("accel", HAS_ARG, QEMU_OPTION_accel,
"-accel [accel=]accelerator[,thread=single|multi]\n"
" select accelerator (kvm, xen, hax or tcg; use 'help' for a list)\n"
" thread=single|multi (enable multi-threaded TCG)\n", QEMU_ARCH_ALL)
" select accelerator (kvm, xen, hax, hvf or tcg; use 'help' for a list)\n"
" thread=single|multi (enable multi-threaded TCG)", QEMU_ARCH_ALL)
STEXI
@item -accel @var{name}[,prop=@var{value}[,...]]
@findex -accel
This is used to enable an accelerator. Depending on the target architecture,
kvm, xen, hax or tcg can be available. By default, tcg is used. If there is
kvm, xen, hax, hvf or tcg can be available. By default, tcg is used. If there is
more than one accelerator specified, the next one is used if the previous one
fails to initialize.
@table @option

1
target/i386/Makefile.objs
View file

@ -12,4 +12,5 @@ obj-$(CONFIG_HAX) += hax-all.o hax-mem.o hax-windows.o
endif
ifdef CONFIG_DARWIN
obj-$(CONFIG_HAX) += hax-all.o hax-mem.o hax-darwin.o
obj-$(CONFIG_HVF) += hvf/
endif

4
target/i386/cpu-qom.h
View file

@ -47,7 +47,7 @@ typedef struct X86CPUDefinition X86CPUDefinition;
/**
* X86CPUClass:
* @cpu_def: CPU model definition
* @kvm_required: Whether CPU model requires KVM to be enabled.
* @host_cpuid_required: Whether CPU model requires cpuid from host.
* @ordering: Ordering on the "-cpu help" CPU model list.
* @migration_safe: See CpuDefinitionInfo::migration_safe
* @static_model: See CpuDefinitionInfo::static
@ -66,7 +66,7 @@ typedef struct X86CPUClass {
*/
X86CPUDefinition *cpu_def;
bool kvm_required;
bool host_cpuid_required;
int ordering;
bool migration_safe;
bool static_model;

80
target/i386/cpu.c
View file

@ -22,6 +22,7 @@
#include "cpu.h"
#include "exec/exec-all.h"
#include "sysemu/kvm.h"
#include "sysemu/hvf.h"
#include "sysemu/cpus.h"
#include "kvm_i386.h"
@ -615,6 +616,11 @@ static uint32_t xsave_area_size(uint64_t mask)
return ret;
}
static inline bool accel_uses_host_cpuid(void)
{
return kvm_enabled() || hvf_enabled();
}
static inline uint64_t x86_cpu_xsave_components(X86CPU *cpu)
{
return ((uint64_t)cpu->env.features[FEAT_XSAVE_COMP_HI]) << 32 |
@ -1686,10 +1692,15 @@ static void max_x86_cpu_initfn(Object *obj)
*/
cpu->max_features = true;
if (kvm_enabled()) {
if (accel_uses_host_cpuid()) {
char vendor[CPUID_VENDOR_SZ + 1] = { 0 };
char model_id[CPUID_MODEL_ID_SZ + 1] = { 0 };
int family, model, stepping;
X86CPUDefinition host_cpudef = { };
uint32_t eax = 0, ebx = 0, ecx = 0, edx = 0;
host_cpuid(0x0, 0, &eax, &ebx, &ecx, &edx);
x86_cpu_vendor_words2str(host_cpudef.vendor, ebx, edx, ecx);
host_vendor_fms(vendor, &family, &model, &stepping);
@ -1703,12 +1714,21 @@ static void max_x86_cpu_initfn(Object *obj)
object_property_set_str(OBJECT(cpu), model_id, "model-id",
&error_abort);
env->cpuid_min_level =
kvm_arch_get_supported_cpuid(s, 0x0, 0, R_EAX);
env->cpuid_min_xlevel =
kvm_arch_get_supported_cpuid(s, 0x80000000, 0, R_EAX);
env->cpuid_min_xlevel2 =
kvm_arch_get_supported_cpuid(s, 0xC0000000, 0, R_EAX);
if (kvm_enabled()) {
env->cpuid_min_level =
kvm_arch_get_supported_cpuid(s, 0x0, 0, R_EAX);
env->cpuid_min_xlevel =
kvm_arch_get_supported_cpuid(s, 0x80000000, 0, R_EAX);
env->cpuid_min_xlevel2 =
kvm_arch_get_supported_cpuid(s, 0xC0000000, 0, R_EAX);
} else {
env->cpuid_min_level =
hvf_get_supported_cpuid(0x0, 0, R_EAX);
env->cpuid_min_xlevel =
hvf_get_supported_cpuid(0x80000000, 0, R_EAX);
env->cpuid_min_xlevel2 =
hvf_get_supported_cpuid(0xC0000000, 0, R_EAX);
}
if (lmce_supported()) {
object_property_set_bool(OBJECT(cpu), true, "lmce", &error_abort);
@ -1734,18 +1754,21 @@ static const TypeInfo max_x86_cpu_type_info = {
.class_init = max_x86_cpu_class_init,
};
#ifdef CONFIG_KVM
#if defined(CONFIG_KVM) || defined(CONFIG_HVF)
static void host_x86_cpu_class_init(ObjectClass *oc, void *data)
{
X86CPUClass *xcc = X86_CPU_CLASS(oc);
xcc->kvm_required = true;
xcc->host_cpuid_required = true;
xcc->ordering = 8;
xcc->model_description =
"KVM processor with all supported host features "
"(only available in KVM mode)";
if (kvm_enabled()) {
xcc->model_description =
"KVM processor with all supported host features ";
} else if (hvf_enabled()) {
xcc->model_description =
"HVF processor with all supported host features ";
}
}
static const TypeInfo host_x86_cpu_type_info = {
@ -1767,7 +1790,7 @@ static void report_unavailable_features(FeatureWord w, uint32_t mask)
assert(reg);
warn_report("%s doesn't support requested feature: "
"CPUID.%02XH:%s%s%s [bit %d]",
kvm_enabled() ? "host" : "TCG",
accel_uses_host_cpuid() ? "host" : "TCG",
f->cpuid_eax, reg,
f->feat_names[i] ? "." : "",
f->feat_names[i] ? f->feat_names[i] : "", i);
@ -2218,7 +2241,7 @@ static void x86_cpu_class_check_missing_features(X86CPUClass *xcc,
Error *err = NULL;
strList **next = missing_feats;
if (xcc->kvm_required && !kvm_enabled()) {
if (xcc->host_cpuid_required && !accel_uses_host_cpuid()) {
strList *new = g_new0(strList, 1);
new->value = g_strdup("kvm");
*missing_feats = new;
@ -2380,6 +2403,10 @@ static uint32_t x86_cpu_get_supported_feature_word(FeatureWord w,
r = kvm_arch_get_supported_cpuid(kvm_state, wi->cpuid_eax,
wi->cpuid_ecx,
wi->cpuid_reg);
} else if (hvf_enabled()) {
r = hvf_get_supported_cpuid(wi->cpuid_eax,
wi->cpuid_ecx,
wi->cpuid_reg);
} else if (tcg_enabled()) {
r = wi->tcg_features;
} else {
@ -2439,6 +2466,7 @@ static void x86_cpu_load_def(X86CPU *cpu, X86CPUDefinition *def, Error **errp)
}
/* Special cases not set in the X86CPUDefinition structs: */
/* TODO: in-kernel irqchip for hvf */
if (kvm_enabled()) {
if (!kvm_irqchip_in_kernel()) {
x86_cpu_change_kvm_default("x2apic", "off");
@ -2459,7 +2487,7 @@ static void x86_cpu_load_def(X86CPU *cpu, X86CPUDefinition *def, Error **errp)
* when doing cross vendor migration
*/
vendor = def->vendor;
if (kvm_enabled()) {
if (accel_uses_host_cpuid()) {
uint32_t ebx = 0, ecx = 0, edx = 0;
host_cpuid(0, 0, NULL, &ebx, &ecx, &edx);
x86_cpu_vendor_words2str(host_vendor, ebx, edx, ecx);
@ -2910,6 +2938,11 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
*ebx = kvm_arch_get_supported_cpuid(s, 0xA, count, R_EBX);
*ecx = kvm_arch_get_supported_cpuid(s, 0xA, count, R_ECX);
*edx = kvm_arch_get_supported_cpuid(s, 0xA, count, R_EDX);
} else if (hvf_enabled() && cpu->enable_pmu) {
*eax = hvf_get_supported_cpuid(0xA, count, R_EAX);
*ebx = hvf_get_supported_cpuid(0xA, count, R_EBX);
*ecx = hvf_get_supported_cpuid(0xA, count, R_ECX);
*edx = hvf_get_supported_cpuid(0xA, count, R_EDX);
} else {
*eax = 0;
*ebx = 0;
@ -3252,6 +3285,9 @@ static void x86_cpu_reset(CPUState *s)
memset(env->mtrr_var, 0, sizeof(env->mtrr_var));
memset(env->mtrr_fixed, 0, sizeof(env->mtrr_fixed));
env->interrupt_injected = -1;
env->exception_injected = -1;
env->nmi_injected = false;
#if !defined(CONFIG_USER_ONLY)
/* We hard-wire the BSP to the first CPU. */
apic_designate_bsp(cpu->apic_state, s->cpu_index == 0);
@ -3261,6 +3297,9 @@ static void x86_cpu_reset(CPUState *s)
if (kvm_enabled()) {
kvm_arch_reset_vcpu(cpu);
}
else if (hvf_enabled()) {
hvf_reset_vcpu(s);
}
#endif
}
@ -3300,6 +3339,7 @@ APICCommonClass *apic_get_class(void)
{
const char *apic_type = "apic";
/* TODO: in-kernel irqchip for hvf */
if (kvm_apic_in_kernel()) {
apic_type = "kvm-apic";
} else if (xen_enabled()) {
@ -3613,7 +3653,7 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp)
Error *local_err = NULL;
static bool ht_warned;
if (xcc->kvm_required && !kvm_enabled()) {
if (xcc->host_cpuid_required && !accel_uses_host_cpuid()) {
char *name = x86_cpu_class_get_model_name(xcc);
error_setg(&local_err, "CPU model '%s' requires KVM", name);
g_free(name);
@ -3635,7 +3675,7 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp)
x86_cpu_report_filtered_features(cpu);
if (cpu->enforce_cpuid) {
error_setg(&local_err,
kvm_enabled() ?
accel_uses_host_cpuid() ?
"Host doesn't support requested features" :
"TCG doesn't support requested features");
goto out;
@ -3658,7 +3698,7 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp)
* consumer AMD devices but nothing else.
*/
if (env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_LM) {
if (kvm_enabled()) {
if (accel_uses_host_cpuid()) {
uint32_t host_phys_bits = x86_host_phys_bits();
static bool warned;
@ -4272,7 +4312,7 @@ static void x86_cpu_register_types(void)
}
type_register_static(&max_x86_cpu_type_info);
type_register_static(&x86_base_cpu_type_info);
#ifdef CONFIG_KVM
#if defined(CONFIG_KVM) || defined(CONFIG_HVF)
type_register_static(&host_x86_cpu_type_info);
#endif
}

97
target/i386/cpu.h
View file

@ -30,6 +30,8 @@
#define TARGET_LONG_BITS 32
#endif
#include "exec/cpu-defs.h"
/* The x86 has a strong memory model with some store-after-load re-ordering */
#define TCG_GUEST_DEFAULT_MO (TCG_MO_ALL & ~TCG_MO_ST_LD)
@ -50,48 +52,64 @@
#define CPUArchState struct CPUX86State
#include "exec/cpu-defs.h"
#ifdef CONFIG_TCG
#include "fpu/softfloat.h"
#endif
#define R_EAX 0
#define R_ECX 1
#define R_EDX 2
#define R_EBX 3
#define R_ESP 4
#define R_EBP 5
#define R_ESI 6
#define R_EDI 7
enum {
R_EAX = 0,
R_ECX = 1,
R_EDX = 2,
R_EBX = 3,
R_ESP = 4,
R_EBP = 5,
R_ESI = 6,
R_EDI = 7,
R_R8 = 8,
R_R9 = 9,
R_R10 = 10,
R_R11 = 11,
R_R12 = 12,
R_R13 = 13,
R_R14 = 14,
R_R15 = 15,
#define R_AL 0
#define R_CL 1
#define R_DL 2
#define R_BL 3
#define R_AH 4
#define R_CH 5
#define R_DH 6
#define R_BH 7
R_AL = 0,
R_CL = 1,
R_DL = 2,
R_BL = 3,
R_AH = 4,
R_CH = 5,
R_DH = 6,
R_BH = 7,
};
#define R_ES 0
#define R_CS 1
#define R_SS 2
#define R_DS 3
#define R_FS 4
#define R_GS 5
typedef enum X86Seg {
R_ES = 0,
R_CS = 1,
R_SS = 2,
R_DS = 3,
R_FS = 4,
R_GS = 5,
R_LDTR = 6,
R_TR = 7,
} X86Seg;
/* segment descriptor fields */
#define DESC_G_MASK (1 << 23)
#define DESC_G_SHIFT 23
#define DESC_G_MASK (1 << DESC_G_SHIFT)
#define DESC_B_SHIFT 22
#define DESC_B_MASK (1 << DESC_B_SHIFT)
#define DESC_L_SHIFT 21 /* x86_64 only : 64 bit code segment */
#define DESC_L_MASK (1 << DESC_L_SHIFT)
#define DESC_AVL_MASK (1 << 20)
#define DESC_P_MASK (1 << 15)
#define DESC_AVL_SHIFT 20
#define DESC_AVL_MASK (1 << DESC_AVL_SHIFT)
#define DESC_P_SHIFT 15
#define DESC_P_MASK (1 << DESC_P_SHIFT)
#define DESC_DPL_SHIFT 13
#define DESC_DPL_MASK (3 << DESC_DPL_SHIFT)
#define DESC_S_MASK (1 << 12)
#define DESC_S_SHIFT 12
#define DESC_S_MASK (1 << DESC_S_SHIFT)
#define DESC_TYPE_SHIFT 8
#define DESC_TYPE_MASK (15 << DESC_TYPE_SHIFT)
#define DESC_A_MASK (1 << 8)
@ -631,6 +649,7 @@ typedef uint32_t FeatureWordArray[FEATURE_WORDS];
#define CPUID_7_0_EBX_AVX512BW (1U << 30) /* AVX-512 Byte and Word Instructions */
#define CPUID_7_0_EBX_AVX512VL (1U << 31) /* AVX-512 Vector Length Extensions */
#define CPUID_7_0_ECX_AVX512BMI (1U << 1)
#define CPUID_7_0_ECX_VBMI (1U << 1) /* AVX-512 Vector Byte Manipulation Instrs */
#define CPUID_7_0_ECX_UMIP (1U << 2)
#define CPUID_7_0_ECX_PKU (1U << 3)
@ -812,6 +831,20 @@ typedef struct SegmentCache {
float64 _d_##n[(bits)/64]; \
}
typedef union {
uint8_t _b[16];
uint16_t _w[8];
uint32_t _l[4];
uint64_t _q[2];
} XMMReg;
typedef union {
uint8_t _b[32];
uint16_t _w[16];
uint32_t _l[8];
uint64_t _q[4];
} YMMReg;
typedef MMREG_UNION(ZMMReg, 512) ZMMReg;
typedef MMREG_UNION(MMXReg, 64) MMXReg;
@ -1047,7 +1080,11 @@ typedef struct CPUX86State {
ZMMReg xmm_t0;
MMXReg mmx_t0;
XMMReg ymmh_regs[CPU_NB_REGS];
uint64_t opmask_regs[NB_OPMASK_REGS];
YMMReg zmmh_regs[CPU_NB_REGS];
ZMMReg hi16_zmm_regs[CPU_NB_REGS];
/* sysenter registers */
uint32_t sysenter_cs;
@ -1172,11 +1209,15 @@ typedef struct CPUX86State {
int32_t interrupt_injected;
uint8_t soft_interrupt;
uint8_t has_error_code;
uint32_t ins_len;
uint32_t sipi_vector;
bool tsc_valid;
int64_t tsc_khz;
int64_t user_tsc_khz; /* for sanity check only */
void *kvm_xsave_buf;
#if defined(CONFIG_HVF)
HVFX86EmulatorState *hvf_emul;
#endif
uint64_t mcg_cap;
uint64_t mcg_ctl;

2
target/i386/hvf/Makefile.objs Normal file
View file

@ -0,0 +1,2 @@
obj-y += hvf.o
obj-y += x86.o x86_cpuid.o x86_decode.o x86_descr.o x86_emu.o x86_flags.o x86_mmu.o x86hvf.o x86_task.o

7
target/i386/hvf/README.md Normal file
View file

@ -0,0 +1,7 @@
# OS X Hypervisor.framework support in QEMU
These sources (and ../hvf-all.c) are adapted from Veertu Inc's vdhh (Veertu Desktop Hosted Hypervisor) (last known location: https://github.com/veertuinc/vdhh) with some minor changes, the most significant of which were:
1. Adapt to our current QEMU's `CPUState` structure and `address_space_rw` API; many struct members have been moved around (emulated x86 state, kvm_xsave_buf) due to historical differences + QEMU needing to handle more emulation targets.
2. Removal of `apic_page` and hyperv-related functionality.
3. More relaxed use of `qemu_mutex_lock_iothread`.

48
target/i386/hvf/hvf-i386.h Normal file
View file

@ -0,0 +1,48 @@
/*
* QEMU Hypervisor.framework (HVF) support
*
* Copyright 2017 Google Inc
*
* Adapted from target-i386/hax-i386.h:
* Copyright (c) 2011 Intel Corporation
* Written by:
* Jiang Yunhong<yunhong.jiang@intel.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 _HVF_I386_H
#define _HVF_I386_H
#include "sysemu/hvf.h"
#include "cpu.h"
#include "x86.h"
#define HVF_MAX_VCPU 0x10
#define MAX_VM_ID 0x40
#define MAX_VCPU_ID 0x40
extern struct hvf_state hvf_global;
struct hvf_vm {
int id;
struct hvf_vcpu_state *vcpus[HVF_MAX_VCPU];
};
struct hvf_state {
uint32_t version;
struct hvf_vm *vm;
uint64_t mem_quota;
};
#ifdef NEED_CPU_H
/* Functions exported to host specific mode */
/* Host specific functions */
int hvf_inject_interrupt(CPUArchState *env, int vector);
int hvf_vcpu_run(struct hvf_vcpu_state *vcpu);
#endif
#endif

959
target/i386/hvf/hvf.c Normal file
View file

@ -0,0 +1,959 @@
/* Copyright 2008 IBM Corporation
* 2008 Red Hat, Inc.
* Copyright 2011 Intel Corporation
* Copyright 2016 Veertu, Inc.
* Copyright 2017 The Android Open Source Project
*
* QEMU Hypervisor.framework support
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/error-report.h"
#include "sysemu/hvf.h"
#include "hvf-i386.h"
#include "vmcs.h"
#include "vmx.h"
#include "x86.h"
#include "x86_descr.h"
#include "x86_mmu.h"
#include "x86_decode.h"
#include "x86_emu.h"
#include "x86_task.h"
#include "x86hvf.h"
#include <Hypervisor/hv.h>
#include <Hypervisor/hv_vmx.h>
#include "exec/address-spaces.h"
#include "exec/exec-all.h"
#include "exec/ioport.h"
#include "hw/i386/apic_internal.h"
#include "hw/boards.h"
#include "qemu/main-loop.h"
#include "strings.h"
#include "sysemu/accel.h"
#include "sysemu/sysemu.h"
#include "target/i386/cpu.h"
pthread_rwlock_t mem_lock = PTHREAD_RWLOCK_INITIALIZER;
HVFState *hvf_state;
int hvf_disabled = 1;
static void assert_hvf_ok(hv_return_t ret)
{
if (ret == HV_SUCCESS) {
return;
}
switch (ret) {
case HV_ERROR:
error_report("Error: HV_ERROR\n");
break;
case HV_BUSY:
error_report("Error: HV_BUSY\n");
break;
case HV_BAD_ARGUMENT:
error_report("Error: HV_BAD_ARGUMENT\n");
break;
case HV_NO_RESOURCES:
error_report("Error: HV_NO_RESOURCES\n");
break;
case HV_NO_DEVICE:
error_report("Error: HV_NO_DEVICE\n");
break;
case HV_UNSUPPORTED:
error_report("Error: HV_UNSUPPORTED\n");
break;
default:
error_report("Unknown Error\n");
}
abort();
}
/* Memory slots */
hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t end)
{
hvf_slot *slot;
int x;
for (x = 0; x < hvf_state->num_slots; ++x) {
slot = &hvf_state->slots[x];
if (slot->size && start < (slot->start + slot->size) &&
end > slot->start) {
return slot;
}
}
return NULL;
}
struct mac_slot {
int present;
uint64_t size;
uint64_t gpa_start;
uint64_t gva;
};
struct mac_slot mac_slots[32];
#define ALIGN(x, y) (((x) + (y) - 1) & ~((y) - 1))
static int do_hvf_set_memory(hvf_slot *slot)
{
struct mac_slot *macslot;
hv_memory_flags_t flags;
hv_return_t ret;
macslot = &mac_slots[slot->slot_id];
if (macslot->present) {
if (macslot->size != slot->size) {
macslot->present = 0;
ret = hv_vm_unmap(macslot->gpa_start, macslot->size);
assert_hvf_ok(ret);
}
}
if (!slot->size) {
return 0;
}
flags = HV_MEMORY_READ | HV_MEMORY_WRITE | HV_MEMORY_EXEC;
macslot->present = 1;
macslot->gpa_start = slot->start;
macslot->size = slot->size;
ret = hv_vm_map((hv_uvaddr_t)slot->mem, slot->start, slot->size, flags);
assert_hvf_ok(ret);
return 0;
}
void hvf_set_phys_mem(MemoryRegionSection *section, bool add)
{
hvf_slot *mem;
MemoryRegion *area = section->mr;
if (!memory_region_is_ram(area)) {
return;
}
mem = hvf_find_overlap_slot(
section->offset_within_address_space,
section->offset_within_address_space + int128_get64(section->size));
if (mem && add) {
if (mem->size == int128_get64(section->size) &&
mem->start == section->offset_within_address_space &&
mem->mem == (memory_region_get_ram_ptr(area) +
section->offset_within_region)) {
return; /* Same region was attempted to register, go away. */
}
}
/* Region needs to be reset. set the size to 0 and remap it. */
if (mem) {
mem->size = 0;
if (do_hvf_set_memory(mem)) {
error_report("Failed to reset overlapping slot\n");
abort();
}
}
if (!add) {
return;
}
/* Now make a new slot. */
int x;
for (x = 0; x < hvf_state->num_slots; ++x) {
mem = &hvf_state->slots[x];
if (!mem->size) {
break;
}
}
if (x == hvf_state->num_slots) {
error_report("No free slots\n");
abort();
}
mem->size = int128_get64(section->size);
mem->mem = memory_region_get_ram_ptr(area) + section->offset_within_region;
mem->start = section->offset_within_address_space;
mem->region = area;
if (do_hvf_set_memory(mem)) {
error_report("Error registering new memory slot\n");
abort();
}
}
void vmx_update_tpr(CPUState *cpu)
{
/* TODO: need integrate APIC handling */
X86CPU *x86_cpu = X86_CPU(cpu);
int tpr = cpu_get_apic_tpr(x86_cpu->apic_state) << 4;
int irr = apic_get_highest_priority_irr(x86_cpu->apic_state);
wreg(cpu->hvf_fd, HV_X86_TPR, tpr);
if (irr == -1) {
wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, 0);
} else {
wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, (irr > tpr) ? tpr >> 4 :
irr >> 4);
}
}
void update_apic_tpr(CPUState *cpu)
{
X86CPU *x86_cpu = X86_CPU(cpu);
int tpr = rreg(cpu->hvf_fd, HV_X86_TPR) >> 4;
cpu_set_apic_tpr(x86_cpu->apic_state, tpr);
}
#define VECTORING_INFO_VECTOR_MASK 0xff
static void hvf_handle_interrupt(CPUState * cpu, int mask)
{
cpu->interrupt_request |= mask;
if (!qemu_cpu_is_self(cpu)) {
qemu_cpu_kick(cpu);
}
}
void hvf_handle_io(CPUArchState *env, uint16_t port, void *buffer,
int direction, int size, int count)
{
int i;
uint8_t *ptr = buffer;
for (i = 0; i < count; i++) {
address_space_rw(&address_space_io, port, MEMTXATTRS_UNSPECIFIED,
ptr, size,
direction);
ptr += size;
}
}
/* TODO: synchronize vcpu state */
static void do_hvf_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg)
{
CPUState *cpu_state = cpu;
if (cpu_state->vcpu_dirty == 0) {
hvf_get_registers(cpu_state);
}
cpu_state->vcpu_dirty = 1;
}
void hvf_cpu_synchronize_state(CPUState *cpu_state)
{
if (cpu_state->vcpu_dirty == 0) {
run_on_cpu(cpu_state, do_hvf_cpu_synchronize_state, RUN_ON_CPU_NULL);
}
}
static void do_hvf_cpu_synchronize_post_reset(CPUState *cpu, run_on_cpu_data arg)
{
CPUState *cpu_state = cpu;
hvf_put_registers(cpu_state);
cpu_state->vcpu_dirty = false;
}
void hvf_cpu_synchronize_post_reset(CPUState *cpu_state)
{
run_on_cpu(cpu_state, do_hvf_cpu_synchronize_post_reset, RUN_ON_CPU_NULL);
}
void _hvf_cpu_synchronize_post_init(CPUState *cpu, run_on_cpu_data arg)
{
CPUState *cpu_state = cpu;
hvf_put_registers(cpu_state);
cpu_state->vcpu_dirty = false;
}
void hvf_cpu_synchronize_post_init(CPUState *cpu_state)
{
run_on_cpu(cpu_state, _hvf_cpu_synchronize_post_init, RUN_ON_CPU_NULL);
}
static bool ept_emulation_fault(hvf_slot *slot, uint64_t gpa, uint64_t ept_qual)
{
int read, write;
/* EPT fault on an instruction fetch doesn't make sense here */
if (ept_qual & EPT_VIOLATION_INST_FETCH) {
return false;
}
/* EPT fault must be a read fault or a write fault */
read = ept_qual & EPT_VIOLATION_DATA_READ ? 1 : 0;
write = ept_qual & EPT_VIOLATION_DATA_WRITE ? 1 : 0;
if ((read | write) == 0) {
return false;
}
if (write && slot) {
if (slot->flags & HVF_SLOT_LOG) {
memory_region_set_dirty(slot->region, gpa - slot->start, 1);
hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
HV_MEMORY_READ | HV_MEMORY_WRITE);
}
}
/*
* The EPT violation must have been caused by accessing a
* guest-physical address that is a translation of a guest-linear
* address.
*/
if ((ept_qual & EPT_VIOLATION_GLA_VALID) == 0 ||
(ept_qual & EPT_VIOLATION_XLAT_VALID) == 0) {
return false;
}
return !slot;
}
static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on)
{
hvf_slot *slot;
slot = hvf_find_overlap_slot(
section->offset_within_address_space,
section->offset_within_address_space + int128_get64(section->size));
/* protect region against writes; begin tracking it */
if (on) {
slot->flags |= HVF_SLOT_LOG;
hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
HV_MEMORY_READ);
/* stop tracking region*/
} else {
slot->flags &= ~HVF_SLOT_LOG;
hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
HV_MEMORY_READ | HV_MEMORY_WRITE);
}
}
static void hvf_log_start(MemoryListener *listener,
MemoryRegionSection *section, int old, int new)
{
if (old != 0) {
return;
}
hvf_set_dirty_tracking(section, 1);
}
static void hvf_log_stop(MemoryListener *listener,
MemoryRegionSection *section, int old, int new)
{
if (new != 0) {
return;
}
hvf_set_dirty_tracking(section, 0);
}
static void hvf_log_sync(MemoryListener *listener,
MemoryRegionSection *section)
{
/*
* sync of dirty pages is handled elsewhere; just make sure we keep
* tracking the region.
*/
hvf_set_dirty_tracking(section, 1);
}
static void hvf_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
hvf_set_phys_mem(section, true);
}
static void hvf_region_del(MemoryListener *listener,
MemoryRegionSection *section)
{
hvf_set_phys_mem(section, false);
}
static MemoryListener hvf_memory_listener = {
.priority = 10,
.region_add = hvf_region_add,
.region_del = hvf_region_del,
.log_start = hvf_log_start,
.log_stop = hvf_log_stop,
.log_sync = hvf_log_sync,
};
void hvf_reset_vcpu(CPUState *cpu) {
/* TODO: this shouldn't be needed; there is already a call to
* cpu_synchronize_all_post_reset in vl.c
*/
wvmcs(cpu->hvf_fd, VMCS_ENTRY_CTLS, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER, 0);
macvm_set_cr0(cpu->hvf_fd, 0x60000010);
wvmcs(cpu->hvf_fd, VMCS_CR4_MASK, CR4_VMXE_MASK);
wvmcs(cpu->hvf_fd, VMCS_CR4_SHADOW, 0x0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_CR4, CR4_VMXE_MASK);
/* set VMCS guest state fields */
wvmcs(cpu->hvf_fd, VMCS_GUEST_CS_SELECTOR, 0xf000);
wvmcs(cpu->hvf_fd, VMCS_GUEST_CS_LIMIT, 0xffff);
wvmcs(cpu->hvf_fd, VMCS_GUEST_CS_ACCESS_RIGHTS, 0x9b);
wvmcs(cpu->hvf_fd, VMCS_GUEST_CS_BASE, 0xffff0000);
wvmcs(cpu->hvf_fd, VMCS_GUEST_DS_SELECTOR, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_DS_LIMIT, 0xffff);
wvmcs(cpu->hvf_fd, VMCS_GUEST_DS_ACCESS_RIGHTS, 0x93);
wvmcs(cpu->hvf_fd, VMCS_GUEST_DS_BASE, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_ES_SELECTOR, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_ES_LIMIT, 0xffff);
wvmcs(cpu->hvf_fd, VMCS_GUEST_ES_ACCESS_RIGHTS, 0x93);
wvmcs(cpu->hvf_fd, VMCS_GUEST_ES_BASE, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_FS_SELECTOR, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_FS_LIMIT, 0xffff);
wvmcs(cpu->hvf_fd, VMCS_GUEST_FS_ACCESS_RIGHTS, 0x93);
wvmcs(cpu->hvf_fd, VMCS_GUEST_FS_BASE, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_GS_SELECTOR, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_GS_LIMIT, 0xffff);
wvmcs(cpu->hvf_fd, VMCS_GUEST_GS_ACCESS_RIGHTS, 0x93);
wvmcs(cpu->hvf_fd, VMCS_GUEST_GS_BASE, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_SS_SELECTOR, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_SS_LIMIT, 0xffff);
wvmcs(cpu->hvf_fd, VMCS_GUEST_SS_ACCESS_RIGHTS, 0x93);
wvmcs(cpu->hvf_fd, VMCS_GUEST_SS_BASE, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_SELECTOR, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_LIMIT, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_ACCESS_RIGHTS, 0x10000);
wvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_BASE, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_TR_SELECTOR, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_TR_LIMIT, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_TR_ACCESS_RIGHTS, 0x83);
wvmcs(cpu->hvf_fd, VMCS_GUEST_TR_BASE, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_LIMIT, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_BASE, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_IDTR_LIMIT, 0);
wvmcs(cpu->hvf_fd, VMCS_GUEST_IDTR_BASE, 0);
/*wvmcs(cpu->hvf_fd, VMCS_GUEST_CR2, 0x0);*/
wvmcs(cpu->hvf_fd, VMCS_GUEST_CR3, 0x0);
wreg(cpu->hvf_fd, HV_X86_RIP, 0xfff0);
wreg(cpu->hvf_fd, HV_X86_RDX, 0x623);
wreg(cpu->hvf_fd, HV_X86_RFLAGS, 0x2);
wreg(cpu->hvf_fd, HV_X86_RSP, 0x0);
wreg(cpu->hvf_fd, HV_X86_RAX, 0x0);
wreg(cpu->hvf_fd, HV_X86_RBX, 0x0);
wreg(cpu->hvf_fd, HV_X86_RCX, 0x0);
wreg(cpu->hvf_fd, HV_X86_RSI, 0x0);
wreg(cpu->hvf_fd, HV_X86_RDI, 0x0);
wreg(cpu->hvf_fd, HV_X86_RBP, 0x0);
for (int i = 0; i < 8; i++) {
wreg(cpu->hvf_fd, HV_X86_R8 + i, 0x0);
}
hv_vm_sync_tsc(0);
cpu->halted = 0;
hv_vcpu_invalidate_tlb(cpu->hvf_fd);
hv_vcpu_flush(cpu->hvf_fd);
}
void hvf_vcpu_destroy(CPUState *cpu)
{
hv_return_t ret = hv_vcpu_destroy((hv_vcpuid_t)cpu->hvf_fd);
assert_hvf_ok(ret);
}
static void dummy_signal(int sig)
{
}
int hvf_init_vcpu(CPUState *cpu)
{
X86CPU *x86cpu = X86_CPU(cpu);
CPUX86State *env = &x86cpu->env;
int r;
/* init cpu signals */
sigset_t set;
struct sigaction sigact;
memset(&sigact, 0, sizeof(sigact));
sigact.sa_handler = dummy_signal;
sigaction(SIG_IPI, &sigact, NULL);
pthread_sigmask(SIG_BLOCK, NULL, &set);
sigdelset(&set, SIG_IPI);
init_emu();
init_decoder();
hvf_state->hvf_caps = g_new0(struct hvf_vcpu_caps, 1);
env->hvf_emul = g_new0(HVFX86EmulatorState, 1);
r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf_fd, HV_VCPU_DEFAULT);
cpu->vcpu_dirty = 1;
assert_hvf_ok(r);
if (hv_vmx_read_capability(HV_VMX_CAP_PINBASED,
&hvf_state->hvf_caps->vmx_cap_pinbased)) {
abort();
}
if (hv_vmx_read_capability(HV_VMX_CAP_PROCBASED,
&hvf_state->hvf_caps->vmx_cap_procbased)) {
abort();
}
if (hv_vmx_read_capability(HV_VMX_CAP_PROCBASED2,
&hvf_state->hvf_caps->vmx_cap_procbased2)) {
abort();
}
if (hv_vmx_read_capability(HV_VMX_CAP_ENTRY,
&hvf_state->hvf_caps->vmx_cap_entry)) {
abort();
}
/* set VMCS control fields */
wvmcs(cpu->hvf_fd, VMCS_PIN_BASED_CTLS,
cap2ctrl(hvf_state->hvf_caps->vmx_cap_pinbased,
VMCS_PIN_BASED_CTLS_EXTINT |
VMCS_PIN_BASED_CTLS_NMI |
VMCS_PIN_BASED_CTLS_VNMI));
wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS,
cap2ctrl(hvf_state->hvf_caps->vmx_cap_procbased,
VMCS_PRI_PROC_BASED_CTLS_HLT |
VMCS_PRI_PROC_BASED_CTLS_MWAIT |
VMCS_PRI_PROC_BASED_CTLS_TSC_OFFSET |
VMCS_PRI_PROC_BASED_CTLS_TPR_SHADOW) |
VMCS_PRI_PROC_BASED_CTLS_SEC_CONTROL);
wvmcs(cpu->hvf_fd, VMCS_SEC_PROC_BASED_CTLS,
cap2ctrl(hvf_state->hvf_caps->vmx_cap_procbased2,
VMCS_PRI_PROC_BASED2_CTLS_APIC_ACCESSES));
wvmcs(cpu->hvf_fd, VMCS_ENTRY_CTLS, cap2ctrl(hvf_state->hvf_caps->vmx_cap_entry,
0));
wvmcs(cpu->hvf_fd, VMCS_EXCEPTION_BITMAP, 0); /* Double fault */
wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, 0);
hvf_reset_vcpu(cpu);
x86cpu = X86_CPU(cpu);
x86cpu->env.kvm_xsave_buf = qemu_memalign(4096, 4096);
hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_STAR, 1);
hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_LSTAR, 1);
hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_CSTAR, 1);
hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_FMASK, 1);
hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_FSBASE, 1);
hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_GSBASE, 1);
hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_KERNELGSBASE, 1);
hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_TSC_AUX, 1);
/*hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_TSC, 1);*/
hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_CS, 1);
hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_EIP, 1);
hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_ESP, 1);
return 0;
}
void hvf_disable(int shouldDisable)
{
hvf_disabled = shouldDisable;
}
static void hvf_store_events(CPUState *cpu, uint32_t ins_len, uint64_t idtvec_info)
{
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
env->exception_injected = -1;
env->interrupt_injected = -1;
env->nmi_injected = false;
if (idtvec_info & VMCS_IDT_VEC_VALID) {
switch (idtvec_info & VMCS_IDT_VEC_TYPE) {
case VMCS_IDT_VEC_HWINTR:
case VMCS_IDT_VEC_SWINTR:
env->interrupt_injected = idtvec_info & VMCS_IDT_VEC_VECNUM;
break;
case VMCS_IDT_VEC_NMI:
env->nmi_injected = true;
break;
case VMCS_IDT_VEC_HWEXCEPTION:
case VMCS_IDT_VEC_SWEXCEPTION:
env->exception_injected = idtvec_info & VMCS_IDT_VEC_VECNUM;
break;
case VMCS_IDT_VEC_PRIV_SWEXCEPTION:
default:
abort();
}
if ((idtvec_info & VMCS_IDT_VEC_TYPE) == VMCS_IDT_VEC_SWEXCEPTION ||
(idtvec_info & VMCS_IDT_VEC_TYPE) == VMCS_IDT_VEC_SWINTR) {
env->ins_len = ins_len;
}
if (idtvec_info & VMCS_INTR_DEL_ERRCODE) {
env->has_error_code = true;
env->error_code = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_ERROR);
}
}
if ((rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY) &
VMCS_INTERRUPTIBILITY_NMI_BLOCKING)) {
env->hflags2 |= HF2_NMI_MASK;
} else {
env->hflags2 &= ~HF2_NMI_MASK;
}
if (rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY) &
(VMCS_INTERRUPTIBILITY_STI_BLOCKING |
VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)) {
env->hflags |= HF_INHIBIT_IRQ_MASK;
} else {
env->hflags &= ~HF_INHIBIT_IRQ_MASK;
}
}
int hvf_vcpu_exec(CPUState *cpu)
{
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
int ret = 0;
uint64_t rip = 0;
cpu->halted = 0;
if (hvf_process_events(cpu)) {
return EXCP_HLT;
}
do {
if (cpu->vcpu_dirty) {
hvf_put_registers(cpu);
cpu->vcpu_dirty = false;
}
if (hvf_inject_interrupts(cpu)) {
return EXCP_INTERRUPT;
}
vmx_update_tpr(cpu);
qemu_mutex_unlock_iothread();
if (!cpu_is_bsp(X86_CPU(cpu)) && cpu->halted) {
qemu_mutex_lock_iothread();
return EXCP_HLT;
}
hv_return_t r = hv_vcpu_run(cpu->hvf_fd);
assert_hvf_ok(r);
/* handle VMEXIT */
uint64_t exit_reason = rvmcs(cpu->hvf_fd, VMCS_EXIT_REASON);
uint64_t exit_qual = rvmcs(cpu->hvf_fd, VMCS_EXIT_QUALIFICATION);
uint32_t ins_len = (uint32_t)rvmcs(cpu->hvf_fd,
VMCS_EXIT_INSTRUCTION_LENGTH);
uint64_t idtvec_info = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_INFO);
hvf_store_events(cpu, ins_len, idtvec_info);
rip = rreg(cpu->hvf_fd, HV_X86_RIP);
RFLAGS(env) = rreg(cpu->hvf_fd, HV_X86_RFLAGS);
env->eflags = RFLAGS(env);
qemu_mutex_lock_iothread();
update_apic_tpr(cpu);
current_cpu = cpu;
ret = 0;
switch (exit_reason) {
case EXIT_REASON_HLT: {
macvm_set_rip(cpu, rip + ins_len);
if (!((cpu->interrupt_request & CPU_INTERRUPT_HARD) &&
(EFLAGS(env) & IF_MASK))
&& !(cpu->interrupt_request & CPU_INTERRUPT_NMI) &&
!(idtvec_info & VMCS_IDT_VEC_VALID)) {
cpu->halted = 1;
ret = EXCP_HLT;
}
ret = EXCP_INTERRUPT;
break;
}
case EXIT_REASON_MWAIT: {
ret = EXCP_INTERRUPT;
break;
}
/* Need to check if MMIO or unmmaped fault */
case EXIT_REASON_EPT_FAULT:
{
hvf_slot *slot;
uint64_t gpa = rvmcs(cpu->hvf_fd, VMCS_GUEST_PHYSICAL_ADDRESS);
if (((idtvec_info & VMCS_IDT_VEC_VALID) == 0) &&
((exit_qual & EXIT_QUAL_NMIUDTI) != 0)) {
vmx_set_nmi_blocking(cpu);
}
slot = hvf_find_overlap_slot(gpa, gpa);
/* mmio */
if (ept_emulation_fault(slot, gpa, exit_qual)) {
struct x86_decode decode;
load_regs(cpu);
env->hvf_emul->fetch_rip = rip;
decode_instruction(env, &decode);
exec_instruction(env, &decode);
store_regs(cpu);
break;
}
break;
}
case EXIT_REASON_INOUT:
{
uint32_t in = (exit_qual & 8) != 0;
uint32_t size = (exit_qual & 7) + 1;
uint32_t string = (exit_qual & 16) != 0;
uint32_t port = exit_qual >> 16;
/*uint32_t rep = (exit_qual & 0x20) != 0;*/
if (!string && in) {
uint64_t val = 0;
load_regs(cpu);
hvf_handle_io(env, port, &val, 0, size, 1);
if (size == 1) {
AL(env) = val;
} else if (size == 2) {
AX(env) = val;
} else if (size == 4) {
RAX(env) = (uint32_t)val;
} else {
RAX(env) = (uint64_t)val;
}
RIP(env) += ins_len;
store_regs(cpu);
break;
} else if (!string && !in) {
RAX(env) = rreg(cpu->hvf_fd, HV_X86_RAX);
hvf_handle_io(env, port, &RAX(env), 1, size, 1);
macvm_set_rip(cpu, rip + ins_len);
break;
}
struct x86_decode decode;
load_regs(cpu);
env->hvf_emul->fetch_rip = rip;
decode_instruction(env, &decode);
assert(ins_len == decode.len);
exec_instruction(env, &decode);
store_regs(cpu);
break;
}
case EXIT_REASON_CPUID: {
uint32_t rax = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RAX);
uint32_t rbx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RBX);
uint32_t rcx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RCX);
uint32_t rdx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RDX);
cpu_x86_cpuid(env, rax, rcx, &rax, &rbx, &rcx, &rdx);
wreg(cpu->hvf_fd, HV_X86_RAX, rax);
wreg(cpu->hvf_fd, HV_X86_RBX, rbx);
wreg(cpu->hvf_fd, HV_X86_RCX, rcx);
wreg(cpu->hvf_fd, HV_X86_RDX, rdx);
macvm_set_rip(cpu, rip + ins_len);
break;
}
case EXIT_REASON_XSETBV: {
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
uint32_t eax = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RAX);
uint32_t ecx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RCX);
uint32_t edx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RDX);
if (ecx) {
macvm_set_rip(cpu, rip + ins_len);
break;
}
env->xcr0 = ((uint64_t)edx << 32) | eax;
wreg(cpu->hvf_fd, HV_X86_XCR0, env->xcr0 | 1);
macvm_set_rip(cpu, rip + ins_len);
break;
}
case EXIT_REASON_INTR_WINDOW:
vmx_clear_int_window_exiting(cpu);
ret = EXCP_INTERRUPT;
break;
case EXIT_REASON_NMI_WINDOW:
vmx_clear_nmi_window_exiting(cpu);
ret = EXCP_INTERRUPT;
break;
case EXIT_REASON_EXT_INTR:
/* force exit and allow io handling */
ret = EXCP_INTERRUPT;
break;
case EXIT_REASON_RDMSR:
case EXIT_REASON_WRMSR:
{
load_regs(cpu);
if (exit_reason == EXIT_REASON_RDMSR) {
simulate_rdmsr(cpu);
} else {
simulate_wrmsr(cpu);
}
RIP(env) += rvmcs(cpu->hvf_fd, VMCS_EXIT_INSTRUCTION_LENGTH);
store_regs(cpu);
break;
}
case EXIT_REASON_CR_ACCESS: {
int cr;
int reg;
load_regs(cpu);
cr = exit_qual & 15;
reg = (exit_qual >> 8) & 15;
switch (cr) {
case 0x0: {
macvm_set_cr0(cpu->hvf_fd, RRX(env, reg));
break;
}
case 4: {
macvm_set_cr4(cpu->hvf_fd, RRX(env, reg));
break;
}
case 8: {
X86CPU *x86_cpu = X86_CPU(cpu);
if (exit_qual & 0x10) {
RRX(env, reg) = cpu_get_apic_tpr(x86_cpu->apic_state);
} else {
int tpr = RRX(env, reg);
cpu_set_apic_tpr(x86_cpu->apic_state, tpr);
ret = EXCP_INTERRUPT;
}
break;
}
default:
error_report("Unrecognized CR %d\n", cr);
abort();
}
RIP(env) += ins_len;
store_regs(cpu);
break;
}
case EXIT_REASON_APIC_ACCESS: { /* TODO */
struct x86_decode decode;
load_regs(cpu);
env->hvf_emul->fetch_rip = rip;
decode_instruction(env, &decode);
exec_instruction(env, &decode);
store_regs(cpu);
break;
}
case EXIT_REASON_TPR: {
ret = 1;
break;
}
case EXIT_REASON_TASK_SWITCH: {
uint64_t vinfo = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_INFO);
x68_segment_selector sel = {.sel = exit_qual & 0xffff};
vmx_handle_task_switch(cpu, sel, (exit_qual >> 30) & 0x3,
vinfo & VMCS_INTR_VALID, vinfo & VECTORING_INFO_VECTOR_MASK, vinfo
& VMCS_INTR_T_MASK);
break;
}
case EXIT_REASON_TRIPLE_FAULT: {
qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET);
ret = EXCP_INTERRUPT;
break;
}
case EXIT_REASON_RDPMC:
wreg(cpu->hvf_fd, HV_X86_RAX, 0);
wreg(cpu->hvf_fd, HV_X86_RDX, 0);
macvm_set_rip(cpu, rip + ins_len);
break;
case VMX_REASON_VMCALL:
env->exception_injected = EXCP0D_GPF;
env->has_error_code = true;
env->error_code = 0;
break;
default:
error_report("%llx: unhandled exit %llx\n", rip, exit_reason);
}
} while (ret == 0);
return ret;
}
static bool hvf_allowed;
static int hvf_accel_init(MachineState *ms)
{
int x;
hv_return_t ret;
HVFState *s;
hvf_disable(0);
ret = hv_vm_create(HV_VM_DEFAULT);
assert_hvf_ok(ret);
s = g_new0(HVFState, 1);
s->num_slots = 32;
for (x = 0; x < s->num_slots; ++x) {
s->slots[x].size = 0;
s->slots[x].slot_id = x;
}
hvf_state = s;
cpu_interrupt_handler = hvf_handle_interrupt;
memory_listener_register(&hvf_memory_listener, &address_space_memory);
return 0;
}
static void hvf_accel_class_init(ObjectClass *oc, void *data)
{
AccelClass *ac = ACCEL_CLASS(oc);
ac->name = "HVF";
ac->init_machine = hvf_accel_init;
ac->allowed = &hvf_allowed;
}
static const TypeInfo hvf_accel_type = {
.name = TYPE_HVF_ACCEL,
.parent = TYPE_ACCEL,
.class_init = hvf_accel_class_init,
};
static void hvf_type_init(void)
{
type_register_static(&hvf_accel_type);
}
type_init(hvf_type_init);

45
target/i386/hvf/panic.h Normal file
View file

@ -0,0 +1,45 @@
/*
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Google Inc,
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#ifndef HVF_PANIC_H
#define HVF_PANIC_H
#define VM_PANIC(x) {\
printf("%s\n", x); \
abort(); \
}
#define VM_PANIC_ON(x) {\
if (x) { \
printf("%s\n", #x); \
abort(); \
} \
}
#define VM_PANIC_EX(...) {\
printf(__VA_ARGS__); \
abort(); \
}
#define VM_PANIC_ON_EX(x, ...) {\
if (x) { \
printf(__VA_ARGS__); \
abort(); \
} \
}
#endif

374
target/i386/hvf/vmcs.h Normal file
View file

@ -0,0 +1,374 @@
/*-
* Copyright (c) 2011 NetApp, Inc.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY NETAPP, INC ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL NETAPP, INC OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* $FreeBSD$
*/
#ifndef _VMCS_H_
#define _VMCS_H_
#include <Hypervisor/hv.h>
#include <Hypervisor/hv_vmx.h>
#define VMCS_INITIAL 0xffffffffffffffff
#define VMCS_IDENT(encoding) ((encoding) | 0x80000000)
/*
* VMCS field encodings from Appendix H, Intel Architecture Manual Vol3B.
*/
#define VMCS_INVALID_ENCODING 0xffffffff
/* 16-bit control fields */
#define VMCS_VPID 0x00000000
#define VMCS_PIR_VECTOR 0x00000002
/* 16-bit guest-state fields */
#define VMCS_GUEST_ES_SELECTOR 0x00000800
#define VMCS_GUEST_CS_SELECTOR 0x00000802
#define VMCS_GUEST_SS_SELECTOR 0x00000804
#define VMCS_GUEST_DS_SELECTOR 0x00000806
#define VMCS_GUEST_FS_SELECTOR 0x00000808
#define VMCS_GUEST_GS_SELECTOR 0x0000080A
#define VMCS_GUEST_LDTR_SELECTOR 0x0000080C
#define VMCS_GUEST_TR_SELECTOR 0x0000080E
#define VMCS_GUEST_INTR_STATUS 0x00000810
/* 16-bit host-state fields */
#define VMCS_HOST_ES_SELECTOR 0x00000C00
#define VMCS_HOST_CS_SELECTOR 0x00000C02
#define VMCS_HOST_SS_SELECTOR 0x00000C04
#define VMCS_HOST_DS_SELECTOR 0x00000C06
#define VMCS_HOST_FS_SELECTOR 0x00000C08
#define VMCS_HOST_GS_SELECTOR 0x00000C0A
#define VMCS_HOST_TR_SELECTOR 0x00000C0C
/* 64-bit control fields */
#define VMCS_IO_BITMAP_A 0x00002000
#define VMCS_IO_BITMAP_B 0x00002002
#define VMCS_MSR_BITMAP 0x00002004
#define VMCS_EXIT_MSR_STORE 0x00002006
#define VMCS_EXIT_MSR_LOAD 0x00002008
#define VMCS_ENTRY_MSR_LOAD 0x0000200A
#define VMCS_EXECUTIVE_VMCS 0x0000200C
#define VMCS_TSC_OFFSET 0x00002010
#define VMCS_VIRTUAL_APIC 0x00002012
#define VMCS_APIC_ACCESS 0x00002014
#define VMCS_PIR_DESC 0x00002016
#define VMCS_EPTP 0x0000201A
#define VMCS_EOI_EXIT0 0x0000201C
#define VMCS_EOI_EXIT1 0x0000201E
#define VMCS_EOI_EXIT2 0x00002020
#define VMCS_EOI_EXIT3 0x00002022
#define VMCS_EOI_EXIT(vector) (VMCS_EOI_EXIT0 + ((vector) / 64) * 2)
/* 64-bit read-only fields */
#define VMCS_GUEST_PHYSICAL_ADDRESS 0x00002400
/* 64-bit guest-state fields */
#define VMCS_LINK_POINTER 0x00002800
#define VMCS_GUEST_IA32_DEBUGCTL 0x00002802
#define VMCS_GUEST_IA32_PAT 0x00002804
#define VMCS_GUEST_IA32_EFER 0x00002806
#define VMCS_GUEST_IA32_PERF_GLOBAL_CTRL 0x00002808
#define VMCS_GUEST_PDPTE0 0x0000280A
#define VMCS_GUEST_PDPTE1 0x0000280C
#define VMCS_GUEST_PDPTE2 0x0000280E
#define VMCS_GUEST_PDPTE3 0x00002810
/* 64-bit host-state fields */
#define VMCS_HOST_IA32_PAT 0x00002C00
#define VMCS_HOST_IA32_EFER 0x00002C02
#define VMCS_HOST_IA32_PERF_GLOBAL_CTRL 0x00002C04
/* 32-bit control fields */
#define VMCS_PIN_BASED_CTLS 0x00004000
#define VMCS_PRI_PROC_BASED_CTLS 0x00004002
#define VMCS_EXCEPTION_BITMAP 0x00004004
#define VMCS_PF_ERROR_MASK 0x00004006
#define VMCS_PF_ERROR_MATCH 0x00004008
#define VMCS_CR3_TARGET_COUNT 0x0000400A
#define VMCS_EXIT_CTLS 0x0000400C
#define VMCS_EXIT_MSR_STORE_COUNT 0x0000400E
#define VMCS_EXIT_MSR_LOAD_COUNT 0x00004010
#define VMCS_ENTRY_CTLS 0x00004012
#define VMCS_ENTRY_MSR_LOAD_COUNT 0x00004014
#define VMCS_ENTRY_INTR_INFO 0x00004016
#define VMCS_ENTRY_EXCEPTION_ERROR 0x00004018
#define VMCS_ENTRY_INST_LENGTH 0x0000401A
#define VMCS_TPR_THRESHOLD 0x0000401C
#define VMCS_SEC_PROC_BASED_CTLS 0x0000401E
#define VMCS_PLE_GAP 0x00004020
#define VMCS_PLE_WINDOW 0x00004022
/* 32-bit read-only data fields */
#define VMCS_INSTRUCTION_ERROR 0x00004400
#define VMCS_EXIT_REASON 0x00004402
#define VMCS_EXIT_INTR_INFO 0x00004404
#define VMCS_EXIT_INTR_ERRCODE 0x00004406
#define VMCS_IDT_VECTORING_INFO 0x00004408
#define VMCS_IDT_VECTORING_ERROR 0x0000440A
#define VMCS_EXIT_INSTRUCTION_LENGTH 0x0000440C
#define VMCS_EXIT_INSTRUCTION_INFO 0x0000440E
/* 32-bit guest-state fields */
#define VMCS_GUEST_ES_LIMIT 0x00004800
#define VMCS_GUEST_CS_LIMIT 0x00004802
#define VMCS_GUEST_SS_LIMIT 0x00004804
#define VMCS_GUEST_DS_LIMIT 0x00004806
#define VMCS_GUEST_FS_LIMIT 0x00004808
#define VMCS_GUEST_GS_LIMIT 0x0000480A
#define VMCS_GUEST_LDTR_LIMIT 0x0000480C
#define VMCS_GUEST_TR_LIMIT 0x0000480E
#define VMCS_GUEST_GDTR_LIMIT 0x00004810
#define VMCS_GUEST_IDTR_LIMIT 0x00004812
#define VMCS_GUEST_ES_ACCESS_RIGHTS 0x00004814
#define VMCS_GUEST_CS_ACCESS_RIGHTS 0x00004816
#define VMCS_GUEST_SS_ACCESS_RIGHTS 0x00004818
#define VMCS_GUEST_DS_ACCESS_RIGHTS 0x0000481A
#define VMCS_GUEST_FS_ACCESS_RIGHTS 0x0000481C
#define VMCS_GUEST_GS_ACCESS_RIGHTS 0x0000481E
#define VMCS_GUEST_LDTR_ACCESS_RIGHTS 0x00004820
#define VMCS_GUEST_TR_ACCESS_RIGHTS 0x00004822
#define VMCS_GUEST_INTERRUPTIBILITY 0x00004824
#define VMCS_GUEST_ACTIVITY 0x00004826
#define VMCS_GUEST_SMBASE 0x00004828
#define VMCS_GUEST_IA32_SYSENTER_CS 0x0000482A
#define VMCS_PREEMPTION_TIMER_VALUE 0x0000482E
/* 32-bit host state fields */
#define VMCS_HOST_IA32_SYSENTER_CS 0x00004C00
/* Natural Width control fields */
#define VMCS_CR0_MASK 0x00006000
#define VMCS_CR4_MASK 0x00006002
#define VMCS_CR0_SHADOW 0x00006004
#define VMCS_CR4_SHADOW 0x00006006
#define VMCS_CR3_TARGET0 0x00006008
#define VMCS_CR3_TARGET1 0x0000600A
#define VMCS_CR3_TARGET2 0x0000600C
#define VMCS_CR3_TARGET3 0x0000600E
/* Natural Width read-only fields */
#define VMCS_EXIT_QUALIFICATION 0x00006400
#define VMCS_IO_RCX 0x00006402
#define VMCS_IO_RSI 0x00006404
#define VMCS_IO_RDI 0x00006406
#define VMCS_IO_RIP 0x00006408
#define VMCS_GUEST_LINEAR_ADDRESS 0x0000640A
/* Natural Width guest-state fields */
#define VMCS_GUEST_CR0 0x00006800
#define VMCS_GUEST_CR3 0x00006802
#define VMCS_GUEST_CR4 0x00006804
#define VMCS_GUEST_ES_BASE 0x00006806
#define VMCS_GUEST_CS_BASE 0x00006808
#define VMCS_GUEST_SS_BASE 0x0000680A
#define VMCS_GUEST_DS_BASE 0x0000680C
#define VMCS_GUEST_FS_BASE 0x0000680E
#define VMCS_GUEST_GS_BASE 0x00006810
#define VMCS_GUEST_LDTR_BASE 0x00006812
#define VMCS_GUEST_TR_BASE 0x00006814
#define VMCS_GUEST_GDTR_BASE 0x00006816
#define VMCS_GUEST_IDTR_BASE 0x00006818
#define VMCS_GUEST_DR7 0x0000681A
#define VMCS_GUEST_RSP 0x0000681C
#define VMCS_GUEST_RIP 0x0000681E
#define VMCS_GUEST_RFLAGS 0x00006820
#define VMCS_GUEST_PENDING_DBG_EXCEPTIONS 0x00006822
#define VMCS_GUEST_IA32_SYSENTER_ESP 0x00006824
#define VMCS_GUEST_IA32_SYSENTER_EIP 0x00006826
/* Natural Width host-state fields */
#define VMCS_HOST_CR0 0x00006C00
#define VMCS_HOST_CR3 0x00006C02
#define VMCS_HOST_CR4 0x00006C04
#define VMCS_HOST_FS_BASE 0x00006C06
#define VMCS_HOST_GS_BASE 0x00006C08
#define VMCS_HOST_TR_BASE 0x00006C0A
#define VMCS_HOST_GDTR_BASE 0x00006C0C
#define VMCS_HOST_IDTR_BASE 0x00006C0E
#define VMCS_HOST_IA32_SYSENTER_ESP 0x00006C10
#define VMCS_HOST_IA32_SYSENTER_EIP 0x00006C12
#define VMCS_HOST_RSP 0x00006C14
#define VMCS_HOST_RIP 0x00006c16
/*
* VM instruction error numbers
*/
#define VMRESUME_WITH_NON_LAUNCHED_VMCS 5
/*
* VMCS exit reasons
*/
#define EXIT_REASON_EXCEPTION 0
#define EXIT_REASON_EXT_INTR 1
#define EXIT_REASON_TRIPLE_FAULT 2
#define EXIT_REASON_INIT 3
#define EXIT_REASON_SIPI 4
#define EXIT_REASON_IO_SMI 5
#define EXIT_REASON_SMI 6
#define EXIT_REASON_INTR_WINDOW 7
#define EXIT_REASON_NMI_WINDOW 8
#define EXIT_REASON_TASK_SWITCH 9
#define EXIT_REASON_CPUID 10
#define EXIT_REASON_GETSEC 11
#define EXIT_REASON_HLT 12
#define EXIT_REASON_INVD 13
#define EXIT_REASON_INVLPG 14
#define EXIT_REASON_RDPMC 15
#define EXIT_REASON_RDTSC 16
#define EXIT_REASON_RSM 17
#define EXIT_REASON_VMCALL 18
#define EXIT_REASON_VMCLEAR 19
#define EXIT_REASON_VMLAUNCH 20
#define EXIT_REASON_VMPTRLD 21
#define EXIT_REASON_VMPTRST 22
#define EXIT_REASON_VMREAD 23
#define EXIT_REASON_VMRESUME 24
#define EXIT_REASON_VMWRITE 25
#define EXIT_REASON_VMXOFF 26
#define EXIT_REASON_VMXON 27
#define EXIT_REASON_CR_ACCESS 28
#define EXIT_REASON_DR_ACCESS 29
#define EXIT_REASON_INOUT 30
#define EXIT_REASON_RDMSR 31
#define EXIT_REASON_WRMSR 32
#define EXIT_REASON_INVAL_VMCS 33
#define EXIT_REASON_INVAL_MSR 34
#define EXIT_REASON_MWAIT 36
#define EXIT_REASON_MTF 37
#define EXIT_REASON_MONITOR 39
#define EXIT_REASON_PAUSE 40
#define EXIT_REASON_MCE_DURING_ENTR 41
#define EXIT_REASON_TPR 43
#define EXIT_REASON_APIC_ACCESS 44
#define EXIT_REASON_VIRTUALIZED_EOI 45
#define EXIT_REASON_GDTR_IDTR 46
#define EXIT_REASON_LDTR_TR 47
#define EXIT_REASON_EPT_FAULT 48
#define EXIT_REASON_EPT_MISCONFIG 49
#define EXIT_REASON_INVEPT 50
#define EXIT_REASON_RDTSCP 51
#define EXIT_REASON_VMX_PREEMPT 52
#define EXIT_REASON_INVVPID 53
#define EXIT_REASON_WBINVD 54
#define EXIT_REASON_XSETBV 55
#define EXIT_REASON_APIC_WRITE 56
/*
* NMI unblocking due to IRET.
*
* Applies to VM-exits due to hardware exception or EPT fault.
*/
#define EXIT_QUAL_NMIUDTI (1 << 12)
/*
* VMCS interrupt information fields
*/
#define VMCS_INTR_VALID (1U << 31)
#define VMCS_INTR_T_MASK 0x700 /* Interruption-info type */
#define VMCS_INTR_T_HWINTR (0 << 8)
#define VMCS_INTR_T_NMI (2 << 8)
#define VMCS_INTR_T_HWEXCEPTION (3 << 8)
#define VMCS_INTR_T_SWINTR (4 << 8)
#define VMCS_INTR_T_PRIV_SWEXCEPTION (5 << 8)
#define VMCS_INTR_T_SWEXCEPTION (6 << 8)
#define VMCS_INTR_DEL_ERRCODE (1 << 11)
/*
* VMCS IDT-Vectoring information fields
*/
#define VMCS_IDT_VEC_VECNUM 0xFF
#define VMCS_IDT_VEC_VALID (1U << 31)
#define VMCS_IDT_VEC_TYPE 0x700
#define VMCS_IDT_VEC_ERRCODE_VALID (1U << 11)
#define VMCS_IDT_VEC_HWINTR (0 << 8)
#define VMCS_IDT_VEC_NMI (2 << 8)
#define VMCS_IDT_VEC_HWEXCEPTION (3 << 8)
#define VMCS_IDT_VEC_SWINTR (4 << 8)
#define VMCS_IDT_VEC_PRIV_SWEXCEPTION (5 << 8)
#define VMCS_IDT_VEC_SWEXCEPTION (6 << 8)
/*
* VMCS Guest interruptibility field
*/
#define VMCS_INTERRUPTIBILITY_STI_BLOCKING (1 << 0)
#define VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING (1 << 1)
#define VMCS_INTERRUPTIBILITY_SMI_BLOCKING (1 << 2)
#define VMCS_INTERRUPTIBILITY_NMI_BLOCKING (1 << 3)
/*
* Exit qualification for EXIT_REASON_INVAL_VMCS
*/
#define EXIT_QUAL_NMI_WHILE_STI_BLOCKING 3
/*
* Exit qualification for EPT violation
*/
#define EPT_VIOLATION_DATA_READ (1UL << 0)
#define EPT_VIOLATION_DATA_WRITE (1UL << 1)
#define EPT_VIOLATION_INST_FETCH (1UL << 2)
#define EPT_VIOLATION_GPA_READABLE (1UL << 3)
#define EPT_VIOLATION_GPA_WRITEABLE (1UL << 4)
#define EPT_VIOLATION_GPA_EXECUTABLE (1UL << 5)
#define EPT_VIOLATION_GLA_VALID (1UL << 7)
#define EPT_VIOLATION_XLAT_VALID (1UL << 8)
/*
* Exit qualification for APIC-access VM exit
*/
#define APIC_ACCESS_OFFSET(qual) ((qual) & 0xFFF)
#define APIC_ACCESS_TYPE(qual) (((qual) >> 12) & 0xF)
/*
* Exit qualification for APIC-write VM exit
*/
#define APIC_WRITE_OFFSET(qual) ((qual) & 0xFFF)
#define VMCS_PIN_BASED_CTLS_EXTINT (1 << 0)
#define VMCS_PIN_BASED_CTLS_NMI (1 << 3)
#define VMCS_PIN_BASED_CTLS_VNMI (1 << 5)
#define VMCS_PRI_PROC_BASED_CTLS_INT_WINDOW_EXITING (1 << 2)
#define VMCS_PRI_PROC_BASED_CTLS_TSC_OFFSET (1 << 3)
#define VMCS_PRI_PROC_BASED_CTLS_HLT (1 << 7)
#define VMCS_PRI_PROC_BASED_CTLS_MWAIT (1 << 10)
#define VMCS_PRI_PROC_BASED_CTLS_TSC (1 << 12)
#define VMCS_PRI_PROC_BASED_CTLS_CR8_LOAD (1 << 19)
#define VMCS_PRI_PROC_BASED_CTLS_CR8_STORE (1 << 20)
#define VMCS_PRI_PROC_BASED_CTLS_TPR_SHADOW (1 << 21)
#define VMCS_PRI_PROC_BASED_CTLS_NMI_WINDOW_EXITING (1 << 22)
#define VMCS_PRI_PROC_BASED_CTLS_SEC_CONTROL (1 << 31)
#define VMCS_PRI_PROC_BASED2_CTLS_APIC_ACCESSES (1 << 0)
#define VMCS_PRI_PROC_BASED2_CTLS_X2APIC (1 << 4)
enum task_switch_reason {
TSR_CALL,
TSR_IRET,
TSR_JMP,
TSR_IDT_GATE, /* task gate in IDT */
};
#endif

222
target/i386/hvf/vmx.h Normal file
View file

@ -0,0 +1,222 @@
/*
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Google Inc,
* Based on Veertu vddh/vmm/vmx.h
*
* Interfaces to Hypervisor.framework to read/write X86 registers and VMCS.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#ifndef VMX_H
#define VMX_H
#include <stdint.h>
#include <Hypervisor/hv.h>
#include <Hypervisor/hv_vmx.h>
#include "vmcs.h"
#include "cpu.h"
#include "x86.h"
#include "exec/address-spaces.h"
static inline uint64_t rreg(hv_vcpuid_t vcpu, hv_x86_reg_t reg)
{
uint64_t v;
if (hv_vcpu_read_register(vcpu, reg, &v)) {
abort();
}
return v;
}
/* write GPR */
static inline void wreg(hv_vcpuid_t vcpu, hv_x86_reg_t reg, uint64_t v)
{
if (hv_vcpu_write_register(vcpu, reg, v)) {
abort();
}
}
/* read VMCS field */
static inline uint64_t rvmcs(hv_vcpuid_t vcpu, uint32_t field)
{
uint64_t v;
hv_vmx_vcpu_read_vmcs(vcpu, field, &v);
return v;
}
/* write VMCS field */
static inline void wvmcs(hv_vcpuid_t vcpu, uint32_t field, uint64_t v)
{
hv_vmx_vcpu_write_vmcs(vcpu, field, v);
}
/* desired control word constrained by hardware/hypervisor capabilities */
static inline uint64_t cap2ctrl(uint64_t cap, uint64_t ctrl)
{
return (ctrl | (cap & 0xffffffff)) & (cap >> 32);
}
#define VM_ENTRY_GUEST_LMA (1LL << 9)
#define AR_TYPE_ACCESSES_MASK 1
#define AR_TYPE_READABLE_MASK (1 << 1)
#define AR_TYPE_WRITEABLE_MASK (1 << 2)
#define AR_TYPE_CODE_MASK (1 << 3)
#define AR_TYPE_MASK 0x0f
#define AR_TYPE_BUSY_64_TSS 11
#define AR_TYPE_BUSY_32_TSS 11
#define AR_TYPE_BUSY_16_TSS 3
#define AR_TYPE_LDT 2
static void enter_long_mode(hv_vcpuid_t vcpu, uint64_t cr0, uint64_t efer)
{
uint64_t entry_ctls;
efer |= MSR_EFER_LMA;
wvmcs(vcpu, VMCS_GUEST_IA32_EFER, efer);
entry_ctls = rvmcs(vcpu, VMCS_ENTRY_CTLS);
wvmcs(vcpu, VMCS_ENTRY_CTLS, rvmcs(vcpu, VMCS_ENTRY_CTLS) |
VM_ENTRY_GUEST_LMA);
uint64_t guest_tr_ar = rvmcs(vcpu, VMCS_GUEST_TR_ACCESS_RIGHTS);
if ((efer & MSR_EFER_LME) &&
(guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) {
wvmcs(vcpu, VMCS_GUEST_TR_ACCESS_RIGHTS,
(guest_tr_ar & ~AR_TYPE_MASK) | AR_TYPE_BUSY_64_TSS);
}
}
static void exit_long_mode(hv_vcpuid_t vcpu, uint64_t cr0, uint64_t efer)
{
uint64_t entry_ctls;
entry_ctls = rvmcs(vcpu, VMCS_ENTRY_CTLS);
wvmcs(vcpu, VMCS_ENTRY_CTLS, entry_ctls & ~VM_ENTRY_GUEST_LMA);
efer &= ~MSR_EFER_LMA;
wvmcs(vcpu, VMCS_GUEST_IA32_EFER, efer);
}
static inline void macvm_set_cr0(hv_vcpuid_t vcpu, uint64_t cr0)
{
int i;
uint64_t pdpte[4] = {0, 0, 0, 0};
uint64_t efer = rvmcs(vcpu, VMCS_GUEST_IA32_EFER);
uint64_t old_cr0 = rvmcs(vcpu, VMCS_GUEST_CR0);
if ((cr0 & CR0_PG) && (rvmcs(vcpu, VMCS_GUEST_CR4) & CR4_PAE) &&
!(efer & MSR_EFER_LME)) {
address_space_rw(&address_space_memory,
rvmcs(vcpu, VMCS_GUEST_CR3) & ~0x1f,
MEMTXATTRS_UNSPECIFIED,
(uint8_t *)pdpte, 32, 0);
}
for (i = 0; i < 4; i++) {
wvmcs(vcpu, VMCS_GUEST_PDPTE0 + i * 2, pdpte[i]);
}
wvmcs(vcpu, VMCS_CR0_MASK, CR0_CD | CR0_NE | CR0_PG);
wvmcs(vcpu, VMCS_CR0_SHADOW, cr0);
cr0 &= ~CR0_CD;
wvmcs(vcpu, VMCS_GUEST_CR0, cr0 | CR0_NE | CR0_ET);
if (efer & MSR_EFER_LME) {
if (!(old_cr0 & CR0_PG) && (cr0 & CR0_PG)) {
enter_long_mode(vcpu, cr0, efer);
}
if (/*(old_cr0 & CR0_PG) &&*/ !(cr0 & CR0_PG)) {
exit_long_mode(vcpu, cr0, efer);
}
}
hv_vcpu_invalidate_tlb(vcpu);
hv_vcpu_flush(vcpu);
}
static inline void macvm_set_cr4(hv_vcpuid_t vcpu, uint64_t cr4)
{
uint64_t guest_cr4 = cr4 | CR4_VMXE;
wvmcs(vcpu, VMCS_GUEST_CR4, guest_cr4);
wvmcs(vcpu, VMCS_CR4_SHADOW, cr4);
hv_vcpu_invalidate_tlb(vcpu);
hv_vcpu_flush(vcpu);
}
static inline void macvm_set_rip(CPUState *cpu, uint64_t rip)
{
uint64_t val;
/* BUG, should take considering overlap.. */
wreg(cpu->hvf_fd, HV_X86_RIP, rip);
/* after moving forward in rip, we need to clean INTERRUPTABILITY */
val = rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY);
if (val & (VMCS_INTERRUPTIBILITY_STI_BLOCKING |
VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)) {
wvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY,
val & ~(VMCS_INTERRUPTIBILITY_STI_BLOCKING |
VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING));
}
}
static inline void vmx_clear_nmi_blocking(CPUState *cpu)
{
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
env->hflags2 &= ~HF2_NMI_MASK;
uint32_t gi = (uint32_t) rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY);
gi &= ~VMCS_INTERRUPTIBILITY_NMI_BLOCKING;
wvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY, gi);
}
static inline void vmx_set_nmi_blocking(CPUState *cpu)
{
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
env->hflags2 |= HF2_NMI_MASK;
uint32_t gi = (uint32_t)rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY);
gi |= VMCS_INTERRUPTIBILITY_NMI_BLOCKING;
wvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY, gi);
}
static inline void vmx_set_nmi_window_exiting(CPUState *cpu)
{
uint64_t val;
val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS);
wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val |
VMCS_PRI_PROC_BASED_CTLS_NMI_WINDOW_EXITING);
}
static inline void vmx_clear_nmi_window_exiting(CPUState *cpu)
{
uint64_t val;
val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS);
wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val &
~VMCS_PRI_PROC_BASED_CTLS_NMI_WINDOW_EXITING);
}
#endif

186
target/i386/hvf/x86.c Normal file
View file

@ -0,0 +1,186 @@
/*
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Google Inc,
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "cpu.h"
#include "qemu-common.h"
#include "x86_decode.h"
#include "x86_emu.h"
#include "vmcs.h"
#include "vmx.h"
#include "x86_mmu.h"
#include "x86_descr.h"
/* static uint32_t x86_segment_access_rights(struct x86_segment_descriptor *var)
{
uint32_t ar;
if (!var->p) {
ar = 1 << 16;
return ar;
}
ar = var->type & 15;
ar |= (var->s & 1) << 4;
ar |= (var->dpl & 3) << 5;
ar |= (var->p & 1) << 7;
ar |= (var->avl & 1) << 12;
ar |= (var->l & 1) << 13;
ar |= (var->db & 1) << 14;
ar |= (var->g & 1) << 15;
return ar;
}*/
bool x86_read_segment_descriptor(struct CPUState *cpu,
struct x86_segment_descriptor *desc,
x68_segment_selector sel)
{
target_ulong base;
uint32_t limit;
memset(desc, 0, sizeof(*desc));
/* valid gdt descriptors start from index 1 */
if (!sel.index && GDT_SEL == sel.ti) {
return false;
}
if (GDT_SEL == sel.ti) {
base = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_BASE);
limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_LIMIT);
} else {
base = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_BASE);
limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_LIMIT);
}
if (sel.index * 8 >= limit) {
return false;
}
vmx_read_mem(cpu, desc, base + sel.index * 8, sizeof(*desc));
return true;
}
bool x86_write_segment_descriptor(struct CPUState *cpu,
struct x86_segment_descriptor *desc,
x68_segment_selector sel)
{
target_ulong base;
uint32_t limit;
if (GDT_SEL == sel.ti) {
base = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_BASE);
limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_LIMIT);
} else {
base = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_BASE);
limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_LIMIT);
}
if (sel.index * 8 >= limit) {
printf("%s: gdt limit\n", __func__);
return false;
}
vmx_write_mem(cpu, base + sel.index * 8, desc, sizeof(*desc));
return true;
}
bool x86_read_call_gate(struct CPUState *cpu, struct x86_call_gate *idt_desc,
int gate)
{
target_ulong base = rvmcs(cpu->hvf_fd, VMCS_GUEST_IDTR_BASE);
uint32_t limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_IDTR_LIMIT);
memset(idt_desc, 0, sizeof(*idt_desc));
if (gate * 8 >= limit) {
printf("%s: idt limit\n", __func__);
return false;
}
vmx_read_mem(cpu, idt_desc, base + gate * 8, sizeof(*idt_desc));
return true;
}
bool x86_is_protected(struct CPUState *cpu)
{
uint64_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0);
return cr0 & CR0_PE;
}
bool x86_is_real(struct CPUState *cpu)
{
return !x86_is_protected(cpu);
}
bool x86_is_v8086(struct CPUState *cpu)
{
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
return x86_is_protected(cpu) && (RFLAGS(env) & RFLAGS_VM);
}
bool x86_is_long_mode(struct CPUState *cpu)
{
return rvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER) & MSR_EFER_LMA;
}
bool x86_is_long64_mode(struct CPUState *cpu)
{
struct vmx_segment desc;
vmx_read_segment_descriptor(cpu, &desc, R_CS);
return x86_is_long_mode(cpu) && ((desc.ar >> 13) & 1);
}
bool x86_is_paging_mode(struct CPUState *cpu)
{
uint64_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0);
return cr0 & CR0_PG;
}
bool x86_is_pae_enabled(struct CPUState *cpu)
{
uint64_t cr4 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR4);
return cr4 & CR4_PAE;
}
target_ulong linear_addr(struct CPUState *cpu, target_ulong addr, X86Seg seg)
{
return vmx_read_segment_base(cpu, seg) + addr;
}
target_ulong linear_addr_size(struct CPUState *cpu, target_ulong addr, int size,
X86Seg seg)
{
switch (size) {
case 2:
addr = (uint16_t)addr;
break;
case 4:
addr = (uint32_t)addr;
break;
default:
break;
}
return linear_addr(cpu, addr, seg);
}
target_ulong linear_rip(struct CPUState *cpu, target_ulong rip)
{
return linear_addr(cpu, rip, R_CS);
}

400
target/i386/hvf/x86.h Normal file
View file

@ -0,0 +1,400 @@
/*
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Veertu Inc,
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#ifndef HVF_X86_H
#define HVF_X86_H 1
typedef struct x86_register {
union {
struct {
uint64_t rrx; /* full 64 bit */
};
struct {
uint32_t erx; /* low 32 bit part */
uint32_t hi32_unused1;
};
struct {
uint16_t rx; /* low 16 bit part */
uint16_t hi16_unused1;
uint32_t hi32_unused2;
};
struct {
uint8_t lx; /* low 8 bit part */
uint8_t hx; /* high 8 bit */
uint16_t hi16_unused2;
uint32_t hi32_unused3;
};
};
} __attribute__ ((__packed__)) x86_register;
typedef enum x86_rflags {
RFLAGS_CF = (1L << 0),
RFLAGS_PF = (1L << 2),
RFLAGS_AF = (1L << 4),
RFLAGS_ZF = (1L << 6),
RFLAGS_SF = (1L << 7),
RFLAGS_TF = (1L << 8),
RFLAGS_IF = (1L << 9),
RFLAGS_DF = (1L << 10),
RFLAGS_OF = (1L << 11),
RFLAGS_IOPL = (3L << 12),
RFLAGS_NT = (1L << 14),
RFLAGS_RF = (1L << 16),
RFLAGS_VM = (1L << 17),
RFLAGS_AC = (1L << 18),
RFLAGS_VIF = (1L << 19),
RFLAGS_VIP = (1L << 20),
RFLAGS_ID = (1L << 21),
} x86_rflags;
/* rflags register */
typedef struct x86_reg_flags {
union {
struct {
uint64_t rflags;
};
struct {
uint32_t eflags;
uint32_t hi32_unused1;
};
struct {
uint32_t cf:1;
uint32_t unused1:1;
uint32_t pf:1;
uint32_t unused2:1;
uint32_t af:1;
uint32_t unused3:1;
uint32_t zf:1;
uint32_t sf:1;
uint32_t tf:1;
uint32_t ief:1;
uint32_t df:1;
uint32_t of:1;
uint32_t iopl:2;
uint32_t nt:1;
uint32_t unused4:1;
uint32_t rf:1;
uint32_t vm:1;
uint32_t ac:1;
uint32_t vif:1;
uint32_t vip:1;
uint32_t id:1;
uint32_t unused5:10;
uint32_t hi32_unused2;
};
};
} __attribute__ ((__packed__)) x86_reg_flags;
typedef enum x86_reg_cr0 {
CR0_PE = (1L << 0),
CR0_MP = (1L << 1),
CR0_EM = (1L << 2),
CR0_TS = (1L << 3),
CR0_ET = (1L << 4),
CR0_NE = (1L << 5),
CR0_WP = (1L << 16),
CR0_AM = (1L << 18),
CR0_NW = (1L << 29),
CR0_CD = (1L << 30),
CR0_PG = (1L << 31),
} x86_reg_cr0;
typedef enum x86_reg_cr4 {
CR4_VME = (1L << 0),
CR4_PVI = (1L << 1),
CR4_TSD = (1L << 2),
CR4_DE = (1L << 3),
CR4_PSE = (1L << 4),
CR4_PAE = (1L << 5),
CR4_MSE = (1L << 6),
CR4_PGE = (1L << 7),
CR4_PCE = (1L << 8),
CR4_OSFXSR = (1L << 9),
CR4_OSXMMEXCPT = (1L << 10),
CR4_VMXE = (1L << 13),
CR4_SMXE = (1L << 14),
CR4_FSGSBASE = (1L << 16),
CR4_PCIDE = (1L << 17),
CR4_OSXSAVE = (1L << 18),
CR4_SMEP = (1L << 20),
} x86_reg_cr4;
/* 16 bit Task State Segment */
typedef struct x86_tss_segment16 {
uint16_t link;
uint16_t sp0;
uint16_t ss0;
uint32_t sp1;
uint16_t ss1;
uint32_t sp2;
uint16_t ss2;
uint16_t ip;
uint16_t flags;
uint16_t ax;
uint16_t cx;
uint16_t dx;
uint16_t bx;
uint16_t sp;
uint16_t bp;
uint16_t si;
uint16_t di;
uint16_t es;
uint16_t cs;
uint16_t ss;
uint16_t ds;
uint16_t ldtr;
} __attribute__((packed)) x86_tss_segment16;
/* 32 bit Task State Segment */
typedef struct x86_tss_segment32 {
uint32_t prev_tss;
uint32_t esp0;
uint32_t ss0;
uint32_t esp1;
uint32_t ss1;
uint32_t esp2;
uint32_t ss2;
uint32_t cr3;
uint32_t eip;
uint32_t eflags;
uint32_t eax;
uint32_t ecx;
uint32_t edx;
uint32_t ebx;
uint32_t esp;
uint32_t ebp;
uint32_t esi;
uint32_t edi;
uint32_t es;
uint32_t cs;
uint32_t ss;
uint32_t ds;
uint32_t fs;
uint32_t gs;
uint32_t ldt;
uint16_t trap;
uint16_t iomap_base;
} __attribute__ ((__packed__)) x86_tss_segment32;
/* 64 bit Task State Segment */
typedef struct x86_tss_segment64 {
uint32_t unused;
uint64_t rsp0;
uint64_t rsp1;
uint64_t rsp2;
uint64_t unused1;
uint64_t ist1;
uint64_t ist2;
uint64_t ist3;
uint64_t ist4;
uint64_t ist5;
uint64_t ist6;
uint64_t ist7;
uint64_t unused2;
uint16_t unused3;
uint16_t iomap_base;
} __attribute__ ((__packed__)) x86_tss_segment64;
/* segment descriptors */
typedef struct x86_segment_descriptor {
uint64_t limit0:16;
uint64_t base0:16;
uint64_t base1:8;
uint64_t type:4;
uint64_t s:1;
uint64_t dpl:2;
uint64_t p:1;
uint64_t limit1:4;
uint64_t avl:1;
uint64_t l:1;
uint64_t db:1;
uint64_t g:1;
uint64_t base2:8;
} __attribute__ ((__packed__)) x86_segment_descriptor;
static inline uint32_t x86_segment_base(x86_segment_descriptor *desc)
{
return (uint32_t)((desc->base2 << 24) | (desc->base1 << 16) | desc->base0);
}
static inline void x86_set_segment_base(x86_segment_descriptor *desc,
uint32_t base)
{
desc->base2 = base >> 24;
desc->base1 = (base >> 16) & 0xff;
desc->base0 = base & 0xffff;
}
static inline uint32_t x86_segment_limit(x86_segment_descriptor *desc)
{
uint32_t limit = (uint32_t)((desc->limit1 << 16) | desc->limit0);
if (desc->g) {
return (limit << 12) | 0xfff;
}
return limit;
}
static inline void x86_set_segment_limit(x86_segment_descriptor *desc,
uint32_t limit)
{
desc->limit0 = limit & 0xffff;
desc->limit1 = limit >> 16;
}
typedef struct x86_call_gate {
uint64_t offset0:16;
uint64_t selector:16;
uint64_t param_count:4;
uint64_t reserved:3;
uint64_t type:4;
uint64_t dpl:1;
uint64_t p:1;
uint64_t offset1:16;
} __attribute__ ((__packed__)) x86_call_gate;
static inline uint32_t x86_call_gate_offset(x86_call_gate *gate)
{
return (uint32_t)((gate->offset1 << 16) | gate->offset0);
}
#define LDT_SEL 0
#define GDT_SEL 1
typedef struct x68_segment_selector {
union {
uint16_t sel;
struct {
uint16_t rpl:3;
uint16_t ti:1;
uint16_t index:12;
};
};
} __attribute__ ((__packed__)) x68_segment_selector;
typedef struct lazy_flags {
target_ulong result;
target_ulong auxbits;
} lazy_flags;
/* Definition of hvf_x86_state is here */
struct HVFX86EmulatorState {
int interruptable;
uint64_t fetch_rip;
uint64_t rip;
struct x86_register regs[16];
struct x86_reg_flags rflags;
struct lazy_flags lflags;
uint8_t mmio_buf[4096];
};
/* useful register access macros */
#define RIP(cpu) (cpu->hvf_emul->rip)
#define EIP(cpu) ((uint32_t)cpu->hvf_emul->rip)
#define RFLAGS(cpu) (cpu->hvf_emul->rflags.rflags)
#define EFLAGS(cpu) (cpu->hvf_emul->rflags.eflags)
#define RRX(cpu, reg) (cpu->hvf_emul->regs[reg].rrx)
#define RAX(cpu) RRX(cpu, R_EAX)
#define RCX(cpu) RRX(cpu, R_ECX)
#define RDX(cpu) RRX(cpu, R_EDX)
#define RBX(cpu) RRX(cpu, R_EBX)
#define RSP(cpu) RRX(cpu, R_ESP)
#define RBP(cpu) RRX(cpu, R_EBP)
#define RSI(cpu) RRX(cpu, R_ESI)
#define RDI(cpu) RRX(cpu, R_EDI)
#define R8(cpu) RRX(cpu, R_R8)
#define R9(cpu) RRX(cpu, R_R9)
#define R10(cpu) RRX(cpu, R_R10)
#define R11(cpu) RRX(cpu, R_R11)
#define R12(cpu) RRX(cpu, R_R12)
#define R13(cpu) RRX(cpu, R_R13)
#define R14(cpu) RRX(cpu, R_R14)
#define R15(cpu) RRX(cpu, R_R15)
#define ERX(cpu, reg) (cpu->hvf_emul->regs[reg].erx)
#define EAX(cpu) ERX(cpu, R_EAX)
#define ECX(cpu) ERX(cpu, R_ECX)
#define EDX(cpu) ERX(cpu, R_EDX)
#define EBX(cpu) ERX(cpu, R_EBX)
#define ESP(cpu) ERX(cpu, R_ESP)
#define EBP(cpu) ERX(cpu, R_EBP)
#define ESI(cpu) ERX(cpu, R_ESI)
#define EDI(cpu) ERX(cpu, R_EDI)
#define RX(cpu, reg) (cpu->hvf_emul->regs[reg].rx)
#define AX(cpu) RX(cpu, R_EAX)
#define CX(cpu) RX(cpu, R_ECX)
#define DX(cpu) RX(cpu, R_EDX)
#define BP(cpu) RX(cpu, R_EBP)
#define SP(cpu) RX(cpu, R_ESP)
#define BX(cpu) RX(cpu, R_EBX)
#define SI(cpu) RX(cpu, R_ESI)
#define DI(cpu) RX(cpu, R_EDI)
#define RL(cpu, reg) (cpu->hvf_emul->regs[reg].lx)
#define AL(cpu) RL(cpu, R_EAX)
#define CL(cpu) RL(cpu, R_ECX)
#define DL(cpu) RL(cpu, R_EDX)
#define BL(cpu) RL(cpu, R_EBX)
#define RH(cpu, reg) (cpu->hvf_emul->regs[reg].hx)
#define AH(cpu) RH(cpu, R_EAX)
#define CH(cpu) RH(cpu, R_ECX)
#define DH(cpu) RH(cpu, R_EDX)
#define BH(cpu) RH(cpu, R_EBX)
/* deal with GDT/LDT descriptors in memory */
bool x86_read_segment_descriptor(struct CPUState *cpu,
struct x86_segment_descriptor *desc,
x68_segment_selector sel);
bool x86_write_segment_descriptor(struct CPUState *cpu,
struct x86_segment_descriptor *desc,
x68_segment_selector sel);
bool x86_read_call_gate(struct CPUState *cpu, struct x86_call_gate *idt_desc,
int gate);
/* helpers */
bool x86_is_protected(struct CPUState *cpu);
bool x86_is_real(struct CPUState *cpu);
bool x86_is_v8086(struct CPUState *cpu);
bool x86_is_long_mode(struct CPUState *cpu);
bool x86_is_long64_mode(struct CPUState *cpu);
bool x86_is_paging_mode(struct CPUState *cpu);
bool x86_is_pae_enabled(struct CPUState *cpu);
enum X86Seg;
target_ulong linear_addr(struct CPUState *cpu, target_ulong addr, enum X86Seg seg);
target_ulong linear_addr_size(struct CPUState *cpu, target_ulong addr, int size,
enum X86Seg seg);
target_ulong linear_rip(struct CPUState *cpu, target_ulong rip);
static inline uint64_t rdtscp(void)
{
uint64_t tsc;
__asm__ __volatile__("rdtscp; " /* serializing read of tsc */
"shl $32,%%rdx; " /* shift higher 32 bits stored in rdx up */
"or %%rdx,%%rax" /* and or onto rax */
: "=a"(tsc) /* output to tsc variable */
:
: "%rcx", "%rdx"); /* rcx and rdx are clobbered */
return tsc;
}
#endif

166
target/i386/hvf/x86_cpuid.c Normal file
View file

@ -0,0 +1,166 @@
/*
* i386 CPUID helper functions
*
* Copyright (c) 2003 Fabrice Bellard
* Copyright (c) 2017 Google Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*
* cpuid
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "cpu.h"
#include "x86.h"
#include "vmx.h"
#include "sysemu/hvf.h"
static uint64_t xgetbv(uint32_t xcr)
{
uint32_t eax, edx;
__asm__ volatile ("xgetbv"
: "=a" (eax), "=d" (edx)
: "c" (xcr));
return (((uint64_t)edx) << 32) | eax;
}
static bool vmx_mpx_supported()
{
uint64_t cap_exit, cap_entry;
hv_vmx_read_capability(HV_VMX_CAP_ENTRY, &cap_entry);
hv_vmx_read_capability(HV_VMX_CAP_EXIT, &cap_exit);
return ((cap_exit & (1 << 23)) && (cap_entry & (1 << 16)));
}
uint32_t hvf_get_supported_cpuid(uint32_t func, uint32_t idx,
int reg)
{
uint64_t cap;
uint32_t eax, ebx, ecx, edx;
host_cpuid(func, idx, &eax, &ebx, &ecx, &edx);
switch (func) {
case 0:
eax = eax < (uint32_t)0xd ? eax : (uint32_t)0xd;
break;
case 1:
edx &= CPUID_FP87 | CPUID_VME | CPUID_DE | CPUID_PSE | CPUID_TSC |
CPUID_MSR | CPUID_PAE | CPUID_MCE | CPUID_CX8 | CPUID_APIC |
CPUID_SEP | CPUID_MTRR | CPUID_PGE | CPUID_MCA | CPUID_CMOV |
CPUID_PAT | CPUID_PSE36 | CPUID_CLFLUSH | CPUID_MMX |
CPUID_FXSR | CPUID_SSE | CPUID_SSE2 | CPUID_SS;
ecx &= CPUID_EXT_SSE3 | CPUID_EXT_PCLMULQDQ | CPUID_EXT_SSSE3 |
CPUID_EXT_FMA | CPUID_EXT_CX16 | CPUID_EXT_PCID |
CPUID_EXT_SSE41 | CPUID_EXT_SSE42 | CPUID_EXT_MOVBE |
CPUID_EXT_POPCNT | CPUID_EXT_AES | CPUID_EXT_XSAVE |
CPUID_EXT_AVX | CPUID_EXT_F16C | CPUID_EXT_RDRAND;
ecx |= CPUID_EXT_HYPERVISOR;
break;
case 6:
eax = CPUID_6_EAX_ARAT;
ebx = 0;
ecx = 0;
edx = 0;
break;
case 7:
if (idx == 0) {
ebx &= CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 |
CPUID_7_0_EBX_HLE | CPUID_7_0_EBX_AVX2 |
CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 |
CPUID_7_0_EBX_ERMS | CPUID_7_0_EBX_RTM |
CPUID_7_0_EBX_RDSEED | CPUID_7_0_EBX_ADX |
CPUID_7_0_EBX_SMAP | CPUID_7_0_EBX_AVX512IFMA |
CPUID_7_0_EBX_AVX512F | CPUID_7_0_EBX_AVX512PF |
CPUID_7_0_EBX_AVX512ER | CPUID_7_0_EBX_AVX512CD |
CPUID_7_0_EBX_CLFLUSHOPT | CPUID_7_0_EBX_CLWB |
CPUID_7_0_EBX_AVX512DQ | CPUID_7_0_EBX_SHA_NI |
CPUID_7_0_EBX_AVX512BW | CPUID_7_0_EBX_AVX512VL |
CPUID_7_0_EBX_INVPCID | CPUID_7_0_EBX_MPX;
if (!vmx_mpx_supported()) {
ebx &= ~CPUID_7_0_EBX_MPX;
}
hv_vmx_read_capability(HV_VMX_CAP_PROCBASED2, &cap);
if (!(cap & CPU_BASED2_INVPCID)) {
ebx &= ~CPUID_7_0_EBX_INVPCID;
}
ecx &= CPUID_7_0_ECX_AVX512BMI | CPUID_7_0_ECX_AVX512_VPOPCNTDQ;
edx &= CPUID_7_0_EDX_AVX512_4VNNIW | CPUID_7_0_EDX_AVX512_4FMAPS;
} else {
ebx = 0;
ecx = 0;
edx = 0;
}
eax = 0;
break;
case 0xD:
if (idx == 0) {
uint64_t host_xcr0 = xgetbv(0);
uint64_t supp_xcr0 = host_xcr0 & (XSTATE_FP_MASK | XSTATE_SSE_MASK |
XSTATE_YMM_MASK | XSTATE_BNDREGS_MASK |
XSTATE_BNDCSR_MASK | XSTATE_OPMASK_MASK |
XSTATE_ZMM_Hi256_MASK | XSTATE_Hi16_ZMM_MASK);
eax &= supp_xcr0;
if (!vmx_mpx_supported()) {
eax &= ~(XSTATE_BNDREGS_MASK | XSTATE_BNDCSR_MASK);
}
} else if (idx == 1) {
hv_vmx_read_capability(HV_VMX_CAP_PROCBASED2, &cap);
eax &= CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XGETBV1;
if (!(cap & CPU_BASED2_XSAVES_XRSTORS)) {
eax &= ~CPUID_XSAVE_XSAVES;
}
}
break;
case 0x80000001:
/* LM only if HVF in 64-bit mode */
edx &= CPUID_FP87 | CPUID_VME | CPUID_DE | CPUID_PSE | CPUID_TSC |
CPUID_MSR | CPUID_PAE | CPUID_MCE | CPUID_CX8 | CPUID_APIC |
CPUID_EXT2_SYSCALL | CPUID_MTRR | CPUID_PGE | CPUID_MCA | CPUID_CMOV |
CPUID_PAT | CPUID_PSE36 | CPUID_EXT2_MMXEXT | CPUID_MMX |
CPUID_FXSR | CPUID_EXT2_FXSR | CPUID_EXT2_PDPE1GB | CPUID_EXT2_3DNOWEXT |
CPUID_EXT2_3DNOW | CPUID_EXT2_LM | CPUID_EXT2_RDTSCP | CPUID_EXT2_NX;
hv_vmx_read_capability(HV_VMX_CAP_PROCBASED, &cap);
if (!(cap & CPU_BASED_TSC_OFFSET)) {
edx &= ~CPUID_EXT2_RDTSCP;
}
ecx &= CPUID_EXT3_LAHF_LM | CPUID_EXT3_CMP_LEG | CPUID_EXT3_CR8LEG |
CPUID_EXT3_ABM | CPUID_EXT3_SSE4A | CPUID_EXT3_MISALIGNSSE |
CPUID_EXT3_3DNOWPREFETCH | CPUID_EXT3_OSVW | CPUID_EXT3_XOP |
CPUID_EXT3_FMA4 | CPUID_EXT3_TBM;
break;
default:
return 0;
}
switch (reg) {
case R_EAX:
return eax;
case R_EBX:
return ebx;
case R_ECX:
return ecx;
case R_EDX:
return edx;
default:
return 0;
}
}

2186
target/i386/hvf/x86_decode.c Normal file
View file

File diff suppressed because it is too large Load diff

323
target/i386/hvf/x86_decode.h Normal file
View file

@ -0,0 +1,323 @@
/*
* Copyright (C) 2016 Veertu Inc,
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#ifndef HVF_X86_DECODE_H
#define HVF_X86_DECODE_H 1
#include "cpu.h"
#include "x86.h"
typedef enum x86_prefix {
/* group 1 */
PREFIX_LOCK = 0xf0,
PREFIX_REPN = 0xf2,
PREFIX_REP = 0xf3,
/* group 2 */
PREFIX_CS_SEG_OVEERIDE = 0x2e,
PREFIX_SS_SEG_OVEERIDE = 0x36,
PREFIX_DS_SEG_OVEERIDE = 0x3e,
PREFIX_ES_SEG_OVEERIDE = 0x26,
PREFIX_FS_SEG_OVEERIDE = 0x64,
PREFIX_GS_SEG_OVEERIDE = 0x65,
/* group 3 */
PREFIX_OP_SIZE_OVERRIDE = 0x66,
/* group 4 */
PREFIX_ADDR_SIZE_OVERRIDE = 0x67,
PREFIX_REX = 0x40,
} x86_prefix;
enum x86_decode_cmd {
X86_DECODE_CMD_INVL = 0,
X86_DECODE_CMD_PUSH,
X86_DECODE_CMD_PUSH_SEG,
X86_DECODE_CMD_POP,
X86_DECODE_CMD_POP_SEG,
X86_DECODE_CMD_MOV,
X86_DECODE_CMD_MOVSX,
X86_DECODE_CMD_MOVZX,
X86_DECODE_CMD_CALL_NEAR,
X86_DECODE_CMD_CALL_NEAR_ABS_INDIRECT,
X86_DECODE_CMD_CALL_FAR_ABS_INDIRECT,
X86_DECODE_CMD_CALL_FAR,
X86_DECODE_RET_NEAR,
X86_DECODE_RET_FAR,
X86_DECODE_CMD_ADD,
X86_DECODE_CMD_OR,
X86_DECODE_CMD_ADC,
X86_DECODE_CMD_SBB,
X86_DECODE_CMD_AND,
X86_DECODE_CMD_SUB,
X86_DECODE_CMD_XOR,
X86_DECODE_CMD_CMP,
X86_DECODE_CMD_INC,
X86_DECODE_CMD_DEC,
X86_DECODE_CMD_TST,
X86_DECODE_CMD_NOT,
X86_DECODE_CMD_NEG,
X86_DECODE_CMD_JMP_NEAR,
X86_DECODE_CMD_JMP_NEAR_ABS_INDIRECT,
X86_DECODE_CMD_JMP_FAR,
X86_DECODE_CMD_JMP_FAR_ABS_INDIRECT,
X86_DECODE_CMD_LEA,
X86_DECODE_CMD_JXX,
X86_DECODE_CMD_JCXZ,
X86_DECODE_CMD_SETXX,
X86_DECODE_CMD_MOV_TO_SEG,
X86_DECODE_CMD_MOV_FROM_SEG,
X86_DECODE_CMD_CLI,
X86_DECODE_CMD_STI,
X86_DECODE_CMD_CLD,
X86_DECODE_CMD_STD,
X86_DECODE_CMD_STC,
X86_DECODE_CMD_CLC,
X86_DECODE_CMD_OUT,
X86_DECODE_CMD_IN,
X86_DECODE_CMD_INS,
X86_DECODE_CMD_OUTS,
X86_DECODE_CMD_LIDT,
X86_DECODE_CMD_SIDT,
X86_DECODE_CMD_LGDT,
X86_DECODE_CMD_SGDT,
X86_DECODE_CMD_SMSW,
X86_DECODE_CMD_LMSW,
X86_DECODE_CMD_RDTSCP,
X86_DECODE_CMD_INVLPG,
X86_DECODE_CMD_MOV_TO_CR,
X86_DECODE_CMD_MOV_FROM_CR,
X86_DECODE_CMD_MOV_TO_DR,
X86_DECODE_CMD_MOV_FROM_DR,
X86_DECODE_CMD_PUSHF,
X86_DECODE_CMD_POPF,
X86_DECODE_CMD_CPUID,
X86_DECODE_CMD_ROL,
X86_DECODE_CMD_ROR,
X86_DECODE_CMD_RCL,
X86_DECODE_CMD_RCR,
X86_DECODE_CMD_SHL,
X86_DECODE_CMD_SAL,
X86_DECODE_CMD_SHR,
X86_DECODE_CMD_SHRD,
X86_DECODE_CMD_SHLD,
X86_DECODE_CMD_SAR,
X86_DECODE_CMD_DIV,
X86_DECODE_CMD_IDIV,
X86_DECODE_CMD_MUL,
X86_DECODE_CMD_IMUL_3,
X86_DECODE_CMD_IMUL_2,
X86_DECODE_CMD_IMUL_1,
X86_DECODE_CMD_MOVS,
X86_DECODE_CMD_CMPS,
X86_DECODE_CMD_SCAS,
X86_DECODE_CMD_LODS,
X86_DECODE_CMD_STOS,
X86_DECODE_CMD_BSWAP,
X86_DECODE_CMD_XCHG,
X86_DECODE_CMD_RDTSC,
X86_DECODE_CMD_RDMSR,
X86_DECODE_CMD_WRMSR,
X86_DECODE_CMD_ENTER,
X86_DECODE_CMD_LEAVE,
X86_DECODE_CMD_BT,
X86_DECODE_CMD_BTS,
X86_DECODE_CMD_BTC,
X86_DECODE_CMD_BTR,
X86_DECODE_CMD_BSF,
X86_DECODE_CMD_BSR,
X86_DECODE_CMD_IRET,
X86_DECODE_CMD_INT,
X86_DECODE_CMD_POPA,
X86_DECODE_CMD_PUSHA,
X86_DECODE_CMD_CWD,
X86_DECODE_CMD_CBW,
X86_DECODE_CMD_DAS,
X86_DECODE_CMD_AAD,
X86_DECODE_CMD_AAM,
X86_DECODE_CMD_AAS,
X86_DECODE_CMD_LOOP,
X86_DECODE_CMD_SLDT,
X86_DECODE_CMD_STR,
X86_DECODE_CMD_LLDT,
X86_DECODE_CMD_LTR,
X86_DECODE_CMD_VERR,
X86_DECODE_CMD_VERW,
X86_DECODE_CMD_SAHF,
X86_DECODE_CMD_LAHF,
X86_DECODE_CMD_WBINVD,
X86_DECODE_CMD_LDS,
X86_DECODE_CMD_LSS,
X86_DECODE_CMD_LES,
X86_DECODE_XMD_LGS,
X86_DECODE_CMD_LFS,
X86_DECODE_CMD_CMC,
X86_DECODE_CMD_XLAT,
X86_DECODE_CMD_NOP,
X86_DECODE_CMD_CMOV,
X86_DECODE_CMD_CLTS,
X86_DECODE_CMD_XADD,
X86_DECODE_CMD_HLT,
X86_DECODE_CMD_CMPXCHG8B,
X86_DECODE_CMD_CMPXCHG,
X86_DECODE_CMD_POPCNT,
X86_DECODE_CMD_FNINIT,
X86_DECODE_CMD_FLD,
X86_DECODE_CMD_FLDxx,
X86_DECODE_CMD_FNSTCW,
X86_DECODE_CMD_FNSTSW,
X86_DECODE_CMD_FNSETPM,
X86_DECODE_CMD_FSAVE,
X86_DECODE_CMD_FRSTOR,
X86_DECODE_CMD_FXSAVE,
X86_DECODE_CMD_FXRSTOR,
X86_DECODE_CMD_FDIV,
X86_DECODE_CMD_FMUL,
X86_DECODE_CMD_FSUB,
X86_DECODE_CMD_FADD,
X86_DECODE_CMD_EMMS,
X86_DECODE_CMD_MFENCE,
X86_DECODE_CMD_SFENCE,
X86_DECODE_CMD_LFENCE,
X86_DECODE_CMD_PREFETCH,
X86_DECODE_CMD_CLFLUSH,
X86_DECODE_CMD_FST,
X86_DECODE_CMD_FABS,
X86_DECODE_CMD_FUCOM,
X86_DECODE_CMD_FUCOMI,
X86_DECODE_CMD_FLDCW,
X86_DECODE_CMD_FXCH,
X86_DECODE_CMD_FCHS,
X86_DECODE_CMD_FCMOV,
X86_DECODE_CMD_FRNDINT,
X86_DECODE_CMD_FXAM,
X86_DECODE_CMD_LAST,
};
const char *decode_cmd_to_string(enum x86_decode_cmd cmd);
typedef struct x86_modrm {
union {
uint8_t modrm;
struct {
uint8_t rm:3;
uint8_t reg:3;
uint8_t mod:2;
};
};
} __attribute__ ((__packed__)) x86_modrm;
typedef struct x86_sib {
union {
uint8_t sib;
struct {
uint8_t base:3;
uint8_t index:3;
uint8_t scale:2;
};
};
} __attribute__ ((__packed__)) x86_sib;
typedef struct x86_rex {
union {
uint8_t rex;
struct {
uint8_t b:1;
uint8_t x:1;
uint8_t r:1;
uint8_t w:1;
uint8_t unused:4;
};
};
} __attribute__ ((__packed__)) x86_rex;
typedef enum x86_var_type {
X86_VAR_IMMEDIATE,
X86_VAR_OFFSET,
X86_VAR_REG,
X86_VAR_RM,
/* for floating point computations */
X87_VAR_REG,
X87_VAR_FLOATP,
X87_VAR_INTP,
X87_VAR_BYTEP,
} x86_var_type;
typedef struct x86_decode_op {
enum x86_var_type type;
int size;
int reg;
target_ulong val;
target_ulong ptr;
} x86_decode_op;
typedef struct x86_decode {
int len;
uint8_t opcode[4];
uint8_t opcode_len;
enum x86_decode_cmd cmd;
int addressing_size;
int operand_size;
int lock;
int rep;
int op_size_override;
int addr_size_override;
int segment_override;
int control_change_inst;
bool fwait;
bool fpop_stack;
bool frev;
uint32_t displacement;
uint8_t displacement_size;
struct x86_rex rex;
bool is_modrm;
bool sib_present;
struct x86_sib sib;
struct x86_modrm modrm;
struct x86_decode_op op[4];
bool is_fpu;
uint32_t flags_mask;
} x86_decode;
uint64_t sign(uint64_t val, int size);
uint32_t decode_instruction(CPUX86State *env, struct x86_decode *decode);
target_ulong get_reg_ref(CPUX86State *env, int reg, int is_extended, int size);
target_ulong get_reg_val(CPUX86State *env, int reg, int is_extended, int size);
void calc_modrm_operand(CPUX86State *env, struct x86_decode *decode,
struct x86_decode_op *op);
target_ulong decode_linear_addr(CPUX86State *env, struct x86_decode *decode,
target_ulong addr, enum X86Seg seg);
void init_decoder(void);
void calc_modrm_operand16(CPUX86State *env, struct x86_decode *decode,
struct x86_decode_op *op);
void calc_modrm_operand32(CPUX86State *env, struct x86_decode *decode,
struct x86_decode_op *op);
void calc_modrm_operand64(CPUX86State *env, struct x86_decode *decode,
struct x86_decode_op *op);
void set_addressing_size(CPUX86State *env, struct x86_decode *decode);
void set_operand_size(CPUX86State *env, struct x86_decode *decode);
#endif

125
target/i386/hvf/x86_descr.c Normal file
View file

@ -0,0 +1,125 @@
/*
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Google Inc,
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "vmx.h"
#include "x86_descr.h"
#define VMX_SEGMENT_FIELD(seg) \
[R_##seg] = { \
.selector = VMCS_GUEST_##seg##_SELECTOR, \
.base = VMCS_GUEST_##seg##_BASE, \
.limit = VMCS_GUEST_##seg##_LIMIT, \
.ar_bytes = VMCS_GUEST_##seg##_ACCESS_RIGHTS, \
}
static const struct vmx_segment_field {
int selector;
int base;
int limit;
int ar_bytes;
} vmx_segment_fields[] = {
VMX_SEGMENT_FIELD(ES),
VMX_SEGMENT_FIELD(CS),
VMX_SEGMENT_FIELD(SS),
VMX_SEGMENT_FIELD(DS),
VMX_SEGMENT_FIELD(FS),
VMX_SEGMENT_FIELD(GS),
VMX_SEGMENT_FIELD(LDTR),
VMX_SEGMENT_FIELD(TR),
};
uint32_t vmx_read_segment_limit(CPUState *cpu, X86Seg seg)
{
return (uint32_t)rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].limit);
}
uint32_t vmx_read_segment_ar(CPUState *cpu, X86Seg seg)
{
return (uint32_t)rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].ar_bytes);
}
uint64_t vmx_read_segment_base(CPUState *cpu, X86Seg seg)
{
return rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].base);
}
x68_segment_selector vmx_read_segment_selector(CPUState *cpu, X86Seg seg)
{
x68_segment_selector sel;
sel.sel = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].selector);
return sel;
}
void vmx_write_segment_selector(struct CPUState *cpu, x68_segment_selector selector, X86Seg seg)
{
wvmcs(cpu->hvf_fd, vmx_segment_fields[seg].selector, selector.sel);
}
void vmx_read_segment_descriptor(struct CPUState *cpu, struct vmx_segment *desc, X86Seg seg)
{
desc->sel = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].selector);
desc->base = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].base);
desc->limit = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].limit);
desc->ar = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].ar_bytes);
}
void vmx_write_segment_descriptor(CPUState *cpu, struct vmx_segment *desc, X86Seg seg)
{
const struct vmx_segment_field *sf = &vmx_segment_fields[seg];
wvmcs(cpu->hvf_fd, sf->base, desc->base);
wvmcs(cpu->hvf_fd, sf->limit, desc->limit);
wvmcs(cpu->hvf_fd, sf->selector, desc->sel);
wvmcs(cpu->hvf_fd, sf->ar_bytes, desc->ar);
}
void x86_segment_descriptor_to_vmx(struct CPUState *cpu, x68_segment_selector selector, struct x86_segment_descriptor *desc, struct vmx_segment *vmx_desc)
{
vmx_desc->sel = selector.sel;
vmx_desc->base = x86_segment_base(desc);
vmx_desc->limit = x86_segment_limit(desc);
vmx_desc->ar = (selector.sel ? 0 : 1) << 16 |
desc->g << 15 |
desc->db << 14 |
desc->l << 13 |
desc->avl << 12 |
desc->p << 7 |
desc->dpl << 5 |
desc->s << 4 |
desc->type;
}
void vmx_segment_to_x86_descriptor(struct CPUState *cpu, struct vmx_segment *vmx_desc, struct x86_segment_descriptor *desc)
{
x86_set_segment_limit(desc, vmx_desc->limit);
x86_set_segment_base(desc, vmx_desc->base);
desc->type = vmx_desc->ar & 15;
desc->s = (vmx_desc->ar >> 4) & 1;
desc->dpl = (vmx_desc->ar >> 5) & 3;
desc->p = (vmx_desc->ar >> 7) & 1;
desc->avl = (vmx_desc->ar >> 12) & 1;
desc->l = (vmx_desc->ar >> 13) & 1;
desc->db = (vmx_desc->ar >> 14) & 1;
desc->g = (vmx_desc->ar >> 15) & 1;
}

58
target/i386/hvf/x86_descr.h Normal file
View file

@ -0,0 +1,58 @@
/*
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Google Inc,
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#ifndef HVF_X86_DESCR_H
#define HVF_X86_DESCR_H 1
#include "x86.h"
typedef struct vmx_segment {
uint16_t sel;
uint64_t base;
uint64_t limit;
uint64_t ar;
} vmx_segment;
/* deal with vmstate descriptors */
void vmx_read_segment_descriptor(struct CPUState *cpu,
struct vmx_segment *desc, enum X86Seg seg);
void vmx_write_segment_descriptor(CPUState *cpu, struct vmx_segment *desc,
enum X86Seg seg);
x68_segment_selector vmx_read_segment_selector(struct CPUState *cpu,
enum X86Seg seg);
void vmx_write_segment_selector(struct CPUState *cpu,
x68_segment_selector selector,
enum X86Seg seg);
uint64_t vmx_read_segment_base(struct CPUState *cpu, enum X86Seg seg);
void vmx_write_segment_base(struct CPUState *cpu, enum X86Seg seg,
uint64_t base);
void x86_segment_descriptor_to_vmx(struct CPUState *cpu,
x68_segment_selector selector,
struct x86_segment_descriptor *desc,
struct vmx_segment *vmx_desc);
uint32_t vmx_read_segment_limit(CPUState *cpu, enum X86Seg seg);
uint32_t vmx_read_segment_ar(CPUState *cpu, enum X86Seg seg);
void vmx_segment_to_x86_descriptor(struct CPUState *cpu,
struct vmx_segment *vmx_desc,
struct x86_segment_descriptor *desc);
#endif

1483
target/i386/hvf/x86_emu.c Normal file
View file

File diff suppressed because it is too large Load diff

49
target/i386/hvf/x86_emu.h Normal file
View file

@ -0,0 +1,49 @@
/*
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Google Inc,
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#ifndef __X86_EMU_H__
#define __X86_EMU_H__
#include "x86.h"
#include "x86_decode.h"
#include "cpu.h"
void init_emu(void);
bool exec_instruction(struct CPUX86State *env, struct x86_decode *ins);
void load_regs(struct CPUState *cpu);
void store_regs(struct CPUState *cpu);
void simulate_rdmsr(struct CPUState *cpu);
void simulate_wrmsr(struct CPUState *cpu);
target_ulong read_reg(CPUX86State *env, int reg, int size);
void write_reg(CPUX86State *env, int reg, target_ulong val, int size);
target_ulong read_val_from_reg(target_ulong reg_ptr, int size);
void write_val_to_reg(target_ulong reg_ptr, target_ulong val, int size);
void write_val_ext(struct CPUX86State *env, target_ulong ptr, target_ulong val, int size);
uint8_t *read_mmio(struct CPUX86State *env, target_ulong ptr, int bytes);
target_ulong read_val_ext(struct CPUX86State *env, target_ulong ptr, int size);
void exec_movzx(struct CPUX86State *env, struct x86_decode *decode);
void exec_shl(struct CPUX86State *env, struct x86_decode *decode);
void exec_movsx(struct CPUX86State *env, struct x86_decode *decode);
void exec_ror(struct CPUX86State *env, struct x86_decode *decode);
void exec_rol(struct CPUX86State *env, struct x86_decode *decode);
void exec_rcl(struct CPUX86State *env, struct x86_decode *decode);
void exec_rcr(struct CPUX86State *env, struct x86_decode *decode);
#endif

315
target/i386/hvf/x86_flags.c Normal file
View file

@ -0,0 +1,315 @@
/////////////////////////////////////////////////////////////////////////
//
// Copyright (C) 2001-2012 The Bochs Project
// Copyright (C) 2017 Google Inc.
//
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2 of the License, or (at your option) any later version.
//
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
//
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA B 02110-1301 USA
/////////////////////////////////////////////////////////////////////////
/*
* flags functions
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "panic.h"
#include "cpu.h"
#include "x86_flags.h"
#include "x86.h"
/* this is basically bocsh code */
#define LF_SIGN_BIT 31
#define LF_BIT_SD (0) /* lazy Sign Flag Delta */
#define LF_BIT_AF (3) /* lazy Adjust flag */
#define LF_BIT_PDB (8) /* lazy Parity Delta Byte (8 bits) */
#define LF_BIT_CF (31) /* lazy Carry Flag */
#define LF_BIT_PO (30) /* lazy Partial Overflow = CF ^ OF */
#define LF_MASK_SD (0x01 << LF_BIT_SD)
#define LF_MASK_AF (0x01 << LF_BIT_AF)
#define LF_MASK_PDB (0xFF << LF_BIT_PDB)
#define LF_MASK_CF (0x01 << LF_BIT_CF)
#define LF_MASK_PO (0x01 << LF_BIT_PO)
#define ADD_COUT_VEC(op1, op2, result) \
(((op1) & (op2)) | (((op1) | (op2)) & (~(result))))
#define SUB_COUT_VEC(op1, op2, result) \
(((~(op1)) & (op2)) | (((~(op1)) ^ (op2)) & (result)))
#define GET_ADD_OVERFLOW(op1, op2, result, mask) \
((((op1) ^ (result)) & ((op2) ^ (result))) & (mask))
/* ******************* */
/* OSZAPC */
/* ******************* */
/* size, carries, result */
#define SET_FLAGS_OSZAPC_SIZE(size, lf_carries, lf_result) { \
target_ulong temp = ((lf_carries) & (LF_MASK_AF)) | \
(((lf_carries) >> (size - 2)) << LF_BIT_PO); \
env->hvf_emul->lflags.result = (target_ulong)(int##size##_t)(lf_result); \
if ((size) == 32) { \
temp = ((lf_carries) & ~(LF_MASK_PDB | LF_MASK_SD)); \
} else if ((size) == 16) { \
temp = ((lf_carries) & (LF_MASK_AF)) | ((lf_carries) << 16); \
} else if ((size) == 8) { \
temp = ((lf_carries) & (LF_MASK_AF)) | ((lf_carries) << 24); \
} else { \
VM_PANIC("unimplemented"); \
} \
env->hvf_emul->lflags.auxbits = (target_ulong)(uint32_t)temp; \
}
/* carries, result */
#define SET_FLAGS_OSZAPC_8(carries, result) \
SET_FLAGS_OSZAPC_SIZE(8, carries, result)
#define SET_FLAGS_OSZAPC_16(carries, result) \
SET_FLAGS_OSZAPC_SIZE(16, carries, result)
#define SET_FLAGS_OSZAPC_32(carries, result) \
SET_FLAGS_OSZAPC_SIZE(32, carries, result)
/* ******************* */
/* OSZAP */
/* ******************* */
/* size, carries, result */
#define SET_FLAGS_OSZAP_SIZE(size, lf_carries, lf_result) { \
target_ulong temp = ((lf_carries) & (LF_MASK_AF)) | \
(((lf_carries) >> (size - 2)) << LF_BIT_PO); \
if ((size) == 32) { \
temp = ((lf_carries) & ~(LF_MASK_PDB | LF_MASK_SD)); \
} else if ((size) == 16) { \
temp = ((lf_carries) & (LF_MASK_AF)) | ((lf_carries) << 16); \
} else if ((size) == 8) { \
temp = ((lf_carries) & (LF_MASK_AF)) | ((lf_carries) << 24); \
} else { \
VM_PANIC("unimplemented"); \
} \
env->hvf_emul->lflags.result = (target_ulong)(int##size##_t)(lf_result); \
target_ulong delta_c = (env->hvf_emul->lflags.auxbits ^ temp) & LF_MASK_CF; \
delta_c ^= (delta_c >> 1); \
env->hvf_emul->lflags.auxbits = (target_ulong)(uint32_t)(temp ^ delta_c); \
}
/* carries, result */
#define SET_FLAGS_OSZAP_8(carries, result) \
SET_FLAGS_OSZAP_SIZE(8, carries, result)
#define SET_FLAGS_OSZAP_16(carries, result) \
SET_FLAGS_OSZAP_SIZE(16, carries, result)
#define SET_FLAGS_OSZAP_32(carries, result) \
SET_FLAGS_OSZAP_SIZE(32, carries, result)
void SET_FLAGS_OxxxxC(CPUX86State *env, uint32_t new_of, uint32_t new_cf)
{
uint32_t temp_po = new_of ^ new_cf;
env->hvf_emul->lflags.auxbits &= ~(LF_MASK_PO | LF_MASK_CF);
env->hvf_emul->lflags.auxbits |= (temp_po << LF_BIT_PO) |
(new_cf << LF_BIT_CF);
}
void SET_FLAGS_OSZAPC_SUB32(CPUX86State *env, uint32_t v1, uint32_t v2,
uint32_t diff)
{
SET_FLAGS_OSZAPC_32(SUB_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAPC_SUB16(CPUX86State *env, uint16_t v1, uint16_t v2,
uint16_t diff)
{
SET_FLAGS_OSZAPC_16(SUB_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAPC_SUB8(CPUX86State *env, uint8_t v1, uint8_t v2,
uint8_t diff)
{
SET_FLAGS_OSZAPC_8(SUB_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAPC_ADD32(CPUX86State *env, uint32_t v1, uint32_t v2,
uint32_t diff)
{
SET_FLAGS_OSZAPC_32(ADD_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAPC_ADD16(CPUX86State *env, uint16_t v1, uint16_t v2,
uint16_t diff)
{
SET_FLAGS_OSZAPC_16(ADD_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAPC_ADD8(CPUX86State *env, uint8_t v1, uint8_t v2,
uint8_t diff)
{
SET_FLAGS_OSZAPC_8(ADD_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAP_SUB32(CPUX86State *env, uint32_t v1, uint32_t v2,
uint32_t diff)
{
SET_FLAGS_OSZAP_32(SUB_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAP_SUB16(CPUX86State *env, uint16_t v1, uint16_t v2,
uint16_t diff)
{
SET_FLAGS_OSZAP_16(SUB_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAP_SUB8(CPUX86State *env, uint8_t v1, uint8_t v2,
uint8_t diff)
{
SET_FLAGS_OSZAP_8(SUB_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAP_ADD32(CPUX86State *env, uint32_t v1, uint32_t v2,
uint32_t diff)
{
SET_FLAGS_OSZAP_32(ADD_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAP_ADD16(CPUX86State *env, uint16_t v1, uint16_t v2,
uint16_t diff)
{
SET_FLAGS_OSZAP_16(ADD_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAP_ADD8(CPUX86State *env, uint8_t v1, uint8_t v2,
uint8_t diff)
{
SET_FLAGS_OSZAP_8(ADD_COUT_VEC(v1, v2, diff), diff);
}
void SET_FLAGS_OSZAPC_LOGIC32(CPUX86State *env, uint32_t v1, uint32_t v2,
uint32_t diff)
{
SET_FLAGS_OSZAPC_32(0, diff);
}
void SET_FLAGS_OSZAPC_LOGIC16(CPUX86State *env, uint16_t v1, uint16_t v2,
uint16_t diff)
{
SET_FLAGS_OSZAPC_16(0, diff);
}
void SET_FLAGS_OSZAPC_LOGIC8(CPUX86State *env, uint8_t v1, uint8_t v2,
uint8_t diff)
{
SET_FLAGS_OSZAPC_8(0, diff);
}
bool get_PF(CPUX86State *env)
{
uint32_t temp = (255 & env->hvf_emul->lflags.result);
temp = temp ^ (255 & (env->hvf_emul->lflags.auxbits >> LF_BIT_PDB));
temp = (temp ^ (temp >> 4)) & 0x0F;
return (0x9669U >> temp) & 1;
}
void set_PF(CPUX86State *env, bool val)
{
uint32_t temp = (255 & env->hvf_emul->lflags.result) ^ (!val);
env->hvf_emul->lflags.auxbits &= ~(LF_MASK_PDB);
env->hvf_emul->lflags.auxbits |= (temp << LF_BIT_PDB);
}
bool get_OF(CPUX86State *env)
{
return ((env->hvf_emul->lflags.auxbits + (1U << LF_BIT_PO)) >> LF_BIT_CF) & 1;
}
bool get_CF(CPUX86State *env)
{
return (env->hvf_emul->lflags.auxbits >> LF_BIT_CF) & 1;
}
void set_OF(CPUX86State *env, bool val)
{
bool old_cf = get_CF(env);
SET_FLAGS_OxxxxC(env, val, old_cf);
}
void set_CF(CPUX86State *env, bool val)
{
bool old_of = get_OF(env);
SET_FLAGS_OxxxxC(env, old_of, val);
}
bool get_AF(CPUX86State *env)
{
return (env->hvf_emul->lflags.auxbits >> LF_BIT_AF) & 1;
}
void set_AF(CPUX86State *env, bool val)
{
env->hvf_emul->lflags.auxbits &= ~(LF_MASK_AF);
env->hvf_emul->lflags.auxbits |= val << LF_BIT_AF;
}
bool get_ZF(CPUX86State *env)
{
return !env->hvf_emul->lflags.result;
}
void set_ZF(CPUX86State *env, bool val)
{
if (val) {
env->hvf_emul->lflags.auxbits ^=
(((env->hvf_emul->lflags.result >> LF_SIGN_BIT) & 1) << LF_BIT_SD);
/* merge the parity bits into the Parity Delta Byte */
uint32_t temp_pdb = (255 & env->hvf_emul->lflags.result);
env->hvf_emul->lflags.auxbits ^= (temp_pdb << LF_BIT_PDB);
/* now zero the .result value */
env->hvf_emul->lflags.result = 0;
} else {
env->hvf_emul->lflags.result |= (1 << 8);
}
}
bool get_SF(CPUX86State *env)
{
return ((env->hvf_emul->lflags.result >> LF_SIGN_BIT) ^
(env->hvf_emul->lflags.auxbits >> LF_BIT_SD)) & 1;
}
void set_SF(CPUX86State *env, bool val)
{
bool temp_sf = get_SF(env);
env->hvf_emul->lflags.auxbits ^= (temp_sf ^ val) << LF_BIT_SD;
}
void lflags_to_rflags(CPUX86State *env)
{
env->hvf_emul->rflags.cf = get_CF(env);
env->hvf_emul->rflags.pf = get_PF(env);
env->hvf_emul->rflags.af = get_AF(env);
env->hvf_emul->rflags.zf = get_ZF(env);
env->hvf_emul->rflags.sf = get_SF(env);
env->hvf_emul->rflags.of = get_OF(env);
}
void rflags_to_lflags(CPUX86State *env)
{
env->hvf_emul->lflags.auxbits = env->hvf_emul->lflags.result = 0;
set_OF(env, env->hvf_emul->rflags.of);
set_SF(env, env->hvf_emul->rflags.sf);
set_ZF(env, env->hvf_emul->rflags.zf);
set_AF(env, env->hvf_emul->rflags.af);
set_PF(env, env->hvf_emul->rflags.pf);
set_CF(env, env->hvf_emul->rflags.cf);
}

80
target/i386/hvf/x86_flags.h Normal file
View file

@ -0,0 +1,80 @@
/////////////////////////////////////////////////////////////////////////
//
// Copyright (C) 2001-2012 The Bochs Project
// Copyright (C) 2017 Google Inc.
//
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2 of the License, or (at your option) any later version.
//
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
//
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA B 02110-1301 USA
/////////////////////////////////////////////////////////////////////////
/*
* x86 eflags functions
*/
#ifndef __X86_FLAGS_H__
#define __X86_FLAGS_H__
#include "cpu.h"
void lflags_to_rflags(CPUX86State *env);
void rflags_to_lflags(CPUX86State *env);
bool get_PF(CPUX86State *env);
void set_PF(CPUX86State *env, bool val);
bool get_CF(CPUX86State *env);
void set_CF(CPUX86State *env, bool val);
bool get_AF(CPUX86State *env);
void set_AF(CPUX86State *env, bool val);
bool get_ZF(CPUX86State *env);
void set_ZF(CPUX86State *env, bool val);
bool get_SF(CPUX86State *env);
void set_SF(CPUX86State *env, bool val);
bool get_OF(CPUX86State *env);
void set_OF(CPUX86State *env, bool val);
void SET_FLAGS_OxxxxC(CPUX86State *env, uint32_t new_of, uint32_t new_cf);
void SET_FLAGS_OSZAPC_SUB32(CPUX86State *env, uint32_t v1, uint32_t v2,
uint32_t diff);
void SET_FLAGS_OSZAPC_SUB16(CPUX86State *env, uint16_t v1, uint16_t v2,
uint16_t diff);
void SET_FLAGS_OSZAPC_SUB8(CPUX86State *env, uint8_t v1, uint8_t v2,
uint8_t diff);
void SET_FLAGS_OSZAPC_ADD32(CPUX86State *env, uint32_t v1, uint32_t v2,
uint32_t diff);
void SET_FLAGS_OSZAPC_ADD16(CPUX86State *env, uint16_t v1, uint16_t v2,
uint16_t diff);
void SET_FLAGS_OSZAPC_ADD8(CPUX86State *env, uint8_t v1, uint8_t v2,
uint8_t diff);
void SET_FLAGS_OSZAP_SUB32(CPUX86State *env, uint32_t v1, uint32_t v2,
uint32_t diff);
void SET_FLAGS_OSZAP_SUB16(CPUX86State *env, uint16_t v1, uint16_t v2,
uint16_t diff);
void SET_FLAGS_OSZAP_SUB8(CPUX86State *env, uint8_t v1, uint8_t v2,
uint8_t diff);
void SET_FLAGS_OSZAP_ADD32(CPUX86State *env, uint32_t v1, uint32_t v2,
uint32_t diff);
void SET_FLAGS_OSZAP_ADD16(CPUX86State *env, uint16_t v1, uint16_t v2,
uint16_t diff);
void SET_FLAGS_OSZAP_ADD8(CPUX86State *env, uint8_t v1, uint8_t v2,
uint8_t diff);
void SET_FLAGS_OSZAPC_LOGIC32(CPUX86State *env, uint32_t v1, uint32_t v2,
uint32_t diff);
void SET_FLAGS_OSZAPC_LOGIC16(CPUX86State *env, uint16_t v1, uint16_t v2,
uint16_t diff);
void SET_FLAGS_OSZAPC_LOGIC8(CPUX86State *env, uint8_t v1, uint8_t v2,
uint8_t diff);
#endif /* __X86_FLAGS_H__ */

272
target/i386/hvf/x86_mmu.c Normal file
View file

@ -0,0 +1,272 @@
/*
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Google Inc,
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "panic.h"
#include "qemu-common.h"
#include "cpu.h"
#include "x86.h"
#include "x86_mmu.h"
#include "string.h"
#include "vmcs.h"
#include "vmx.h"
#include "memory.h"
#include "exec/address-spaces.h"
#define pte_present(pte) (pte & PT_PRESENT)
#define pte_write_access(pte) (pte & PT_WRITE)
#define pte_user_access(pte) (pte & PT_USER)
#define pte_exec_access(pte) (!(pte & PT_NX))
#define pte_large_page(pte) (pte & PT_PS)
#define pte_global_access(pte) (pte & PT_GLOBAL)
#define PAE_CR3_MASK (~0x1fllu)
#define LEGACY_CR3_MASK (0xffffffff)
#define LEGACY_PTE_PAGE_MASK (0xffffffffllu << 12)
#define PAE_PTE_PAGE_MASK ((-1llu << 12) & ((1llu << 52) - 1))
#define PAE_PTE_LARGE_PAGE_MASK ((-1llu << (21)) & ((1llu << 52) - 1))
struct gpt_translation {
target_ulong gva;
uint64_t gpa;
int err_code;
uint64_t pte[5];
bool write_access;
bool user_access;
bool exec_access;
};
static int gpt_top_level(struct CPUState *cpu, bool pae)
{
if (!pae) {
return 2;
}
if (x86_is_long_mode(cpu)) {
return 4;
}
return 3;
}
static inline int gpt_entry(target_ulong addr, int level, bool pae)
{
int level_shift = pae ? 9 : 10;
return (addr >> (level_shift * (level - 1) + 12)) & ((1 << level_shift) - 1);
}
static inline int pte_size(bool pae)
{
return pae ? 8 : 4;
}
static bool get_pt_entry(struct CPUState *cpu, struct gpt_translation *pt,
int level, bool pae)
{
int index;
uint64_t pte = 0;
uint64_t page_mask = pae ? PAE_PTE_PAGE_MASK : LEGACY_PTE_PAGE_MASK;
uint64_t gpa = pt->pte[level] & page_mask;
if (level == 3 && !x86_is_long_mode(cpu)) {
gpa = pt->pte[level];
}
index = gpt_entry(pt->gva, level, pae);
address_space_rw(&address_space_memory, gpa + index * pte_size(pae),
MEMTXATTRS_UNSPECIFIED, (uint8_t *)&pte, pte_size(pae), 0);
pt->pte[level - 1] = pte;
return true;
}
/* test page table entry */
static bool test_pt_entry(struct CPUState *cpu, struct gpt_translation *pt,
int level, bool *is_large, bool pae)
{
uint64_t pte = pt->pte[level];
if (pt->write_access) {
pt->err_code |= MMU_PAGE_WT;
}
if (pt->user_access) {
pt->err_code |= MMU_PAGE_US;
}
if (pt->exec_access) {
pt->err_code |= MMU_PAGE_NX;
}
if (!pte_present(pte)) {
return false;
}
if (pae && !x86_is_long_mode(cpu) && 2 == level) {
goto exit;
}
if (1 == level && pte_large_page(pte)) {
pt->err_code |= MMU_PAGE_PT;
*is_large = true;
}
if (!level) {
pt->err_code |= MMU_PAGE_PT;
}
uint32_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0);
/* check protection */
if (cr0 & CR0_WP) {
if (pt->write_access && !pte_write_access(pte)) {
return false;
}
}
if (pt->user_access && !pte_user_access(pte)) {
return false;
}
if (pae && pt->exec_access && !pte_exec_access(pte)) {
return false;
}
exit:
/* TODO: check reserved bits */
return true;
}
static inline uint64_t pse_pte_to_page(uint64_t pte)
{
return ((pte & 0x1fe000) << 19) | (pte & 0xffc00000);
}
static inline uint64_t large_page_gpa(struct gpt_translation *pt, bool pae)
{
VM_PANIC_ON(!pte_large_page(pt->pte[1]))
/* 2Mb large page */
if (pae) {
return (pt->pte[1] & PAE_PTE_LARGE_PAGE_MASK) | (pt->gva & 0x1fffff);
}
/* 4Mb large page */
return pse_pte_to_page(pt->pte[1]) | (pt->gva & 0x3fffff);
}
static bool walk_gpt(struct CPUState *cpu, target_ulong addr, int err_code,
struct gpt_translation *pt, bool pae)
{
int top_level, level;
bool is_large = false;
target_ulong cr3 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR3);
uint64_t page_mask = pae ? PAE_PTE_PAGE_MASK : LEGACY_PTE_PAGE_MASK;
memset(pt, 0, sizeof(*pt));
top_level = gpt_top_level(cpu, pae);
pt->pte[top_level] = pae ? (cr3 & PAE_CR3_MASK) : (cr3 & LEGACY_CR3_MASK);
pt->gva = addr;
pt->user_access = (err_code & MMU_PAGE_US);
pt->write_access = (err_code & MMU_PAGE_WT);
pt->exec_access = (err_code & MMU_PAGE_NX);
for (level = top_level; level > 0; level--) {
get_pt_entry(cpu, pt, level, pae);
if (!test_pt_entry(cpu, pt, level - 1, &is_large, pae)) {
return false;
}
if (is_large) {
break;
}
}
if (!is_large) {
pt->gpa = (pt->pte[0] & page_mask) | (pt->gva & 0xfff);
} else {
pt->gpa = large_page_gpa(pt, pae);
}
return true;
}
bool mmu_gva_to_gpa(struct CPUState *cpu, target_ulong gva, uint64_t *gpa)
{
bool res;
struct gpt_translation pt;
int err_code = 0;
if (!x86_is_paging_mode(cpu)) {
*gpa = gva;
return true;
}
res = walk_gpt(cpu, gva, err_code, &pt, x86_is_pae_enabled(cpu));
if (res) {
*gpa = pt.gpa;
return true;
}
return false;
}
void vmx_write_mem(struct CPUState *cpu, target_ulong gva, void *data, int bytes)
{
uint64_t gpa;
while (bytes > 0) {
/* copy page */
int copy = MIN(bytes, 0x1000 - (gva & 0xfff));
if (!mmu_gva_to_gpa(cpu, gva, &gpa)) {
VM_PANIC_EX("%s: mmu_gva_to_gpa %llx failed\n", __func__, gva);
} else {
address_space_rw(&address_space_memory, gpa, MEMTXATTRS_UNSPECIFIED,
data, copy, 1);
}
bytes -= copy;
gva += copy;
data += copy;
}
}
void vmx_read_mem(struct CPUState *cpu, void *data, target_ulong gva, int bytes)
{
uint64_t gpa;
while (bytes > 0) {
/* copy page */
int copy = MIN(bytes, 0x1000 - (gva & 0xfff));
if (!mmu_gva_to_gpa(cpu, gva, &gpa)) {
VM_PANIC_EX("%s: mmu_gva_to_gpa %llx failed\n", __func__, gva);
}
address_space_rw(&address_space_memory, gpa, MEMTXATTRS_UNSPECIFIED,
data, copy, 0);
bytes -= copy;
gva += copy;
data += copy;
}
}

43
target/i386/hvf/x86_mmu.h Normal file
View file

@ -0,0 +1,43 @@
/*
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Google Inc,
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#ifndef __X86_MMU_H__
#define __X86_MMU_H__
#define PT_PRESENT (1 << 0)
#define PT_WRITE (1 << 1)
#define PT_USER (1 << 2)
#define PT_WT (1 << 3)
#define PT_CD (1 << 4)
#define PT_ACCESSED (1 << 5)
#define PT_DIRTY (1 << 6)
#define PT_PS (1 << 7)
#define PT_GLOBAL (1 << 8)
#define PT_NX (1llu << 63)
/* error codes */
#define MMU_PAGE_PT (1 << 0)
#define MMU_PAGE_WT (1 << 1)
#define MMU_PAGE_US (1 << 2)
#define MMU_PAGE_NX (1 << 3)
bool mmu_gva_to_gpa(struct CPUState *cpu, target_ulong gva, uint64_t *gpa);
void vmx_write_mem(struct CPUState *cpu, target_ulong gva, void *data, int bytes);
void vmx_read_mem(struct CPUState *cpu, void *data, target_ulong gva, int bytes);
#endif /* __X86_MMU_H__ */

191
target/i386/hvf/x86_task.c Normal file
View file

@ -0,0 +1,191 @@
// This software is licensed under the terms of the GNU General Public
// License version 2, as published by the Free Software Foundation, and
// may be copied, distributed, and modified under those terms.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
#include "qemu/osdep.h"
#include "panic.h"
#include "qemu-common.h"
#include "qemu/error-report.h"
#include "sysemu/hvf.h"
#include "hvf-i386.h"
#include "vmcs.h"
#include "vmx.h"
#include "x86.h"
#include "x86_descr.h"
#include "x86_mmu.h"
#include "x86_decode.h"
#include "x86_emu.h"
#include "x86_task.h"
#include "x86hvf.h"
#include <Hypervisor/hv.h>
#include <Hypervisor/hv_vmx.h>
#include "exec/address-spaces.h"
#include "exec/exec-all.h"
#include "exec/ioport.h"
#include "hw/i386/apic_internal.h"
#include "hw/boards.h"
#include "qemu/main-loop.h"
#include "strings.h"
#include "sysemu/accel.h"
#include "sysemu/sysemu.h"
#include "target/i386/cpu.h"
// TODO: taskswitch handling
static void save_state_to_tss32(CPUState *cpu, struct x86_tss_segment32 *tss)
{
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
/* CR3 and ldt selector are not saved intentionally */
tss->eip = EIP(env);
tss->eflags = EFLAGS(env);
tss->eax = EAX(env);
tss->ecx = ECX(env);
tss->edx = EDX(env);
tss->ebx = EBX(env);
tss->esp = ESP(env);
tss->ebp = EBP(env);
tss->esi = ESI(env);
tss->edi = EDI(env);
tss->es = vmx_read_segment_selector(cpu, R_ES).sel;
tss->cs = vmx_read_segment_selector(cpu, R_CS).sel;
tss->ss = vmx_read_segment_selector(cpu, R_SS).sel;
tss->ds = vmx_read_segment_selector(cpu, R_DS).sel;
tss->fs = vmx_read_segment_selector(cpu, R_FS).sel;
tss->gs = vmx_read_segment_selector(cpu, R_GS).sel;
}
static void load_state_from_tss32(CPUState *cpu, struct x86_tss_segment32 *tss)
{
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
wvmcs(cpu->hvf_fd, VMCS_GUEST_CR3, tss->cr3);
RIP(env) = tss->eip;
EFLAGS(env) = tss->eflags | 2;
/* General purpose registers */
RAX(env) = tss->eax;
RCX(env) = tss->ecx;
RDX(env) = tss->edx;
RBX(env) = tss->ebx;
RSP(env) = tss->esp;
RBP(env) = tss->ebp;
RSI(env) = tss->esi;
RDI(env) = tss->edi;
vmx_write_segment_selector(cpu, (x68_segment_selector){{tss->ldt}}, R_LDTR);
vmx_write_segment_selector(cpu, (x68_segment_selector){{tss->es}}, R_ES);
vmx_write_segment_selector(cpu, (x68_segment_selector){{tss->cs}}, R_CS);
vmx_write_segment_selector(cpu, (x68_segment_selector){{tss->ss}}, R_SS);
vmx_write_segment_selector(cpu, (x68_segment_selector){{tss->ds}}, R_DS);
vmx_write_segment_selector(cpu, (x68_segment_selector){{tss->fs}}, R_FS);
vmx_write_segment_selector(cpu, (x68_segment_selector){{tss->gs}}, R_GS);
}
static int task_switch_32(CPUState *cpu, x68_segment_selector tss_sel, x68_segment_selector old_tss_sel,
uint64_t old_tss_base, struct x86_segment_descriptor *new_desc)
{
struct x86_tss_segment32 tss_seg;
uint32_t new_tss_base = x86_segment_base(new_desc);
uint32_t eip_offset = offsetof(struct x86_tss_segment32, eip);
uint32_t ldt_sel_offset = offsetof(struct x86_tss_segment32, ldt);
vmx_read_mem(cpu, &tss_seg, old_tss_base, sizeof(tss_seg));
save_state_to_tss32(cpu, &tss_seg);
vmx_write_mem(cpu, old_tss_base + eip_offset, &tss_seg.eip, ldt_sel_offset - eip_offset);
vmx_read_mem(cpu, &tss_seg, new_tss_base, sizeof(tss_seg));
if (old_tss_sel.sel != 0xffff) {
tss_seg.prev_tss = old_tss_sel.sel;
vmx_write_mem(cpu, new_tss_base, &tss_seg.prev_tss, sizeof(tss_seg.prev_tss));
}
load_state_from_tss32(cpu, &tss_seg);
return 0;
}
void vmx_handle_task_switch(CPUState *cpu, x68_segment_selector tss_sel, int reason, bool gate_valid, uint8_t gate, uint64_t gate_type)
{
uint64_t rip = rreg(cpu->hvf_fd, HV_X86_RIP);
if (!gate_valid || (gate_type != VMCS_INTR_T_HWEXCEPTION &&
gate_type != VMCS_INTR_T_HWINTR &&
gate_type != VMCS_INTR_T_NMI)) {
int ins_len = rvmcs(cpu->hvf_fd, VMCS_EXIT_INSTRUCTION_LENGTH);
macvm_set_rip(cpu, rip + ins_len);
return;
}
load_regs(cpu);
struct x86_segment_descriptor curr_tss_desc, next_tss_desc;
int ret;
x68_segment_selector old_tss_sel = vmx_read_segment_selector(cpu, R_TR);
uint64_t old_tss_base = vmx_read_segment_base(cpu, R_TR);
uint32_t desc_limit;
struct x86_call_gate task_gate_desc;
struct vmx_segment vmx_seg;
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
x86_read_segment_descriptor(cpu, &next_tss_desc, tss_sel);
x86_read_segment_descriptor(cpu, &curr_tss_desc, old_tss_sel);
if (reason == TSR_IDT_GATE && gate_valid) {
int dpl;
ret = x86_read_call_gate(cpu, &task_gate_desc, gate);
dpl = task_gate_desc.dpl;
x68_segment_selector cs = vmx_read_segment_selector(cpu, R_CS);
if (tss_sel.rpl > dpl || cs.rpl > dpl)
;//DPRINTF("emulate_gp");
}
desc_limit = x86_segment_limit(&next_tss_desc);
if (!next_tss_desc.p || ((desc_limit < 0x67 && (next_tss_desc.type & 8)) || desc_limit < 0x2b)) {
VM_PANIC("emulate_ts");
}
if (reason == TSR_IRET || reason == TSR_JMP) {
curr_tss_desc.type &= ~(1 << 1); /* clear busy flag */
x86_write_segment_descriptor(cpu, &curr_tss_desc, old_tss_sel);
}
if (reason == TSR_IRET)
EFLAGS(env) &= ~RFLAGS_NT;
if (reason != TSR_CALL && reason != TSR_IDT_GATE)
old_tss_sel.sel = 0xffff;
if (reason != TSR_IRET) {
next_tss_desc.type |= (1 << 1); /* set busy flag */
x86_write_segment_descriptor(cpu, &next_tss_desc, tss_sel);
}
if (next_tss_desc.type & 8)
ret = task_switch_32(cpu, tss_sel, old_tss_sel, old_tss_base, &next_tss_desc);
else
//ret = task_switch_16(cpu, tss_sel, old_tss_sel, old_tss_base, &next_tss_desc);
VM_PANIC("task_switch_16");
macvm_set_cr0(cpu->hvf_fd, rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0) | CR0_TS);
x86_segment_descriptor_to_vmx(cpu, tss_sel, &next_tss_desc, &vmx_seg);
vmx_write_segment_descriptor(cpu, &vmx_seg, R_TR);
store_regs(cpu);
hv_vcpu_invalidate_tlb(cpu->hvf_fd);
hv_vcpu_flush(cpu->hvf_fd);
}

18
target/i386/hvf/x86_task.h Normal file
View file

@ -0,0 +1,18 @@
/* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation; either version 2 or
* (at your option) version 3 of the License.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#ifndef HVF_TASK
#define HVF_TASK
void vmx_handle_task_switch(CPUState *cpu, x68_segment_selector tss_sel,
int reason, bool gate_valid, uint8_t gate, uint64_t gate_type);
#endif

465
target/i386/hvf/x86hvf.c Normal file
View file

@ -0,0 +1,465 @@
/*
* Copyright (c) 2003-2008 Fabrice Bellard
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Google Inc,
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "x86hvf.h"
#include "vmx.h"
#include "vmcs.h"
#include "cpu.h"
#include "x86_descr.h"
#include "x86_decode.h"
#include "hw/i386/apic_internal.h"
#include <stdio.h>
#include <stdlib.h>
#include <Hypervisor/hv.h>
#include <Hypervisor/hv_vmx.h>
#include <stdint.h>
void hvf_set_segment(struct CPUState *cpu, struct vmx_segment *vmx_seg,
SegmentCache *qseg, bool is_tr)
{
vmx_seg->sel = qseg->selector;
vmx_seg->base = qseg->base;
vmx_seg->limit = qseg->limit;
if (!qseg->selector && !x86_is_real(cpu) && !is_tr) {
/* the TR register is usable after processor reset despite
* having a null selector */
vmx_seg->ar = 1 << 16;
return;
}
vmx_seg->ar = (qseg->flags >> DESC_TYPE_SHIFT) & 0xf;
vmx_seg->ar |= ((qseg->flags >> DESC_G_SHIFT) & 1) << 15;
vmx_seg->ar |= ((qseg->flags >> DESC_B_SHIFT) & 1) << 14;
vmx_seg->ar |= ((qseg->flags >> DESC_L_SHIFT) & 1) << 13;
vmx_seg->ar |= ((qseg->flags >> DESC_AVL_SHIFT) & 1) << 12;
vmx_seg->ar |= ((qseg->flags >> DESC_P_SHIFT) & 1) << 7;
vmx_seg->ar |= ((qseg->flags >> DESC_DPL_SHIFT) & 3) << 5;
vmx_seg->ar |= ((qseg->flags >> DESC_S_SHIFT) & 1) << 4;
}
void hvf_get_segment(SegmentCache *qseg, struct vmx_segment *vmx_seg)
{
qseg->limit = vmx_seg->limit;
qseg->base = vmx_seg->base;
qseg->selector = vmx_seg->sel;
qseg->flags = ((vmx_seg->ar & 0xf) << DESC_TYPE_SHIFT) |
(((vmx_seg->ar >> 4) & 1) << DESC_S_SHIFT) |
(((vmx_seg->ar >> 5) & 3) << DESC_DPL_SHIFT) |
(((vmx_seg->ar >> 7) & 1) << DESC_P_SHIFT) |
(((vmx_seg->ar >> 12) & 1) << DESC_AVL_SHIFT) |
(((vmx_seg->ar >> 13) & 1) << DESC_L_SHIFT) |
(((vmx_seg->ar >> 14) & 1) << DESC_B_SHIFT) |
(((vmx_seg->ar >> 15) & 1) << DESC_G_SHIFT);
}
void hvf_put_xsave(CPUState *cpu_state)
{
struct X86XSaveArea *xsave;
xsave = X86_CPU(cpu_state)->env.kvm_xsave_buf;
x86_cpu_xsave_all_areas(X86_CPU(cpu_state), xsave);
if (hv_vcpu_write_fpstate(cpu_state->hvf_fd, (void*)xsave, 4096)) {
abort();
}
}
void hvf_put_segments(CPUState *cpu_state)
{
CPUX86State *env = &X86_CPU(cpu_state)->env;
struct vmx_segment seg;
wvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_LIMIT, env->idt.limit);
wvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_BASE, env->idt.base);
wvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_LIMIT, env->gdt.limit);
wvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_BASE, env->gdt.base);
/* wvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR2, env->cr[2]); */
wvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR3, env->cr[3]);
vmx_update_tpr(cpu_state);
wvmcs(cpu_state->hvf_fd, VMCS_GUEST_IA32_EFER, env->efer);
macvm_set_cr4(cpu_state->hvf_fd, env->cr[4]);
macvm_set_cr0(cpu_state->hvf_fd, env->cr[0]);
hvf_set_segment(cpu_state, &seg, &env->segs[R_CS], false);
vmx_write_segment_descriptor(cpu_state, &seg, R_CS);
hvf_set_segment(cpu_state, &seg, &env->segs[R_DS], false);
vmx_write_segment_descriptor(cpu_state, &seg, R_DS);
hvf_set_segment(cpu_state, &seg, &env->segs[R_ES], false);
vmx_write_segment_descriptor(cpu_state, &seg, R_ES);
hvf_set_segment(cpu_state, &seg, &env->segs[R_SS], false);
vmx_write_segment_descriptor(cpu_state, &seg, R_SS);
hvf_set_segment(cpu_state, &seg, &env->segs[R_FS], false);
vmx_write_segment_descriptor(cpu_state, &seg, R_FS);
hvf_set_segment(cpu_state, &seg, &env->segs[R_GS], false);
vmx_write_segment_descriptor(cpu_state, &seg, R_GS);
hvf_set_segment(cpu_state, &seg, &env->tr, true);
vmx_write_segment_descriptor(cpu_state, &seg, R_TR);
hvf_set_segment(cpu_state, &seg, &env->ldt, false);
vmx_write_segment_descriptor(cpu_state, &seg, R_LDTR);
hv_vcpu_flush(cpu_state->hvf_fd);
}
void hvf_put_msrs(CPUState *cpu_state)
{
CPUX86State *env = &X86_CPU(cpu_state)->env;
hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_CS,
env->sysenter_cs);
hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_ESP,
env->sysenter_esp);
hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_EIP,
env->sysenter_eip);
hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_STAR, env->star);
#ifdef TARGET_X86_64
hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_CSTAR, env->cstar);
hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_KERNELGSBASE, env->kernelgsbase);
hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_FMASK, env->fmask);
hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_LSTAR, env->lstar);
#endif
hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_GSBASE, env->segs[R_GS].base);
hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_FSBASE, env->segs[R_FS].base);
/* if (!osx_is_sierra())
wvmcs(cpu_state->hvf_fd, VMCS_TSC_OFFSET, env->tsc - rdtscp());*/
hv_vm_sync_tsc(env->tsc);
}
void hvf_get_xsave(CPUState *cpu_state)
{
struct X86XSaveArea *xsave;
xsave = X86_CPU(cpu_state)->env.kvm_xsave_buf;
if (hv_vcpu_read_fpstate(cpu_state->hvf_fd, (void*)xsave, 4096)) {
abort();
}
x86_cpu_xrstor_all_areas(X86_CPU(cpu_state), xsave);
}
void hvf_get_segments(CPUState *cpu_state)
{
CPUX86State *env = &X86_CPU(cpu_state)->env;
struct vmx_segment seg;
env->interrupt_injected = -1;
vmx_read_segment_descriptor(cpu_state, &seg, R_CS);
hvf_get_segment(&env->segs[R_CS], &seg);
vmx_read_segment_descriptor(cpu_state, &seg, R_DS);
hvf_get_segment(&env->segs[R_DS], &seg);
vmx_read_segment_descriptor(cpu_state, &seg, R_ES);
hvf_get_segment(&env->segs[R_ES], &seg);
vmx_read_segment_descriptor(cpu_state, &seg, R_FS);
hvf_get_segment(&env->segs[R_FS], &seg);
vmx_read_segment_descriptor(cpu_state, &seg, R_GS);
hvf_get_segment(&env->segs[R_GS], &seg);
vmx_read_segment_descriptor(cpu_state, &seg, R_SS);
hvf_get_segment(&env->segs[R_SS], &seg);
vmx_read_segment_descriptor(cpu_state, &seg, R_TR);
hvf_get_segment(&env->tr, &seg);
vmx_read_segment_descriptor(cpu_state, &seg, R_LDTR);
hvf_get_segment(&env->ldt, &seg);
env->idt.limit = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_LIMIT);
env->idt.base = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_BASE);
env->gdt.limit = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_LIMIT);
env->gdt.base = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_BASE);
env->cr[0] = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR0);
env->cr[2] = 0;
env->cr[3] = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR3);
env->cr[4] = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR4);
env->efer = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_IA32_EFER);
}
void hvf_get_msrs(CPUState *cpu_state)
{
CPUX86State *env = &X86_CPU(cpu_state)->env;
uint64_t tmp;
hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_CS, &tmp);
env->sysenter_cs = tmp;
hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_ESP, &tmp);
env->sysenter_esp = tmp;
hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_EIP, &tmp);
env->sysenter_eip = tmp;
hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_STAR, &env->star);
#ifdef TARGET_X86_64
hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_CSTAR, &env->cstar);
hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_KERNELGSBASE, &env->kernelgsbase);
hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_FMASK, &env->fmask);
hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_LSTAR, &env->lstar);
#endif
hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_APICBASE, &tmp);
env->tsc = rdtscp() + rvmcs(cpu_state->hvf_fd, VMCS_TSC_OFFSET);
}
int hvf_put_registers(CPUState *cpu_state)
{
X86CPU *x86cpu = X86_CPU(cpu_state);
CPUX86State *env = &x86cpu->env;
wreg(cpu_state->hvf_fd, HV_X86_RAX, env->regs[R_EAX]);
wreg(cpu_state->hvf_fd, HV_X86_RBX, env->regs[R_EBX]);
wreg(cpu_state->hvf_fd, HV_X86_RCX, env->regs[R_ECX]);
wreg(cpu_state->hvf_fd, HV_X86_RDX, env->regs[R_EDX]);
wreg(cpu_state->hvf_fd, HV_X86_RBP, env->regs[R_EBP]);
wreg(cpu_state->hvf_fd, HV_X86_RSP, env->regs[R_ESP]);
wreg(cpu_state->hvf_fd, HV_X86_RSI, env->regs[R_ESI]);
wreg(cpu_state->hvf_fd, HV_X86_RDI, env->regs[R_EDI]);
wreg(cpu_state->hvf_fd, HV_X86_R8, env->regs[8]);
wreg(cpu_state->hvf_fd, HV_X86_R9, env->regs[9]);
wreg(cpu_state->hvf_fd, HV_X86_R10, env->regs[10]);
wreg(cpu_state->hvf_fd, HV_X86_R11, env->regs[11]);
wreg(cpu_state->hvf_fd, HV_X86_R12, env->regs[12]);
wreg(cpu_state->hvf_fd, HV_X86_R13, env->regs[13]);
wreg(cpu_state->hvf_fd, HV_X86_R14, env->regs[14]);
wreg(cpu_state->hvf_fd, HV_X86_R15, env->regs[15]);
wreg(cpu_state->hvf_fd, HV_X86_RFLAGS, env->eflags);
wreg(cpu_state->hvf_fd, HV_X86_RIP, env->eip);
wreg(cpu_state->hvf_fd, HV_X86_XCR0, env->xcr0);
hvf_put_xsave(cpu_state);
hvf_put_segments(cpu_state);
hvf_put_msrs(cpu_state);
wreg(cpu_state->hvf_fd, HV_X86_DR0, env->dr[0]);
wreg(cpu_state->hvf_fd, HV_X86_DR1, env->dr[1]);
wreg(cpu_state->hvf_fd, HV_X86_DR2, env->dr[2]);
wreg(cpu_state->hvf_fd, HV_X86_DR3, env->dr[3]);
wreg(cpu_state->hvf_fd, HV_X86_DR4, env->dr[4]);
wreg(cpu_state->hvf_fd, HV_X86_DR5, env->dr[5]);
wreg(cpu_state->hvf_fd, HV_X86_DR6, env->dr[6]);
wreg(cpu_state->hvf_fd, HV_X86_DR7, env->dr[7]);
return 0;
}
int hvf_get_registers(CPUState *cpu_state)
{
X86CPU *x86cpu = X86_CPU(cpu_state);
CPUX86State *env = &x86cpu->env;
env->regs[R_EAX] = rreg(cpu_state->hvf_fd, HV_X86_RAX);
env->regs[R_EBX] = rreg(cpu_state->hvf_fd, HV_X86_RBX);
env->regs[R_ECX] = rreg(cpu_state->hvf_fd, HV_X86_RCX);
env->regs[R_EDX] = rreg(cpu_state->hvf_fd, HV_X86_RDX);
env->regs[R_EBP] = rreg(cpu_state->hvf_fd, HV_X86_RBP);
env->regs[R_ESP] = rreg(cpu_state->hvf_fd, HV_X86_RSP);
env->regs[R_ESI] = rreg(cpu_state->hvf_fd, HV_X86_RSI);
env->regs[R_EDI] = rreg(cpu_state->hvf_fd, HV_X86_RDI);
env->regs[8] = rreg(cpu_state->hvf_fd, HV_X86_R8);
env->regs[9] = rreg(cpu_state->hvf_fd, HV_X86_R9);
env->regs[10] = rreg(cpu_state->hvf_fd, HV_X86_R10);
env->regs[11] = rreg(cpu_state->hvf_fd, HV_X86_R11);
env->regs[12] = rreg(cpu_state->hvf_fd, HV_X86_R12);
env->regs[13] = rreg(cpu_state->hvf_fd, HV_X86_R13);
env->regs[14] = rreg(cpu_state->hvf_fd, HV_X86_R14);
env->regs[15] = rreg(cpu_state->hvf_fd, HV_X86_R15);
env->eflags = rreg(cpu_state->hvf_fd, HV_X86_RFLAGS);
env->eip = rreg(cpu_state->hvf_fd, HV_X86_RIP);
hvf_get_xsave(cpu_state);
env->xcr0 = rreg(cpu_state->hvf_fd, HV_X86_XCR0);
hvf_get_segments(cpu_state);
hvf_get_msrs(cpu_state);
env->dr[0] = rreg(cpu_state->hvf_fd, HV_X86_DR0);
env->dr[1] = rreg(cpu_state->hvf_fd, HV_X86_DR1);
env->dr[2] = rreg(cpu_state->hvf_fd, HV_X86_DR2);
env->dr[3] = rreg(cpu_state->hvf_fd, HV_X86_DR3);
env->dr[4] = rreg(cpu_state->hvf_fd, HV_X86_DR4);
env->dr[5] = rreg(cpu_state->hvf_fd, HV_X86_DR5);
env->dr[6] = rreg(cpu_state->hvf_fd, HV_X86_DR6);
env->dr[7] = rreg(cpu_state->hvf_fd, HV_X86_DR7);
return 0;
}
static void vmx_set_int_window_exiting(CPUState *cpu)
{
uint64_t val;
val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS);
wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val |
VMCS_PRI_PROC_BASED_CTLS_INT_WINDOW_EXITING);
}
void vmx_clear_int_window_exiting(CPUState *cpu)
{
uint64_t val;
val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS);
wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val &
~VMCS_PRI_PROC_BASED_CTLS_INT_WINDOW_EXITING);
}
#define NMI_VEC 2
bool hvf_inject_interrupts(CPUState *cpu_state)
{
X86CPU *x86cpu = X86_CPU(cpu_state);
CPUX86State *env = &x86cpu->env;
uint8_t vector;
uint64_t intr_type;
bool have_event = true;
if (env->interrupt_injected != -1) {
vector = env->interrupt_injected;
intr_type = VMCS_INTR_T_SWINTR;
} else if (env->exception_injected != -1) {
vector = env->exception_injected;
if (vector == EXCP03_INT3 || vector == EXCP04_INTO) {
intr_type = VMCS_INTR_T_SWEXCEPTION;
} else {
intr_type = VMCS_INTR_T_HWEXCEPTION;
}
} else if (env->nmi_injected) {
vector = NMI_VEC;
intr_type = VMCS_INTR_T_NMI;
} else {
have_event = false;
}
uint64_t info = 0;
if (have_event) {
info = vector | intr_type | VMCS_INTR_VALID;
uint64_t reason = rvmcs(cpu_state->hvf_fd, VMCS_EXIT_REASON);
if (env->nmi_injected && reason != EXIT_REASON_TASK_SWITCH) {
vmx_clear_nmi_blocking(cpu_state);
}
if (!(env->hflags2 & HF2_NMI_MASK) || intr_type != VMCS_INTR_T_NMI) {
info &= ~(1 << 12); /* clear undefined bit */
if (intr_type == VMCS_INTR_T_SWINTR ||
intr_type == VMCS_INTR_T_SWEXCEPTION) {
wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INST_LENGTH, env->ins_len);
}
if (env->has_error_code) {
wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_EXCEPTION_ERROR,
env->error_code);
}
/*printf("reinject %lx err %d\n", info, err);*/
wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INTR_INFO, info);
};
}
if (cpu_state->interrupt_request & CPU_INTERRUPT_NMI) {
if (!(env->hflags2 & HF2_NMI_MASK) && !(info & VMCS_INTR_VALID)) {
cpu_state->interrupt_request &= ~CPU_INTERRUPT_NMI;
info = VMCS_INTR_VALID | VMCS_INTR_T_NMI | NMI_VEC;
wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INTR_INFO, info);
} else {
vmx_set_nmi_window_exiting(cpu_state);
}
}
if (!(env->hflags & HF_INHIBIT_IRQ_MASK) &&
(cpu_state->interrupt_request & CPU_INTERRUPT_HARD) &&
(EFLAGS(env) & IF_MASK) && !(info & VMCS_INTR_VALID)) {
int line = cpu_get_pic_interrupt(&x86cpu->env);
cpu_state->interrupt_request &= ~CPU_INTERRUPT_HARD;
if (line >= 0) {
wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INTR_INFO, line |
VMCS_INTR_VALID | VMCS_INTR_T_HWINTR);
}
}
if (cpu_state->interrupt_request & CPU_INTERRUPT_HARD) {
vmx_set_int_window_exiting(cpu_state);
}
return (cpu_state->interrupt_request
& (CPU_INTERRUPT_INIT | CPU_INTERRUPT_TPR));
}
int hvf_process_events(CPUState *cpu_state)
{
X86CPU *cpu = X86_CPU(cpu_state);
CPUX86State *env = &cpu->env;
EFLAGS(env) = rreg(cpu_state->hvf_fd, HV_X86_RFLAGS);
if (cpu_state->interrupt_request & CPU_INTERRUPT_INIT) {
hvf_cpu_synchronize_state(cpu_state);
do_cpu_init(cpu);
}
if (cpu_state->interrupt_request & CPU_INTERRUPT_POLL) {
cpu_state->interrupt_request &= ~CPU_INTERRUPT_POLL;
apic_poll_irq(cpu->apic_state);
}
if (((cpu_state->interrupt_request & CPU_INTERRUPT_HARD) &&
(EFLAGS(env) & IF_MASK)) ||
(cpu_state->interrupt_request & CPU_INTERRUPT_NMI)) {
cpu_state->halted = 0;
}
if (cpu_state->interrupt_request & CPU_INTERRUPT_SIPI) {
hvf_cpu_synchronize_state(cpu_state);
do_cpu_sipi(cpu);
}
if (cpu_state->interrupt_request & CPU_INTERRUPT_TPR) {
cpu_state->interrupt_request &= ~CPU_INTERRUPT_TPR;
hvf_cpu_synchronize_state(cpu_state);
apic_handle_tpr_access_report(cpu->apic_state, env->eip,
env->tpr_access_type);
}
return cpu_state->halted;
}

39
target/i386/hvf/x86hvf.h Normal file
View file

@ -0,0 +1,39 @@
/*
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Google Inc,
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#ifndef X86HVF_H
#define X86HVF_H
#include "cpu.h"
#include "x86_descr.h"
int hvf_process_events(CPUState *);
int hvf_put_registers(CPUState *);
int hvf_get_registers(CPUState *);
bool hvf_inject_interrupts(CPUState *);
void hvf_set_segment(struct CPUState *cpu, struct vmx_segment *vmx_seg,
SegmentCache *qseg, bool is_tr);
void hvf_get_segment(SegmentCache *qseg, struct vmx_segment *vmx_seg);
void hvf_put_xsave(CPUState *cpu_state);
void hvf_put_segments(CPUState *cpu_state);
void hvf_put_msrs(CPUState *cpu_state);
void hvf_get_xsave(CPUState *cpu_state);
void hvf_get_msrs(CPUState *cpu_state);
void vmx_clear_int_window_exiting(CPUState *cpu);
void hvf_get_segments(CPUState *cpu_state);
void vmx_update_tpr(CPUState *cpu);
void hvf_cpu_synchronize_state(CPUState *cpu_state);
#endif

2
target/i386/kvm.c
View file

@ -1038,8 +1038,6 @@ void kvm_arch_reset_vcpu(X86CPU *cpu)
{
CPUX86State *env = &cpu->env;
env->exception_injected = -1;
env->interrupt_injected = -1;
env->xcr0 = 1;
if (kvm_irqchip_in_kernel()) {
env->mp_state = cpu_is_bsp(cpu) ? KVM_MP_STATE_RUNNABLE :