Now that Apple Silicon is widely available, people are obviously excited to try and run virtualized workloads on them, such as Linux and Windows. This patch set implements a rudimentary, first version to get the ball going on that. With this applied, I can successfully run both Linux and Windows as guests, albeit with a few caveats: * no WFI emulation, a vCPU always uses 100% * vtimer handling is a bit hacky * we handle most sysregs flying blindly, just returning 0 * XHCI breaks in OVMF, works in Linux+Windows Despite those drawbacks, it's still an exciting place to start playing with the power of Apple Silicon. Enjoy! Alex Alexander Graf (8): hvf: Add hypervisor entitlement to output binaries hvf: Move common code out arm: Set PSCI to 0.2 for HVF arm: Synchronize CPU on PSCI on hvf: Add Apple Silicon support hvf: Use OS provided vcpu kick function arm: Add Hypervisor.framework build target hw/arm/virt: Disable highmem when on hypervisor.framework MAINTAINERS | 14 +- accel/hvf/entitlements.plist | 8 + accel/hvf/hvf-all.c | 56 ++++ accel/hvf/hvf-cpus.c | 484 +++++++++++++++++++++++++++++++++++ accel/hvf/meson.build | 7 + accel/meson.build | 1 + hw/arm/virt.c | 9 + include/hw/core/cpu.h | 3 +- include/sysemu/hvf_int.h | 69 +++++ meson.build | 39 ++- scripts/entitlement.sh | 11 + target/arm/arm-powerctl.c | 3 + target/arm/cpu.c | 4 + target/arm/hvf/hvf.c | 345 +++++++++++++++++++++++++ target/arm/hvf/meson.build | 3 + target/arm/meson.build | 2 + target/i386/hvf/hvf-cpus.c | 131 ---------- target/i386/hvf/hvf-cpus.h | 25 -- target/i386/hvf/hvf-i386.h | 48 +--- target/i386/hvf/hvf.c | 360 +------------------------- target/i386/hvf/meson.build | 1 - target/i386/hvf/x86hvf.c | 11 +- target/i386/hvf/x86hvf.h | 2 - 23 files changed, 1061 insertions(+), 575 deletions(-) create mode 100644 accel/hvf/entitlements.plist create mode 100644 accel/hvf/hvf-all.c create mode 100644 accel/hvf/hvf-cpus.c create mode 100644 accel/hvf/meson.build create mode 100644 include/sysemu/hvf_int.h create mode 100755 scripts/entitlement.sh create mode 100644 target/arm/hvf/hvf.c create mode 100644 target/arm/hvf/meson.build delete mode 100644 target/i386/hvf/hvf-cpus.c delete mode 100644 target/i386/hvf/hvf-cpus.h -- 2.24.3 (Apple Git-128) In macOS 11, QEMU only gets access to Hypervisor.framework if it has the respective entitlement. Add an entitlement template and automatically self sign and apply the entitlement in the build. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- accel/hvf/entitlements.plist | 8 ++++++++ meson.build | 30 ++++++++++++++++++++++++++---- scripts/entitlement.sh | 11 +++++++++++ 3 files changed, 45 insertions(+), 4 deletions(-) create mode 100644 accel/hvf/entitlements.plist create mode 100755 scripts/entitlement.sh diff --git a/accel/hvf/entitlements.plist b/accel/hvf/entitlements.plist new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/accel/hvf/entitlements.plist @@ -XXX,XX +XXX,XX @@ +<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd"> +<plist version="1.0"> +<dict> + <key>com.apple.security.hypervisor</key> + <true/> +</dict> +</plist> diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ foreach target : target_dirs }] endif foreach exe: execs - emulators += {exe['name']: - executable(exe['name'], exe['sources'], - install: true, + exe_name = exe['name'] + exe_sign = 'CONFIG_HVF' in config_target + if exe_sign + exe_name += '-unsigned' + endif + + emulator = executable(exe_name, exe['sources'], + install: not exe_sign, c_args: c_args, dependencies: arch_deps + deps + exe['dependencies'], objects: lib.extract_all_objects(recursive: true), @@ -XXX,XX +XXX,XX @@ foreach target : target_dirs link_depends: [block_syms, qemu_syms] + exe.get('link_depends', []), link_args: link_args, gui_app: exe['gui']) - } + + if exe_sign + exe_full = meson.current_build_dir() / exe['name'] + emulators += {exe['name'] : custom_target(exe['name'], + install: true, + install_dir: get_option('bindir'), + depends: emulator, + output: exe['name'], + command: [ + meson.current_source_dir() / 'scripts/entitlement.sh', + meson.current_build_dir() / exe['name'] + '-unsigned', + meson.current_build_dir() / exe['name'], + meson.current_source_dir() / 'accel/hvf/entitlements.plist' + ]) + } + else + emulators += {exe['name']: emulator} + endif if 'CONFIG_TRACE_SYSTEMTAP' in config_host foreach stp: [ diff --git a/scripts/entitlement.sh b/scripts/entitlement.sh new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/scripts/entitlement.sh @@ -XXX,XX +XXX,XX @@ +#!/bin/sh -e +# +# Helper script for the build process to apply entitlements + +SRC="$1" +DST="$2" +ENTITLEMENT="$3" + +rm -f "$2" +cp -a "$SRC" "$DST" +codesign --entitlements "$ENTITLEMENT" --force -s - "$DST" -- 2.24.3 (Apple Git-128) Until now, Hypervisor.framework has only been available on x86_64 systems. With Apple Silicon shipping now, it extends its reach to aarch64. To prepare for support for multiple architectures, let's move common code out into its own accel directory. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- MAINTAINERS | 9 +- accel/hvf/hvf-all.c | 56 +++++ accel/hvf/hvf-cpus.c | 468 ++++++++++++++++++++++++++++++++++++ accel/hvf/meson.build | 7 + accel/meson.build | 1 + include/sysemu/hvf_int.h | 69 ++++++ target/i386/hvf/hvf-cpus.c | 131 ---------- target/i386/hvf/hvf-cpus.h | 25 -- target/i386/hvf/hvf-i386.h | 48 +--- target/i386/hvf/hvf.c | 360 +-------------------------- target/i386/hvf/meson.build | 1 - target/i386/hvf/x86hvf.c | 11 +- target/i386/hvf/x86hvf.h | 2 - 13 files changed, 619 insertions(+), 569 deletions(-) create mode 100644 accel/hvf/hvf-all.c create mode 100644 accel/hvf/hvf-cpus.c create mode 100644 accel/hvf/meson.build create mode 100644 include/sysemu/hvf_int.h delete mode 100644 target/i386/hvf/hvf-cpus.c delete mode 100644 target/i386/hvf/hvf-cpus.h diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Cameron Esfahani <dirty@apple.com> M: Roman Bolshakov <r.bolshakov@yadro.com> W: https://wiki.qemu.org/Features/HVF S: Maintained -F: accel/stubs/hvf-stub.c F: target/i386/hvf/ + +HVF +M: Cameron Esfahani <dirty@apple.com> +M: Roman Bolshakov <r.bolshakov@yadro.com> +W: https://wiki.qemu.org/Features/HVF +S: Maintained +F: accel/hvf/ F: include/sysemu/hvf.h +F: include/sysemu/hvf_int.h WHPX CPUs M: Sunil Muthuswamy <sunilmut@microsoft.com> diff --git a/accel/hvf/hvf-all.c b/accel/hvf/hvf-all.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/accel/hvf/hvf-all.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU Hypervisor.framework support + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/error-report.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" +#include "sysemu/runstate.h" + +#include "qemu/main-loop.h" +#include "sysemu/accel.h" + +#include <Hypervisor/Hypervisor.h> + +bool hvf_allowed; +HVFState *hvf_state; + +void assert_hvf_ok(hv_return_t ret) +{ + if (ret == HV_SUCCESS) { + return; + } + + switch (ret) { + case HV_ERROR: + error_report("Error: HV_ERROR"); + break; + case HV_BUSY: + error_report("Error: HV_BUSY"); + break; + case HV_BAD_ARGUMENT: + error_report("Error: HV_BAD_ARGUMENT"); + break; + case HV_NO_RESOURCES: + error_report("Error: HV_NO_RESOURCES"); + break; + case HV_NO_DEVICE: + error_report("Error: HV_NO_DEVICE"); + break; + case HV_UNSUPPORTED: + error_report("Error: HV_UNSUPPORTED"); + break; + default: + error_report("Unknown Error"); + } + + abort(); +} diff --git a/accel/hvf/hvf-cpus.c b/accel/hvf/hvf-cpus.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/accel/hvf/hvf-cpus.c @@ -XXX,XX +XXX,XX @@ +/* + * 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 + * 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/>. + * + * This file contain code under public domain from the hvdos project: + * https://github.com/mist64/hvdos + * + * Parts 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. + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "exec/address-spaces.h" +#include "exec/exec-all.h" +#include "sysemu/cpus.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" +#include "sysemu/runstate.h" +#include "qemu/guest-random.h" + +#include <Hypervisor/Hypervisor.h> + +/* Memory slots */ + +struct mac_slot { + int present; + uint64_t size; + uint64_t gpa_start; + uint64_t gva; +}; + +hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t size) +{ + 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) && + (start + size) > slot->start) { + return slot; + } + } + return NULL; +} + +struct mac_slot mac_slots[32]; + +static int do_hvf_set_memory(hvf_slot *slot, hv_memory_flags_t flags) +{ + struct mac_slot *macslot; + 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; + } + + macslot->present = 1; + macslot->gpa_start = slot->start; + macslot->size = slot->size; + ret = hv_vm_map(slot->mem, slot->start, slot->size, flags); + assert_hvf_ok(ret); + return 0; +} + +static void hvf_set_phys_mem(MemoryRegionSection *section, bool add) +{ + hvf_slot *mem; + MemoryRegion *area = section->mr; + bool writeable = !area->readonly && !area->rom_device; + hv_memory_flags_t flags; + + if (!memory_region_is_ram(area)) { + if (writeable) { + return; + } else if (!memory_region_is_romd(area)) { + /* + * If the memory device is not in romd_mode, then we actually want + * to remove the hvf memory slot so all accesses will trap. + */ + add = false; + } + } + + mem = hvf_find_overlap_slot( + 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, 0)) { + error_report("Failed to reset overlapping slot"); + abort(); + } + } + + if (!add) { + return; + } + + if (area->readonly || + (!memory_region_is_ram(area) && memory_region_is_romd(area))) { + flags = HV_MEMORY_READ | HV_MEMORY_EXEC; + } else { + flags = HV_MEMORY_READ | HV_MEMORY_WRITE | HV_MEMORY_EXEC; + } + + /* 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"); + 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, flags)) { + error_report("Error registering new memory slot"); + abort(); + } +} + +static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on) +{ + hvf_slot *slot; + + slot = hvf_find_overlap_slot( + 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((uintptr_t)slot->start, (size_t)slot->size, + HV_MEMORY_READ); + /* stop tracking region*/ + } else { + slot->flags &= ~HVF_SLOT_LOG; + hv_vm_protect((uintptr_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, +}; + +static void do_hvf_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg) +{ + if (!cpu->vcpu_dirty) { + hvf_get_registers(cpu); + cpu->vcpu_dirty = true; + } +} + +static void hvf_cpu_synchronize_state(CPUState *cpu) +{ + if (!cpu->vcpu_dirty) { + run_on_cpu(cpu, do_hvf_cpu_synchronize_state, RUN_ON_CPU_NULL); + } +} + +static void do_hvf_cpu_synchronize_post_reset(CPUState *cpu, + run_on_cpu_data arg) +{ + hvf_put_registers(cpu); + cpu->vcpu_dirty = false; +} + +static void hvf_cpu_synchronize_post_reset(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_post_reset, RUN_ON_CPU_NULL); +} + +static void do_hvf_cpu_synchronize_post_init(CPUState *cpu, + run_on_cpu_data arg) +{ + hvf_put_registers(cpu); + cpu->vcpu_dirty = false; +} + +static void hvf_cpu_synchronize_post_init(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_post_init, RUN_ON_CPU_NULL); +} + +static void do_hvf_cpu_synchronize_pre_loadvm(CPUState *cpu, + run_on_cpu_data arg) +{ + cpu->vcpu_dirty = true; +} + +static void hvf_cpu_synchronize_pre_loadvm(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_pre_loadvm, RUN_ON_CPU_NULL); +} + +static void hvf_vcpu_destroy(CPUState *cpu) +{ + hv_return_t ret = hv_vcpu_destroy(cpu->hvf_fd); + assert_hvf_ok(ret); + + hvf_arch_vcpu_destroy(cpu); +} + +static void dummy_signal(int sig) +{ +} + +static int hvf_init_vcpu(CPUState *cpu) +{ + 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); + +#ifdef __aarch64__ + r = hv_vcpu_create(&cpu->hvf_fd, (hv_vcpu_exit_t **)&cpu->hvf_exit, NULL); +#else + r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf_fd, HV_VCPU_DEFAULT); +#endif + cpu->vcpu_dirty = 1; + assert_hvf_ok(r); + + return hvf_arch_init_vcpu(cpu); +} + +/* + * The HVF-specific vCPU thread function. This one should only run when the host + * CPU supports the VMX "unrestricted guest" feature. + */ +static void *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_thread_signal_created(cpu); + qemu_guest_random_seed_thread_part2(cpu->random_seed); + + do { + if (cpu_can_run(cpu)) { + r = hvf_vcpu_exec(cpu); + if (r == EXCP_DEBUG) { + cpu_handle_guest_debug(cpu); + } + } + qemu_wait_io_event(cpu); + } while (!cpu->unplug || cpu_can_run(cpu)); + + hvf_vcpu_destroy(cpu); + cpu_thread_signal_destroyed(cpu); + qemu_mutex_unlock_iothread(); + rcu_unregister_thread(); + return NULL; +} + +static void hvf_start_vcpu_thread(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, hvf_cpu_thread_fn, + cpu, QEMU_THREAD_JOINABLE); +} + +static const CpusAccel hvf_cpus = { + .create_vcpu_thread = hvf_start_vcpu_thread, + + .synchronize_post_reset = hvf_cpu_synchronize_post_reset, + .synchronize_post_init = hvf_cpu_synchronize_post_init, + .synchronize_state = hvf_cpu_synchronize_state, + .synchronize_pre_loadvm = hvf_cpu_synchronize_pre_loadvm, +}; + +static int hvf_accel_init(MachineState *ms) +{ + int x; + hv_return_t ret; + HVFState *s; + + 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; + memory_listener_register(&hvf_memory_listener, &address_space_memory); + cpus_register_accel(&hvf_cpus); + 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); diff --git a/accel/hvf/meson.build b/accel/hvf/meson.build new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/accel/hvf/meson.build @@ -XXX,XX +XXX,XX @@ +hvf_ss = ss.source_set() +hvf_ss.add(files( + 'hvf-all.c', + 'hvf-cpus.c', +)) + +specific_ss.add_all(when: 'CONFIG_HVF', if_true: hvf_ss) diff --git a/accel/meson.build b/accel/meson.build index XXXXXXX..XXXXXXX 100644 --- a/accel/meson.build +++ b/accel/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(files('accel.c')) +subdir('hvf') subdir('qtest') subdir('kvm') subdir('tcg') diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/sysemu/hvf_int.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU Hypervisor.framework (HVF) support + * + * 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 HVF-specific code */ + +#ifndef HVF_INT_H +#define HVF_INT_H + +#include <Hypervisor/Hypervisor.h> + +#define HVF_MAX_VCPU 0x10 + +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; +}; + +/* 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; + +struct HVFState { + AccelState parent; + hvf_slot slots[32]; + int num_slots; + + hvf_vcpu_caps *hvf_caps; +}; +extern HVFState *hvf_state; + +void assert_hvf_ok(hv_return_t ret); +int hvf_get_registers(CPUState *cpu); +int hvf_put_registers(CPUState *cpu); +int hvf_arch_init_vcpu(CPUState *cpu); +void hvf_arch_vcpu_destroy(CPUState *cpu); +int hvf_vcpu_exec(CPUState *cpu); +hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t); + +#endif diff --git a/target/i386/hvf/hvf-cpus.c b/target/i386/hvf/hvf-cpus.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/target/i386/hvf/hvf-cpus.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * 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 - * 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/>. - * - * This file contain code under public domain from the hvdos project: - * https://github.com/mist64/hvdos - * - * Parts 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. - */ - -#include "qemu/osdep.h" -#include "qemu/error-report.h" -#include "qemu/main-loop.h" -#include "sysemu/hvf.h" -#include "sysemu/runstate.h" -#include "target/i386/cpu.h" -#include "qemu/guest-random.h" - -#include "hvf-cpus.h" - -/* - * The HVF-specific vCPU thread function. This one should only run when the host - * CPU supports the VMX "unrestricted guest" feature. - */ -static void *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_thread_signal_created(cpu); - qemu_guest_random_seed_thread_part2(cpu->random_seed); - - do { - if (cpu_can_run(cpu)) { - r = hvf_vcpu_exec(cpu); - if (r == EXCP_DEBUG) { - cpu_handle_guest_debug(cpu); - } - } - qemu_wait_io_event(cpu); - } while (!cpu->unplug || cpu_can_run(cpu)); - - hvf_vcpu_destroy(cpu); - cpu_thread_signal_destroyed(cpu); - qemu_mutex_unlock_iothread(); - rcu_unregister_thread(); - return NULL; -} - -static void hvf_start_vcpu_thread(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, hvf_cpu_thread_fn, - cpu, QEMU_THREAD_JOINABLE); -} - -const CpusAccel hvf_cpus = { - .create_vcpu_thread = hvf_start_vcpu_thread, - - .synchronize_post_reset = hvf_cpu_synchronize_post_reset, - .synchronize_post_init = hvf_cpu_synchronize_post_init, - .synchronize_state = hvf_cpu_synchronize_state, - .synchronize_pre_loadvm = hvf_cpu_synchronize_pre_loadvm, -}; diff --git a/target/i386/hvf/hvf-cpus.h b/target/i386/hvf/hvf-cpus.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/target/i386/hvf/hvf-cpus.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Accelerator CPUS Interface - * - * Copyright 2020 SUSE LLC - * - * 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_CPUS_H -#define HVF_CPUS_H - -#include "sysemu/cpus.h" - -extern const CpusAccel hvf_cpus; - -int hvf_init_vcpu(CPUState *); -int hvf_vcpu_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_pre_loadvm(CPUState *); -void hvf_vcpu_destroy(CPUState *); - -#endif /* HVF_CPUS_H */ diff --git a/target/i386/hvf/hvf-i386.h b/target/i386/hvf/hvf-i386.h index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/hvf-i386.h +++ b/target/i386/hvf/hvf-i386.h @@ -XXX,XX +XXX,XX @@ #include "sysemu/accel.h" #include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" #include "cpu.h" #include "x86.h" -#define HVF_MAX_VCPU 0x10 - -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; -}; - -/* 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; - -struct HVFState { - AccelState parent; - hvf_slot slots[32]; - int num_slots; - - hvf_vcpu_caps *hvf_caps; -}; -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); #ifdef NEED_CPU_H /* Functions exported to host specific mode */ diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/hvf.c +++ b/target/i386/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" #include "sysemu/runstate.h" #include "hvf-i386.h" #include "vmcs.h" @@ -XXX,XX +XXX,XX @@ #include "sysemu/accel.h" #include "target/i386/cpu.h" -#include "hvf-cpus.h" - -HVFState *hvf_state; - -static void assert_hvf_ok(hv_return_t ret) -{ - if (ret == HV_SUCCESS) { - return; - } - - switch (ret) { - case HV_ERROR: - error_report("Error: HV_ERROR"); - break; - case HV_BUSY: - error_report("Error: HV_BUSY"); - break; - case HV_BAD_ARGUMENT: - error_report("Error: HV_BAD_ARGUMENT"); - break; - case HV_NO_RESOURCES: - error_report("Error: HV_NO_RESOURCES"); - break; - case HV_NO_DEVICE: - error_report("Error: HV_NO_DEVICE"); - break; - case HV_UNSUPPORTED: - error_report("Error: HV_UNSUPPORTED"); - break; - default: - error_report("Unknown Error"); - } - - abort(); -} - -/* Memory slots */ -hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t size) -{ - 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) && - (start + size) > 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]; - -static int do_hvf_set_memory(hvf_slot *slot, hv_memory_flags_t flags) -{ - struct mac_slot *macslot; - 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; - } - - 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; - bool writeable = !area->readonly && !area->rom_device; - hv_memory_flags_t flags; - - if (!memory_region_is_ram(area)) { - if (writeable) { - return; - } else if (!memory_region_is_romd(area)) { - /* - * If the memory device is not in romd_mode, then we actually want - * to remove the hvf memory slot so all accesses will trap. - */ - add = false; - } - } - - mem = hvf_find_overlap_slot( - 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, 0)) { - error_report("Failed to reset overlapping slot"); - abort(); - } - } - - if (!add) { - return; - } - - if (area->readonly || - (!memory_region_is_ram(area) && memory_region_is_romd(area))) { - flags = HV_MEMORY_READ | HV_MEMORY_EXEC; - } else { - flags = HV_MEMORY_READ | HV_MEMORY_WRITE | HV_MEMORY_EXEC; - } - - /* 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"); - 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, flags)) { - error_report("Error registering new memory slot"); - abort(); - } -} - void vmx_update_tpr(CPUState *cpu) { /* TODO: need integrate APIC handling */ @@ -XXX,XX +XXX,XX @@ void hvf_handle_io(CPUArchState *env, uint16_t port, void *buffer, } } -static void do_hvf_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg) -{ - if (!cpu->vcpu_dirty) { - hvf_get_registers(cpu); - cpu->vcpu_dirty = true; - } -} - -void hvf_cpu_synchronize_state(CPUState *cpu) -{ - if (!cpu->vcpu_dirty) { - run_on_cpu(cpu, do_hvf_cpu_synchronize_state, RUN_ON_CPU_NULL); - } -} - -static void do_hvf_cpu_synchronize_post_reset(CPUState *cpu, - run_on_cpu_data arg) -{ - hvf_put_registers(cpu); - cpu->vcpu_dirty = false; -} - -void hvf_cpu_synchronize_post_reset(CPUState *cpu) -{ - run_on_cpu(cpu, do_hvf_cpu_synchronize_post_reset, RUN_ON_CPU_NULL); -} - -static void do_hvf_cpu_synchronize_post_init(CPUState *cpu, - run_on_cpu_data arg) -{ - hvf_put_registers(cpu); - cpu->vcpu_dirty = false; -} - -void hvf_cpu_synchronize_post_init(CPUState *cpu) -{ - run_on_cpu(cpu, do_hvf_cpu_synchronize_post_init, RUN_ON_CPU_NULL); -} - -static void do_hvf_cpu_synchronize_pre_loadvm(CPUState *cpu, - run_on_cpu_data arg) -{ - cpu->vcpu_dirty = true; -} - -void hvf_cpu_synchronize_pre_loadvm(CPUState *cpu) -{ - run_on_cpu(cpu, do_hvf_cpu_synchronize_pre_loadvm, RUN_ON_CPU_NULL); -} - static bool ept_emulation_fault(hvf_slot *slot, uint64_t gpa, uint64_t ept_qual) { int read, write; @@ -XXX,XX +XXX,XX @@ static bool ept_emulation_fault(hvf_slot *slot, uint64_t gpa, uint64_t ept_qual) return false; } -static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on) -{ - hvf_slot *slot; - - slot = hvf_find_overlap_slot( - 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_vcpu_destroy(CPUState *cpu) +void hvf_arch_vcpu_destroy(CPUState *cpu) { X86CPU *x86_cpu = X86_CPU(cpu); CPUX86State *env = &x86_cpu->env; - hv_return_t ret = hv_vcpu_destroy((hv_vcpuid_t)cpu->hvf_fd); g_free(env->hvf_mmio_buf); - assert_hvf_ok(ret); -} - -static void dummy_signal(int sig) -{ } -int hvf_init_vcpu(CPUState *cpu) +int hvf_arch_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(); @@ -XXX,XX +XXX,XX @@ int hvf_init_vcpu(CPUState *cpu) hvf_state->hvf_caps = g_new0(struct hvf_vcpu_caps, 1); env->hvf_mmio_buf = g_new(char, 4096); - 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(); @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) return ret; } - -bool hvf_allowed; - -static int hvf_accel_init(MachineState *ms) -{ - int x; - hv_return_t ret; - HVFState *s; - - 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; - memory_listener_register(&hvf_memory_listener, &address_space_memory); - cpus_register_accel(&hvf_cpus); - 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); diff --git a/target/i386/hvf/meson.build b/target/i386/hvf/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/meson.build +++ b/target/i386/hvf/meson.build @@ -XXX,XX +XXX,XX @@ i386_softmmu_ss.add(when: [hvf, 'CONFIG_HVF'], if_true: files( 'hvf.c', - 'hvf-cpus.c', 'x86.c', 'x86_cpuid.c', 'x86_decode.c', diff --git a/target/i386/hvf/x86hvf.c b/target/i386/hvf/x86hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/x86hvf.c +++ b/target/i386/hvf/x86hvf.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qemu-common.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" +#include "sysemu/hw_accel.h" #include "x86hvf.h" #include "vmx.h" #include "vmcs.h" @@ -XXX,XX +XXX,XX @@ #include <Hypervisor/hv.h> #include <Hypervisor/hv_vmx.h> -#include "hvf-cpus.h" - void hvf_set_segment(struct CPUState *cpu, struct vmx_segment *vmx_seg, SegmentCache *qseg, bool is_tr) { @@ -XXX,XX +XXX,XX @@ int hvf_process_events(CPUState *cpu_state) env->eflags = rreg(cpu_state->hvf_fd, HV_X86_RFLAGS); if (cpu_state->interrupt_request & CPU_INTERRUPT_INIT) { - hvf_cpu_synchronize_state(cpu_state); + cpu_synchronize_state(cpu_state); do_cpu_init(cpu); } @@ -XXX,XX +XXX,XX @@ int hvf_process_events(CPUState *cpu_state) cpu_state->halted = 0; } if (cpu_state->interrupt_request & CPU_INTERRUPT_SIPI) { - hvf_cpu_synchronize_state(cpu_state); + 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); + cpu_synchronize_state(cpu_state); apic_handle_tpr_access_report(cpu->apic_state, env->eip, env->tpr_access_type); } diff --git a/target/i386/hvf/x86hvf.h b/target/i386/hvf/x86hvf.h index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/x86hvf.h +++ b/target/i386/hvf/x86hvf.h @@ -XXX,XX +XXX,XX @@ #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); -- 2.24.3 (Apple Git-128) In Hypervisor.framework, we just pass PSCI calls straight on to the QEMU emulation of it. That means, if TCG is compatible with PSCI 0.2, so are we. Let's transpose that fact in code too. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- target/arm/cpu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_initfn(Object *obj) if (tcg_enabled()) { cpu->psci_version = 2; /* TCG implements PSCI 0.2 */ } + + if (hvf_enabled()) { + cpu->psci_version = 2; /* HVF uses TCG's PSCI */ + } } static Property arm_cpu_gt_cntfrq_property = -- 2.24.3 (Apple Git-128) We are going to reuse the TCG PSCI code for HVF. This however means that we need to ensure that CPU register state is synchronized properly between the two worlds. So let's make sure that at least on the PSCI on call, the secondary core gets to sync its registers after reset, so that changes also propagate. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- target/arm/arm-powerctl.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/target/arm/arm-powerctl.c b/target/arm/arm-powerctl.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/arm-powerctl.c +++ b/target/arm/arm-powerctl.c @@ -XXX,XX +XXX,XX @@ #include "arm-powerctl.h" #include "qemu/log.h" #include "qemu/main-loop.h" +#include "sysemu/hw_accel.h" #ifndef DEBUG_ARM_POWERCTL #define DEBUG_ARM_POWERCTL 0 @@ -XXX,XX +XXX,XX @@ static void arm_set_cpu_on_async_work(CPUState *target_cpu_state, cpu_reset(target_cpu_state); target_cpu_state->halted = 0; + cpu_synchronize_state(target_cpu_state); + if (info->target_aa64) { if ((info->target_el < 3) && arm_feature(&target_cpu->env, ARM_FEATURE_EL3)) { -- 2.24.3 (Apple Git-128) With Apple Silicon available to the masses, it's a good time to add support for driving its virtualization extensions from QEMU. This patch adds all necessary architecture specific code to get basic VMs working. It's still pretty raw, but definitely functional. Known limitations: - Vtimer acknowledgement is hacky - Should implement more sysregs and fault on invalid ones then - WFI handling is missing, need to marry it with vtimer Signed-off-by: Alexander Graf <agraf@csgraf.de> --- MAINTAINERS | 5 + accel/hvf/hvf-cpus.c | 4 + include/hw/core/cpu.h | 3 +- target/arm/hvf/hvf.c | 345 ++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 356 insertions(+), 1 deletion(-) create mode 100644 target/arm/hvf/hvf.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: accel/accel.c F: accel/Makefile.objs F: accel/stubs/Makefile.objs +Apple Silicon HVF CPUs +M: Alexander Graf <agraf@csgraf.de> +S: Maintained +F: target/arm/hvf/ + X86 HVF CPUs M: Cameron Esfahani <dirty@apple.com> M: Roman Bolshakov <r.bolshakov@yadro.com> diff --git a/accel/hvf/hvf-cpus.c b/accel/hvf/hvf-cpus.c index XXXXXXX..XXXXXXX 100644 --- a/accel/hvf/hvf-cpus.c +++ b/accel/hvf/hvf-cpus.c @@ -XXX,XX +XXX,XX @@ #include <Hypervisor/Hypervisor.h> +#ifdef __aarch64__ +#define HV_VM_DEFAULT NULL +#endif + /* Memory slots */ struct mac_slot { diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -XXX,XX +XXX,XX @@ struct CPUState { struct hax_vcpu_state *hax_vcpu; - int hvf_fd; + uint64_t hvf_fd; + void *hvf_exit; /* track IOMMUs whose translations we've cached in the TCG TLB */ GArray *iommu_notifiers; diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU Hypervisor.framework support for Apple Silicon + + * Copyright 2020 Alexander Graf <agraf@csgraf.de> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/error-report.h" + +#include "sysemu/runstate.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" +#include "sysemu/hw_accel.h" + +#include <Hypervisor/Hypervisor.h> + +#include "exec/address-spaces.h" +#include "hw/irq.h" +#include "qemu/main-loop.h" +#include "sysemu/accel.h" +#include "target/arm/cpu.h" +#include "target/arm/internals.h" + +#define HVF_DEBUG 0 +#define DPRINTF(...) \ + if (HVF_DEBUG) { \ + fprintf(stderr, "HVF %s:%d ", __func__, __LINE__); \ + fprintf(stderr, __VA_ARGS__); \ + fprintf(stderr, "\n"); \ + } + +#define SYSREG(op0, op1, op2, crn, crm) \ + ((op0 << 20) | (op2 << 17) | (op1 << 14) | (crn << 10) | (crm << 1)) +#define SYSREG_MASK SYSREG(0x3, 0x7, 0x7, 0xf, 0xf) +#define SYSREG_CNTPCT_EL0 SYSREG(3, 3, 1, 14, 0) +#define SYSREG_PMCCNTR_EL0 SYSREG(3, 3, 0, 9, 13) + +struct hvf_reg_match { + int reg; + uint64_t offset; +}; + +static const struct hvf_reg_match hvf_reg_match[] = { + { HV_REG_X0, offsetof(CPUARMState, xregs[0]) }, + { HV_REG_X1, offsetof(CPUARMState, xregs[1]) }, + { HV_REG_X2, offsetof(CPUARMState, xregs[2]) }, + { HV_REG_X3, offsetof(CPUARMState, xregs[3]) }, + { HV_REG_X4, offsetof(CPUARMState, xregs[4]) }, + { HV_REG_X5, offsetof(CPUARMState, xregs[5]) }, + { HV_REG_X6, offsetof(CPUARMState, xregs[6]) }, + { HV_REG_X7, offsetof(CPUARMState, xregs[7]) }, + { HV_REG_X8, offsetof(CPUARMState, xregs[8]) }, + { HV_REG_X9, offsetof(CPUARMState, xregs[9]) }, + { HV_REG_X10, offsetof(CPUARMState, xregs[10]) }, + { HV_REG_X11, offsetof(CPUARMState, xregs[11]) }, + { HV_REG_X12, offsetof(CPUARMState, xregs[12]) }, + { HV_REG_X13, offsetof(CPUARMState, xregs[13]) }, + { HV_REG_X14, offsetof(CPUARMState, xregs[14]) }, + { HV_REG_X15, offsetof(CPUARMState, xregs[15]) }, + { HV_REG_X16, offsetof(CPUARMState, xregs[16]) }, + { HV_REG_X17, offsetof(CPUARMState, xregs[17]) }, + { HV_REG_X18, offsetof(CPUARMState, xregs[18]) }, + { HV_REG_X19, offsetof(CPUARMState, xregs[19]) }, + { HV_REG_X20, offsetof(CPUARMState, xregs[20]) }, + { HV_REG_X21, offsetof(CPUARMState, xregs[21]) }, + { HV_REG_X22, offsetof(CPUARMState, xregs[22]) }, + { HV_REG_X23, offsetof(CPUARMState, xregs[23]) }, + { HV_REG_X24, offsetof(CPUARMState, xregs[24]) }, + { HV_REG_X25, offsetof(CPUARMState, xregs[25]) }, + { HV_REG_X26, offsetof(CPUARMState, xregs[26]) }, + { HV_REG_X27, offsetof(CPUARMState, xregs[27]) }, + { HV_REG_X28, offsetof(CPUARMState, xregs[28]) }, + { HV_REG_X29, offsetof(CPUARMState, xregs[29]) }, + { HV_REG_X30, offsetof(CPUARMState, xregs[30]) }, + { HV_REG_PC, offsetof(CPUARMState, pc) }, +}; + +int hvf_get_registers(CPUState *cpu) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + hv_return_t ret; + uint64_t val; + int i; + + for (i = 0; i < ARRAY_SIZE(hvf_reg_match); i++) { + ret = hv_vcpu_get_reg(cpu->hvf_fd, hvf_reg_match[i].reg, &val); + *(uint64_t *)((void *)env + hvf_reg_match[i].offset) = val; + assert_hvf_ok(ret); + } + + val = 0; + ret = hv_vcpu_get_reg(cpu->hvf_fd, HV_REG_FPCR, &val); + assert_hvf_ok(ret); + vfp_set_fpcr(env, val); + + val = 0; + ret = hv_vcpu_get_reg(cpu->hvf_fd, HV_REG_FPSR, &val); + assert_hvf_ok(ret); + vfp_set_fpsr(env, val); + + ret = hv_vcpu_get_reg(cpu->hvf_fd, HV_REG_CPSR, &val); + assert_hvf_ok(ret); + pstate_write(env, val); + + return 0; +} + +int hvf_put_registers(CPUState *cpu) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + hv_return_t ret; + uint64_t val; + int i; + + for (i = 0; i < ARRAY_SIZE(hvf_reg_match); i++) { + val = *(uint64_t *)((void *)env + hvf_reg_match[i].offset); + ret = hv_vcpu_set_reg(cpu->hvf_fd, hvf_reg_match[i].reg, val); + + assert_hvf_ok(ret); + } + + ret = hv_vcpu_set_reg(cpu->hvf_fd, HV_REG_FPCR, vfp_get_fpcr(env)); + assert_hvf_ok(ret); + + ret = hv_vcpu_set_reg(cpu->hvf_fd, HV_REG_FPSR, vfp_get_fpsr(env)); + assert_hvf_ok(ret); + + ret = hv_vcpu_set_reg(cpu->hvf_fd, HV_REG_CPSR, pstate_read(env)); + assert_hvf_ok(ret); + + ret = hv_vcpu_set_sys_reg(cpu->hvf_fd, HV_SYS_REG_MPIDR_EL1, + arm_cpu->mp_affinity); + assert_hvf_ok(ret); + + return 0; +} + +void hvf_arch_vcpu_destroy(CPUState *cpu) +{ +} + +int hvf_arch_init_vcpu(CPUState *cpu) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + + env->aarch64 = 1; + + return 0; +} + +static int hvf_process_events(CPUState *cpu) +{ + DPRINTF(""); + return 0; +} + +static int hvf_inject_interrupts(CPUState *cpu) +{ + if (cpu->interrupt_request & CPU_INTERRUPT_FIQ) { + DPRINTF("injecting FIQ"); + hv_vcpu_set_pending_interrupt(cpu->hvf_fd, HV_INTERRUPT_TYPE_FIQ, true); + } + + if (cpu->interrupt_request & CPU_INTERRUPT_HARD) { + DPRINTF("injecting IRQ"); + hv_vcpu_set_pending_interrupt(cpu->hvf_fd, HV_INTERRUPT_TYPE_IRQ, true); + } + + return 0; +} + +int hvf_vcpu_exec(CPUState *cpu) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + hv_vcpu_exit_t *hvf_exit = cpu->hvf_exit; + int ret = 0; + + if (hvf_process_events(cpu)) { + return EXCP_HLT; + } + + do { + process_queued_cpu_work(cpu); + + if (cpu->vcpu_dirty) { + hvf_put_registers(cpu); + cpu->vcpu_dirty = false; + } + + if (hvf_inject_interrupts(cpu)) { + return EXCP_INTERRUPT; + } + + qemu_mutex_unlock_iothread(); + if (cpu->cpu_index && cpu->halted) { + qemu_mutex_lock_iothread(); + return EXCP_HLT; + } + + assert_hvf_ok(hv_vcpu_run(cpu->hvf_fd)); + + /* handle VMEXIT */ + uint64_t exit_reason = hvf_exit->reason; + uint64_t syndrome = hvf_exit->exception.syndrome; + uint32_t ec = syn_get_ec(syndrome); + + cpu_synchronize_state(cpu); + + qemu_mutex_lock_iothread(); + + current_cpu = cpu; + + switch (exit_reason) { + case HV_EXIT_REASON_EXCEPTION: + /* This is the main one, handle below. */ + break; + case HV_EXIT_REASON_VTIMER_ACTIVATED: + qemu_set_irq(arm_cpu->gt_timer_outputs[GTIMER_VIRT], 1); + continue; + case HV_EXIT_REASON_CANCELED: + /* we got kicked, no exit to process */ + continue; + default: + assert(0); + } + + ret = 0; + switch (ec) { + case EC_DATAABORT: { + bool isv = syndrome & ARM_EL_ISV; + bool iswrite = (syndrome >> 6) & 1; + bool s1ptw = (syndrome >> 7) & 1; + uint32_t sas = (syndrome >> 22) & 3; + uint32_t len = 1 << sas; + uint32_t srt = (syndrome >> 16) & 0x1f; + uint64_t val = 0; + + DPRINTF("data abort: [pc=0x%llx va=0x%016llx pa=0x%016llx isv=%x " + "iswrite=%x s1ptw=%x len=%d srt=%d]\n", + env->pc, hvf_exit->exception.virtual_address, + hvf_exit->exception.physical_address, isv, iswrite, + s1ptw, len, srt); + + assert(isv); + + if (iswrite) { + val = env->xregs[srt]; + address_space_write(&address_space_memory, + hvf_exit->exception.physical_address, + MEMTXATTRS_UNSPECIFIED, &val, len); + + /* + * We do not have a callback to see if the timer is out of + * state. That means every MMIO write could potentially be + * an EOI ends the vtimer. Until we get an actual callback, + * let's just see if the timer is still pending on every + * possible toggle point. + */ + qemu_set_irq(arm_cpu->gt_timer_outputs[GTIMER_VIRT], 0); + hv_vcpu_set_vtimer_mask(cpu->hvf_fd, false); + } else { + address_space_read(&address_space_memory, + hvf_exit->exception.physical_address, + MEMTXATTRS_UNSPECIFIED, &val, len); + env->xregs[srt] = val; + } + + env->pc += 4; + break; + } + case EC_SYSTEMREGISTERTRAP: { + bool isread = (syndrome >> 21) & 1; + uint32_t rt = (syndrome >> 5) & 0x1f; + uint32_t reg = syndrome & SYSREG_MASK; + uint64_t val = 0; + + if (isread) { + switch (reg) { + case SYSREG_CNTPCT_EL0: + val = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) / + gt_cntfrq_period_ns(arm_cpu); + break; + case SYSREG_PMCCNTR_EL0: + val = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + break; + default: + DPRINTF("unhandled sysreg read %08x (op0=%d op1=%d op2=%d " + "crn=%d crm=%d)", reg, (reg >> 20) & 0x3, + (reg >> 14) & 0x7, (reg >> 17) & 0x7, + (reg >> 10) & 0xf, (reg >> 1) & 0xf); + break; + } + + env->xregs[rt] = val; + } else { + val = env->xregs[rt]; + switch (reg) { + case SYSREG_CNTPCT_EL0: + break; + default: + DPRINTF("unhandled sysreg write %08x", reg); + break; + } + } + + env->pc += 4; + break; + } + case EC_WFX_TRAP: + /* No halting yet */ + break; + case EC_AA64_HVC: + if (arm_is_psci_call(arm_cpu, EXCP_HVC)) { + arm_handle_psci_call(arm_cpu); + } else { + DPRINTF("unknown HVC! %016llx", env->xregs[0]); + env->xregs[0] = -1; + } + break; + case EC_AA64_SMC: + if (arm_is_psci_call(arm_cpu, EXCP_SMC)) { + arm_handle_psci_call(arm_cpu); + } else { + DPRINTF("unknown SMC! %016llx", env->xregs[0]); + env->xregs[0] = -1; + env->pc += 4; + } + break; + default: + DPRINTF("exit: %llx [ec=0x%x pc=0x%llx]", syndrome, ec, env->pc); + error_report("%llx: unhandled exit %llx", env->pc, exit_reason); + } + } while (ret == 0); + + return ret; +} -- 2.24.3 (Apple Git-128) When kicking another vCPU, we get an OS function that explicitly does that for us on Apple Silicon. That works better than the current signaling logic, let's make use of it there. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- accel/hvf/hvf-cpus.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/accel/hvf/hvf-cpus.c b/accel/hvf/hvf-cpus.c index XXXXXXX..XXXXXXX 100644 --- a/accel/hvf/hvf-cpus.c +++ b/accel/hvf/hvf-cpus.c @@ -XXX,XX +XXX,XX @@ static void hvf_start_vcpu_thread(CPUState *cpu) cpu, QEMU_THREAD_JOINABLE); } +#ifdef __aarch64__ +static void hvf_kick_vcpu_thread(CPUState *cpu) +{ + if (!qemu_cpu_is_self(cpu)) { + hv_vcpus_exit(&cpu->hvf_fd, 1); + } +} +#endif + static const CpusAccel hvf_cpus = { .create_vcpu_thread = hvf_start_vcpu_thread, +#ifdef __aarch64__ + .kick_vcpu_thread = hvf_kick_vcpu_thread, +#endif .synchronize_post_reset = hvf_cpu_synchronize_post_reset, .synchronize_post_init = hvf_cpu_synchronize_post_init, -- 2.24.3 (Apple Git-128) Now that we have all logic in place that we need to handle Hypervisor.framework on Apple Silicon systems, let's add CONFIG_HVF for aarch64 as well so that we can build it. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- meson.build | 9 ++++++++- target/arm/hvf/meson.build | 3 +++ target/arm/meson.build | 2 ++ 3 files changed, 13 insertions(+), 1 deletion(-) create mode 100644 target/arm/hvf/meson.build diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ else endif accelerator_targets = { 'CONFIG_KVM': kvm_targets } + +if cpu in ['x86', 'x86_64'] + hvf_targets = ['i386-softmmu', 'x86_64-softmmu'] +elif cpu in ['aarch64'] + hvf_targets = ['aarch64-softmmu'] +endif + if cpu in ['x86', 'x86_64', 'arm', 'aarch64'] # i368 emulator provides xenpv machine type for multiple architectures accelerator_targets += { 'CONFIG_XEN': ['i386-softmmu', 'x86_64-softmmu'], + 'CONFIG_HVF': hvf_targets, } endif if cpu in ['x86', 'x86_64'] accelerator_targets += { 'CONFIG_HAX': ['i386-softmmu', 'x86_64-softmmu'], - 'CONFIG_HVF': ['x86_64-softmmu'], 'CONFIG_WHPX': ['i386-softmmu', 'x86_64-softmmu'], } endif diff --git a/target/arm/hvf/meson.build b/target/arm/hvf/meson.build new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/hvf/meson.build @@ -XXX,XX +XXX,XX @@ +arm_softmmu_ss.add(when: [hvf, 'CONFIG_HVF'], if_true: files( + 'hvf.c', +)) diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_softmmu_ss.add(files( 'psci.c', )) +subdir('hvf') + target_arch += {'arm': arm_ss} target_softmmu_arch += {'arm': arm_softmmu_ss} -- 2.24.3 (Apple Git-128) The Apple M1 only supports up to 36 bits of physical address space. That means we can not fit the 64bit MMIO BAR region into our address space. To fix this, let's not expose a 64bit MMIO BAR region when running on Apple Silicon. I have not been able to find a way to enumerate that easily, so let's just assume we always have that little PA space on hypervisor.framework systems. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- hw/arm/virt.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ #include "hw/display/ramfb.h" #include "net/net.h" #include "sysemu/device_tree.h" +#include "sysemu/hvf.h" #include "sysemu/numa.h" #include "sysemu/runstate.h" #include "sysemu/sysemu.h" @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) unsigned int smp_cpus = machine->smp.cpus; unsigned int max_cpus = machine->smp.max_cpus; + /* + * On Hypervisor.framework capable systems, we only have 36 bits of PA + * space, which is not enough to fit a 64bit BAR space + */ + if (hvf_enabled()) { + vms->highmem = false; + } + /* * In accelerated mode, the memory map is computed earlier in kvm_type() * to create a VM with the right number of IPA bits. -- 2.24.3 (Apple Git-128) Now that Apple Silicon is widely available, people are obviously excited to try and run virtualized workloads on them, such as Linux and Windows. This patch set implements a fully functional version to get the ball going on that. With this applied, I can successfully run both Linux and Windows as guests. I am not aware of any limitations specific to Hypervisor.framework apart from: - Live migration / savevm - gdbstub debugging (SP register) Enjoy! Alex v1 -> v2: - New patch: hvf: Actually set SIG_IPI mask - New patch: hvf: Introduce hvf vcpu struct - New patch: hvf: arm: Mark CPU as dirty on reset - Removed patch: hw/arm/virt: Disable highmem when on hypervisor.framework - Removed patch: arm: Synchronize CPU on PSCI on - Fix build on 32bit arm - Merge vcpu kick function patch into ARM enablement - Implement WFI handling (allows vCPUs to sleep) - Synchronize system registers (fixes OVMF crashes and reboot) - Don't always call cpu_synchronize_state() - Use more fine grained iothread locking - Populate aa64mmfr0 from hardware - Make safe to ctrl-C entitlement application Alexander Graf (8): hvf: Add hypervisor entitlement to output binaries hvf: Move common code out hvf: Actually set SIG_IPI mask hvf: Introduce hvf vcpu struct arm: Set PSCI to 0.2 for HVF hvf: arm: Mark CPU as dirty on reset hvf: Add Apple Silicon support arm: Add Hypervisor.framework build target MAINTAINERS | 14 +- accel/hvf/entitlements.plist | 8 + accel/hvf/hvf-all.c | 56 ++++ accel/hvf/hvf-cpus.c | 483 ++++++++++++++++++++++++++++ accel/hvf/meson.build | 7 + accel/meson.build | 1 + include/hw/core/cpu.h | 3 +- include/sysemu/hvf_int.h | 78 +++++ meson.build | 41 ++- scripts/entitlement.sh | 13 + target/arm/arm-powerctl.c | 1 + target/arm/cpu.c | 6 + target/arm/hvf/hvf.c | 603 +++++++++++++++++++++++++++++++++++ target/arm/hvf/meson.build | 3 + target/arm/meson.build | 2 + target/i386/hvf/hvf-cpus.c | 131 -------- target/i386/hvf/hvf-cpus.h | 25 -- target/i386/hvf/hvf-i386.h | 48 +-- target/i386/hvf/hvf.c | 462 ++++----------------------- target/i386/hvf/meson.build | 1 - target/i386/hvf/vmx.h | 24 +- target/i386/hvf/x86.c | 28 +- target/i386/hvf/x86_descr.c | 26 +- target/i386/hvf/x86_emu.c | 62 ++-- target/i386/hvf/x86_mmu.c | 4 +- target/i386/hvf/x86_task.c | 12 +- target/i386/hvf/x86hvf.c | 221 ++++++------- target/i386/hvf/x86hvf.h | 2 - 28 files changed, 1557 insertions(+), 808 deletions(-) create mode 100644 accel/hvf/entitlements.plist create mode 100644 accel/hvf/hvf-all.c create mode 100644 accel/hvf/hvf-cpus.c create mode 100644 accel/hvf/meson.build create mode 100644 include/sysemu/hvf_int.h create mode 100755 scripts/entitlement.sh create mode 100644 target/arm/hvf/hvf.c create mode 100644 target/arm/hvf/meson.build delete mode 100644 target/i386/hvf/hvf-cpus.c delete mode 100644 target/i386/hvf/hvf-cpus.h -- 2.24.3 (Apple Git-128) In macOS 11, QEMU only gets access to Hypervisor.framework if it has the respective entitlement. Add an entitlement template and automatically self sign and apply the entitlement in the build. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- v1 -> v2: - Make safe to ctrl-C --- accel/hvf/entitlements.plist | 8 ++++++++ meson.build | 30 ++++++++++++++++++++++++++---- scripts/entitlement.sh | 13 +++++++++++++ 3 files changed, 47 insertions(+), 4 deletions(-) create mode 100644 accel/hvf/entitlements.plist create mode 100755 scripts/entitlement.sh diff --git a/accel/hvf/entitlements.plist b/accel/hvf/entitlements.plist new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/accel/hvf/entitlements.plist @@ -XXX,XX +XXX,XX @@ +<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd"> +<plist version="1.0"> +<dict> + <key>com.apple.security.hypervisor</key> + <true/> +</dict> +</plist> diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ foreach target : target_dirs }] endif foreach exe: execs - emulators += {exe['name']: - executable(exe['name'], exe['sources'], - install: true, + exe_name = exe['name'] + exe_sign = 'CONFIG_HVF' in config_target + if exe_sign + exe_name += '-unsigned' + endif + + emulator = executable(exe_name, exe['sources'], + install: not exe_sign, c_args: c_args, dependencies: arch_deps + deps + exe['dependencies'], objects: lib.extract_all_objects(recursive: true), @@ -XXX,XX +XXX,XX @@ foreach target : target_dirs link_depends: [block_syms, qemu_syms] + exe.get('link_depends', []), link_args: link_args, gui_app: exe['gui']) - } + + if exe_sign + exe_full = meson.current_build_dir() / exe['name'] + emulators += {exe['name'] : custom_target(exe['name'], + install: true, + install_dir: get_option('bindir'), + depends: emulator, + output: exe['name'], + command: [ + meson.current_source_dir() / 'scripts/entitlement.sh', + meson.current_build_dir() / exe['name'] + '-unsigned', + meson.current_build_dir() / exe['name'], + meson.current_source_dir() / 'accel/hvf/entitlements.plist' + ]) + } + else + emulators += {exe['name']: emulator} + endif if 'CONFIG_TRACE_SYSTEMTAP' in config_host foreach stp: [ diff --git a/scripts/entitlement.sh b/scripts/entitlement.sh new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/scripts/entitlement.sh @@ -XXX,XX +XXX,XX @@ +#!/bin/sh -e +# +# Helper script for the build process to apply entitlements + +SRC="$1" +DST="$2" +ENTITLEMENT="$3" + +trap 'rm "$DST.tmp"' exit +cp -af "$SRC" "$DST.tmp" +codesign --entitlements "$ENTITLEMENT" --force -s - "$DST.tmp" +mv "$DST.tmp" "$DST" +trap '' exit -- 2.24.3 (Apple Git-128) Until now, Hypervisor.framework has only been available on x86_64 systems. With Apple Silicon shipping now, it extends its reach to aarch64. To prepare for support for multiple architectures, let's move common code out into its own accel directory. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- MAINTAINERS | 9 +- accel/hvf/hvf-all.c | 56 +++++ accel/hvf/hvf-cpus.c | 464 ++++++++++++++++++++++++++++++++++++ accel/hvf/meson.build | 7 + accel/meson.build | 1 + include/sysemu/hvf_int.h | 69 ++++++ target/i386/hvf/hvf-cpus.c | 131 ---------- target/i386/hvf/hvf-cpus.h | 25 -- target/i386/hvf/hvf-i386.h | 48 +--- target/i386/hvf/hvf.c | 360 +--------------------------- target/i386/hvf/meson.build | 1 - target/i386/hvf/x86hvf.c | 11 +- target/i386/hvf/x86hvf.h | 2 - 13 files changed, 615 insertions(+), 569 deletions(-) create mode 100644 accel/hvf/hvf-all.c create mode 100644 accel/hvf/hvf-cpus.c create mode 100644 accel/hvf/meson.build create mode 100644 include/sysemu/hvf_int.h delete mode 100644 target/i386/hvf/hvf-cpus.c delete mode 100644 target/i386/hvf/hvf-cpus.h diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Cameron Esfahani <dirty@apple.com> M: Roman Bolshakov <r.bolshakov@yadro.com> W: https://wiki.qemu.org/Features/HVF S: Maintained -F: accel/stubs/hvf-stub.c F: target/i386/hvf/ + +HVF +M: Cameron Esfahani <dirty@apple.com> +M: Roman Bolshakov <r.bolshakov@yadro.com> +W: https://wiki.qemu.org/Features/HVF +S: Maintained +F: accel/hvf/ F: include/sysemu/hvf.h +F: include/sysemu/hvf_int.h WHPX CPUs M: Sunil Muthuswamy <sunilmut@microsoft.com> diff --git a/accel/hvf/hvf-all.c b/accel/hvf/hvf-all.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/accel/hvf/hvf-all.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU Hypervisor.framework support + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/error-report.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" +#include "sysemu/runstate.h" + +#include "qemu/main-loop.h" +#include "sysemu/accel.h" + +#include <Hypervisor/Hypervisor.h> + +bool hvf_allowed; +HVFState *hvf_state; + +void assert_hvf_ok(hv_return_t ret) +{ + if (ret == HV_SUCCESS) { + return; + } + + switch (ret) { + case HV_ERROR: + error_report("Error: HV_ERROR"); + break; + case HV_BUSY: + error_report("Error: HV_BUSY"); + break; + case HV_BAD_ARGUMENT: + error_report("Error: HV_BAD_ARGUMENT"); + break; + case HV_NO_RESOURCES: + error_report("Error: HV_NO_RESOURCES"); + break; + case HV_NO_DEVICE: + error_report("Error: HV_NO_DEVICE"); + break; + case HV_UNSUPPORTED: + error_report("Error: HV_UNSUPPORTED"); + break; + default: + error_report("Unknown Error"); + } + + abort(); +} diff --git a/accel/hvf/hvf-cpus.c b/accel/hvf/hvf-cpus.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/accel/hvf/hvf-cpus.c @@ -XXX,XX +XXX,XX @@ +/* + * 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 + * 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/>. + * + * This file contain code under public domain from the hvdos project: + * https://github.com/mist64/hvdos + * + * Parts 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. + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "exec/address-spaces.h" +#include "exec/exec-all.h" +#include "sysemu/cpus.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" +#include "sysemu/runstate.h" +#include "qemu/guest-random.h" + +#include <Hypervisor/Hypervisor.h> + +/* Memory slots */ + +struct mac_slot { + int present; + uint64_t size; + uint64_t gpa_start; + uint64_t gva; +}; + +hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t size) +{ + 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) && + (start + size) > slot->start) { + return slot; + } + } + return NULL; +} + +struct mac_slot mac_slots[32]; + +static int do_hvf_set_memory(hvf_slot *slot, hv_memory_flags_t flags) +{ + struct mac_slot *macslot; + 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; + } + + macslot->present = 1; + macslot->gpa_start = slot->start; + macslot->size = slot->size; + ret = hv_vm_map(slot->mem, slot->start, slot->size, flags); + assert_hvf_ok(ret); + return 0; +} + +static void hvf_set_phys_mem(MemoryRegionSection *section, bool add) +{ + hvf_slot *mem; + MemoryRegion *area = section->mr; + bool writeable = !area->readonly && !area->rom_device; + hv_memory_flags_t flags; + + if (!memory_region_is_ram(area)) { + if (writeable) { + return; + } else if (!memory_region_is_romd(area)) { + /* + * If the memory device is not in romd_mode, then we actually want + * to remove the hvf memory slot so all accesses will trap. + */ + add = false; + } + } + + mem = hvf_find_overlap_slot( + 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, 0)) { + error_report("Failed to reset overlapping slot"); + abort(); + } + } + + if (!add) { + return; + } + + if (area->readonly || + (!memory_region_is_ram(area) && memory_region_is_romd(area))) { + flags = HV_MEMORY_READ | HV_MEMORY_EXEC; + } else { + flags = HV_MEMORY_READ | HV_MEMORY_WRITE | HV_MEMORY_EXEC; + } + + /* 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"); + 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, flags)) { + error_report("Error registering new memory slot"); + abort(); + } +} + +static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on) +{ + hvf_slot *slot; + + slot = hvf_find_overlap_slot( + 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((uintptr_t)slot->start, (size_t)slot->size, + HV_MEMORY_READ); + /* stop tracking region*/ + } else { + slot->flags &= ~HVF_SLOT_LOG; + hv_vm_protect((uintptr_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, +}; + +static void do_hvf_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg) +{ + if (!cpu->vcpu_dirty) { + hvf_get_registers(cpu); + cpu->vcpu_dirty = true; + } +} + +static void hvf_cpu_synchronize_state(CPUState *cpu) +{ + if (!cpu->vcpu_dirty) { + run_on_cpu(cpu, do_hvf_cpu_synchronize_state, RUN_ON_CPU_NULL); + } +} + +static void do_hvf_cpu_synchronize_post_reset(CPUState *cpu, + run_on_cpu_data arg) +{ + hvf_put_registers(cpu); + cpu->vcpu_dirty = false; +} + +static void hvf_cpu_synchronize_post_reset(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_post_reset, RUN_ON_CPU_NULL); +} + +static void do_hvf_cpu_synchronize_post_init(CPUState *cpu, + run_on_cpu_data arg) +{ + hvf_put_registers(cpu); + cpu->vcpu_dirty = false; +} + +static void hvf_cpu_synchronize_post_init(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_post_init, RUN_ON_CPU_NULL); +} + +static void do_hvf_cpu_synchronize_pre_loadvm(CPUState *cpu, + run_on_cpu_data arg) +{ + cpu->vcpu_dirty = true; +} + +static void hvf_cpu_synchronize_pre_loadvm(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_pre_loadvm, RUN_ON_CPU_NULL); +} + +static void hvf_vcpu_destroy(CPUState *cpu) +{ + hv_return_t ret = hv_vcpu_destroy(cpu->hvf_fd); + assert_hvf_ok(ret); + + hvf_arch_vcpu_destroy(cpu); +} + +static void dummy_signal(int sig) +{ +} + +static int hvf_init_vcpu(CPUState *cpu) +{ + 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); + + r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf_fd, HV_VCPU_DEFAULT); + cpu->vcpu_dirty = 1; + assert_hvf_ok(r); + + return hvf_arch_init_vcpu(cpu); +} + +/* + * The HVF-specific vCPU thread function. This one should only run when the host + * CPU supports the VMX "unrestricted guest" feature. + */ +static void *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_thread_signal_created(cpu); + qemu_guest_random_seed_thread_part2(cpu->random_seed); + + do { + if (cpu_can_run(cpu)) { + r = hvf_vcpu_exec(cpu); + if (r == EXCP_DEBUG) { + cpu_handle_guest_debug(cpu); + } + } + qemu_wait_io_event(cpu); + } while (!cpu->unplug || cpu_can_run(cpu)); + + hvf_vcpu_destroy(cpu); + cpu_thread_signal_destroyed(cpu); + qemu_mutex_unlock_iothread(); + rcu_unregister_thread(); + return NULL; +} + +static void hvf_start_vcpu_thread(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, hvf_cpu_thread_fn, + cpu, QEMU_THREAD_JOINABLE); +} + +static const CpusAccel hvf_cpus = { + .create_vcpu_thread = hvf_start_vcpu_thread, + + .synchronize_post_reset = hvf_cpu_synchronize_post_reset, + .synchronize_post_init = hvf_cpu_synchronize_post_init, + .synchronize_state = hvf_cpu_synchronize_state, + .synchronize_pre_loadvm = hvf_cpu_synchronize_pre_loadvm, +}; + +static int hvf_accel_init(MachineState *ms) +{ + int x; + hv_return_t ret; + HVFState *s; + + 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; + memory_listener_register(&hvf_memory_listener, &address_space_memory); + cpus_register_accel(&hvf_cpus); + 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); diff --git a/accel/hvf/meson.build b/accel/hvf/meson.build new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/accel/hvf/meson.build @@ -XXX,XX +XXX,XX @@ +hvf_ss = ss.source_set() +hvf_ss.add(files( + 'hvf-all.c', + 'hvf-cpus.c', +)) + +specific_ss.add_all(when: 'CONFIG_HVF', if_true: hvf_ss) diff --git a/accel/meson.build b/accel/meson.build index XXXXXXX..XXXXXXX 100644 --- a/accel/meson.build +++ b/accel/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(files('accel.c')) +subdir('hvf') subdir('qtest') subdir('kvm') subdir('tcg') diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/sysemu/hvf_int.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU Hypervisor.framework (HVF) support + * + * 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 HVF-specific code */ + +#ifndef HVF_INT_H +#define HVF_INT_H + +#include <Hypervisor/Hypervisor.h> + +#define HVF_MAX_VCPU 0x10 + +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; +}; + +/* 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; + +struct HVFState { + AccelState parent; + hvf_slot slots[32]; + int num_slots; + + hvf_vcpu_caps *hvf_caps; +}; +extern HVFState *hvf_state; + +void assert_hvf_ok(hv_return_t ret); +int hvf_get_registers(CPUState *cpu); +int hvf_put_registers(CPUState *cpu); +int hvf_arch_init_vcpu(CPUState *cpu); +void hvf_arch_vcpu_destroy(CPUState *cpu); +int hvf_vcpu_exec(CPUState *cpu); +hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t); + +#endif diff --git a/target/i386/hvf/hvf-cpus.c b/target/i386/hvf/hvf-cpus.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/target/i386/hvf/hvf-cpus.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * 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 - * 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/>. - * - * This file contain code under public domain from the hvdos project: - * https://github.com/mist64/hvdos - * - * Parts 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. - */ - -#include "qemu/osdep.h" -#include "qemu/error-report.h" -#include "qemu/main-loop.h" -#include "sysemu/hvf.h" -#include "sysemu/runstate.h" -#include "target/i386/cpu.h" -#include "qemu/guest-random.h" - -#include "hvf-cpus.h" - -/* - * The HVF-specific vCPU thread function. This one should only run when the host - * CPU supports the VMX "unrestricted guest" feature. - */ -static void *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_thread_signal_created(cpu); - qemu_guest_random_seed_thread_part2(cpu->random_seed); - - do { - if (cpu_can_run(cpu)) { - r = hvf_vcpu_exec(cpu); - if (r == EXCP_DEBUG) { - cpu_handle_guest_debug(cpu); - } - } - qemu_wait_io_event(cpu); - } while (!cpu->unplug || cpu_can_run(cpu)); - - hvf_vcpu_destroy(cpu); - cpu_thread_signal_destroyed(cpu); - qemu_mutex_unlock_iothread(); - rcu_unregister_thread(); - return NULL; -} - -static void hvf_start_vcpu_thread(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, hvf_cpu_thread_fn, - cpu, QEMU_THREAD_JOINABLE); -} - -const CpusAccel hvf_cpus = { - .create_vcpu_thread = hvf_start_vcpu_thread, - - .synchronize_post_reset = hvf_cpu_synchronize_post_reset, - .synchronize_post_init = hvf_cpu_synchronize_post_init, - .synchronize_state = hvf_cpu_synchronize_state, - .synchronize_pre_loadvm = hvf_cpu_synchronize_pre_loadvm, -}; diff --git a/target/i386/hvf/hvf-cpus.h b/target/i386/hvf/hvf-cpus.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/target/i386/hvf/hvf-cpus.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Accelerator CPUS Interface - * - * Copyright 2020 SUSE LLC - * - * 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_CPUS_H -#define HVF_CPUS_H - -#include "sysemu/cpus.h" - -extern const CpusAccel hvf_cpus; - -int hvf_init_vcpu(CPUState *); -int hvf_vcpu_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_pre_loadvm(CPUState *); -void hvf_vcpu_destroy(CPUState *); - -#endif /* HVF_CPUS_H */ diff --git a/target/i386/hvf/hvf-i386.h b/target/i386/hvf/hvf-i386.h index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/hvf-i386.h +++ b/target/i386/hvf/hvf-i386.h @@ -XXX,XX +XXX,XX @@ #include "sysemu/accel.h" #include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" #include "cpu.h" #include "x86.h" -#define HVF_MAX_VCPU 0x10 - -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; -}; - -/* 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; - -struct HVFState { - AccelState parent; - hvf_slot slots[32]; - int num_slots; - - hvf_vcpu_caps *hvf_caps; -}; -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); #ifdef NEED_CPU_H /* Functions exported to host specific mode */ diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/hvf.c +++ b/target/i386/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" #include "sysemu/runstate.h" #include "hvf-i386.h" #include "vmcs.h" @@ -XXX,XX +XXX,XX @@ #include "sysemu/accel.h" #include "target/i386/cpu.h" -#include "hvf-cpus.h" - -HVFState *hvf_state; - -static void assert_hvf_ok(hv_return_t ret) -{ - if (ret == HV_SUCCESS) { - return; - } - - switch (ret) { - case HV_ERROR: - error_report("Error: HV_ERROR"); - break; - case HV_BUSY: - error_report("Error: HV_BUSY"); - break; - case HV_BAD_ARGUMENT: - error_report("Error: HV_BAD_ARGUMENT"); - break; - case HV_NO_RESOURCES: - error_report("Error: HV_NO_RESOURCES"); - break; - case HV_NO_DEVICE: - error_report("Error: HV_NO_DEVICE"); - break; - case HV_UNSUPPORTED: - error_report("Error: HV_UNSUPPORTED"); - break; - default: - error_report("Unknown Error"); - } - - abort(); -} - -/* Memory slots */ -hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t size) -{ - 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) && - (start + size) > 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]; - -static int do_hvf_set_memory(hvf_slot *slot, hv_memory_flags_t flags) -{ - struct mac_slot *macslot; - 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; - } - - 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; - bool writeable = !area->readonly && !area->rom_device; - hv_memory_flags_t flags; - - if (!memory_region_is_ram(area)) { - if (writeable) { - return; - } else if (!memory_region_is_romd(area)) { - /* - * If the memory device is not in romd_mode, then we actually want - * to remove the hvf memory slot so all accesses will trap. - */ - add = false; - } - } - - mem = hvf_find_overlap_slot( - 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, 0)) { - error_report("Failed to reset overlapping slot"); - abort(); - } - } - - if (!add) { - return; - } - - if (area->readonly || - (!memory_region_is_ram(area) && memory_region_is_romd(area))) { - flags = HV_MEMORY_READ | HV_MEMORY_EXEC; - } else { - flags = HV_MEMORY_READ | HV_MEMORY_WRITE | HV_MEMORY_EXEC; - } - - /* 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"); - 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, flags)) { - error_report("Error registering new memory slot"); - abort(); - } -} - void vmx_update_tpr(CPUState *cpu) { /* TODO: need integrate APIC handling */ @@ -XXX,XX +XXX,XX @@ void hvf_handle_io(CPUArchState *env, uint16_t port, void *buffer, } } -static void do_hvf_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg) -{ - if (!cpu->vcpu_dirty) { - hvf_get_registers(cpu); - cpu->vcpu_dirty = true; - } -} - -void hvf_cpu_synchronize_state(CPUState *cpu) -{ - if (!cpu->vcpu_dirty) { - run_on_cpu(cpu, do_hvf_cpu_synchronize_state, RUN_ON_CPU_NULL); - } -} - -static void do_hvf_cpu_synchronize_post_reset(CPUState *cpu, - run_on_cpu_data arg) -{ - hvf_put_registers(cpu); - cpu->vcpu_dirty = false; -} - -void hvf_cpu_synchronize_post_reset(CPUState *cpu) -{ - run_on_cpu(cpu, do_hvf_cpu_synchronize_post_reset, RUN_ON_CPU_NULL); -} - -static void do_hvf_cpu_synchronize_post_init(CPUState *cpu, - run_on_cpu_data arg) -{ - hvf_put_registers(cpu); - cpu->vcpu_dirty = false; -} - -void hvf_cpu_synchronize_post_init(CPUState *cpu) -{ - run_on_cpu(cpu, do_hvf_cpu_synchronize_post_init, RUN_ON_CPU_NULL); -} - -static void do_hvf_cpu_synchronize_pre_loadvm(CPUState *cpu, - run_on_cpu_data arg) -{ - cpu->vcpu_dirty = true; -} - -void hvf_cpu_synchronize_pre_loadvm(CPUState *cpu) -{ - run_on_cpu(cpu, do_hvf_cpu_synchronize_pre_loadvm, RUN_ON_CPU_NULL); -} - static bool ept_emulation_fault(hvf_slot *slot, uint64_t gpa, uint64_t ept_qual) { int read, write; @@ -XXX,XX +XXX,XX @@ static bool ept_emulation_fault(hvf_slot *slot, uint64_t gpa, uint64_t ept_qual) return false; } -static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on) -{ - hvf_slot *slot; - - slot = hvf_find_overlap_slot( - 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_vcpu_destroy(CPUState *cpu) +void hvf_arch_vcpu_destroy(CPUState *cpu) { X86CPU *x86_cpu = X86_CPU(cpu); CPUX86State *env = &x86_cpu->env; - hv_return_t ret = hv_vcpu_destroy((hv_vcpuid_t)cpu->hvf_fd); g_free(env->hvf_mmio_buf); - assert_hvf_ok(ret); -} - -static void dummy_signal(int sig) -{ } -int hvf_init_vcpu(CPUState *cpu) +int hvf_arch_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(); @@ -XXX,XX +XXX,XX @@ int hvf_init_vcpu(CPUState *cpu) hvf_state->hvf_caps = g_new0(struct hvf_vcpu_caps, 1); env->hvf_mmio_buf = g_new(char, 4096); - 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(); @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) return ret; } - -bool hvf_allowed; - -static int hvf_accel_init(MachineState *ms) -{ - int x; - hv_return_t ret; - HVFState *s; - - 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; - memory_listener_register(&hvf_memory_listener, &address_space_memory); - cpus_register_accel(&hvf_cpus); - 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); diff --git a/target/i386/hvf/meson.build b/target/i386/hvf/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/meson.build +++ b/target/i386/hvf/meson.build @@ -XXX,XX +XXX,XX @@ i386_softmmu_ss.add(when: [hvf, 'CONFIG_HVF'], if_true: files( 'hvf.c', - 'hvf-cpus.c', 'x86.c', 'x86_cpuid.c', 'x86_decode.c', diff --git a/target/i386/hvf/x86hvf.c b/target/i386/hvf/x86hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/x86hvf.c +++ b/target/i386/hvf/x86hvf.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qemu-common.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" +#include "sysemu/hw_accel.h" #include "x86hvf.h" #include "vmx.h" #include "vmcs.h" @@ -XXX,XX +XXX,XX @@ #include <Hypervisor/hv.h> #include <Hypervisor/hv_vmx.h> -#include "hvf-cpus.h" - void hvf_set_segment(struct CPUState *cpu, struct vmx_segment *vmx_seg, SegmentCache *qseg, bool is_tr) { @@ -XXX,XX +XXX,XX @@ int hvf_process_events(CPUState *cpu_state) env->eflags = rreg(cpu_state->hvf_fd, HV_X86_RFLAGS); if (cpu_state->interrupt_request & CPU_INTERRUPT_INIT) { - hvf_cpu_synchronize_state(cpu_state); + cpu_synchronize_state(cpu_state); do_cpu_init(cpu); } @@ -XXX,XX +XXX,XX @@ int hvf_process_events(CPUState *cpu_state) cpu_state->halted = 0; } if (cpu_state->interrupt_request & CPU_INTERRUPT_SIPI) { - hvf_cpu_synchronize_state(cpu_state); + 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); + cpu_synchronize_state(cpu_state); apic_handle_tpr_access_report(cpu->apic_state, env->eip, env->tpr_access_type); } diff --git a/target/i386/hvf/x86hvf.h b/target/i386/hvf/x86hvf.h index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/x86hvf.h +++ b/target/i386/hvf/x86hvf.h @@ -XXX,XX +XXX,XX @@ #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); -- 2.24.3 (Apple Git-128) In the hvf init function, we prepare a signal mask for SIG_IPI, but then fail to set it. This seems to work by chance on some systems, where SIGUSR2 is already unmasked by default. It fails however on ARM Big Sur. So let's set the signal mask as intended. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- accel/hvf/hvf-cpus.c | 1 + 1 file changed, 1 insertion(+) diff --git a/accel/hvf/hvf-cpus.c b/accel/hvf/hvf-cpus.c index XXXXXXX..XXXXXXX 100644 --- a/accel/hvf/hvf-cpus.c +++ b/accel/hvf/hvf-cpus.c @@ -XXX,XX +XXX,XX @@ static int hvf_init_vcpu(CPUState *cpu) pthread_sigmask(SIG_BLOCK, NULL, &set); sigdelset(&set, SIG_IPI); + pthread_sigmask(SIG_SETMASK, &set, NULL); r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf_fd, HV_VCPU_DEFAULT); cpu->vcpu_dirty = 1; -- 2.24.3 (Apple Git-128) We will need more than a single field for hvf going forward. To keep the global vcpu struct uncluttered, let's allocate a special hvf vcpu struct, similar to how hax does it. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- accel/hvf/hvf-cpus.c | 8 +- include/hw/core/cpu.h | 3 +- include/sysemu/hvf_int.h | 4 + target/i386/hvf/hvf.c | 102 +++++++++--------- target/i386/hvf/vmx.h | 24 +++-- target/i386/hvf/x86.c | 28 ++--- target/i386/hvf/x86_descr.c | 26 ++--- target/i386/hvf/x86_emu.c | 62 +++++------ target/i386/hvf/x86_mmu.c | 4 +- target/i386/hvf/x86_task.c | 12 +-- target/i386/hvf/x86hvf.c | 210 ++++++++++++++++++------------------ 11 files changed, 247 insertions(+), 236 deletions(-) diff --git a/accel/hvf/hvf-cpus.c b/accel/hvf/hvf-cpus.c index XXXXXXX..XXXXXXX 100644 --- a/accel/hvf/hvf-cpus.c +++ b/accel/hvf/hvf-cpus.c @@ -XXX,XX +XXX,XX @@ static void hvf_cpu_synchronize_pre_loadvm(CPUState *cpu) static void hvf_vcpu_destroy(CPUState *cpu) { - hv_return_t ret = hv_vcpu_destroy(cpu->hvf_fd); + hv_return_t ret = hv_vcpu_destroy(cpu->hvf->fd); assert_hvf_ok(ret); hvf_arch_vcpu_destroy(cpu); + free(cpu->hvf); + cpu->hvf = NULL; } static void dummy_signal(int sig) @@ -XXX,XX +XXX,XX @@ static int hvf_init_vcpu(CPUState *cpu) { int r; + cpu->hvf = g_malloc0(sizeof(*cpu->hvf)); + /* init cpu signals */ sigset_t set; struct sigaction sigact; @@ -XXX,XX +XXX,XX @@ static int hvf_init_vcpu(CPUState *cpu) sigdelset(&set, SIG_IPI); pthread_sigmask(SIG_SETMASK, &set, NULL); - r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf_fd, HV_VCPU_DEFAULT); + r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf->fd, HV_VCPU_DEFAULT); cpu->vcpu_dirty = 1; assert_hvf_ok(r); diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -XXX,XX +XXX,XX @@ struct KVMState; struct kvm_run; struct hax_vcpu_state; +struct hvf_vcpu_state; #define TB_JMP_CACHE_BITS 12 #define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS) @@ -XXX,XX +XXX,XX @@ struct CPUState { struct hax_vcpu_state *hax_vcpu; - int hvf_fd; + struct hvf_vcpu_state *hvf; /* track IOMMUs whose translations we've cached in the TCG TLB */ GArray *iommu_notifiers; diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/hvf_int.h +++ b/include/sysemu/hvf_int.h @@ -XXX,XX +XXX,XX @@ struct HVFState { }; extern HVFState *hvf_state; +struct hvf_vcpu_state { + int fd; +}; + void assert_hvf_ok(hv_return_t ret); int hvf_get_registers(CPUState *cpu); int hvf_put_registers(CPUState *cpu); diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/hvf.c +++ b/target/i386/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ void vmx_update_tpr(CPUState *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); + wreg(cpu->hvf->fd, HV_X86_TPR, tpr); if (irr == -1) { - wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, 0); + wvmcs(cpu->hvf->fd, VMCS_TPR_THRESHOLD, 0); } else { - wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, (irr > tpr) ? tpr >> 4 : + wvmcs(cpu->hvf->fd, VMCS_TPR_THRESHOLD, (irr > tpr) ? tpr >> 4 : irr >> 4); } } @@ -XXX,XX +XXX,XX @@ void vmx_update_tpr(CPUState *cpu) static void update_apic_tpr(CPUState *cpu) { X86CPU *x86_cpu = X86_CPU(cpu); - int tpr = rreg(cpu->hvf_fd, HV_X86_TPR) >> 4; + int tpr = rreg(cpu->hvf->fd, HV_X86_TPR) >> 4; cpu_set_apic_tpr(x86_cpu->apic_state, tpr); } @@ -XXX,XX +XXX,XX @@ int hvf_arch_init_vcpu(CPUState *cpu) } /* set VMCS control fields */ - wvmcs(cpu->hvf_fd, VMCS_PIN_BASED_CTLS, + 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, + 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, + 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, + 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_EXCEPTION_BITMAP, 0); /* Double fault */ - wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, 0); + wvmcs(cpu->hvf->fd, VMCS_TPR_THRESHOLD, 0); x86cpu = X86_CPU(cpu); x86cpu->env.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); + 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; } @@ -XXX,XX +XXX,XX @@ static void hvf_store_events(CPUState *cpu, uint32_t ins_len, uint64_t idtvec_in } if (idtvec_info & VMCS_IDT_VEC_ERRCODE_VALID) { env->has_error_code = true; - env->error_code = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_ERROR); + env->error_code = rvmcs(cpu->hvf->fd, VMCS_IDT_VECTORING_ERROR); } } - if ((rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY) & + 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) & + if (rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY) & (VMCS_INTERRUPTIBILITY_STI_BLOCKING | VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)) { env->hflags |= HF_INHIBIT_IRQ_MASK; @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) return EXCP_HLT; } - hv_return_t r = hv_vcpu_run(cpu->hvf_fd); + 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, + 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); + 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); - env->eflags = rreg(cpu->hvf_fd, HV_X86_RFLAGS); + rip = rreg(cpu->hvf->fd, HV_X86_RIP); + env->eflags = rreg(cpu->hvf->fd, HV_X86_RFLAGS); qemu_mutex_lock_iothread(); @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) case EXIT_REASON_EPT_FAULT: { hvf_slot *slot; - uint64_t gpa = rvmcs(cpu->hvf_fd, VMCS_GUEST_PHYSICAL_ADDRESS); + 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)) { @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) store_regs(cpu); break; } else if (!string && !in) { - RAX(env) = rreg(cpu->hvf_fd, HV_X86_RAX); + 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; @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *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); + 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); + 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; @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) 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); + 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); + wreg(cpu->hvf->fd, HV_X86_XCR0, env->xcr0 | 1); macvm_set_rip(cpu, rip + ins_len); break; } @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) switch (cr) { case 0x0: { - macvm_set_cr0(cpu->hvf_fd, RRX(env, reg)); + macvm_set_cr0(cpu->hvf->fd, RRX(env, reg)); break; } case 4: { - macvm_set_cr4(cpu->hvf_fd, RRX(env, reg)); + macvm_set_cr4(cpu->hvf->fd, RRX(env, reg)); break; } case 8: { @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) break; } case EXIT_REASON_TASK_SWITCH: { - uint64_t vinfo = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_INFO); + 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 @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) break; } case EXIT_REASON_RDPMC: - wreg(cpu->hvf_fd, HV_X86_RAX, 0); - wreg(cpu->hvf_fd, HV_X86_RDX, 0); + 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: diff --git a/target/i386/hvf/vmx.h b/target/i386/hvf/vmx.h index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/vmx.h +++ b/target/i386/hvf/vmx.h @@ -XXX,XX +XXX,XX @@ #include "vmcs.h" #include "cpu.h" #include "x86.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" #include "exec/address-spaces.h" @@ -XXX,XX +XXX,XX @@ 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); + wreg(cpu->hvf->fd, HV_X86_RIP, rip); env->eip = rip; /* after moving forward in rip, we need to clean INTERRUPTABILITY */ - val = rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY); + val = rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY); if (val & (VMCS_INTERRUPTIBILITY_STI_BLOCKING | VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)) { env->hflags &= ~HF_INHIBIT_IRQ_MASK; - wvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY, + wvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY, val & ~(VMCS_INTERRUPTIBILITY_STI_BLOCKING | VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)); } @@ -XXX,XX +XXX,XX @@ static inline void vmx_clear_nmi_blocking(CPUState *cpu) CPUX86State *env = &x86_cpu->env; env->hflags2 &= ~HF2_NMI_MASK; - uint32_t gi = (uint32_t) rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY); + 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); + wvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY, gi); } static inline void vmx_set_nmi_blocking(CPUState *cpu) @@ -XXX,XX +XXX,XX @@ static inline void vmx_set_nmi_blocking(CPUState *cpu) CPUX86State *env = &x86_cpu->env; env->hflags2 |= HF2_NMI_MASK; - uint32_t gi = (uint32_t)rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY); + 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); + 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 | + 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); } @@ -XXX,XX +XXX,XX @@ 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 & + 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); } diff --git a/target/i386/hvf/x86.c b/target/i386/hvf/x86.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/x86.c +++ b/target/i386/hvf/x86.c @@ -XXX,XX +XXX,XX @@ bool x86_read_segment_descriptor(struct CPUState *cpu, } if (GDT_SEL == sel.ti) { - base = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_BASE); - limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_LIMIT); + 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); + base = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_BASE); + limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_LIMIT); } if (sel.index * 8 >= limit) { @@ -XXX,XX +XXX,XX @@ bool x86_write_segment_descriptor(struct CPUState *cpu, 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); + 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); + base = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_BASE); + limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_LIMIT); } if (sel.index * 8 >= limit) { @@ -XXX,XX +XXX,XX @@ bool x86_write_segment_descriptor(struct CPUState *cpu, 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); + 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) { @@ -XXX,XX +XXX,XX @@ bool x86_read_call_gate(struct CPUState *cpu, struct x86_call_gate *idt_desc, bool x86_is_protected(struct CPUState *cpu) { - uint64_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0); + uint64_t cr0 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR0); return cr0 & CR0_PE; } @@ -XXX,XX +XXX,XX @@ bool x86_is_v8086(struct CPUState *cpu) bool x86_is_long_mode(struct CPUState *cpu) { - return rvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER) & MSR_EFER_LMA; + return rvmcs(cpu->hvf->fd, VMCS_GUEST_IA32_EFER) & MSR_EFER_LMA; } bool x86_is_long64_mode(struct CPUState *cpu) @@ -XXX,XX +XXX,XX @@ bool x86_is_long64_mode(struct CPUState *cpu) bool x86_is_paging_mode(struct CPUState *cpu) { - uint64_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0); + 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); + uint64_t cr4 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR4); return cr4 & CR4_PAE; } diff --git a/target/i386/hvf/x86_descr.c b/target/i386/hvf/x86_descr.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/x86_descr.c +++ b/target/i386/hvf/x86_descr.c @@ -XXX,XX +XXX,XX @@ static const struct vmx_segment_field { uint32_t vmx_read_segment_limit(CPUState *cpu, X86Seg seg) { - return (uint32_t)rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].limit); + 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); + 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); + 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); + 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); + 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); + 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); + 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) diff --git a/target/i386/hvf/x86_emu.c b/target/i386/hvf/x86_emu.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/x86_emu.c +++ b/target/i386/hvf/x86_emu.c @@ -XXX,XX +XXX,XX @@ void simulate_rdmsr(struct CPUState *cpu) switch (msr) { case MSR_IA32_TSC: - val = rdtscp() + rvmcs(cpu->hvf_fd, VMCS_TSC_OFFSET); + val = rdtscp() + rvmcs(cpu->hvf->fd, VMCS_TSC_OFFSET); break; case MSR_IA32_APICBASE: val = cpu_get_apic_base(X86_CPU(cpu)->apic_state); @@ -XXX,XX +XXX,XX @@ void simulate_rdmsr(struct CPUState *cpu) val = x86_cpu->ucode_rev; break; case MSR_EFER: - val = rvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER); + val = rvmcs(cpu->hvf->fd, VMCS_GUEST_IA32_EFER); break; case MSR_FSBASE: - val = rvmcs(cpu->hvf_fd, VMCS_GUEST_FS_BASE); + val = rvmcs(cpu->hvf->fd, VMCS_GUEST_FS_BASE); break; case MSR_GSBASE: - val = rvmcs(cpu->hvf_fd, VMCS_GUEST_GS_BASE); + val = rvmcs(cpu->hvf->fd, VMCS_GUEST_GS_BASE); break; case MSR_KERNELGSBASE: - val = rvmcs(cpu->hvf_fd, VMCS_HOST_FS_BASE); + val = rvmcs(cpu->hvf->fd, VMCS_HOST_FS_BASE); break; case MSR_STAR: abort(); @@ -XXX,XX +XXX,XX @@ void simulate_wrmsr(struct CPUState *cpu) cpu_set_apic_base(X86_CPU(cpu)->apic_state, data); break; case MSR_FSBASE: - wvmcs(cpu->hvf_fd, VMCS_GUEST_FS_BASE, data); + wvmcs(cpu->hvf->fd, VMCS_GUEST_FS_BASE, data); break; case MSR_GSBASE: - wvmcs(cpu->hvf_fd, VMCS_GUEST_GS_BASE, data); + wvmcs(cpu->hvf->fd, VMCS_GUEST_GS_BASE, data); break; case MSR_KERNELGSBASE: - wvmcs(cpu->hvf_fd, VMCS_HOST_FS_BASE, data); + wvmcs(cpu->hvf->fd, VMCS_HOST_FS_BASE, data); break; case MSR_STAR: abort(); @@ -XXX,XX +XXX,XX @@ void simulate_wrmsr(struct CPUState *cpu) break; case MSR_EFER: /*printf("new efer %llx\n", EFER(cpu));*/ - wvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER, data); + wvmcs(cpu->hvf->fd, VMCS_GUEST_IA32_EFER, data); if (data & MSR_EFER_NXE) { - hv_vcpu_invalidate_tlb(cpu->hvf_fd); + hv_vcpu_invalidate_tlb(cpu->hvf->fd); } break; case MSR_MTRRphysBase(0): @@ -XXX,XX +XXX,XX @@ void load_regs(struct CPUState *cpu) CPUX86State *env = &x86_cpu->env; int i = 0; - RRX(env, R_EAX) = rreg(cpu->hvf_fd, HV_X86_RAX); - RRX(env, R_EBX) = rreg(cpu->hvf_fd, HV_X86_RBX); - RRX(env, R_ECX) = rreg(cpu->hvf_fd, HV_X86_RCX); - RRX(env, R_EDX) = rreg(cpu->hvf_fd, HV_X86_RDX); - RRX(env, R_ESI) = rreg(cpu->hvf_fd, HV_X86_RSI); - RRX(env, R_EDI) = rreg(cpu->hvf_fd, HV_X86_RDI); - RRX(env, R_ESP) = rreg(cpu->hvf_fd, HV_X86_RSP); - RRX(env, R_EBP) = rreg(cpu->hvf_fd, HV_X86_RBP); + RRX(env, R_EAX) = rreg(cpu->hvf->fd, HV_X86_RAX); + RRX(env, R_EBX) = rreg(cpu->hvf->fd, HV_X86_RBX); + RRX(env, R_ECX) = rreg(cpu->hvf->fd, HV_X86_RCX); + RRX(env, R_EDX) = rreg(cpu->hvf->fd, HV_X86_RDX); + RRX(env, R_ESI) = rreg(cpu->hvf->fd, HV_X86_RSI); + RRX(env, R_EDI) = rreg(cpu->hvf->fd, HV_X86_RDI); + RRX(env, R_ESP) = rreg(cpu->hvf->fd, HV_X86_RSP); + RRX(env, R_EBP) = rreg(cpu->hvf->fd, HV_X86_RBP); for (i = 8; i < 16; i++) { - RRX(env, i) = rreg(cpu->hvf_fd, HV_X86_RAX + i); + RRX(env, i) = rreg(cpu->hvf->fd, HV_X86_RAX + i); } - env->eflags = rreg(cpu->hvf_fd, HV_X86_RFLAGS); + env->eflags = rreg(cpu->hvf->fd, HV_X86_RFLAGS); rflags_to_lflags(env); - env->eip = rreg(cpu->hvf_fd, HV_X86_RIP); + env->eip = rreg(cpu->hvf->fd, HV_X86_RIP); } void store_regs(struct CPUState *cpu) @@ -XXX,XX +XXX,XX @@ void store_regs(struct CPUState *cpu) CPUX86State *env = &x86_cpu->env; int i = 0; - wreg(cpu->hvf_fd, HV_X86_RAX, RAX(env)); - wreg(cpu->hvf_fd, HV_X86_RBX, RBX(env)); - wreg(cpu->hvf_fd, HV_X86_RCX, RCX(env)); - wreg(cpu->hvf_fd, HV_X86_RDX, RDX(env)); - wreg(cpu->hvf_fd, HV_X86_RSI, RSI(env)); - wreg(cpu->hvf_fd, HV_X86_RDI, RDI(env)); - wreg(cpu->hvf_fd, HV_X86_RBP, RBP(env)); - wreg(cpu->hvf_fd, HV_X86_RSP, RSP(env)); + wreg(cpu->hvf->fd, HV_X86_RAX, RAX(env)); + wreg(cpu->hvf->fd, HV_X86_RBX, RBX(env)); + wreg(cpu->hvf->fd, HV_X86_RCX, RCX(env)); + wreg(cpu->hvf->fd, HV_X86_RDX, RDX(env)); + wreg(cpu->hvf->fd, HV_X86_RSI, RSI(env)); + wreg(cpu->hvf->fd, HV_X86_RDI, RDI(env)); + wreg(cpu->hvf->fd, HV_X86_RBP, RBP(env)); + wreg(cpu->hvf->fd, HV_X86_RSP, RSP(env)); for (i = 8; i < 16; i++) { - wreg(cpu->hvf_fd, HV_X86_RAX + i, RRX(env, i)); + wreg(cpu->hvf->fd, HV_X86_RAX + i, RRX(env, i)); } lflags_to_rflags(env); - wreg(cpu->hvf_fd, HV_X86_RFLAGS, env->eflags); + wreg(cpu->hvf->fd, HV_X86_RFLAGS, env->eflags); macvm_set_rip(cpu, env->eip); } diff --git a/target/i386/hvf/x86_mmu.c b/target/i386/hvf/x86_mmu.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/x86_mmu.c +++ b/target/i386/hvf/x86_mmu.c @@ -XXX,XX +XXX,XX @@ static bool test_pt_entry(struct CPUState *cpu, struct gpt_translation *pt, pt->err_code |= MMU_PAGE_PT; } - uint32_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0); + uint32_t cr0 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR0); /* check protection */ if (cr0 & CR0_WP) { if (pt->write_access && !pte_write_access(pte)) { @@ -XXX,XX +XXX,XX @@ static bool walk_gpt(struct CPUState *cpu, target_ulong addr, int err_code, { int top_level, level; bool is_large = false; - target_ulong cr3 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR3); + 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)); diff --git a/target/i386/hvf/x86_task.c b/target/i386/hvf/x86_task.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/x86_task.c +++ b/target/i386/hvf/x86_task.c @@ -XXX,XX +XXX,XX @@ 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); + wvmcs(cpu->hvf->fd, VMCS_GUEST_CR3, tss->cr3); env->eip = tss->eip; env->eflags = tss->eflags | 2; @@ -XXX,XX +XXX,XX @@ static int task_switch_32(CPUState *cpu, x68_segment_selector tss_sel, x68_segme 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); + 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); + int ins_len = rvmcs(cpu->hvf->fd, VMCS_EXIT_INSTRUCTION_LENGTH); macvm_set_rip(cpu, rip + ins_len); return; } @@ -XXX,XX +XXX,XX @@ void vmx_handle_task_switch(CPUState *cpu, x68_segment_selector tss_sel, int rea //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); + 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); + hv_vcpu_invalidate_tlb(cpu->hvf->fd); + hv_vcpu_flush(cpu->hvf->fd); } diff --git a/target/i386/hvf/x86hvf.c b/target/i386/hvf/x86hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/x86hvf.c +++ b/target/i386/hvf/x86hvf.c @@ -XXX,XX +XXX,XX @@ void hvf_put_xsave(CPUState *cpu_state) x86_cpu_xsave_all_areas(X86_CPU(cpu_state), xsave); - if (hv_vcpu_write_fpstate(cpu_state->hvf_fd, (void*)xsave, 4096)) { + if (hv_vcpu_write_fpstate(cpu_state->hvf->fd, (void*)xsave, 4096)) { abort(); } } @@ -XXX,XX +XXX,XX @@ 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_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_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]); + /* 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); + 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]); + 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); @@ -XXX,XX +XXX,XX @@ void hvf_put_segments(CPUState *cpu_state) 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); + 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, + 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, + 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, + 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); + 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); + 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); + 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); } @@ -XXX,XX +XXX,XX @@ void hvf_get_xsave(CPUState *cpu_state) xsave = X86_CPU(cpu_state)->env.xsave_buf; - if (hv_vcpu_read_fpstate(cpu_state->hvf_fd, (void*)xsave, 4096)) { + if (hv_vcpu_read_fpstate(cpu_state->hvf->fd, (void*)xsave, 4096)) { abort(); } @@ -XXX,XX +XXX,XX @@ void hvf_get_segments(CPUState *cpu_state) 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->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[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->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); + env->efer = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_IA32_EFER); } void hvf_get_msrs(CPUState *cpu_state) @@ -XXX,XX +XXX,XX @@ 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); + 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); + 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); + 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); + 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); + 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); + hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_IA32_APICBASE, &tmp); - env->tsc = rdtscp() + rvmcs(cpu_state->hvf_fd, VMCS_TSC_OFFSET); + env->tsc = rdtscp() + rvmcs(cpu_state->hvf->fd, VMCS_TSC_OFFSET); } int hvf_put_registers(CPUState *cpu_state) @@ -XXX,XX +XXX,XX @@ 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_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); + wreg(cpu_state->hvf->fd, HV_X86_XCR0, env->xcr0); hvf_put_xsave(cpu_state); @@ -XXX,XX +XXX,XX @@ int hvf_put_registers(CPUState *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]); + 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; } @@ -XXX,XX +XXX,XX @@ 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->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); + 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); + 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); + 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); x86_update_hflags(env); return 0; @@ -XXX,XX +XXX,XX @@ int hvf_get_registers(CPUState *cpu_state) 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 | + 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 & + 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); } @@ -XXX,XX +XXX,XX @@ bool hvf_inject_interrupts(CPUState *cpu_state) 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); + 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); } @@ -XXX,XX +XXX,XX @@ bool hvf_inject_interrupts(CPUState *cpu_state) 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); + 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, + wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_EXCEPTION_ERROR, env->error_code); /* Indicate that VMCS_ENTRY_EXCEPTION_ERROR is valid */ info |= VMCS_INTR_DEL_ERRCODE; } /*printf("reinject %lx err %d\n", info, err);*/ - wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INTR_INFO, info); + wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_INTR_INFO, info); }; } @@ -XXX,XX +XXX,XX @@ bool hvf_inject_interrupts(CPUState *cpu_state) 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 | EXCP02_NMI; - wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INTR_INFO, info); + wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_INTR_INFO, info); } else { vmx_set_nmi_window_exiting(cpu_state); } @@ -XXX,XX +XXX,XX @@ bool hvf_inject_interrupts(CPUState *cpu_state) 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 | + wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_INTR_INFO, line | VMCS_INTR_VALID | VMCS_INTR_T_HWINTR); } } @@ -XXX,XX +XXX,XX @@ int hvf_process_events(CPUState *cpu_state) X86CPU *cpu = X86_CPU(cpu_state); CPUX86State *env = &cpu->env; - env->eflags = rreg(cpu_state->hvf_fd, HV_X86_RFLAGS); + env->eflags = rreg(cpu_state->hvf->fd, HV_X86_RFLAGS); if (cpu_state->interrupt_request & CPU_INTERRUPT_INIT) { cpu_synchronize_state(cpu_state); -- 2.24.3 (Apple Git-128) In Hypervisor.framework, we just pass PSCI calls straight on to the QEMU emulation of it. That means, if TCG is compatible with PSCI 0.2, so are we. Let's transpose that fact in code too. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- target/arm/cpu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_initfn(Object *obj) if (tcg_enabled()) { cpu->psci_version = 2; /* TCG implements PSCI 0.2 */ } + + if (hvf_enabled()) { + cpu->psci_version = 2; /* HVF uses TCG's PSCI */ + } } static Property arm_cpu_gt_cntfrq_property = -- 2.24.3 (Apple Git-128) When clearing internal state of a CPU, we should also make sure that HVF knows about it and can push the new values down to vcpu state. Make sure that with HVF enabled, we tell it that it should synchronize CPU state on next entry after a reset. This fixes PSCI handling, because now newly pushed state such as X0 and PC on remote CPU enablement also get pushed into HVF. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- target/arm/arm-powerctl.c | 1 + target/arm/cpu.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/target/arm/arm-powerctl.c b/target/arm/arm-powerctl.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/arm-powerctl.c +++ b/target/arm/arm-powerctl.c @@ -XXX,XX +XXX,XX @@ #include "arm-powerctl.h" #include "qemu/log.h" #include "qemu/main-loop.h" +#include "sysemu/hw_accel.h" #ifndef DEBUG_ARM_POWERCTL #define DEBUG_ARM_POWERCTL 0 diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(DeviceState *dev) #ifndef CONFIG_USER_ONLY if (kvm_enabled()) { kvm_arm_reset_vcpu(cpu); + } else if (hvf_enabled()) { + s->vcpu_dirty = true; } #endif -- 2.24.3 (Apple Git-128) With Apple Silicon available to the masses, it's a good time to add support for driving its virtualization extensions from QEMU. This patch adds all necessary architecture specific code to get basic VMs working. It's still pretty raw, but definitely functional. Known limitations: - Vtimer acknowledgement is hacky - Should implement more sysregs and fault on invalid ones then - WFI handling is missing, need to marry it with vtimer Signed-off-by: Alexander Graf <agraf@csgraf.de> --- v1 -> v2: - Merge vcpu kick function patch - Implement WFI handling (allows vCPUs to sleep) - Synchronize system registers (fixes OVMF crashes and reboot) - Don't always call cpu_synchronize_state() - Use more fine grained iothread locking - Populate aa64mmfr0 from hardware --- MAINTAINERS | 5 + accel/hvf/hvf-cpus.c | 14 + include/sysemu/hvf_int.h | 7 +- target/arm/hvf/hvf.c | 603 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 628 insertions(+), 1 deletion(-) create mode 100644 target/arm/hvf/hvf.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: accel/accel.c F: accel/Makefile.objs F: accel/stubs/Makefile.objs +Apple Silicon HVF CPUs +M: Alexander Graf <agraf@csgraf.de> +S: Maintained +F: target/arm/hvf/ + X86 HVF CPUs M: Cameron Esfahani <dirty@apple.com> M: Roman Bolshakov <r.bolshakov@yadro.com> diff --git a/accel/hvf/hvf-cpus.c b/accel/hvf/hvf-cpus.c index XXXXXXX..XXXXXXX 100644 --- a/accel/hvf/hvf-cpus.c +++ b/accel/hvf/hvf-cpus.c @@ -XXX,XX +XXX,XX @@ #include <Hypervisor/Hypervisor.h> +#ifdef __aarch64__ +#define HV_VM_DEFAULT NULL +#endif + /* Memory slots */ struct mac_slot { @@ -XXX,XX +XXX,XX @@ static int hvf_init_vcpu(CPUState *cpu) sigdelset(&set, SIG_IPI); pthread_sigmask(SIG_SETMASK, &set, NULL); +#ifdef __aarch64__ + r = hv_vcpu_create(&cpu->hvf->fd, (hv_vcpu_exit_t **)&cpu->hvf->exit, NULL); +#else r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf->fd, HV_VCPU_DEFAULT); +#endif cpu->vcpu_dirty = 1; assert_hvf_ok(r); @@ -XXX,XX +XXX,XX @@ static void hvf_start_vcpu_thread(CPUState *cpu) cpu, QEMU_THREAD_JOINABLE); } +__attribute__((weak)) void hvf_kick_vcpu_thread(CPUState *cpu) +{ + cpus_kick_thread(cpu); +} + static const CpusAccel hvf_cpus = { .create_vcpu_thread = hvf_start_vcpu_thread, + .kick_vcpu_thread = hvf_kick_vcpu_thread, .synchronize_post_reset = hvf_cpu_synchronize_post_reset, .synchronize_post_init = hvf_cpu_synchronize_post_init, diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/hvf_int.h +++ b/include/sysemu/hvf_int.h @@ -XXX,XX +XXX,XX @@ #ifndef HVF_INT_H #define HVF_INT_H +#include "qemu/osdep.h" #include <Hypervisor/Hypervisor.h> #define HVF_MAX_VCPU 0x10 @@ -XXX,XX +XXX,XX @@ struct HVFState { extern HVFState *hvf_state; struct hvf_vcpu_state { - int fd; + uint64_t fd; + void *exit; + struct timespec ts; + bool sleeping; }; void assert_hvf_ok(hv_return_t ret); @@ -XXX,XX +XXX,XX @@ int hvf_arch_init_vcpu(CPUState *cpu); void hvf_arch_vcpu_destroy(CPUState *cpu); int hvf_vcpu_exec(CPUState *cpu); hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t); +void hvf_kick_vcpu_thread(CPUState *cpu); #endif diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU Hypervisor.framework support for Apple Silicon + + * Copyright 2020 Alexander Graf <agraf@csgraf.de> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/error-report.h" + +#include "sysemu/runstate.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" +#include "sysemu/hw_accel.h" + +#include <Hypervisor/Hypervisor.h> + +#include "exec/address-spaces.h" +#include "hw/irq.h" +#include "qemu/main-loop.h" +#include "sysemu/accel.h" +#include "sysemu/cpus.h" +#include "target/arm/cpu.h" +#include "target/arm/internals.h" + +#define HVF_DEBUG 0 +#define DPRINTF(...) \ + if (HVF_DEBUG) { \ + fprintf(stderr, "HVF %s:%d ", __func__, __LINE__); \ + fprintf(stderr, __VA_ARGS__); \ + fprintf(stderr, "\n"); \ + } + +#define SYSREG(op0, op1, op2, crn, crm) \ + ((op0 << 20) | (op2 << 17) | (op1 << 14) | (crn << 10) | (crm << 1)) +#define SYSREG_MASK SYSREG(0x3, 0x7, 0x7, 0xf, 0xf) +#define SYSREG_CNTPCT_EL0 SYSREG(3, 3, 1, 14, 0) +#define SYSREG_PMCCNTR_EL0 SYSREG(3, 3, 0, 9, 13) + +#define WFX_IS_WFE (1 << 0) + +struct hvf_reg_match { + int reg; + uint64_t offset; +}; + +static const struct hvf_reg_match hvf_reg_match[] = { + { HV_REG_X0, offsetof(CPUARMState, xregs[0]) }, + { HV_REG_X1, offsetof(CPUARMState, xregs[1]) }, + { HV_REG_X2, offsetof(CPUARMState, xregs[2]) }, + { HV_REG_X3, offsetof(CPUARMState, xregs[3]) }, + { HV_REG_X4, offsetof(CPUARMState, xregs[4]) }, + { HV_REG_X5, offsetof(CPUARMState, xregs[5]) }, + { HV_REG_X6, offsetof(CPUARMState, xregs[6]) }, + { HV_REG_X7, offsetof(CPUARMState, xregs[7]) }, + { HV_REG_X8, offsetof(CPUARMState, xregs[8]) }, + { HV_REG_X9, offsetof(CPUARMState, xregs[9]) }, + { HV_REG_X10, offsetof(CPUARMState, xregs[10]) }, + { HV_REG_X11, offsetof(CPUARMState, xregs[11]) }, + { HV_REG_X12, offsetof(CPUARMState, xregs[12]) }, + { HV_REG_X13, offsetof(CPUARMState, xregs[13]) }, + { HV_REG_X14, offsetof(CPUARMState, xregs[14]) }, + { HV_REG_X15, offsetof(CPUARMState, xregs[15]) }, + { HV_REG_X16, offsetof(CPUARMState, xregs[16]) }, + { HV_REG_X17, offsetof(CPUARMState, xregs[17]) }, + { HV_REG_X18, offsetof(CPUARMState, xregs[18]) }, + { HV_REG_X19, offsetof(CPUARMState, xregs[19]) }, + { HV_REG_X20, offsetof(CPUARMState, xregs[20]) }, + { HV_REG_X21, offsetof(CPUARMState, xregs[21]) }, + { HV_REG_X22, offsetof(CPUARMState, xregs[22]) }, + { HV_REG_X23, offsetof(CPUARMState, xregs[23]) }, + { HV_REG_X24, offsetof(CPUARMState, xregs[24]) }, + { HV_REG_X25, offsetof(CPUARMState, xregs[25]) }, + { HV_REG_X26, offsetof(CPUARMState, xregs[26]) }, + { HV_REG_X27, offsetof(CPUARMState, xregs[27]) }, + { HV_REG_X28, offsetof(CPUARMState, xregs[28]) }, + { HV_REG_X29, offsetof(CPUARMState, xregs[29]) }, + { HV_REG_X30, offsetof(CPUARMState, xregs[30]) }, + { HV_REG_PC, offsetof(CPUARMState, pc) }, +}; + +static const struct hvf_reg_match hvf_sreg_match[] = { + { HV_SYS_REG_DBGBVR0_EL1, offsetof(CPUARMState, cp15.dbgbvr[0]) }, + { HV_SYS_REG_DBGBCR0_EL1, offsetof(CPUARMState, cp15.dbgbcr[0]) }, + { HV_SYS_REG_DBGWVR0_EL1, offsetof(CPUARMState, cp15.dbgwvr[0]) }, + { HV_SYS_REG_DBGWCR0_EL1, offsetof(CPUARMState, cp15.dbgwcr[0]) }, + { HV_SYS_REG_DBGBVR1_EL1, offsetof(CPUARMState, cp15.dbgbvr[1]) }, + { HV_SYS_REG_DBGBCR1_EL1, offsetof(CPUARMState, cp15.dbgbcr[1]) }, + { HV_SYS_REG_DBGWVR1_EL1, offsetof(CPUARMState, cp15.dbgwvr[1]) }, + { HV_SYS_REG_DBGWCR1_EL1, offsetof(CPUARMState, cp15.dbgwcr[1]) }, + { HV_SYS_REG_MDSCR_EL1, offsetof(CPUARMState, cp15.mdscr_el1) }, + { HV_SYS_REG_DBGBVR2_EL1, offsetof(CPUARMState, cp15.dbgbvr[2]) }, + { HV_SYS_REG_DBGBCR2_EL1, offsetof(CPUARMState, cp15.dbgbcr[2]) }, + { HV_SYS_REG_DBGWVR2_EL1, offsetof(CPUARMState, cp15.dbgwvr[2]) }, + { HV_SYS_REG_DBGWCR2_EL1, offsetof(CPUARMState, cp15.dbgwcr[2]) }, + { HV_SYS_REG_DBGBVR3_EL1, offsetof(CPUARMState, cp15.dbgbvr[3]) }, + { HV_SYS_REG_DBGBCR3_EL1, offsetof(CPUARMState, cp15.dbgbcr[3]) }, + { HV_SYS_REG_DBGWVR3_EL1, offsetof(CPUARMState, cp15.dbgwvr[3]) }, + { HV_SYS_REG_DBGWCR3_EL1, offsetof(CPUARMState, cp15.dbgwcr[3]) }, + { HV_SYS_REG_DBGBVR4_EL1, offsetof(CPUARMState, cp15.dbgbvr[4]) }, + { HV_SYS_REG_DBGBCR4_EL1, offsetof(CPUARMState, cp15.dbgbcr[4]) }, + { HV_SYS_REG_DBGWVR4_EL1, offsetof(CPUARMState, cp15.dbgwvr[4]) }, + { HV_SYS_REG_DBGWCR4_EL1, offsetof(CPUARMState, cp15.dbgwcr[4]) }, + { HV_SYS_REG_DBGBVR5_EL1, offsetof(CPUARMState, cp15.dbgbvr[5]) }, + { HV_SYS_REG_DBGBCR5_EL1, offsetof(CPUARMState, cp15.dbgbcr[5]) }, + { HV_SYS_REG_DBGWVR5_EL1, offsetof(CPUARMState, cp15.dbgwvr[5]) }, + { HV_SYS_REG_DBGWCR5_EL1, offsetof(CPUARMState, cp15.dbgwcr[5]) }, + { HV_SYS_REG_DBGBVR6_EL1, offsetof(CPUARMState, cp15.dbgbvr[6]) }, + { HV_SYS_REG_DBGBCR6_EL1, offsetof(CPUARMState, cp15.dbgbcr[6]) }, + { HV_SYS_REG_DBGWVR6_EL1, offsetof(CPUARMState, cp15.dbgwvr[6]) }, + { HV_SYS_REG_DBGWCR6_EL1, offsetof(CPUARMState, cp15.dbgwcr[6]) }, + { HV_SYS_REG_DBGBVR7_EL1, offsetof(CPUARMState, cp15.dbgbvr[7]) }, + { HV_SYS_REG_DBGBCR7_EL1, offsetof(CPUARMState, cp15.dbgbcr[7]) }, + { HV_SYS_REG_DBGWVR7_EL1, offsetof(CPUARMState, cp15.dbgwvr[7]) }, + { HV_SYS_REG_DBGWCR7_EL1, offsetof(CPUARMState, cp15.dbgwcr[7]) }, + { HV_SYS_REG_DBGBVR8_EL1, offsetof(CPUARMState, cp15.dbgbvr[8]) }, + { HV_SYS_REG_DBGBCR8_EL1, offsetof(CPUARMState, cp15.dbgbcr[8]) }, + { HV_SYS_REG_DBGWVR8_EL1, offsetof(CPUARMState, cp15.dbgwvr[8]) }, + { HV_SYS_REG_DBGWCR8_EL1, offsetof(CPUARMState, cp15.dbgwcr[8]) }, + { HV_SYS_REG_DBGBVR9_EL1, offsetof(CPUARMState, cp15.dbgbvr[9]) }, + { HV_SYS_REG_DBGBCR9_EL1, offsetof(CPUARMState, cp15.dbgbcr[9]) }, + { HV_SYS_REG_DBGWVR9_EL1, offsetof(CPUARMState, cp15.dbgwvr[9]) }, + { HV_SYS_REG_DBGWCR9_EL1, offsetof(CPUARMState, cp15.dbgwcr[9]) }, + { HV_SYS_REG_DBGBVR10_EL1, offsetof(CPUARMState, cp15.dbgbvr[10]) }, + { HV_SYS_REG_DBGBCR10_EL1, offsetof(CPUARMState, cp15.dbgbcr[10]) }, + { HV_SYS_REG_DBGWVR10_EL1, offsetof(CPUARMState, cp15.dbgwvr[10]) }, + { HV_SYS_REG_DBGWCR10_EL1, offsetof(CPUARMState, cp15.dbgwcr[10]) }, + { HV_SYS_REG_DBGBVR11_EL1, offsetof(CPUARMState, cp15.dbgbvr[11]) }, + { HV_SYS_REG_DBGBCR11_EL1, offsetof(CPUARMState, cp15.dbgbcr[11]) }, + { HV_SYS_REG_DBGWVR11_EL1, offsetof(CPUARMState, cp15.dbgwvr[11]) }, + { HV_SYS_REG_DBGWCR11_EL1, offsetof(CPUARMState, cp15.dbgwcr[11]) }, + { HV_SYS_REG_DBGBVR12_EL1, offsetof(CPUARMState, cp15.dbgbvr[12]) }, + { HV_SYS_REG_DBGBCR12_EL1, offsetof(CPUARMState, cp15.dbgbcr[12]) }, + { HV_SYS_REG_DBGWVR12_EL1, offsetof(CPUARMState, cp15.dbgwvr[12]) }, + { HV_SYS_REG_DBGWCR12_EL1, offsetof(CPUARMState, cp15.dbgwcr[12]) }, + { HV_SYS_REG_DBGBVR13_EL1, offsetof(CPUARMState, cp15.dbgbvr[13]) }, + { HV_SYS_REG_DBGBCR13_EL1, offsetof(CPUARMState, cp15.dbgbcr[13]) }, + { HV_SYS_REG_DBGWVR13_EL1, offsetof(CPUARMState, cp15.dbgwvr[13]) }, + { HV_SYS_REG_DBGWCR13_EL1, offsetof(CPUARMState, cp15.dbgwcr[13]) }, + { HV_SYS_REG_DBGBVR14_EL1, offsetof(CPUARMState, cp15.dbgbvr[14]) }, + { HV_SYS_REG_DBGBCR14_EL1, offsetof(CPUARMState, cp15.dbgbcr[14]) }, + { HV_SYS_REG_DBGWVR14_EL1, offsetof(CPUARMState, cp15.dbgwvr[14]) }, + { HV_SYS_REG_DBGWCR14_EL1, offsetof(CPUARMState, cp15.dbgwcr[14]) }, + { HV_SYS_REG_DBGBVR15_EL1, offsetof(CPUARMState, cp15.dbgbvr[15]) }, + { HV_SYS_REG_DBGBCR15_EL1, offsetof(CPUARMState, cp15.dbgbcr[15]) }, + { HV_SYS_REG_DBGWVR15_EL1, offsetof(CPUARMState, cp15.dbgwvr[15]) }, + { HV_SYS_REG_DBGWCR15_EL1, offsetof(CPUARMState, cp15.dbgwcr[15]) }, + { HV_SYS_REG_MIDR_EL1, offsetof(CPUARMState, cp15.c0_cpuid) }, + { HV_SYS_REG_SCTLR_EL1, offsetof(CPUARMState, cp15.sctlr_ns) }, + { HV_SYS_REG_CPACR_EL1, offsetof(CPUARMState, cp15.cpacr_el1) }, + { HV_SYS_REG_TTBR0_EL1, offsetof(CPUARMState, cp15.ttbr0_ns) }, + { HV_SYS_REG_TTBR1_EL1, offsetof(CPUARMState, cp15.ttbr1_ns) }, + { HV_SYS_REG_TCR_EL1, offsetof(CPUARMState, cp15.tcr_el[1]) }, + { HV_SYS_REG_APIAKEYLO_EL1, offsetof(CPUARMState, keys.apia.lo) }, + { HV_SYS_REG_APIAKEYHI_EL1, offsetof(CPUARMState, keys.apia.hi) }, + { HV_SYS_REG_APIBKEYLO_EL1, offsetof(CPUARMState, keys.apib.lo) }, + { HV_SYS_REG_APIBKEYHI_EL1, offsetof(CPUARMState, keys.apib.hi) }, + { HV_SYS_REG_APDAKEYLO_EL1, offsetof(CPUARMState, keys.apda.lo) }, + { HV_SYS_REG_APDAKEYHI_EL1, offsetof(CPUARMState, keys.apda.hi) }, + { HV_SYS_REG_APDBKEYLO_EL1, offsetof(CPUARMState, keys.apdb.lo) }, + { HV_SYS_REG_APDBKEYHI_EL1, offsetof(CPUARMState, keys.apdb.hi) }, + { HV_SYS_REG_APGAKEYLO_EL1, offsetof(CPUARMState, keys.apga.lo) }, + { HV_SYS_REG_APGAKEYHI_EL1, offsetof(CPUARMState, keys.apga.hi) }, + { HV_SYS_REG_SPSR_EL1, offsetof(CPUARMState, banked_spsr[BANK_SVC]) }, + { HV_SYS_REG_ELR_EL1, offsetof(CPUARMState, elr_el[1]) }, + { HV_SYS_REG_SP_EL0, offsetof(CPUARMState, sp_el[0]) }, + { HV_SYS_REG_ESR_EL1, offsetof(CPUARMState, cp15.esr_el[1]) }, + { HV_SYS_REG_FAR_EL1, offsetof(CPUARMState, cp15.far_el[1]) }, + { HV_SYS_REG_PAR_EL1, offsetof(CPUARMState, cp15.par_el[1]) }, + { HV_SYS_REG_MAIR_EL1, offsetof(CPUARMState, cp15.mair_el[1]) }, + { HV_SYS_REG_VBAR_EL1, offsetof(CPUARMState, cp15.vbar_ns) }, + { HV_SYS_REG_CONTEXTIDR_EL1, offsetof(CPUARMState, cp15.contextidr_el[1]) }, + { HV_SYS_REG_TPIDR_EL1, offsetof(CPUARMState, cp15.tpidr_el[1]) }, + { HV_SYS_REG_CNTKCTL_EL1, offsetof(CPUARMState, cp15.c14_cntkctl) }, + { HV_SYS_REG_CSSELR_EL1, offsetof(CPUARMState, cp15.csselr_ns) }, + { HV_SYS_REG_TPIDR_EL0, offsetof(CPUARMState, cp15.tpidr_el[0]) }, + { HV_SYS_REG_TPIDRRO_EL0, offsetof(CPUARMState, cp15.tpidrro_el[0]) }, + { HV_SYS_REG_CNTV_CTL_EL0, offsetof(CPUARMState, cp15.c14_timer[GTIMER_VIRT].ctl) }, + { HV_SYS_REG_CNTV_CVAL_EL0, offsetof(CPUARMState, cp15.c14_timer[GTIMER_VIRT].cval) }, + { HV_SYS_REG_SP_EL1, offsetof(CPUARMState, sp_el[1]) }, +}; + +int hvf_get_registers(CPUState *cpu) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + hv_return_t ret; + uint64_t val; + int i; + + for (i = 0; i < ARRAY_SIZE(hvf_reg_match); i++) { + ret = hv_vcpu_get_reg(cpu->hvf->fd, hvf_reg_match[i].reg, &val); + *(uint64_t *)((void *)env + hvf_reg_match[i].offset) = val; + assert_hvf_ok(ret); + } + + val = 0; + ret = hv_vcpu_get_reg(cpu->hvf->fd, HV_REG_FPCR, &val); + assert_hvf_ok(ret); + vfp_set_fpcr(env, val); + + val = 0; + ret = hv_vcpu_get_reg(cpu->hvf->fd, HV_REG_FPSR, &val); + assert_hvf_ok(ret); + vfp_set_fpsr(env, val); + + ret = hv_vcpu_get_reg(cpu->hvf->fd, HV_REG_CPSR, &val); + assert_hvf_ok(ret); + pstate_write(env, val); + + for (i = 0; i < ARRAY_SIZE(hvf_sreg_match); i++) { + ret = hv_vcpu_get_sys_reg(cpu->hvf->fd, hvf_sreg_match[i].reg, &val); + *(uint64_t *)((void *)env + hvf_sreg_match[i].offset) = val; + assert_hvf_ok(ret); + } + + return 0; +} + +int hvf_put_registers(CPUState *cpu) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + hv_return_t ret; + uint64_t val; + int i; + + for (i = 0; i < ARRAY_SIZE(hvf_reg_match); i++) { + val = *(uint64_t *)((void *)env + hvf_reg_match[i].offset); + ret = hv_vcpu_set_reg(cpu->hvf->fd, hvf_reg_match[i].reg, val); + + assert_hvf_ok(ret); + } + + ret = hv_vcpu_set_reg(cpu->hvf->fd, HV_REG_FPCR, vfp_get_fpcr(env)); + assert_hvf_ok(ret); + + ret = hv_vcpu_set_reg(cpu->hvf->fd, HV_REG_FPSR, vfp_get_fpsr(env)); + assert_hvf_ok(ret); + + ret = hv_vcpu_set_reg(cpu->hvf->fd, HV_REG_CPSR, pstate_read(env)); + assert_hvf_ok(ret); + + for (i = 0; i < ARRAY_SIZE(hvf_sreg_match); i++) { + val = *(uint64_t *)((void *)env + hvf_sreg_match[i].offset); + ret = hv_vcpu_set_sys_reg(cpu->hvf->fd, hvf_sreg_match[i].reg, val); + + assert_hvf_ok(ret); + } + + ret = hv_vcpu_set_sys_reg(cpu->hvf->fd, HV_SYS_REG_MPIDR_EL1, + arm_cpu->mp_affinity); + assert_hvf_ok(ret); + + return 0; +} + +static void flush_cpu_state(CPUState *cpu) +{ + if (cpu->vcpu_dirty) { + hvf_put_registers(cpu); + cpu->vcpu_dirty = false; + } +} + +static void hvf_set_reg(CPUState *cpu, int rt, uint64_t val) +{ + hv_return_t r; + + flush_cpu_state(cpu); + + if (rt < 31) { + r = hv_vcpu_set_reg(cpu->hvf->fd, HV_REG_X0 + rt, val); + assert_hvf_ok(r); + } +} + +static uint64_t hvf_get_reg(CPUState *cpu, int rt) +{ + uint64_t val = 0; + hv_return_t r; + + flush_cpu_state(cpu); + + if (rt < 31) { + r = hv_vcpu_get_reg(cpu->hvf->fd, HV_REG_X0 + rt, &val); + assert_hvf_ok(r); + } + + return val; +} + +void hvf_arch_vcpu_destroy(CPUState *cpu) +{ +} + +int hvf_arch_init_vcpu(CPUState *cpu) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + hv_return_t ret; + + env->aarch64 = 1; + asm volatile("mrs %0, cntfrq_el0" : "=r"(arm_cpu->gt_cntfrq_hz)); + + ret = hv_vcpu_set_sys_reg(cpu->hvf->fd, HV_SYS_REG_SCTLR_EL1, + arm_cpu->reset_sctlr); + assert_hvf_ok(ret); + + /* We're limited to local hardware caps, override internal versions */ + ret = hv_vcpu_get_sys_reg(cpu->hvf->fd, HV_SYS_REG_ID_AA64MMFR0_EL1, + &arm_cpu->isar.id_aa64mmfr0); + + return 0; +} + +void hvf_kick_vcpu_thread(CPUState *cpu) +{ + if (cpu->hvf->sleeping) { + /* + * When sleeping, make sure we always send signals. Also, clear the + * timespec, so that an IPI that arrives between setting hvf->sleeping + * and the nanosleep syscall still aborts the sleep. + */ + cpu->thread_kicked = false; + cpu->hvf->ts = (struct timespec){ }; + cpus_kick_thread(cpu); + } else { + hv_vcpus_exit(&cpu->hvf->fd, 1); + } +} + +static int hvf_inject_interrupts(CPUState *cpu) +{ + if (cpu->interrupt_request & CPU_INTERRUPT_FIQ) { + DPRINTF("injecting FIQ"); + hv_vcpu_set_pending_interrupt(cpu->hvf->fd, HV_INTERRUPT_TYPE_FIQ, true); + } + + if (cpu->interrupt_request & CPU_INTERRUPT_HARD) { + DPRINTF("injecting IRQ"); + hv_vcpu_set_pending_interrupt(cpu->hvf->fd, HV_INTERRUPT_TYPE_IRQ, true); + } + + return 0; +} + +int hvf_vcpu_exec(CPUState *cpu) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + hv_vcpu_exit_t *hvf_exit = cpu->hvf->exit; + hv_return_t r; + int ret = 0; + + qemu_mutex_unlock_iothread(); + + do { + bool advance_pc = false; + + qemu_mutex_lock_iothread(); + current_cpu = cpu; + qemu_wait_io_event_common(cpu); + qemu_mutex_unlock_iothread(); + + flush_cpu_state(cpu); + + if (hvf_inject_interrupts(cpu)) { + return EXCP_INTERRUPT; + } + + if (cpu->halted) { + qemu_mutex_lock_iothread(); + return EXCP_HLT; + } + + assert_hvf_ok(hv_vcpu_run(cpu->hvf->fd)); + + /* handle VMEXIT */ + uint64_t exit_reason = hvf_exit->reason; + uint64_t syndrome = hvf_exit->exception.syndrome; + uint32_t ec = syn_get_ec(syndrome); + + switch (exit_reason) { + case HV_EXIT_REASON_EXCEPTION: + /* This is the main one, handle below. */ + break; + case HV_EXIT_REASON_VTIMER_ACTIVATED: + qemu_mutex_lock_iothread(); + current_cpu = cpu; + qemu_set_irq(arm_cpu->gt_timer_outputs[GTIMER_VIRT], 1); + qemu_mutex_unlock_iothread(); + continue; + case HV_EXIT_REASON_CANCELED: + /* we got kicked, no exit to process */ + continue; + default: + assert(0); + } + + ret = 0; + switch (ec) { + case EC_DATAABORT: { + bool isv = syndrome & ARM_EL_ISV; + bool iswrite = (syndrome >> 6) & 1; + bool s1ptw = (syndrome >> 7) & 1; + uint32_t sas = (syndrome >> 22) & 3; + uint32_t len = 1 << sas; + uint32_t srt = (syndrome >> 16) & 0x1f; + uint64_t val = 0; + + qemu_mutex_lock_iothread(); + current_cpu = cpu; + + DPRINTF("data abort: [pc=0x%llx va=0x%016llx pa=0x%016llx isv=%x " + "iswrite=%x s1ptw=%x len=%d srt=%d]\n", + env->pc, hvf_exit->exception.virtual_address, + hvf_exit->exception.physical_address, isv, iswrite, + s1ptw, len, srt); + + assert(isv); + + if (iswrite) { + val = hvf_get_reg(cpu, srt); + address_space_write(&address_space_memory, + hvf_exit->exception.physical_address, + MEMTXATTRS_UNSPECIFIED, &val, len); + + /* + * We do not have a callback to see if the timer is out of + * pending state. That means every MMIO write could + * potentially be an EOI ends the vtimer. Until we get an + * actual callback, let's just see if the timer is still + * pending on every possible toggle point. + */ + qemu_set_irq(arm_cpu->gt_timer_outputs[GTIMER_VIRT], 0); + hv_vcpu_set_vtimer_mask(cpu->hvf->fd, false); + } else { + address_space_read(&address_space_memory, + hvf_exit->exception.physical_address, + MEMTXATTRS_UNSPECIFIED, &val, len); + hvf_set_reg(cpu, srt, val); + } + + qemu_mutex_unlock_iothread(); + + advance_pc = true; + break; + } + case EC_SYSTEMREGISTERTRAP: { + bool isread = (syndrome >> 21) & 1; + uint32_t rt = (syndrome >> 5) & 0x1f; + uint32_t reg = syndrome & SYSREG_MASK; + uint64_t val = 0; + + if (isread) { + switch (reg) { + case SYSREG_CNTPCT_EL0: + val = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) / + gt_cntfrq_period_ns(arm_cpu); + break; + case SYSREG_PMCCNTR_EL0: + val = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + break; + default: + DPRINTF("unhandled sysreg read %08x (op0=%d op1=%d op2=%d " + "crn=%d crm=%d)", reg, (reg >> 20) & 0x3, + (reg >> 14) & 0x7, (reg >> 17) & 0x7, + (reg >> 10) & 0xf, (reg >> 1) & 0xf); + break; + } + + hvf_set_reg(cpu, rt, val); + } else { + val = hvf_get_reg(cpu, rt); + + switch (reg) { + case SYSREG_CNTPCT_EL0: + break; + default: + DPRINTF("unhandled sysreg write %08x", reg); + break; + } + } + + advance_pc = true; + break; + } + case EC_WFX_TRAP: + if (!(syndrome & WFX_IS_WFE) && !(cpu->interrupt_request & + (CPU_INTERRUPT_HARD | CPU_INTERRUPT_FIQ))) { + uint64_t cval, ctl, val, diff, now; + + /* Set up a local timer for vtimer if necessary ... */ + r = hv_vcpu_get_sys_reg(cpu->hvf->fd, HV_SYS_REG_CNTV_CTL_EL0, &ctl); + assert_hvf_ok(r); + r = hv_vcpu_get_sys_reg(cpu->hvf->fd, HV_SYS_REG_CNTV_CVAL_EL0, &cval); + assert_hvf_ok(r); + + asm volatile("mrs %0, cntvct_el0" : "=r"(val)); + diff = cval - val; + + now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) / + gt_cntfrq_period_ns(arm_cpu); + + /* Timer disabled or masked, just wait for long */ + if (!(ctl & 1) || (ctl & 2)) { + diff = (120 * NANOSECONDS_PER_SECOND) / + gt_cntfrq_period_ns(arm_cpu); + } + + if (diff < INT64_MAX) { + uint64_t ns = diff * gt_cntfrq_period_ns(arm_cpu); + struct timespec *ts = &cpu->hvf->ts; + + *ts = (struct timespec){ + .tv_sec = ns / NANOSECONDS_PER_SECOND, + .tv_nsec = ns % NANOSECONDS_PER_SECOND, + }; + + /* + * Waking up easily takes 1ms, don't go to sleep for smaller + * time periods than 2ms. + */ + if (!ts->tv_sec && (ts->tv_nsec < (SCALE_MS * 2))) { + advance_pc = true; + break; + } + + /* Set cpu->hvf->sleeping so that we get a SIG_IPI signal. */ + cpu->hvf->sleeping = true; + smp_mb(); + + /* Bail out if we received an IRQ meanwhile */ + if (cpu->thread_kicked || (cpu->interrupt_request & + (CPU_INTERRUPT_HARD | CPU_INTERRUPT_FIQ))) { + cpu->hvf->sleeping = false; + break; + } + + /* nanosleep returns on signal, so we wake up on kick. */ + nanosleep(ts, NULL); + + /* Out of sleep - either naturally or because of a kick */ + cpu->hvf->sleeping = false; + } + + advance_pc = true; + } + break; + case EC_AA64_HVC: + cpu_synchronize_state(cpu); + qemu_mutex_lock_iothread(); + current_cpu = cpu; + if (arm_is_psci_call(arm_cpu, EXCP_HVC)) { + arm_handle_psci_call(arm_cpu); + } else { + DPRINTF("unknown HVC! %016llx", env->xregs[0]); + env->xregs[0] = -1; + } + qemu_mutex_unlock_iothread(); + break; + case EC_AA64_SMC: + cpu_synchronize_state(cpu); + qemu_mutex_lock_iothread(); + current_cpu = cpu; + if (arm_is_psci_call(arm_cpu, EXCP_SMC)) { + arm_handle_psci_call(arm_cpu); + } else { + DPRINTF("unknown SMC! %016llx", env->xregs[0]); + env->xregs[0] = -1; + env->pc += 4; + } + qemu_mutex_unlock_iothread(); + break; + default: + cpu_synchronize_state(cpu); + DPRINTF("exit: %llx [ec=0x%x pc=0x%llx]", syndrome, ec, env->pc); + error_report("%llx: unhandled exit %llx", env->pc, exit_reason); + } + + if (advance_pc) { + uint64_t pc; + + flush_cpu_state(cpu); + + r = hv_vcpu_get_reg(cpu->hvf->fd, HV_REG_PC, &pc); + assert_hvf_ok(r); + pc += 4; + r = hv_vcpu_set_reg(cpu->hvf->fd, HV_REG_PC, pc); + assert_hvf_ok(r); + } + } while (ret == 0); + + qemu_mutex_lock_iothread(); + current_cpu = cpu; + + return ret; +} -- 2.24.3 (Apple Git-128) Now that we have all logic in place that we need to handle Hypervisor.framework on Apple Silicon systems, let's add CONFIG_HVF for aarch64 as well so that we can build it. Signed-off-by: Alexander Graf <agraf@csgraf.de> --- v1 -> v2: - Fix build on 32bit arm --- meson.build | 11 ++++++++++- target/arm/hvf/meson.build | 3 +++ target/arm/meson.build | 2 ++ 3 files changed, 15 insertions(+), 1 deletion(-) create mode 100644 target/arm/hvf/meson.build diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ else endif accelerator_targets = { 'CONFIG_KVM': kvm_targets } + +if cpu in ['x86', 'x86_64'] + hvf_targets = ['i386-softmmu', 'x86_64-softmmu'] +elif cpu in ['aarch64'] + hvf_targets = ['aarch64-softmmu'] +else + hvf_targets = [] +endif + if cpu in ['x86', 'x86_64', 'arm', 'aarch64'] # i368 emulator provides xenpv machine type for multiple architectures accelerator_targets += { 'CONFIG_XEN': ['i386-softmmu', 'x86_64-softmmu'], + 'CONFIG_HVF': hvf_targets, } endif if cpu in ['x86', 'x86_64'] accelerator_targets += { 'CONFIG_HAX': ['i386-softmmu', 'x86_64-softmmu'], - 'CONFIG_HVF': ['x86_64-softmmu'], 'CONFIG_WHPX': ['i386-softmmu', 'x86_64-softmmu'], } endif diff --git a/target/arm/hvf/meson.build b/target/arm/hvf/meson.build new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/hvf/meson.build @@ -XXX,XX +XXX,XX @@ +arm_softmmu_ss.add(when: [hvf, 'CONFIG_HVF'], if_true: files( + 'hvf.c', +)) diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_softmmu_ss.add(files( 'psci.c', )) +subdir('hvf') + target_arch += {'arm': arm_ss} target_softmmu_arch += {'arm': arm_softmmu_ss} -- 2.24.3 (Apple Git-128)