static unsigned int __init get_max_acpi_id(void)
{
struct xenpf_pcpuinfo *info;
struct xen_platform_op op = {
.cmd = XENPF_get_cpuinfo,
.interface_version = XENPF_INTERFACE_VERSION,
};
int ret = 0;
unsigned int i, last_cpu, max_acpi_id = 0;
info = &op.u.pcpu_info;
info->xen_cpuid = 0;
ret = HYPERVISOR_dom0_op(&op);
if (ret)
return NR_CPUS;
last_cpu = op.u.pcpu_info.max_present;
for (i = 0; i <= last_cpu; i++) {
info->xen_cpuid = i;
ret = HYPERVISOR_dom0_op(&op);
if (ret)
continue;
max_acpi_id = max(info->acpi_id, max_acpi_id);
}
max_acpi_id *= 2;
pr_debug(DRV_NAME "Max ACPI ID: %u\n", max_acpi_id);
return max_acpi_id;
}
static unsigned int __init get_max_acpi_id(void)
{
struct xenpf_pcpuinfo *info;
struct xen_platform_op op = {
.cmd = XENPF_get_cpuinfo,
.interface_version = XENPF_INTERFACE_VERSION,
};
int ret = 0;
unsigned int i, last_cpu, max_acpi_id = 0;
info = &op.u.pcpu_info;
info->xen_cpuid = 0;
ret = HYPERVISOR_dom0_op(&op);
if (ret)
return NR_CPUS;
/* The max_present is the same irregardless of the xen_cpuid */
last_cpu = op.u.pcpu_info.max_present;
for (i = 0; i <= last_cpu; i++) {
info->xen_cpuid = i;
ret = HYPERVISOR_dom0_op(&op);
if (ret)
continue;
max_acpi_id = max(info->acpi_id, max_acpi_id);
}
max_acpi_id *= 2; /* Slack for CPU hotplug support. */
pr_debug("Max ACPI ID: %u\n", max_acpi_id);
return max_acpi_id;
}
efi_system_table_t __init *xen_efi_probe(void)
{
struct xen_platform_op op = {
.cmd = XENPF_firmware_info,
.u.firmware_info = {
.type = XEN_FW_EFI_INFO,
.index = XEN_FW_EFI_CONFIG_TABLE
}
};
union xenpf_efi_info *info = &op.u.firmware_info.u.efi_info;
if (!xen_initial_domain() || HYPERVISOR_dom0_op(&op) < 0)
return NULL;
/* Here we know that Xen runs on EFI platform. */
efi = efi_xen;
efi_systab_xen.tables = info->cfg.addr;
efi_systab_xen.nr_tables = info->cfg.nent;
op.cmd = XENPF_firmware_info;
op.u.firmware_info.type = XEN_FW_EFI_INFO;
op.u.firmware_info.index = XEN_FW_EFI_VENDOR;
info->vendor.bufsz = sizeof(vendor);
set_xen_guest_handle(info->vendor.name, vendor);
if (HYPERVISOR_dom0_op(&op) == 0) {
efi_systab_xen.fw_vendor = __pa_symbol(vendor);
efi_systab_xen.fw_revision = info->vendor.revision;
} else
efi_systab_xen.fw_vendor = __pa_symbol(L"UNKNOWN");
op.cmd = XENPF_firmware_info;
op.u.firmware_info.type = XEN_FW_EFI_INFO;
op.u.firmware_info.index = XEN_FW_EFI_VERSION;
if (HYPERVISOR_dom0_op(&op) == 0)
efi_systab_xen.hdr.revision = info->version;
op.cmd = XENPF_firmware_info;
op.u.firmware_info.type = XEN_FW_EFI_INFO;
op.u.firmware_info.index = XEN_FW_EFI_RT_VERSION;
if (HYPERVISOR_dom0_op(&op) == 0)
efi.runtime_version = info->version;
return &efi_systab_xen;
}
static int xen_hotadd_cpu(struct acpi_processor *pr)
{
int cpu_id, apic_id, pxm;
struct xen_platform_op op;
apic_id = xen_apic_id(pr->handle);
if (apic_id < 0) {
pr_err(PREFIX "Failed to get apic_id for acpi_id %d\n",
pr->acpi_id);
return -ENODEV;
}
pxm = xen_acpi_get_pxm(pr->handle);
if (pxm < 0) {
pr_err(PREFIX "Failed to get _PXM for acpi_id %d\n",
pr->acpi_id);
return pxm;
}
op.cmd = XENPF_cpu_hotadd;
op.u.cpu_add.apic_id = apic_id;
op.u.cpu_add.acpi_id = pr->acpi_id;
op.u.cpu_add.pxm = pxm;
cpu_id = HYPERVISOR_dom0_op(&op);
if (cpu_id < 0)
pr_err(PREFIX "Failed to hotadd CPU for acpi_id %d\n",
pr->acpi_id);
return cpu_id;
}
int mtrr_add_page(unsigned long base, unsigned long size,
unsigned int type, char increment)
{
int error;
dom0_op_t op;
mutex_lock(&mtrr_mutex);
op.cmd = DOM0_ADD_MEMTYPE;
op.u.add_memtype.mfn = base;
op.u.add_memtype.nr_mfns = size;
op.u.add_memtype.type = type;
error = HYPERVISOR_dom0_op(&op);
if (error) {
mutex_unlock(&mtrr_mutex);
BUG_ON(error > 0);
return error;
}
if (increment)
++usage_table[op.u.add_memtype.reg];
mutex_unlock(&mtrr_mutex);
return op.u.add_memtype.reg;
}
static u32 xen_apic_read(u32 reg)
{
struct xen_platform_op op = {
.cmd = XENPF_get_cpuinfo,
.interface_version = XENPF_INTERFACE_VERSION,
.u.pcpu_info.xen_cpuid = 0,
};
int ret = 0;
if (!xen_initial_domain() || smp_processor_id())
return 0;
if (reg == APIC_LVR)
return 0x10;
if (reg != APIC_ID)
return 0;
ret = HYPERVISOR_dom0_op(&op);
if (ret)
return 0;
return op.u.pcpu_info.apic_id << 24;
}
static void xen_apic_write(u32 reg, u32 val)
{
WARN_ON(1);
}
static u32 xen_apic_read(u32 reg)
{
struct xen_platform_op op = {
.cmd = XENPF_get_cpuinfo,
.interface_version = XENPF_INTERFACE_VERSION,
.u.pcpu_info.xen_cpuid = 0,
};
int ret = 0;
/* Shouldn't need this as APIC is turned off for PV, and we only
* get called on the bootup processor. But just in case. */
if (!xen_initial_domain() || smp_processor_id())
return 0;
if (reg == APIC_LVR)
return 0x10;
if (reg != APIC_ID)
return 0;
ret = HYPERVISOR_dom0_op(&op);
if (ret)
return 0;
return op.u.pcpu_info.apic_id << 24;
}
static void xen_apic_write(u32 reg, u32 val)
{
/* Warn to see if there's any stray references */
WARN_ON(1);
}
static int xen_pvclock_gtod_notify(struct notifier_block *nb,
unsigned long was_set, void *priv)
{
/* Protected by the calling core code serialization */
static struct timespec next_sync;
struct xen_platform_op op;
struct timespec now;
now = __current_kernel_time();
/*
* We only take the expensive HV call when the clock was set
* or when the 11 minutes RTC synchronization time elapsed.
*/
if (!was_set && timespec_compare(&now, &next_sync) < 0)
return NOTIFY_OK;
op.cmd = XENPF_settime;
op.u.settime.secs = now.tv_sec;
op.u.settime.nsecs = now.tv_nsec;
op.u.settime.system_time = xen_clocksource_read();
(void)HYPERVISOR_dom0_op(&op);
/*
* Move the next drift compensation time 11 minutes
* ahead. That's emulating the sync_cmos_clock() update for
* the hardware RTC.
*/
next_sync = now;
next_sync.tv_sec += 11 * 60;
return NOTIFY_OK;
}
static int xen_acpi_notify_hypervisor_state(u8 sleep_state,
u32 val_a, u32 val_b,
bool extended)
{
unsigned int bits = extended ? 8 : 16;
struct xen_platform_op op = {
.cmd = XENPF_enter_acpi_sleep,
.interface_version = XENPF_INTERFACE_VERSION,
.u.enter_acpi_sleep = {
.val_a = (u16)val_a,
.val_b = (u16)val_b,
.sleep_state = sleep_state,
.flags = extended ? XENPF_ACPI_SLEEP_EXTENDED : 0,
},
};
if (WARN((val_a & (~0 << bits)) || (val_b & (~0 << bits)),
"Using more than %u bits of sleep control values %#x/%#x!"
"Email [email protected] - Thank you.\n", \
bits, val_a, val_b))
return -1;
HYPERVISOR_dom0_op(&op);
return 1;
}
static int xen_acpi_pad_idle_cpus(unsigned int idle_nums)
{
struct xen_platform_op op;
op.cmd = XENPF_core_parking;
op.u.core_parking.type = XEN_CORE_PARKING_SET;
op.u.core_parking.idle_nums = idle_nums;
return HYPERVISOR_dom0_op(&op);
}
static efi_status_t xen_efi_get_next_high_mono_count(u32 *count)
{
struct xen_platform_op op = INIT_EFI_OP(get_next_high_monotonic_count);
if (HYPERVISOR_dom0_op(&op) < 0)
return EFI_UNSUPPORTED;
*count = efi_data(op).misc;
return efi_data(op).status;
}
static void __cpuinit set_num_var_ranges(void)
{
dom0_op_t op;
for (num_var_ranges = 0; ; num_var_ranges++) {
op.cmd = DOM0_READ_MEMTYPE;
op.u.read_memtype.reg = num_var_ranges;
if (HYPERVISOR_dom0_op(&op) != 0)
break;
}
}
static efi_status_t xen_efi_set_time(efi_time_t *tm)
{
struct xen_platform_op op = INIT_EFI_OP(set_time);
BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.set_time));
memcpy(&efi_data(op).u.set_time, tm, sizeof(*tm));
if (HYPERVISOR_dom0_op(&op) < 0)
return EFI_UNSUPPORTED;
return efi_data(op).status;
}
void generic_get_mtrr(unsigned int reg, unsigned long *base,
unsigned int *size, mtrr_type * type)
{
dom0_op_t op;
op.cmd = DOM0_READ_MEMTYPE;
op.u.read_memtype.reg = reg;
(void)HYPERVISOR_dom0_op(&op);
*size = op.u.read_memtype.nr_mfns;
*base = op.u.read_memtype.mfn;
*type = op.u.read_memtype.type;
}
static u32 xen_apic_read(u32 reg)
{
struct xen_platform_op op = {
.cmd = XENPF_get_cpuinfo,
.interface_version = XENPF_INTERFACE_VERSION,
.u.pcpu_info.xen_cpuid = 0,
};
int ret = 0;
/* Shouldn't need this as APIC is turned off for PV, and we only
* get called on the bootup processor. But just in case. */
if (!xen_initial_domain() || smp_processor_id())
return 0;
if (reg == APIC_LVR)
return 0x10;
#ifdef CONFIG_X86_32
if (reg == APIC_LDR)
return SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
#endif
if (reg != APIC_ID)
return 0;
ret = HYPERVISOR_dom0_op(&op);
if (ret)
op.u.pcpu_info.apic_id = BAD_APICID;
return op.u.pcpu_info.apic_id << 24;
}
static void xen_apic_write(u32 reg, u32 val)
{
if (reg == APIC_LVTPC) {
(void)pmu_apic_update(reg);
return;
}
/* Warn to see if there's any stray references */
WARN(1,"register: %x, value: %x\n", reg, val);
}
static u64 xen_apic_icr_read(void)
{
return 0;
}
static void xen_apic_icr_write(u32 low, u32 id)
{
/* Warn to see if there's any stray references */
WARN_ON(1);
}
static efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
{
struct xen_platform_op op = INIT_EFI_OP(set_wakeup_time);
BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.set_wakeup_time));
if (enabled)
efi_data(op).misc = XEN_EFI_SET_WAKEUP_TIME_ENABLE;
if (tm)
memcpy(&efi_data(op).u.set_wakeup_time, tm, sizeof(*tm));
else
efi_data(op).misc |= XEN_EFI_SET_WAKEUP_TIME_ENABLE_ONLY;
if (HYPERVISOR_dom0_op(&op) < 0)
return EFI_UNSUPPORTED;
return efi_data(op).status;
}
int mtrr_del_page(int reg, unsigned long base, unsigned long size)
{
unsigned i;
mtrr_type ltype;
unsigned long lbase;
unsigned int lsize;
int error = -EINVAL;
dom0_op_t op;
mutex_lock(&mtrr_mutex);
if (reg < 0) {
/* Search for existing MTRR */
for (i = 0; i < num_var_ranges; ++i) {
mtrr_if->get(i, &lbase, &lsize, <ype);
if (lbase == base && lsize == size) {
reg = i;
break;
}
}
if (reg < 0) {
printk(KERN_DEBUG "mtrr: no MTRR for %lx000,%lx000 found\n", base,
size);
goto out;
}
}
if (usage_table[reg] < 1) {
printk(KERN_WARNING "mtrr: reg: %d has count=0\n", reg);
goto out;
}
if (--usage_table[reg] < 1) {
op.cmd = DOM0_DEL_MEMTYPE;
op.u.del_memtype.handle = 0;
op.u.del_memtype.reg = reg;
error = HYPERVISOR_dom0_op(&op);
if (error) {
BUG_ON(error > 0);
goto out;
}
}
error = reg;
out:
mutex_unlock(&mtrr_mutex);
return error;
}
static int xen_set_wallclock(unsigned long now)
{
struct xen_platform_op op;
int rc;
/* do nothing for domU */
if (!xen_initial_domain())
return -1;
op.cmd = XENPF_settime;
op.u.settime.secs = now;
op.u.settime.nsecs = 0;
op.u.settime.system_time = xen_clocksource_read();
rc = HYPERVISOR_dom0_op(&op);
WARN(rc != 0, "XENPF_settime failed: now=%ld\n", now);
return rc;
}
static efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
unsigned long count,
unsigned long sg_list)
{
struct xen_platform_op op = INIT_EFI_OP(update_capsule);
if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
return EFI_UNSUPPORTED;
set_xen_guest_handle(efi_data(op).u.update_capsule.capsule_header_array,
capsules);
efi_data(op).u.update_capsule.capsule_count = count;
efi_data(op).u.update_capsule.sg_list = sg_list;
if (HYPERVISOR_dom0_op(&op) < 0)
return EFI_UNSUPPORTED;
return efi_data(op).status;
}
static efi_status_t xen_efi_query_variable_info(u32 attr,
u64 *storage_space,
u64 *remaining_space,
u64 *max_variable_size)
{
struct xen_platform_op op = INIT_EFI_OP(query_variable_info);
if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
return EFI_UNSUPPORTED;
efi_data(op).u.query_variable_info.attr = attr;
if (HYPERVISOR_dom0_op(&op) < 0)
return EFI_UNSUPPORTED;
*storage_space = efi_data(op).u.query_variable_info.max_store_size;
*remaining_space = efi_data(op).u.query_variable_info.remain_store_size;
*max_variable_size = efi_data(op).u.query_variable_info.max_size;
return efi_data(op).status;
}
static efi_status_t xen_efi_set_variable(efi_char16_t *name,
efi_guid_t *vendor,
u32 attr,
unsigned long data_size,
void *data)
{
struct xen_platform_op op = INIT_EFI_OP(set_variable);
set_xen_guest_handle(efi_data(op).u.set_variable.name, name);
efi_data(op).misc = attr;
BUILD_BUG_ON(sizeof(*vendor) !=
sizeof(efi_data(op).u.set_variable.vendor_guid));
memcpy(&efi_data(op).u.set_variable.vendor_guid, vendor, sizeof(*vendor));
efi_data(op).u.set_variable.size = data_size;
set_xen_guest_handle(efi_data(op).u.set_variable.data, data);
if (HYPERVISOR_dom0_op(&op) < 0)
return EFI_UNSUPPORTED;
return efi_data(op).status;
}
static efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
{
struct xen_platform_op op = INIT_EFI_OP(get_time);
if (HYPERVISOR_dom0_op(&op) < 0)
return EFI_UNSUPPORTED;
if (tm) {
BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.get_time.time));
memcpy(tm, &efi_data(op).u.get_time.time, sizeof(*tm));
}
if (tc) {
tc->resolution = efi_data(op).u.get_time.resolution;
tc->accuracy = efi_data(op).u.get_time.accuracy;
tc->sets_to_zero = !!(efi_data(op).misc &
XEN_EFI_GET_TIME_SET_CLEARS_NS);
}
return efi_data(op).status;
}
static efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
unsigned long count,
u64 *max_size,
int *reset_type)
{
struct xen_platform_op op = INIT_EFI_OP(query_capsule_capabilities);
if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
return EFI_UNSUPPORTED;
set_xen_guest_handle(efi_data(op).u.query_capsule_capabilities.capsule_header_array,
capsules);
efi_data(op).u.query_capsule_capabilities.capsule_count = count;
if (HYPERVISOR_dom0_op(&op) < 0)
return EFI_UNSUPPORTED;
*max_size = efi_data(op).u.query_capsule_capabilities.max_capsule_size;
*reset_type = efi_data(op).u.query_capsule_capabilities.reset_type;
return efi_data(op).status;
}
static efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled,
efi_bool_t *pending,
efi_time_t *tm)
{
struct xen_platform_op op = INIT_EFI_OP(get_wakeup_time);
if (HYPERVISOR_dom0_op(&op) < 0)
return EFI_UNSUPPORTED;
if (tm) {
BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.get_wakeup_time));
memcpy(tm, &efi_data(op).u.get_wakeup_time, sizeof(*tm));
}
if (enabled)
*enabled = !!(efi_data(op).misc & XEN_EFI_GET_WAKEUP_TIME_ENABLED);
if (pending)
*pending = !!(efi_data(op).misc & XEN_EFI_GET_WAKEUP_TIME_PENDING);
return efi_data(op).status;
}
static efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
efi_char16_t *name,
efi_guid_t *vendor)
{
struct xen_platform_op op = INIT_EFI_OP(get_next_variable_name);
efi_data(op).u.get_next_variable_name.size = *name_size;
set_xen_guest_handle(efi_data(op).u.get_next_variable_name.name, name);
BUILD_BUG_ON(sizeof(*vendor) !=
sizeof(efi_data(op).u.get_next_variable_name.vendor_guid));
memcpy(&efi_data(op).u.get_next_variable_name.vendor_guid, vendor,
sizeof(*vendor));
if (HYPERVISOR_dom0_op(&op) < 0)
return EFI_UNSUPPORTED;
*name_size = efi_data(op).u.get_next_variable_name.size;
memcpy(vendor, &efi_data(op).u.get_next_variable_name.vendor_guid,
sizeof(*vendor));
return efi_data(op).status;
}
void
resettodr()
{
#ifdef DOM0OPS
dom0_op_t op;
int s;
#endif
#ifdef DEBUG_CLOCK
struct clock_ymdhms dt;
#endif
/*
* We might have been called by boot() due to a crash early
* on. Don't reset the clock chip in this case.
*/
if (!timeset)
return;
#ifdef DEBUG_CLOCK
clock_secs_to_ymdhms(time.tv_sec - rtc_offset * 60, &dt);
printf("setclock: %d/%d/%d %02d:%02d:%02d\n", dt.dt_year,
dt.dt_mon, dt.dt_day, dt.dt_hour, dt.dt_min, dt.dt_sec);
#endif
#ifdef DOM0OPS
if (xen_start_info.dom_id == 0) {
s = splclock();
op.cmd = DOM0_SETTIME;
op.u.settime.secs = time.tv_sec - rtc_offset * 60;
op.u.settime.usecs = time.tv_usec;
op.u.settime.system_time = shadow_system_time;
HYPERVISOR_dom0_op(&op);
splx(s);
}
#endif
}
static bool __init xen_check_mwait(void)
{
#if defined(CONFIG_ACPI) && !defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) && \
!defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE)
struct xen_platform_op op = {
.cmd = XENPF_set_processor_pminfo,
.u.set_pminfo.id = -1,
.u.set_pminfo.type = XEN_PM_PDC,
};
uint32_t buf[3];
unsigned int ax, bx, cx, dx;
unsigned int mwait_mask;
/* We need to determine whether it is OK to expose the MWAIT
* capability to the kernel to harvest deeper than C3 states from ACPI
* _CST using the processor_harvest_xen.c module. For this to work, we
* need to gather the MWAIT_LEAF values (which the cstate.c code
* checks against). The hypervisor won't expose the MWAIT flag because
* it would break backwards compatibility; so we will find out directly
* from the hardware and hypercall.
*/
if (!xen_initial_domain())
return false;
ax = 1;
cx = 0;
native_cpuid(&ax, &bx, &cx, &dx);
mwait_mask = (1 << (X86_FEATURE_EST % 32)) |
(1 << (X86_FEATURE_MWAIT % 32));
if ((cx & mwait_mask) != mwait_mask)
return false;
/* We need to emulate the MWAIT_LEAF and for that we need both
* ecx and edx. The hypercall provides only partial information.
*/
ax = CPUID_MWAIT_LEAF;
bx = 0;
cx = 0;
dx = 0;
native_cpuid(&ax, &bx, &cx, &dx);
/* Ask the Hypervisor whether to clear ACPI_PDC_C_C2C3_FFH. If so,
* don't expose MWAIT_LEAF and let ACPI pick the IOPORT version of C3.
*/
buf[0] = ACPI_PDC_REVISION_ID;
buf[1] = 1;
buf[2] = (ACPI_PDC_C_CAPABILITY_SMP | ACPI_PDC_EST_CAPABILITY_SWSMP);
set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
if ((HYPERVISOR_dom0_op(&op) == 0) &&
(buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) {
cpuid_leaf5_ecx_val = cx;
cpuid_leaf5_edx_val = dx;
}
return true;
#else
return false;
#endif
}
static void __init xen_init_cpuid_mask(void)
{
unsigned int ax, bx, cx, dx;
unsigned int xsave_mask;
cpuid_leaf1_edx_mask =
~((1 << X86_FEATURE_MCE) | /* disable MCE */
(1 << X86_FEATURE_MCA) | /* disable MCA */
(1 << X86_FEATURE_MTRR) | /* disable MTRR */
(1 << X86_FEATURE_ACC)); /* thermal monitoring */
if (!xen_initial_domain())
cpuid_leaf1_edx_mask &=
~((1 << X86_FEATURE_APIC) | /* disable local APIC */
(1 << X86_FEATURE_ACPI)); /* disable ACPI */
ax = 1;
cx = 0;
xen_cpuid(&ax, &bx, &cx, &dx);
xsave_mask =
(1 << (X86_FEATURE_XSAVE % 32)) |
(1 << (X86_FEATURE_OSXSAVE % 32));
/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
if ((cx & xsave_mask) != xsave_mask)
cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
if (xen_check_mwait())
cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32));
}
static bool __init xen_check_mwait(void)
{
#if defined(CONFIG_ACPI) && !defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) && \
!defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE)
struct xen_platform_op op = {
.cmd = XENPF_set_processor_pminfo,
.u.set_pminfo.id = -1,
.u.set_pminfo.type = XEN_PM_PDC,
};
uint32_t buf[3];
unsigned int ax, bx, cx, dx;
unsigned int mwait_mask;
if (!xen_initial_domain())
return false;
ax = 1;
cx = 0;
native_cpuid(&ax, &bx, &cx, &dx);
mwait_mask = (1 << (X86_FEATURE_EST % 32)) |
(1 << (X86_FEATURE_MWAIT % 32));
if ((cx & mwait_mask) != mwait_mask)
return false;
ax = CPUID_MWAIT_LEAF;
bx = 0;
cx = 0;
dx = 0;
native_cpuid(&ax, &bx, &cx, &dx);
buf[0] = ACPI_PDC_REVISION_ID;
buf[1] = 1;
buf[2] = (ACPI_PDC_C_CAPABILITY_SMP | ACPI_PDC_EST_CAPABILITY_SWSMP);
set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
if ((HYPERVISOR_dom0_op(&op) == 0) &&
(buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) {
cpuid_leaf5_ecx_val = cx;
cpuid_leaf5_edx_val = dx;
}
return true;
#else
return false;
#endif
}
static void __init xen_init_cpuid_mask(void)
{
unsigned int ax, bx, cx, dx;
unsigned int xsave_mask;
cpuid_leaf1_edx_mask =
~((1 << X86_FEATURE_MCE) |
(1 << X86_FEATURE_MCA) |
(1 << X86_FEATURE_MTRR) |
(1 << X86_FEATURE_ACC));
if (!xen_initial_domain())
cpuid_leaf1_edx_mask &=
~((1 << X86_FEATURE_APIC) |
(1 << X86_FEATURE_ACPI));
ax = 1;
cx = 0;
xen_cpuid(&ax, &bx, &cx, &dx);
xsave_mask =
(1 << (X86_FEATURE_XSAVE % 32)) |
(1 << (X86_FEATURE_OSXSAVE % 32));
if ((cx & xsave_mask) != xsave_mask)
cpuid_leaf1_ecx_mask &= ~xsave_mask;
if (xen_check_mwait())
cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32));
}
static int push_pxx_to_hypervisor(struct acpi_processor *_pr)
{
int ret = 0;
struct xen_platform_op op = {
.cmd = XENPF_set_processor_pminfo,
.interface_version = XENPF_INTERFACE_VERSION,
.u.set_pminfo.id = _pr->acpi_id,
.u.set_pminfo.type = XEN_PM_PX,
};
struct xen_processor_performance *dst_perf;
struct xen_processor_px *dst_states = NULL;
dst_perf = &op.u.set_pminfo.perf;
dst_perf->platform_limit = _pr->performance_platform_limit;
dst_perf->flags |= XEN_PX_PPC;
xen_copy_pct_data(&(_pr->performance->control_register),
&dst_perf->control_register);
xen_copy_pct_data(&(_pr->performance->status_register),
&dst_perf->status_register);
dst_perf->flags |= XEN_PX_PCT;
dst_states = xen_copy_pss_data(_pr, dst_perf);
if (!IS_ERR_OR_NULL(dst_states)) {
set_xen_guest_handle(dst_perf->states, dst_states);
dst_perf->flags |= XEN_PX_PSS;
}
if (!xen_copy_psd_data(_pr, dst_perf))
dst_perf->flags |= XEN_PX_PSD;
if (dst_perf->flags != (XEN_PX_PSD | XEN_PX_PSS | XEN_PX_PCT | XEN_PX_PPC)) {
pr_warn(DRV_NAME "ACPI CPU%u missing some P-state data (%x), skipping.\n",
_pr->acpi_id, dst_perf->flags);
ret = -ENODEV;
goto err_free;
}
if (!no_hypercall)
ret = HYPERVISOR_dom0_op(&op);
if (!ret) {
struct acpi_processor_performance *perf;
unsigned int i;
perf = _pr->performance;
pr_debug("ACPI CPU%u - P-states uploaded.\n", _pr->acpi_id);
for (i = 0; i < perf->state_count; i++) {
pr_debug(" %cP%d: %d MHz, %d mW, %d uS\n",
(i == perf->state ? '*' : ' '), i,
(u32) perf->states[i].core_frequency,
(u32) perf->states[i].power,
(u32) perf->states[i].transition_latency);
}
} else if (ret != -EINVAL)
pr_warn(DRV_NAME "(_PXX): Hypervisor error (%d) for ACPI CPU%u\n",
ret, _pr->acpi_id);
err_free:
if (!IS_ERR_OR_NULL(dst_states))
kfree(dst_states);
return ret;
}
static int upload_pm_data(struct acpi_processor *_pr)
{
int err = 0;
mutex_lock(&acpi_ids_mutex);
if (__test_and_set_bit(_pr->acpi_id, acpi_ids_done)) {
mutex_unlock(&acpi_ids_mutex);
return -EBUSY;
}
if (_pr->flags.power)
err = push_cxx_to_hypervisor(_pr);
if (_pr->performance && _pr->performance->states)
err |= push_pxx_to_hypervisor(_pr);
mutex_unlock(&acpi_ids_mutex);
return err;
}
static int push_cxx_to_hypervisor(struct acpi_processor *_pr)
{
struct xen_platform_op op = {
.cmd = XENPF_set_processor_pminfo,
.interface_version = XENPF_INTERFACE_VERSION,
.u.set_pminfo.id = _pr->acpi_id,
.u.set_pminfo.type = XEN_PM_CX,
};
struct xen_processor_cx *dst_cx, *dst_cx_states = NULL;
struct acpi_processor_cx *cx;
unsigned int i, ok;
int ret = 0;
dst_cx_states = kcalloc(_pr->power.count,
sizeof(struct xen_processor_cx), GFP_KERNEL);
if (!dst_cx_states)
return -ENOMEM;
for (ok = 0, i = 1; i <= _pr->power.count; i++) {
cx = &_pr->power.states[i];
if (!cx->valid)
continue;
dst_cx = &(dst_cx_states[ok++]);
dst_cx->reg.space_id = ACPI_ADR_SPACE_SYSTEM_IO;
if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
dst_cx->reg.bit_width = 8;
dst_cx->reg.bit_offset = 0;
dst_cx->reg.access_size = 1;
} else {
dst_cx->reg.space_id = ACPI_ADR_SPACE_FIXED_HARDWARE;
if (cx->entry_method == ACPI_CSTATE_FFH) {
dst_cx->reg.bit_offset = 2;
dst_cx->reg.bit_width = 1;
}
dst_cx->reg.access_size = 0;
}
dst_cx->reg.address = cx->address;
dst_cx->type = cx->type;
dst_cx->latency = cx->latency;
dst_cx->power = cx->power;
dst_cx->dpcnt = 0;
set_xen_guest_handle(dst_cx->dp, NULL);
}
if (!ok) {
pr_debug(DRV_NAME "No _Cx for ACPI CPU %u\n", _pr->acpi_id);
kfree(dst_cx_states);
return -EINVAL;
}
op.u.set_pminfo.power.count = ok;
op.u.set_pminfo.power.flags.bm_control = _pr->flags.bm_control;
op.u.set_pminfo.power.flags.bm_check = _pr->flags.bm_check;
op.u.set_pminfo.power.flags.has_cst = _pr->flags.has_cst;
op.u.set_pminfo.power.flags.power_setup_done =
_pr->flags.power_setup_done;
set_xen_guest_handle(op.u.set_pminfo.power.states, dst_cx_states);
if (!no_hypercall)
ret = HYPERVISOR_dom0_op(&op);
if (!ret) {
pr_debug("ACPI CPU%u - C-states uploaded.\n", _pr->acpi_id);
for (i = 1; i <= _pr->power.count; i++) {
cx = &_pr->power.states[i];
if (!cx->valid)
continue;
pr_debug(" C%d: %s %d uS\n",
cx->type, cx->desc, (u32)cx->latency);
}
} else if (ret != -EINVAL)
pr_err(DRV_NAME "(CX): Hypervisor error (%d) for ACPI CPU%u\n",
ret, _pr->acpi_id);
kfree(dst_cx_states);
return ret;
}
static struct xen_processor_px *
xen_copy_pss_data(struct acpi_processor *_pr,
struct xen_processor_performance *dst_perf)
{
struct xen_processor_px *dst_states = NULL;
unsigned int i;
BUILD_BUG_ON(sizeof(struct xen_processor_px) !=
sizeof(struct acpi_processor_px));
dst_states = kcalloc(_pr->performance->state_count,
sizeof(struct xen_processor_px), GFP_KERNEL);
if (!dst_states)
return ERR_PTR(-ENOMEM);
dst_perf->state_count = _pr->performance->state_count;
for (i = 0; i < _pr->performance->state_count; i++) {
memcpy(&(dst_states[i]), &(_pr->performance->states[i]),
sizeof(struct acpi_processor_px));
}
return dst_states;
}
static int xen_copy_psd_data(struct acpi_processor *_pr,
struct xen_processor_performance *dst)
{
struct acpi_psd_package *pdomain;
BUILD_BUG_ON(sizeof(struct xen_psd_package) !=
sizeof(struct acpi_psd_package));
dst->shared_type = _pr->performance->shared_type;
pdomain = &(_pr->performance->domain_info);
if (pdomain->num_processors <= 1) {
if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
dst->shared_type = CPUFREQ_SHARED_TYPE_ALL;
else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
dst->shared_type = CPUFREQ_SHARED_TYPE_HW;
else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
dst->shared_type = CPUFREQ_SHARED_TYPE_ANY;
}
memcpy(&(dst->domain_info), pdomain, sizeof(struct acpi_psd_package));
return 0;
}
static int xen_copy_pct_data(struct acpi_pct_register *pct,
struct xen_pct_register *dst_pct)
{
dst_pct->descriptor = pct->descriptor;
dst_pct->length = pct->length;
dst_pct->space_id = pct->space_id;
dst_pct->bit_width = pct->bit_width;
dst_pct->bit_offset = pct->bit_offset;
dst_pct->reserved = pct->reserved;
dst_pct->address = pct->address;
return 0;
}
