/* mask must never be zero, except for A20 change call */
static void tcg_handle_interrupt(CPUState *cpu, int mask)
{
int old_mask;
old_mask = cpu->interrupt_request;
cpu->interrupt_request |= mask;
/*
* If called from iothread context, wake the target cpu in
* case its halted.
*/
if (!qemu_cpu_is_self(cpu)) {
qemu_cpu_kick(cpu);
return;
}
if (use_icount) {
cpu->icount_decr.u16.high = 0xffff;
if (!cpu->can_do_io
&& (mask & ~old_mask) != 0) {
cpu_abort(cpu, "Raised interrupt while not in I/O function");
}
} else {
cpu->tcg_exit_req = 1;
}
}
void run_on_cpu(CPUState *cpu, void (*func)(void *data), void *data)
{
struct qemu_work_item wi;
if (qemu_cpu_is_self(cpu)) {
func(data);
return;
}
wi.func = func;
wi.data = data;
if (cpu->queued_work_first == NULL) {
cpu->queued_work_first = &wi;
} else {
cpu->queued_work_last->next = &wi;
}
cpu->queued_work_last = &wi;
wi.next = NULL;
wi.done = false;
qemu_cpu_kick(cpu);
while (!wi.done) {
CPUArchState *self_env = cpu_single_env;
qemu_cond_wait(&qemu_work_cond, &qemu_global_mutex);
cpu_single_env = self_env;
}
}
static void kvm_handle_interrupt(CPUState *env, int mask)
{
env->interrupt_request |= mask;
if (!qemu_cpu_is_self(env)) {
qemu_cpu_kick(env);
}
}
static void whpx_handle_interrupt(CPUState *cpu, int mask)
{
cpu->interrupt_request |= mask;
if (!qemu_cpu_is_self(cpu)) {
qemu_cpu_kick(cpu);
}
}
void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap)
{
tlb_debug("mmu_idx: 0x%" PRIx16 "\n", idxmap);
if (cpu->created && !qemu_cpu_is_self(cpu)) {
async_run_on_cpu(cpu, tlb_flush_by_mmuidx_async_work,
RUN_ON_CPU_HOST_INT(idxmap));
} else {
tlb_flush_by_mmuidx_async_work(cpu, RUN_ON_CPU_HOST_INT(idxmap));
}
}
static void apic_sync_vapic(APICCommonState *s, int sync_type)
{
VAPICState vapic_state;
//size_t length;
//off_t start;
int vector;
if (!s->vapic_paddr) {
return;
}
if (sync_type & SYNC_FROM_VAPIC) {
cpu_physical_memory_read(NULL, s->vapic_paddr, &vapic_state,
sizeof(vapic_state));
s->tpr = vapic_state.tpr;
}
if (sync_type & (SYNC_TO_VAPIC | SYNC_ISR_IRR_TO_VAPIC)) {
//start = offsetof(VAPICState, isr);
//length = offsetof(VAPICState, enabled) - offsetof(VAPICState, isr);
if (sync_type & SYNC_TO_VAPIC) {
assert(qemu_cpu_is_self(CPU(s->cpu)));
vapic_state.tpr = s->tpr;
vapic_state.enabled = 1;
//start = 0;
//length = sizeof(VAPICState);
}
vector = get_highest_priority_int(s->isr);
if (vector < 0) {
vector = 0;
}
vapic_state.isr = vector & 0xf0;
vapic_state.zero = 0;
vector = get_highest_priority_int(s->irr);
if (vector < 0) {
vector = 0;
}
vapic_state.irr = vector & 0xff;
//cpu_physical_memory_write_rom(&address_space_memory,
// s->vapic_paddr + start,
// ((void *)&vapic_state) + start, length);
// FIXME qq
}
}
static void qemu_cpu_kick_thread(CPUState *cpu)
{
#ifndef _WIN32
int err;
err = pthread_kill(cpu->thread->thread, SIG_IPI);
if (err) {
fprintf(stderr, "qemu:%s: %s", __func__, strerror(err));
exit(1);
}
#else /* _WIN32 */
if (!qemu_cpu_is_self(cpu)) {
SuspendThread(cpu->hThread);
cpu_signal(0);
ResumeThread(cpu->hThread);
}
#endif
}
void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong addr, uint16_t idxmap)
{
target_ulong addr_and_mmu_idx;
tlb_debug("addr: "TARGET_FMT_lx" mmu_idx:%" PRIx16 "\n", addr, idxmap);
/* This should already be page aligned */
addr_and_mmu_idx = addr & TARGET_PAGE_MASK;
addr_and_mmu_idx |= idxmap;
if (!qemu_cpu_is_self(cpu)) {
async_run_on_cpu(cpu, tlb_flush_page_by_mmuidx_async_work,
RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
} else {
tlb_flush_page_by_mmuidx_async_work(
cpu, RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
}
}
static void qemu_cpu_kick_thread(CPUState *cpu)
{
#ifndef _WIN32
int err;
err = pthread_kill(cpu->thread->thread, SIG_IPI);
if (err) {
fprintf(stderr, "qemu:%s: %s", __func__, strerror(err));
exit(1);
}
#else /* _WIN32 */
if (!qemu_cpu_is_self(cpu)) {
CONTEXT tcgContext;
if (SuspendThread(cpu->hThread) == (DWORD)-1) {
fprintf(stderr, "qemu:%s: GetLastError:%lu\n", __func__,
GetLastError());
exit(1);
}
/* On multi-core systems, we are not sure that the thread is actually
* suspended until we can get the context.
*/
tcgContext.ContextFlags = CONTEXT_CONTROL;
while (GetThreadContext(cpu->hThread, &tcgContext) != 0) {
continue;
}
cpu_signal(0);
if (ResumeThread(cpu->hThread) == (DWORD)-1) {
fprintf(stderr, "qemu:%s: GetLastError:%lu\n", __func__,
GetLastError());
exit(1);
}
}
#endif
}
static void qemu_cpu_kick_thread(CPUArchState *env)
{
#ifndef _WIN32
int err;
LOGD_CPUS("%s1\n", __func__);
err = pthread_kill(env->thread->thread, SIG_IPI);
LOGD_CPUS("%s2: KILL pthread\n", __func__);
if (err) {
LOGD_CPUS("%s3: ERROR = %d:%s\n", __func__, err, strerror(err));
fprintf(stderr, "qemu:%s: %s", __func__, strerror(err));
exit(1);
}
LOGD_CPUS("%s4\n", __func__);
#else /* _WIN32 */
if (!qemu_cpu_is_self(env)) {
SuspendThread(env->hThread);
cpu_signal(0);
ResumeThread(env->hThread);
}
#endif
}
void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data,
QemuMutex *mutex)
{
struct qemu_work_item wi;
if (qemu_cpu_is_self(cpu)) {
func(cpu, data);
return;
}
wi.func = func;
wi.data = data;
wi.done = false;
wi.free = false;
wi.exclusive = false;
queue_work_on_cpu(cpu, &wi);
while (!atomic_mb_read(&wi.done)) {
CPUState *self_cpu = current_cpu;
qemu_cond_wait(&qemu_work_cond, mutex);
current_cpu = self_cpu;
}
}
void async_run_on_cpu(CPUState *cpu, void (*func)(void *data), void *data)
{
struct qemu_work_item *wi;
if (qemu_cpu_is_self(cpu)) {
func(data);
return;
}
wi = g_malloc0(sizeof(struct qemu_work_item));
wi->func = func;
wi->data = data;
wi->free = true;
if (cpu->queued_work_first == NULL) {
cpu->queued_work_first = wi;
} else {
cpu->queued_work_last->next = wi;
}
cpu->queued_work_last = wi;
wi->next = NULL;
wi->done = false;
qemu_cpu_kick(cpu);
}
static bool qemu_in_vcpu_thread(void)
{
return cpu_single_env && qemu_cpu_is_self(ENV_GET_CPU(cpu_single_env));
}
static void whpx_get_registers(CPUState *cpu)
{
struct whpx_state *whpx = &whpx_global;
struct whpx_vcpu *vcpu = get_whpx_vcpu(cpu);
struct CPUX86State *env = (CPUArchState *)(cpu->env_ptr);
X86CPU *x86_cpu = X86_CPU(cpu);
struct whpx_register_set vcxt;
uint64_t tpr, apic_base;
HRESULT hr;
int idx = 0;
int i;
assert(cpu_is_stopped(cpu) || qemu_cpu_is_self(cpu));
hr = WHvGetVirtualProcessorRegisters(whpx->partition, cpu->cpu_index,
whpx_register_names,
RTL_NUMBER_OF(whpx_register_names),
&vcxt.values[0]);
if (FAILED(hr)) {
error_report("WHPX: Failed to get virtual processor context, hr=%08lx",
hr);
}
/* Indexes for first 16 registers match between HV and QEMU definitions */
for (idx = 0; idx < CPU_NB_REGS64; idx += 1) {
env->regs[idx] = vcxt.values[idx].Reg64;
}
/* Same goes for RIP and RFLAGS */
assert(whpx_register_names[idx] == WHvX64RegisterRip);
env->eip = vcxt.values[idx++].Reg64;
assert(whpx_register_names[idx] == WHvX64RegisterRflags);
env->eflags = vcxt.values[idx++].Reg64;
/* Translate 6+4 segment registers. HV and QEMU order matches */
assert(idx == WHvX64RegisterEs);
for (i = 0; i < 6; i += 1, idx += 1) {
env->segs[i] = whpx_seg_h2q(&vcxt.values[idx].Segment);
}
assert(idx == WHvX64RegisterLdtr);
env->ldt = whpx_seg_h2q(&vcxt.values[idx++].Segment);
assert(idx == WHvX64RegisterTr);
env->tr = whpx_seg_h2q(&vcxt.values[idx++].Segment);
assert(idx == WHvX64RegisterIdtr);
env->idt.base = vcxt.values[idx].Table.Base;
env->idt.limit = vcxt.values[idx].Table.Limit;
idx += 1;
assert(idx == WHvX64RegisterGdtr);
env->gdt.base = vcxt.values[idx].Table.Base;
env->gdt.limit = vcxt.values[idx].Table.Limit;
idx += 1;
/* CR0, 2, 3, 4, 8 */
assert(whpx_register_names[idx] == WHvX64RegisterCr0);
env->cr[0] = vcxt.values[idx++].Reg64;
assert(whpx_register_names[idx] == WHvX64RegisterCr2);
env->cr[2] = vcxt.values[idx++].Reg64;
assert(whpx_register_names[idx] == WHvX64RegisterCr3);
env->cr[3] = vcxt.values[idx++].Reg64;
assert(whpx_register_names[idx] == WHvX64RegisterCr4);
env->cr[4] = vcxt.values[idx++].Reg64;
assert(whpx_register_names[idx] == WHvX64RegisterCr8);
tpr = vcxt.values[idx++].Reg64;
if (tpr != vcpu->tpr) {
vcpu->tpr = tpr;
cpu_set_apic_tpr(x86_cpu->apic_state, tpr);
}
/* 8 Debug Registers - Skipped */
/* 16 XMM registers */
assert(whpx_register_names[idx] == WHvX64RegisterXmm0);
for (i = 0; i < 16; i += 1, idx += 1) {
env->xmm_regs[i].ZMM_Q(0) = vcxt.values[idx].Reg128.Low64;
env->xmm_regs[i].ZMM_Q(1) = vcxt.values[idx].Reg128.High64;
}
/* 8 FP registers */
assert(whpx_register_names[idx] == WHvX64RegisterFpMmx0);
for (i = 0; i < 8; i += 1, idx += 1) {
env->fpregs[i].mmx.MMX_Q(0) = vcxt.values[idx].Fp.AsUINT128.Low64;
/* env->fpregs[i].mmx.MMX_Q(1) =
vcxt.values[idx].Fp.AsUINT128.High64;
*/
}
/* FP control status register */
assert(whpx_register_names[idx] == WHvX64RegisterFpControlStatus);
env->fpuc = vcxt.values[idx].FpControlStatus.FpControl;
env->fpstt = (vcxt.values[idx].FpControlStatus.FpStatus >> 11) & 0x7;
env->fpus = vcxt.values[idx].FpControlStatus.FpStatus & ~0x3800;
for (i = 0; i < 8; ++i) {
env->fptags[i] = !((vcxt.values[idx].FpControlStatus.FpTag >> i) & 1);
}
env->fpop = vcxt.values[idx].FpControlStatus.LastFpOp;
env->fpip = vcxt.values[idx].FpControlStatus.LastFpRip;
idx += 1;
/* XMM control status register */
assert(whpx_register_names[idx] == WHvX64RegisterXmmControlStatus);
env->mxcsr = vcxt.values[idx].XmmControlStatus.XmmStatusControl;
idx += 1;
/* MSRs */
assert(whpx_register_names[idx] == WHvX64RegisterTsc);
env->tsc = vcxt.values[idx++].Reg64;
assert(whpx_register_names[idx] == WHvX64RegisterEfer);
env->efer = vcxt.values[idx++].Reg64;
#ifdef TARGET_X86_64
assert(whpx_register_names[idx] == WHvX64RegisterKernelGsBase);
env->kernelgsbase = vcxt.values[idx++].Reg64;
#endif
assert(whpx_register_names[idx] == WHvX64RegisterApicBase);
apic_base = vcxt.values[idx++].Reg64;
if (apic_base != vcpu->apic_base) {
vcpu->apic_base = apic_base;
cpu_set_apic_base(x86_cpu->apic_state, vcpu->apic_base);
}
/* WHvX64RegisterPat - Skipped */
assert(whpx_register_names[idx] == WHvX64RegisterSysenterCs);
env->sysenter_cs = vcxt.values[idx++].Reg64;;
assert(whpx_register_names[idx] == WHvX64RegisterSysenterEip);
env->sysenter_eip = vcxt.values[idx++].Reg64;
assert(whpx_register_names[idx] == WHvX64RegisterSysenterEsp);
env->sysenter_esp = vcxt.values[idx++].Reg64;
assert(whpx_register_names[idx] == WHvX64RegisterStar);
env->star = vcxt.values[idx++].Reg64;
#ifdef TARGET_X86_64
assert(whpx_register_names[idx] == WHvX64RegisterLstar);
env->lstar = vcxt.values[idx++].Reg64;
assert(whpx_register_names[idx] == WHvX64RegisterCstar);
env->cstar = vcxt.values[idx++].Reg64;
assert(whpx_register_names[idx] == WHvX64RegisterSfmask);
env->fmask = vcxt.values[idx++].Reg64;
#endif
/* Interrupt / Event Registers - Skipped */
assert(idx == RTL_NUMBER_OF(whpx_register_names));
return;
}
static void whpx_set_registers(CPUState *cpu)
{
struct whpx_state *whpx = &whpx_global;
struct whpx_vcpu *vcpu = get_whpx_vcpu(cpu);
struct CPUX86State *env = (CPUArchState *)(cpu->env_ptr);
X86CPU *x86_cpu = X86_CPU(cpu);
struct whpx_register_set vcxt = {0};
HRESULT hr;
int idx = 0;
int i;
int v86, r86;
assert(cpu_is_stopped(cpu) || qemu_cpu_is_self(cpu));
v86 = (env->eflags & VM_MASK);
r86 = !(env->cr[0] & CR0_PE_MASK);
vcpu->tpr = cpu_get_apic_tpr(x86_cpu->apic_state);
vcpu->apic_base = cpu_get_apic_base(x86_cpu->apic_state);
/* Indexes for first 16 registers match between HV and QEMU definitions */
for (idx = 0; idx < CPU_NB_REGS64; idx += 1) {
vcxt.values[idx].Reg64 = env->regs[idx];
}
/* Same goes for RIP and RFLAGS */
assert(whpx_register_names[idx] == WHvX64RegisterRip);
vcxt.values[idx++].Reg64 = env->eip;
assert(whpx_register_names[idx] == WHvX64RegisterRflags);
vcxt.values[idx++].Reg64 = env->eflags;
/* Translate 6+4 segment registers. HV and QEMU order matches */
assert(idx == WHvX64RegisterEs);
for (i = 0; i < 6; i += 1, idx += 1) {
vcxt.values[idx].Segment = whpx_seg_q2h(&env->segs[i], v86, r86);
}
assert(idx == WHvX64RegisterLdtr);
vcxt.values[idx++].Segment = whpx_seg_q2h(&env->ldt, 0, 0);
assert(idx == WHvX64RegisterTr);
vcxt.values[idx++].Segment = whpx_seg_q2h(&env->tr, 0, 0);
assert(idx == WHvX64RegisterIdtr);
vcxt.values[idx].Table.Base = env->idt.base;
vcxt.values[idx].Table.Limit = env->idt.limit;
idx += 1;
assert(idx == WHvX64RegisterGdtr);
vcxt.values[idx].Table.Base = env->gdt.base;
vcxt.values[idx].Table.Limit = env->gdt.limit;
idx += 1;
/* CR0, 2, 3, 4, 8 */
assert(whpx_register_names[idx] == WHvX64RegisterCr0);
vcxt.values[idx++].Reg64 = env->cr[0];
assert(whpx_register_names[idx] == WHvX64RegisterCr2);
vcxt.values[idx++].Reg64 = env->cr[2];
assert(whpx_register_names[idx] == WHvX64RegisterCr3);
vcxt.values[idx++].Reg64 = env->cr[3];
assert(whpx_register_names[idx] == WHvX64RegisterCr4);
vcxt.values[idx++].Reg64 = env->cr[4];
assert(whpx_register_names[idx] == WHvX64RegisterCr8);
vcxt.values[idx++].Reg64 = vcpu->tpr;
/* 8 Debug Registers - Skipped */
/* 16 XMM registers */
assert(whpx_register_names[idx] == WHvX64RegisterXmm0);
for (i = 0; i < 16; i += 1, idx += 1) {
vcxt.values[idx].Reg128.Low64 = env->xmm_regs[i].ZMM_Q(0);
vcxt.values[idx].Reg128.High64 = env->xmm_regs[i].ZMM_Q(1);
}
/* 8 FP registers */
assert(whpx_register_names[idx] == WHvX64RegisterFpMmx0);
for (i = 0; i < 8; i += 1, idx += 1) {
vcxt.values[idx].Fp.AsUINT128.Low64 = env->fpregs[i].mmx.MMX_Q(0);
/* vcxt.values[idx].Fp.AsUINT128.High64 =
env->fpregs[i].mmx.MMX_Q(1);
*/
}
/* FP control status register */
assert(whpx_register_names[idx] == WHvX64RegisterFpControlStatus);
vcxt.values[idx].FpControlStatus.FpControl = env->fpuc;
vcxt.values[idx].FpControlStatus.FpStatus =
(env->fpus & ~0x3800) | (env->fpstt & 0x7) << 11;
vcxt.values[idx].FpControlStatus.FpTag = 0;
for (i = 0; i < 8; ++i) {
vcxt.values[idx].FpControlStatus.FpTag |= (!env->fptags[i]) << i;
}
vcxt.values[idx].FpControlStatus.Reserved = 0;
vcxt.values[idx].FpControlStatus.LastFpOp = env->fpop;
vcxt.values[idx].FpControlStatus.LastFpRip = env->fpip;
idx += 1;
/* XMM control status register */
assert(whpx_register_names[idx] == WHvX64RegisterXmmControlStatus);
vcxt.values[idx].XmmControlStatus.LastFpRdp = 0;
vcxt.values[idx].XmmControlStatus.XmmStatusControl = env->mxcsr;
vcxt.values[idx].XmmControlStatus.XmmStatusControlMask = 0x0000ffff;
idx += 1;
/* MSRs */
assert(whpx_register_names[idx] == WHvX64RegisterTsc);
vcxt.values[idx++].Reg64 = env->tsc;
assert(whpx_register_names[idx] == WHvX64RegisterEfer);
vcxt.values[idx++].Reg64 = env->efer;
#ifdef TARGET_X86_64
assert(whpx_register_names[idx] == WHvX64RegisterKernelGsBase);
vcxt.values[idx++].Reg64 = env->kernelgsbase;
#endif
assert(whpx_register_names[idx] == WHvX64RegisterApicBase);
vcxt.values[idx++].Reg64 = vcpu->apic_base;
/* WHvX64RegisterPat - Skipped */
assert(whpx_register_names[idx] == WHvX64RegisterSysenterCs);
vcxt.values[idx++].Reg64 = env->sysenter_cs;
assert(whpx_register_names[idx] == WHvX64RegisterSysenterEip);
vcxt.values[idx++].Reg64 = env->sysenter_eip;
assert(whpx_register_names[idx] == WHvX64RegisterSysenterEsp);
vcxt.values[idx++].Reg64 = env->sysenter_esp;
assert(whpx_register_names[idx] == WHvX64RegisterStar);
vcxt.values[idx++].Reg64 = env->star;
#ifdef TARGET_X86_64
assert(whpx_register_names[idx] == WHvX64RegisterLstar);
vcxt.values[idx++].Reg64 = env->lstar;
assert(whpx_register_names[idx] == WHvX64RegisterCstar);
vcxt.values[idx++].Reg64 = env->cstar;
assert(whpx_register_names[idx] == WHvX64RegisterSfmask);
vcxt.values[idx++].Reg64 = env->fmask;
#endif
/* Interrupt / Event Registers - Skipped */
assert(idx == RTL_NUMBER_OF(whpx_register_names));
hr = WHvSetVirtualProcessorRegisters(whpx->partition, cpu->cpu_index,
whpx_register_names,
RTL_NUMBER_OF(whpx_register_names),
&vcxt.values[0]);
if (FAILED(hr)) {
error_report("WHPX: Failed to set virtual processor context, hr=%08lx",
hr);
}
return;
}
static bool qemu_in_vcpu_thread(void)
{
return current_cpu && qemu_cpu_is_self(current_cpu);
}