static void early_init_intel(struct cpuinfo_x86 *c)
{
/* Netburst reports 64 bytes clflush size, but does IO in 128 bytes */
if (c->x86 == 15 && c->x86_cache_alignment == 64)
c->x86_cache_alignment = 128;
/* Unmask CPUID levels and NX if masked: */
if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
u64 misc_enable, disable;
rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
disable = misc_enable & (MSR_IA32_MISC_ENABLE_LIMIT_CPUID |
MSR_IA32_MISC_ENABLE_XD_DISABLE);
if (disable) {
wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable & ~disable);
bootsym(trampoline_misc_enable_off) |= disable;
}
if (disable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID)
printk(KERN_INFO "revised cpuid level: %d\n",
cpuid_eax(0));
if (disable & MSR_IA32_MISC_ENABLE_XD_DISABLE) {
write_efer(read_efer() | EFER_NX);
printk(KERN_INFO
"re-enabled NX (Execute Disable) protection\n");
}
}
/* CPUID workaround for Intel 0F33/0F34 CPU */
if (boot_cpu_data.x86 == 0xF && boot_cpu_data.x86_model == 3 &&
(boot_cpu_data.x86_mask == 3 || boot_cpu_data.x86_mask == 4))
paddr_bits = 36;
}
/* Main interface to do xen specific suspend/resume */
static int enter_state(u32 state)
{
unsigned long flags;
int error;
unsigned long cr4;
if ( (state <= ACPI_STATE_S0) || (state > ACPI_S_STATES_MAX) )
return -EINVAL;
if ( !spin_trylock(&pm_lock) )
return -EBUSY;
BUG_ON(system_state != SYS_STATE_active);
system_state = SYS_STATE_suspend;
printk(XENLOG_INFO "Preparing system for ACPI S%d state.\n", state);
freeze_domains();
acpi_dmar_reinstate();
if ( (error = disable_nonboot_cpus()) )
{
system_state = SYS_STATE_resume;
goto enable_cpu;
}
cpufreq_del_cpu(0);
hvm_cpu_down();
acpi_sleep_prepare(state);
console_start_sync();
printk("Entering ACPI S%d state.\n", state);
local_irq_save(flags);
spin_debug_disable();
if ( (error = device_power_down()) )
{
printk(XENLOG_ERR "Some devices failed to power down.");
system_state = SYS_STATE_resume;
goto done;
}
ACPI_FLUSH_CPU_CACHE();
switch ( state )
{
case ACPI_STATE_S3:
do_suspend_lowlevel();
system_reset_counter++;
error = tboot_s3_resume();
break;
case ACPI_STATE_S5:
acpi_enter_sleep_state(ACPI_STATE_S5);
break;
default:
error = -EINVAL;
break;
}
system_state = SYS_STATE_resume;
/* Restore CR4 and EFER from cached values. */
cr4 = read_cr4();
write_cr4(cr4 & ~X86_CR4_MCE);
write_efer(read_efer());
device_power_up();
mcheck_init(&boot_cpu_data, 0);
write_cr4(cr4);
printk(XENLOG_INFO "Finishing wakeup from ACPI S%d state.\n", state);
if ( (state == ACPI_STATE_S3) && error )
tboot_s3_error(error);
done:
spin_debug_enable();
local_irq_restore(flags);
console_end_sync();
acpi_sleep_post(state);
if ( hvm_cpu_up() )
BUG();
enable_cpu:
cpufreq_add_cpu(0);
microcode_resume_cpu(0);
rcu_barrier();
mtrr_aps_sync_begin();
enable_nonboot_cpus();
mtrr_aps_sync_end();
adjust_vtd_irq_affinities();
acpi_dmar_zap();
thaw_domains();
system_state = SYS_STATE_active;
spin_unlock(&pm_lock);
return error;
}
void cpuid_viridian_leaves(const struct vcpu *v, uint32_t leaf,
uint32_t subleaf, struct cpuid_leaf *res)
{
const struct domain *d = v->domain;
ASSERT(is_viridian_domain(d));
ASSERT(leaf >= 0x40000000 && leaf < 0x40000100);
leaf -= 0x40000000;
switch ( leaf )
{
case 0:
res->a = 0x40000006; /* Maximum leaf */
res->b = 0x7263694d; /* Magic numbers */
res->c = 0x666F736F;
res->d = 0x76482074;
break;
case 1:
res->a = 0x31237648; /* Version number */
break;
case 2:
/* Hypervisor information, but only if the guest has set its
own version number. */
if ( d->arch.hvm_domain.viridian.guest_os_id.raw == 0 )
break;
res->a = 1; /* Build number */
res->b = (xen_major_version() << 16) | xen_minor_version();
res->c = 0; /* SP */
res->d = 0; /* Service branch and number */
break;
case 3:
/* Which hypervisor MSRs are available to the guest */
res->a = (CPUID3A_MSR_APIC_ACCESS |
CPUID3A_MSR_HYPERCALL |
CPUID3A_MSR_VP_INDEX);
if ( !(viridian_feature_mask(d) & HVMPV_no_freq) )
res->a |= CPUID3A_MSR_FREQ;
if ( viridian_feature_mask(d) & HVMPV_time_ref_count )
res->a |= CPUID3A_MSR_TIME_REF_COUNT;
if ( viridian_feature_mask(d) & HVMPV_reference_tsc )
res->a |= CPUID3A_MSR_REFERENCE_TSC;
break;
case 4:
/* Recommended hypercall usage. */
if ( (d->arch.hvm_domain.viridian.guest_os_id.raw == 0) ||
(d->arch.hvm_domain.viridian.guest_os_id.fields.os < 4) )
break;
res->a = CPUID4A_RELAX_TIMER_INT;
if ( viridian_feature_mask(d) & HVMPV_hcall_remote_tlb_flush )
res->a |= CPUID4A_HCALL_REMOTE_TLB_FLUSH;
if ( !cpu_has_vmx_apic_reg_virt )
res->a |= CPUID4A_MSR_BASED_APIC;
res->b = 2047; /* long spin count */
break;
case 6:
/* Detected and in use hardware features. */
if ( cpu_has_vmx_virtualize_apic_accesses )
res->a |= CPUID6A_APIC_OVERLAY;
if ( cpu_has_vmx_msr_bitmap || (read_efer() & EFER_SVME) )
res->a |= CPUID6A_MSR_BITMAPS;
if ( hap_enabled(d) )
res->a |= CPUID6A_NESTED_PAGING;
break;
}
}
/* Main interface to do xen specific suspend/resume */
static int enter_state(u32 state)
{
unsigned long flags;
int error;
if ( (state <= ACPI_STATE_S0) || (state > ACPI_S_STATES_MAX) )
return -EINVAL;
if ( !spin_trylock(&pm_lock) )
return -EBUSY;
printk(XENLOG_INFO "Preparing system for ACPI S%d state.", state);
freeze_domains();
disable_nonboot_cpus();
if ( num_online_cpus() != 1 )
{
error = -EBUSY;
goto enable_cpu;
}
cpufreq_del_cpu(0);
hvm_cpu_down();
acpi_sleep_prepare(state);
console_start_sync();
printk("Entering ACPI S%d state.\n", state);
local_irq_save(flags);
spin_debug_disable();
if ( (error = device_power_down()) )
{
printk(XENLOG_ERR "Some devices failed to power down.");
goto done;
}
ACPI_FLUSH_CPU_CACHE();
switch ( state )
{
case ACPI_STATE_S3:
do_suspend_lowlevel();
system_reset_counter++;
error = tboot_s3_resume();
break;
case ACPI_STATE_S5:
acpi_enter_sleep_state(ACPI_STATE_S5);
break;
default:
error = -EINVAL;
break;
}
/* Restore CR4 and EFER from cached values. */
write_cr4(read_cr4());
if ( cpu_has_efer )
write_efer(read_efer());
device_power_up();
printk(XENLOG_INFO "Finishing wakeup from ACPI S%d state.\n", state);
if ( (state == ACPI_STATE_S3) && error )
panic("Memory integrity was lost on resume (%d)\n", error);
done:
spin_debug_enable();
local_irq_restore(flags);
console_end_sync();
acpi_sleep_post(state);
if ( !hvm_cpu_up() )
BUG();
enable_cpu:
cpufreq_add_cpu(0);
microcode_resume_cpu(0);
enable_nonboot_cpus();
thaw_domains();
spin_unlock(&pm_lock);
return error;
}
int cpuid_viridian_leaves(unsigned int leaf, unsigned int *eax,
unsigned int *ebx, unsigned int *ecx,
unsigned int *edx)
{
struct domain *d = current->domain;
if ( !is_viridian_domain(d) )
return 0;
leaf -= 0x40000000;
if ( leaf > 6 )
return 0;
*eax = *ebx = *ecx = *edx = 0;
switch ( leaf )
{
case 0:
*eax = 0x40000006; /* Maximum leaf */
*ebx = 0x7263694d; /* Magic numbers */
*ecx = 0x666F736F;
*edx = 0x76482074;
break;
case 1:
*eax = 0x31237648; /* Version number */
break;
case 2:
/* Hypervisor information, but only if the guest has set its
own version number. */
if ( d->arch.hvm_domain.viridian.guest_os_id.raw == 0 )
break;
*eax = 1; /* Build number */
*ebx = (xen_major_version() << 16) | xen_minor_version();
*ecx = 0; /* SP */
*edx = 0; /* Service branch and number */
break;
case 3:
/* Which hypervisor MSRs are available to the guest */
*eax = (CPUID3A_MSR_APIC_ACCESS |
CPUID3A_MSR_HYPERCALL |
CPUID3A_MSR_VP_INDEX);
break;
case 4:
/* Recommended hypercall usage. */
if ( (d->arch.hvm_domain.viridian.guest_os_id.raw == 0) ||
(d->arch.hvm_domain.viridian.guest_os_id.fields.os < 4) )
break;
*eax = CPUID4A_RELAX_TIMER_INT;
if ( !cpu_has_vmx_apic_reg_virt )
*eax |= CPUID4A_MSR_BASED_APIC;
*ebx = 2047; /* long spin count */
break;
case 6:
/* Detected and in use hardware features. */
if ( cpu_has_vmx_virtualize_apic_accesses )
*eax |= CPUID6A_APIC_OVERLAY;
if ( cpu_has_vmx_msr_bitmap || (read_efer() & EFER_SVME) )
*eax |= CPUID6A_MSR_BITMAPS;
if ( hap_enabled(d) )
*eax |= CPUID6A_NESTED_PAGING;
break;
}
return 1;
}