int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int r;
sigset_t sigsaved;
vcpu_load(vcpu);
if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
kvm_vcpu_block(vcpu);
vcpu_put(vcpu);
return -EAGAIN;
}
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
if (vcpu->mmio_needed) {
memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
kvm_set_mmio_data(vcpu);
vcpu->mmio_read_completed = 1;
vcpu->mmio_needed = 0;
}
r = __vcpu_run(vcpu, kvm_run);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
vcpu_put(vcpu);
return r;
}
void kvmppc_vcpu_block(struct kvm_vcpu *vcpu)
{
u64 now;
unsigned long dec_nsec;
now = get_tb();
if (now >= vcpu->arch.dec_expires && !kvmppc_core_pending_dec(vcpu))
kvmppc_core_queue_dec(vcpu);
if (vcpu->arch.pending_exceptions)
return;
if (vcpu->arch.dec_expires != ~(u64)0) {
dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC /
tb_ticks_per_sec;
hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
HRTIMER_MODE_REL);
}
kvmppc_vcpu_blocked(vcpu);
kvm_vcpu_block(vcpu);
vcpu->stat.halt_wakeup++;
if (vcpu->arch.dec_expires != ~(u64)0)
hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
kvmppc_vcpu_unblocked(vcpu);
}
/**
* kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
* instruction executed by a guest
*
* @vcpu: the vcpu pointer
*
* WFE: Yield the CPU and come back to this vcpu when the scheduler
* decides to.
* WFI: Simply call kvm_vcpu_block(), which will halt execution of
* world-switches and schedule other host processes until there is an
* incoming IRQ or FIQ to the VM.
*/
static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
if (kvm_vcpu_get_hsr(vcpu) & ESR_EL2_EC_WFI_ISS_WFE)
kvm_vcpu_on_spin(vcpu);
else
kvm_vcpu_block(vcpu);
return 1;
}
/**
* kvm_handle_wfx - handle a WFI or WFE instructions trapped in guests
* @vcpu: the vcpu pointer
* @run: the kvm_run structure pointer
*
* WFE: Yield the CPU and come back to this vcpu when the scheduler
* decides to.
* WFI: Simply call kvm_vcpu_block(), which will halt execution of
* world-switches and schedule other host processes until there is an
* incoming IRQ or FIQ to the VM.
*/
static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
trace_kvm_wfi(*vcpu_pc(vcpu));
if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE)
kvm_vcpu_on_spin(vcpu);
else
kvm_vcpu_block(vcpu);
return 1;
}
/**
* kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
* instruction executed by a guest
*
* @vcpu: the vcpu pointer
*
* WFE: Yield the CPU and come back to this vcpu when the scheduler
* decides to.
* WFI: Simply call kvm_vcpu_block(), which will halt execution of
* world-switches and schedule other host processes until there is an
* incoming IRQ or FIQ to the VM.
*/
static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
if (kvm_vcpu_get_hsr(vcpu) & ESR_EL2_EC_WFI_ISS_WFE)
kvm_vcpu_on_spin(vcpu);
else
kvm_vcpu_block(vcpu);
kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
return 1;
}
int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
{
int nr = kvmppc_get_gpr(vcpu, 11);
int r;
unsigned long __maybe_unused param1 = kvmppc_get_gpr(vcpu, 3);
unsigned long __maybe_unused param2 = kvmppc_get_gpr(vcpu, 4);
unsigned long __maybe_unused param3 = kvmppc_get_gpr(vcpu, 5);
unsigned long __maybe_unused param4 = kvmppc_get_gpr(vcpu, 6);
unsigned long r2 = 0;
if (!(vcpu->arch.shared->msr & MSR_SF)) {
/* 32 bit mode */
param1 &= 0xffffffff;
param2 &= 0xffffffff;
param3 &= 0xffffffff;
param4 &= 0xffffffff;
}
switch (nr) {
case KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE):
{
vcpu->arch.magic_page_pa = param1;
vcpu->arch.magic_page_ea = param2;
r2 = KVM_MAGIC_FEAT_SR | KVM_MAGIC_FEAT_MAS0_TO_SPRG7;
r = EV_SUCCESS;
break;
}
case KVM_HCALL_TOKEN(KVM_HC_FEATURES):
r = EV_SUCCESS;
#if defined(CONFIG_PPC_BOOK3S) || defined(CONFIG_KVM_E500V2)
/* XXX Missing magic page on 44x */
r2 |= (1 << KVM_FEATURE_MAGIC_PAGE);
#endif
/* Second return value is in r4 */
break;
case EV_HCALL_TOKEN(EV_IDLE):
r = EV_SUCCESS;
kvm_vcpu_block(vcpu);
clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
break;
default:
r = EV_UNIMPLEMENTED;
break;
}
kvmppc_set_gpr(vcpu, 4, r2);
return r;
}
/**
* kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
* instruction executed by a guest
*
* @vcpu: the vcpu pointer
*
* WFE: Yield the CPU and come back to this vcpu when the scheduler
* decides to.
* WFI: Simply call kvm_vcpu_block(), which will halt execution of
* world-switches and schedule other host processes until there is an
* incoming IRQ or FIQ to the VM.
*/
static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
kvm_vcpu_on_spin(vcpu);
} else {
trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
kvm_vcpu_block(vcpu);
}
kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
return 1;
}
/* Check pending exceptions and deliver one, if possible. */
void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
{
WARN_ON_ONCE(!irqs_disabled());
kvmppc_core_check_exceptions(vcpu);
if (vcpu->arch.shared->msr & MSR_WE) {
local_irq_enable();
kvm_vcpu_block(vcpu);
local_irq_disable();
kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
kvmppc_core_check_exceptions(vcpu);
};
}
/**
* kvm_handle_wfx - handle a WFI or WFE instructions trapped in guests
* @vcpu: the vcpu pointer
* @run: the kvm_run structure pointer
*
* WFE: Yield the CPU and come back to this vcpu when the scheduler
* decides to.
* WFI: Simply call kvm_vcpu_block(), which will halt execution of
* world-switches and schedule other host processes until there is an
* incoming IRQ or FIQ to the VM.
*/
static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) {
trace_kvm_wfx(*vcpu_pc(vcpu), true);
vcpu->stat.wfe_exit_stat++;
kvm_vcpu_on_spin(vcpu);
} else {
trace_kvm_wfx(*vcpu_pc(vcpu), false);
vcpu->stat.wfi_exit_stat++;
kvm_vcpu_block(vcpu);
}
kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
return 1;
}
/**
* kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
* instruction executed by a guest
*
* @vcpu: the vcpu pointer
*
* WFE: Yield the CPU and come back to this vcpu when the scheduler
* decides to.
* WFI: Simply call kvm_vcpu_block(), which will halt execution of
* world-switches and schedule other host processes until there is an
* incoming IRQ or FIQ to the VM.
*/
static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
vcpu->stat.wfe_exit_stat++;
kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
} else {
trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
vcpu->stat.wfi_exit_stat++;
kvm_vcpu_block(vcpu);
kvm_clear_request(KVM_REQ_UNHALT, vcpu);
}
kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
return 1;
}
int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
{
int rc, idx;
switch (cmd) {
case H_ENTER:
return kvmppc_h_pr_enter(vcpu);
case H_REMOVE:
return kvmppc_h_pr_remove(vcpu);
case H_PROTECT:
return kvmppc_h_pr_protect(vcpu);
case H_BULK_REMOVE:
return kvmppc_h_pr_bulk_remove(vcpu);
case H_PUT_TCE:
return kvmppc_h_pr_put_tce(vcpu);
case H_CEDE:
vcpu->arch.shared->msr |= MSR_EE;
kvm_vcpu_block(vcpu);
clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
vcpu->stat.halt_wakeup++;
return EMULATE_DONE;
case H_XIRR:
case H_CPPR:
case H_EOI:
case H_IPI:
case H_IPOLL:
case H_XIRR_X:
if (kvmppc_xics_enabled(vcpu))
return kvmppc_h_pr_xics_hcall(vcpu, cmd);
break;
case H_RTAS:
if (list_empty(&vcpu->kvm->arch.rtas_tokens))
break;
idx = srcu_read_lock(&vcpu->kvm->srcu);
rc = kvmppc_rtas_hcall(vcpu);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (rc)
break;
kvmppc_set_gpr(vcpu, 3, 0);
return EMULATE_DONE;
}
return EMULATE_FAIL;
}
static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
{
/*
* NOTE: For simplicity, we make VCPU suspend emulation to be
* same-as WFI (Wait-for-interrupt) emulation.
*
* This means for KVM the wakeup events are interrupts and
* this is consistent with intended use of StateID as described
* in section 5.4.1 of PSCI v0.2 specification (ARM DEN 0022A).
*
* Further, we also treat power-down request to be same as
* stand-by request as-per section 5.4.2 clause 3 of PSCI v0.2
* specification (ARM DEN 0022A). This means all suspend states
* for KVM will preserve the register state.
*/
kvm_vcpu_block(vcpu);
return PSCI_RET_SUCCESS;
}
/* Check pending exceptions and deliver one, if possible. */
int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
{
int r = 0;
WARN_ON_ONCE(!irqs_disabled());
kvmppc_core_check_exceptions(vcpu);
if (vcpu->arch.shared->msr & MSR_WE) {
local_irq_enable();
kvm_vcpu_block(vcpu);
clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
local_irq_disable();
kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
r = 1;
};
return r;
}
int kvm_emulate_halt(struct kvm_vcpu *vcpu)
{
ktime_t kt;
long itc_diff;
unsigned long vcpu_now_itc;
unsigned long expires;
struct hrtimer *p_ht = &vcpu->arch.hlt_timer;
unsigned long cyc_per_usec = local_cpu_data->cyc_per_usec;
struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
vcpu_now_itc = ia64_getreg(_IA64_REG_AR_ITC) + vcpu->arch.itc_offset;
if (time_after(vcpu_now_itc, vpd->itm)) {
vcpu->arch.timer_check = 1;
return 1;
}
itc_diff = vpd->itm - vcpu_now_itc;
if (itc_diff < 0)
itc_diff = -itc_diff;
expires = div64_u64(itc_diff, cyc_per_usec);
kt = ktime_set(0, 1000 * expires);
vcpu->arch.ht_active = 1;
hrtimer_start(p_ht, kt, HRTIMER_MODE_ABS);
if (irqchip_in_kernel(vcpu->kvm)) {
vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
kvm_vcpu_block(vcpu);
hrtimer_cancel(p_ht);
vcpu->arch.ht_active = 0;
if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
return -EINTR;
return 1;
} else {
printk(KERN_ERR"kvm: Unsupported userspace halt!");
return 0;
}
}
/**
* kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest
* @vcpu: the vcpu pointer
* @run: the kvm_run structure pointer
*
* Simply sets the wait_for_interrupts flag on the vcpu structure, which will
* halt execution of world-switches and schedule other host processes until
* there is an incoming IRQ or FIQ to the VM.
*/
static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
trace_kvm_wfi(*vcpu_pc(vcpu));
kvm_vcpu_block(vcpu);
return 1;
}
int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
{
int nr = kvmppc_get_gpr(vcpu, 11);
int r;
unsigned long __maybe_unused param1 = kvmppc_get_gpr(vcpu, 3);
unsigned long __maybe_unused param2 = kvmppc_get_gpr(vcpu, 4);
unsigned long __maybe_unused param3 = kvmppc_get_gpr(vcpu, 5);
unsigned long __maybe_unused param4 = kvmppc_get_gpr(vcpu, 6);
unsigned long r2 = 0;
if (!(kvmppc_get_msr(vcpu) & MSR_SF)) {
/* 32 bit mode */
param1 &= 0xffffffff;
param2 &= 0xffffffff;
param3 &= 0xffffffff;
param4 &= 0xffffffff;
}
switch (nr) {
case KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE):
{
#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
/* Book3S can be little endian, find it out here */
int shared_big_endian = true;
if (vcpu->arch.intr_msr & MSR_LE)
shared_big_endian = false;
if (shared_big_endian != vcpu->arch.shared_big_endian)
kvmppc_swab_shared(vcpu);
vcpu->arch.shared_big_endian = shared_big_endian;
#endif
if (!(param2 & MAGIC_PAGE_FLAG_NOT_MAPPED_NX)) {
/*
* Older versions of the Linux magic page code had
* a bug where they would map their trampoline code
* NX. If that's the case, remove !PR NX capability.
*/
vcpu->arch.disable_kernel_nx = true;
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
vcpu->arch.magic_page_pa = param1 & ~0xfffULL;
vcpu->arch.magic_page_ea = param2 & ~0xfffULL;
#ifdef CONFIG_PPC_64K_PAGES
/*
* Make sure our 4k magic page is in the same window of a 64k
* page within the guest and within the host's page.
*/
if ((vcpu->arch.magic_page_pa & 0xf000) !=
((ulong)vcpu->arch.shared & 0xf000)) {
void *old_shared = vcpu->arch.shared;
ulong shared = (ulong)vcpu->arch.shared;
void *new_shared;
shared &= PAGE_MASK;
shared |= vcpu->arch.magic_page_pa & 0xf000;
new_shared = (void*)shared;
memcpy(new_shared, old_shared, 0x1000);
vcpu->arch.shared = new_shared;
}
#endif
r2 = KVM_MAGIC_FEAT_SR | KVM_MAGIC_FEAT_MAS0_TO_SPRG7;
r = EV_SUCCESS;
break;
}
case KVM_HCALL_TOKEN(KVM_HC_FEATURES):
r = EV_SUCCESS;
#if defined(CONFIG_PPC_BOOK3S) || defined(CONFIG_KVM_E500V2)
r2 |= (1 << KVM_FEATURE_MAGIC_PAGE);
#endif
/* Second return value is in r4 */
break;
case EV_HCALL_TOKEN(EV_IDLE):
r = EV_SUCCESS;
kvm_vcpu_block(vcpu);
clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
break;
default:
r = EV_UNIMPLEMENTED;
break;
}
kvmppc_set_gpr(vcpu, 4, r2);
return r;
}
/**
* kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest
* @vcpu: the vcpu pointer
*
* Simply call kvm_vcpu_block(), which will halt execution of
* world-switches and schedule other host processes until there is an
* incoming IRQ or FIQ to the VM.
*/
static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
kvm_vcpu_block(vcpu);
return 1;
}
