/*
* AMD Erratum 400 aware idle routine. We check for C1E active in the interrupt
* pending message MSR. If we detect C1E, then we handle it the same
* way as C3 power states (local apic timer and TSC stop)
*/
static void amd_e400_idle(void)
{
if (!amd_e400_c1e_detected) {
u32 lo, hi;
rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
if (lo & K8_INTP_C1E_ACTIVE_MASK) {
amd_e400_c1e_detected = true;
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
mark_tsc_unstable("TSC halt in AMD C1E");
pr_info("System has AMD C1E enabled\n");
}
}
if (amd_e400_c1e_detected) {
int cpu = smp_processor_id();
if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) {
cpumask_set_cpu(cpu, amd_e400_c1e_mask);
/* Force broadcast so ACPI can not interfere. */
tick_broadcast_force();
pr_info("Switch to broadcast mode on CPU%d\n", cpu);
}
tick_broadcast_enter();
default_idle();
/*
* The switch back from broadcast mode needs to be
* called with interrupts disabled.
*/
local_irq_disable();
tick_broadcast_exit();
local_irq_enable();
} else
default_idle();
}
/*
* Source CPU calls into this - it waits for the freshly booted
* target CPU to arrive and then starts the measurement:
*/
void __cpuinit check_tsc_sync_source(int cpu)
{
unsigned long flags;
int cpus = 2;
/*
* No need to check if we already know that the TSC is not
* synchronized:
*/
if (unsynchronized_tsc())
return;
printk(KERN_INFO "checking TSC synchronization [CPU#%d -> CPU#%d]:",
smp_processor_id(), cpu);
/*
* Reset it - in case this is a second bootup:
*/
atomic_set(&stop_count, 0);
/*
* Wait for the target to arrive:
*/
local_save_flags(flags);
local_irq_enable();
while (atomic_read(&start_count) != cpus-1)
cpu_relax();
local_irq_restore(flags);
/*
* Trigger the target to continue into the measurement too:
*/
atomic_inc(&start_count);
check_tsc_warp();
while (atomic_read(&stop_count) != cpus-1)
cpu_relax();
/*
* Reset it - just in case we boot another CPU later:
*/
atomic_set(&start_count, 0);
if (nr_warps) {
printk("\n");
printk(KERN_WARNING "Measured %Ld cycles TSC warp between CPUs,"
" turning off TSC clock.\n", max_warp);
mark_tsc_unstable();
nr_warps = 0;
max_warp = 0;
last_tsc = 0;
} else {
printk(" passed.\n");
}
/*
* Let the target continue with the bootup:
*/
atomic_inc(&stop_count);
}
/* Hook from generic ACPI tables.c */
static int summit_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
if (!strncmp(oem_id, "IBM", 3) &&
(!strncmp(oem_table_id, "SERVIGIL", 8)
|| !strncmp(oem_table_id, "EXA", 3))){
mark_tsc_unstable("Summit based system");
use_cyclone = 1; /*enable cyclone-timer*/
setup_summit();
return 1;
}
return 0;
}
static int summit_mps_oem_check(struct mpc_table *mpc, char *oem,
char *productid)
{
if (!strncmp(oem, "IBM ENSW", 8) &&
(!strncmp(productid, "VIGIL SMP", 9)
|| !strncmp(productid, "EXA", 3)
|| !strncmp(productid, "RUTHLESS SMP", 12))){
mark_tsc_unstable("Summit based system");
use_cyclone = 1; /*enable cyclone-timer*/
setup_summit();
return 1;
}
return 0;
}
static void __init ms_hyperv_init_platform(void)
{
/*
* Extract the features and hints
*/
ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
pr_info("HyperV: features 0x%x, hints 0x%x\n",
ms_hyperv.features, ms_hyperv.hints);
#ifdef CONFIG_X86_LOCAL_APIC
if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) {
/*
* Get the APIC frequency.
*/
u64 hv_lapic_frequency;
rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
lapic_timer_frequency = hv_lapic_frequency;
pr_info("HyperV: LAPIC Timer Frequency: %#x\n",
lapic_timer_frequency);
}
register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST,
"hv_nmi_unknown");
#endif
if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
#ifdef CONFIG_X86_IO_APIC
no_timer_check = 1;
#endif
#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE)
machine_ops.shutdown = hv_machine_shutdown;
machine_ops.crash_shutdown = hv_machine_crash_shutdown;
#endif
mark_tsc_unstable("running on Hyper-V");
/*
* Generation 2 instances don't support reading the NMI status from
* 0x61 port.
*/
if (efi_enabled(EFI_BOOT))
x86_platform.get_nmi_reason = hv_get_nmi_reason;
}
static void power_saving_mwait_init(void)
{
unsigned int eax, ebx, ecx, edx;
unsigned int highest_cstate = 0;
unsigned int highest_subcstate = 0;
int i;
if (!boot_cpu_has(X86_FEATURE_MWAIT))
return;
if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
return;
cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
!(ecx & CPUID5_ECX_INTERRUPT_BREAK))
return;
edx >>= MWAIT_SUBSTATE_SIZE;
for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
if (edx & MWAIT_SUBSTATE_MASK) {
highest_cstate = i;
highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
}
}
power_saving_mwait_eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
(highest_subcstate - 1);
for_each_online_cpu(i)
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &i);
#if defined(CONFIG_GENERIC_TIME) && defined(CONFIG_X86)
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
case X86_VENDOR_INTEL:
/*
* AMD Fam10h TSC will tick in all
* C/P/S0/S1 states when this bit is set.
*/
if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
return;
/*FALL THROUGH*/
default:
/* TSC could halt in idle, so notify users */
mark_tsc_unstable("TSC halts in idle");
}
#endif
}
static void tsc_check_state(int state)
{
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
case X86_VENDOR_INTEL:
if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
return;
default:
if (state > ACPI_STATE_C1)
mark_tsc_unstable("TSC halts in idle");
}
}
static void tsc_check_state(int state)
{
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
case X86_VENDOR_INTEL:
/*
* AMD Fam10h TSC will tick in all
* C/P/S0/S1 states when this bit is set.
*/
if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
return;
/*FALL THROUGH*/
default:
/* TSC could halt in idle, so notify users */
if (state > ACPI_STATE_C1)
mark_tsc_unstable("TSC halts in idle");
}
}
static int __init kretprobe_init(void)
{
int ret;
my_kretprobe.kp.symbol_name = func_name;
ret = register_kretprobe(&my_kretprobe);
if (ret < 0) {
printk(KERN_INFO "register_kretprobe failed, returned %d\n",
ret);
return -1;
}
mark_tsc_unstable("kernel uptime bug");
printk(KERN_INFO "Planted return probe at %s: %p\n",
my_kretprobe.kp.symbol_name, my_kretprobe.kp.addr);
return 0;
}
static void __init ms_hyperv_init_platform(void)
{
/*
* Extract the features and hints
*/
ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
pr_info("HyperV: features 0x%x, hints 0x%x\n",
ms_hyperv.features, ms_hyperv.hints);
#ifdef CONFIG_X86_LOCAL_APIC
if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) {
/*
* Get the APIC frequency.
*/
u64 hv_lapic_frequency;
rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
lapic_timer_frequency = hv_lapic_frequency;
pr_info("HyperV: LAPIC Timer Frequency: %#x\n",
lapic_timer_frequency);
}
#endif
if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
#ifdef CONFIG_X86_IO_APIC
no_timer_check = 1;
#endif
#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE)
machine_ops.shutdown = hv_machine_shutdown;
machine_ops.crash_shutdown = hv_machine_crash_shutdown;
#endif
mark_tsc_unstable("running on Hyper-V");
}
void __init arch_post_acpi_subsys_init(void)
{
u32 lo, hi;
if (!boot_cpu_has_bug(X86_BUG_AMD_E400))
return;
/*
* AMD E400 detection needs to happen after ACPI has been enabled. If
* the machine is affected K8_INTP_C1E_ACTIVE_MASK bits are set in
* MSR_K8_INT_PENDING_MSG.
*/
rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
if (!(lo & K8_INTP_C1E_ACTIVE_MASK))
return;
boot_cpu_set_bug(X86_BUG_AMD_APIC_C1E);
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
mark_tsc_unstable("TSC halt in AMD C1E");
pr_info("System has AMD C1E enabled\n");
}
/*
* Source CPU calls into this - it waits for the freshly booted
* target CPU to arrive and then starts the measurement:
*/
void __cpuinit check_tsc_sync_source(int cpu)
{
int cpus = 2;
/*
* No need to check if we already know that the TSC is not
* synchronized:
*/
if (unsynchronized_tsc())
return;
if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
printk(KERN_INFO
"Skipping synchronization checks as TSC is reliable.\n");
return;
}
printk(KERN_INFO "checking TSC synchronization [CPU#%d -> CPU#%d]:",
smp_processor_id(), cpu);
/*
* Reset it - in case this is a second bootup:
*/
atomic_set(&stop_count, 0);
/*
* Wait for the target to arrive:
*/
while (atomic_read(&start_count) != cpus-1)
cpu_relax();
/*
* Trigger the target to continue into the measurement too:
*/
atomic_inc(&start_count);
check_tsc_warp();
while (atomic_read(&stop_count) != cpus-1)
cpu_relax();
if (nr_warps) {
printk("\n");
printk(KERN_WARNING "Measured %Ld cycles TSC warp between CPUs,"
" turning off TSC clock.\n", max_warp);
mark_tsc_unstable("check_tsc_sync_source failed");
} else {
printk(" passed.\n");
}
/*
* Reset it - just in case we boot another CPU later:
*/
atomic_set(&start_count, 0);
nr_warps = 0;
max_warp = 0;
last_tsc = 0;
/*
* Let the target continue with the bootup:
*/
atomic_inc(&stop_count);
}
/**
* acpi_idle_enter_bm - enters C3 with proper BM handling
* @dev: the target CPU
* @state: the state data
*
* If BM is detected, the deepest non-C3 idle state is entered instead.
*/
static int acpi_idle_enter_bm(struct cpuidle_device *dev,
struct cpuidle_state *state)
{
struct acpi_processor *pr;
struct acpi_processor_cx *cx = cpuidle_get_statedata(state);
u32 t1, t2;
int sleep_ticks = 0;
pr = __get_cpu_var(processors);
if (unlikely(!pr))
return 0;
if (acpi_idle_suspend)
return(acpi_idle_enter_c1(dev, state));
if (acpi_idle_bm_check()) {
if (dev->safe_state) {
dev->last_state = dev->safe_state;
return dev->safe_state->enter(dev, dev->safe_state);
} else {
local_irq_disable();
acpi_safe_halt();
local_irq_enable();
return 0;
}
}
local_irq_disable();
current_thread_info()->status &= ~TS_POLLING;
/*
* TS_POLLING-cleared state must be visible before we test
* NEED_RESCHED:
*/
smp_mb();
if (unlikely(need_resched())) {
current_thread_info()->status |= TS_POLLING;
local_irq_enable();
return 0;
}
acpi_unlazy_tlb(smp_processor_id());
/* Tell the scheduler that we are going deep-idle: */
sched_clock_idle_sleep_event();
/*
* Must be done before busmaster disable as we might need to
* access HPET !
*/
acpi_state_timer_broadcast(pr, cx, 1);
/*
* disable bus master
* bm_check implies we need ARB_DIS
* !bm_check implies we need cache flush
* bm_control implies whether we can do ARB_DIS
*
* That leaves a case where bm_check is set and bm_control is
* not set. In that case we cannot do much, we enter C3
* without doing anything.
*/
if (pr->flags.bm_check && pr->flags.bm_control) {
spin_lock(&c3_lock);
c3_cpu_count++;
/* Disable bus master arbitration when all CPUs are in C3 */
if (c3_cpu_count == num_online_cpus())
acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1);
spin_unlock(&c3_lock);
} else if (!pr->flags.bm_check) {
ACPI_FLUSH_CPU_CACHE();
}
t1 = inl(acpi_gbl_FADT.xpm_timer_block.address);
acpi_idle_do_entry(cx);
t2 = inl(acpi_gbl_FADT.xpm_timer_block.address);
/* Re-enable bus master arbitration */
if (pr->flags.bm_check && pr->flags.bm_control) {
spin_lock(&c3_lock);
acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0);
c3_cpu_count--;
spin_unlock(&c3_lock);
}
#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86)
/* TSC could halt in idle, so notify users */
if (tsc_halts_in_c(ACPI_STATE_C3))
mark_tsc_unstable("TSC halts in idle");
#endif
sleep_ticks = ticks_elapsed(t1, t2);
/* Tell the scheduler how much we idled: */
sched_clock_idle_wakeup_event(sleep_ticks*PM_TIMER_TICK_NS);
local_irq_enable();
current_thread_info()->status |= TS_POLLING;
cx->usage++;
acpi_state_timer_broadcast(pr, cx, 0);
cx->time += sleep_ticks;
return ticks_elapsed_in_us(t1, t2);
}
/**
* acpi_idle_enter_simple - enters an ACPI state without BM handling
* @dev: the target CPU
* @state: the state data
*/
static int acpi_idle_enter_simple(struct cpuidle_device *dev,
struct cpuidle_state *state)
{
struct acpi_processor *pr;
struct acpi_processor_cx *cx = cpuidle_get_statedata(state);
u32 t1, t2;
int sleep_ticks = 0;
pr = __get_cpu_var(processors);
if (unlikely(!pr))
return 0;
if (acpi_idle_suspend)
return(acpi_idle_enter_c1(dev, state));
local_irq_disable();
current_thread_info()->status &= ~TS_POLLING;
/*
* TS_POLLING-cleared state must be visible before we test
* NEED_RESCHED:
*/
smp_mb();
if (unlikely(need_resched())) {
current_thread_info()->status |= TS_POLLING;
local_irq_enable();
return 0;
}
/*
* Must be done before busmaster disable as we might need to
* access HPET !
*/
acpi_state_timer_broadcast(pr, cx, 1);
if (cx->type == ACPI_STATE_C3)
ACPI_FLUSH_CPU_CACHE();
t1 = inl(acpi_gbl_FADT.xpm_timer_block.address);
/* Tell the scheduler that we are going deep-idle: */
sched_clock_idle_sleep_event();
acpi_idle_do_entry(cx);
t2 = inl(acpi_gbl_FADT.xpm_timer_block.address);
#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86)
/* TSC could halt in idle, so notify users */
if (tsc_halts_in_c(cx->type))
mark_tsc_unstable("TSC halts in idle");;
#endif
sleep_ticks = ticks_elapsed(t1, t2);
/* Tell the scheduler how much we idled: */
sched_clock_idle_wakeup_event(sleep_ticks*PM_TIMER_TICK_NS);
local_irq_enable();
current_thread_info()->status |= TS_POLLING;
cx->usage++;
acpi_state_timer_broadcast(pr, cx, 0);
cx->time += sleep_ticks;
return ticks_elapsed_in_us(t1, t2);
}
/* avoid HT sibilings if possible */
if (cpumask_empty(tmp))
cpumask_andnot(tmp, cpu_online_mask, pad_busy_cpus);
if (cpumask_empty(tmp)) {
mutex_unlock(&round_robin_lock);
return;
}
for_each_cpu(cpu, tmp) {
if (cpu_weight[cpu] < min_weight) {
min_weight = cpu_weight[cpu];
preferred_cpu = cpu;
}
}
if (tsk_in_cpu[tsk_index] != -1)
cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
tsk_in_cpu[tsk_index] = preferred_cpu;
cpumask_set_cpu(preferred_cpu, pad_busy_cpus);
cpu_weight[preferred_cpu]++;
mutex_unlock(&round_robin_lock);
set_cpus_allowed_ptr(current, cpumask_of(preferred_cpu));
}
static void exit_round_robin(unsigned int tsk_index)
{
struct cpumask *pad_busy_cpus = to_cpumask(pad_busy_cpus_bits);
cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
tsk_in_cpu[tsk_index] = -1;
}
static unsigned int idle_pct = 5; /* percentage */
static unsigned int round_robin_time = 1; /* second */
static int power_saving_thread(void *data)
{
struct sched_param param = {.sched_priority = 1};
int do_sleep;
unsigned int tsk_index = (unsigned long)data;
u64 last_jiffies = 0;
sched_setscheduler(current, SCHED_RR, ¶m);
while (!kthread_should_stop()) {
unsigned long expire_time;
try_to_freeze();
/* round robin to cpus */
expire_time = last_jiffies + round_robin_time * HZ;
if (time_before(expire_time, jiffies)) {
last_jiffies = jiffies;
round_robin_cpu(tsk_index);
}
do_sleep = 0;
expire_time = jiffies + HZ * (100 - idle_pct) / 100;
while (!need_resched()) {
if (tsc_detected_unstable && !tsc_marked_unstable) {
/* TSC could halt in idle, so notify users */
mark_tsc_unstable("TSC halts in idle");
tsc_marked_unstable = 1;
}
local_irq_disable();
tick_broadcast_enable();
tick_broadcast_enter();
stop_critical_timings();
mwait_idle_with_hints(power_saving_mwait_eax, 1);
start_critical_timings();
tick_broadcast_exit();
local_irq_enable();
if (time_before(expire_time, jiffies)) {
do_sleep = 1;
break;
}
}
/*
* current sched_rt has threshold for rt task running time.
* When a rt task uses 95% CPU time, the rt thread will be
* scheduled out for 5% CPU time to not starve other tasks. But
* the mechanism only works when all CPUs have RT task running,
* as if one CPU hasn't RT task, RT task from other CPUs will
* borrow CPU time from this CPU and cause RT task use > 95%
* CPU time. To make 'avoid starvation' work, takes a nap here.
*/
if (unlikely(do_sleep))
schedule_timeout_killable(HZ * idle_pct / 100);
/* If an external event has set the need_resched flag, then
* we need to deal with it, or this loop will continue to
* spin without calling __mwait().
*/
if (unlikely(need_resched()))
schedule();
}
exit_round_robin(tsk_index);
return 0;
}
static struct task_struct *ps_tsks[NR_CPUS];
static unsigned int ps_tsk_num;
static int create_power_saving_task(void)
{
int rc;
ps_tsks[ps_tsk_num] = kthread_run(power_saving_thread,
(void *)(unsigned long)ps_tsk_num,
"acpi_pad/%d", ps_tsk_num);
if (IS_ERR(ps_tsks[ps_tsk_num])) {
rc = PTR_ERR(ps_tsks[ps_tsk_num]);
ps_tsks[ps_tsk_num] = NULL;
} else {
rc = 0;
ps_tsk_num++;
}
return rc;
}
/*
* Source CPU calls into this - it waits for the freshly booted
* target CPU to arrive and then starts the measurement:
*/
void check_tsc_sync_source(int cpu)
{
int cpus = 2;
/*
* No need to check if we already know that the TSC is not
* synchronized or if we have no TSC.
*/
if (unsynchronized_tsc())
return;
/*
* Set the maximum number of test runs to
* 1 if the CPU does not provide the TSC_ADJUST MSR
* 3 if the MSR is available, so the target can try to adjust
*/
if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST))
atomic_set(&test_runs, 1);
else
atomic_set(&test_runs, 3);
retry:
/*
* Wait for the target to start or to skip the test:
*/
while (atomic_read(&start_count) != cpus - 1) {
if (atomic_read(&skip_test) > 0) {
atomic_set(&skip_test, 0);
return;
}
cpu_relax();
}
/*
* Trigger the target to continue into the measurement too:
*/
atomic_inc(&start_count);
check_tsc_warp(loop_timeout(cpu));
while (atomic_read(&stop_count) != cpus-1)
cpu_relax();
/*
* If the test was successful set the number of runs to zero and
* stop. If not, decrement the number of runs an check if we can
* retry. In case of random warps no retry is attempted.
*/
if (!nr_warps) {
atomic_set(&test_runs, 0);
pr_debug("TSC synchronization [CPU#%d -> CPU#%d]: passed\n",
smp_processor_id(), cpu);
} else if (atomic_dec_and_test(&test_runs) || random_warps) {
/* Force it to 0 if random warps brought us here */
atomic_set(&test_runs, 0);
pr_warning("TSC synchronization [CPU#%d -> CPU#%d]:\n",
smp_processor_id(), cpu);
pr_warning("Measured %Ld cycles TSC warp between CPUs, "
"turning off TSC clock.\n", max_warp);
if (random_warps)
pr_warning("TSC warped randomly between CPUs\n");
mark_tsc_unstable("check_tsc_sync_source failed");
}
/*
* Reset it - just in case we boot another CPU later:
*/
atomic_set(&start_count, 0);
random_warps = 0;
nr_warps = 0;
max_warp = 0;
last_tsc = 0;
/*
* Let the target continue with the bootup:
*/
atomic_inc(&stop_count);
/*
* Retry, if there is a chance to do so.
*/
if (atomic_read(&test_runs) > 0)
goto retry;
}
/* avoid HT sibilings if possible */
if (cpumask_empty(tmp))
cpumask_andnot(tmp, cpu_online_mask, pad_busy_cpus);
if (cpumask_empty(tmp)) {
mutex_unlock(&round_robin_lock);
return;
}
for_each_cpu(cpu, tmp) {
if (cpu_weight[cpu] < min_weight) {
min_weight = cpu_weight[cpu];
preferred_cpu = cpu;
}
}
if (tsk_in_cpu[tsk_index] != -1)
cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
tsk_in_cpu[tsk_index] = preferred_cpu;
cpumask_set_cpu(preferred_cpu, pad_busy_cpus);
cpu_weight[preferred_cpu]++;
mutex_unlock(&round_robin_lock);
set_cpus_allowed_ptr(current, cpumask_of(preferred_cpu));
}
static void exit_round_robin(unsigned int tsk_index)
{
struct cpumask *pad_busy_cpus = to_cpumask(pad_busy_cpus_bits);
cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
tsk_in_cpu[tsk_index] = -1;
}
static unsigned int idle_pct = 5; /* percentage */
static unsigned int round_robin_time = 1; /* second */
static int power_saving_thread(void *data)
{
struct sched_param param = {.sched_priority = 1};
int do_sleep;
unsigned int tsk_index = (unsigned long)data;
u64 last_jiffies = 0;
sched_setscheduler(current, SCHED_RR, ¶m);
set_freezable();
while (!kthread_should_stop()) {
int cpu;
u64 expire_time;
try_to_freeze();
/* round robin to cpus */
if (last_jiffies + round_robin_time * HZ < jiffies) {
last_jiffies = jiffies;
round_robin_cpu(tsk_index);
}
do_sleep = 0;
expire_time = jiffies + HZ * (100 - idle_pct) / 100;
while (!need_resched()) {
if (tsc_detected_unstable && !tsc_marked_unstable) {
/* TSC could halt in idle, so notify users */
mark_tsc_unstable("TSC halts in idle");
tsc_marked_unstable = 1;
}
if (lapic_detected_unstable && !lapic_marked_unstable) {
int i;
/* LAPIC could halt in idle, so notify users */
for_each_online_cpu(i)
clockevents_notify(
CLOCK_EVT_NOTIFY_BROADCAST_ON,
&i);
lapic_marked_unstable = 1;
}
local_irq_disable();
cpu = smp_processor_id();
if (lapic_marked_unstable)
clockevents_notify(
CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
stop_critical_timings();
__monitor((void *)¤t_thread_info()->flags, 0, 0);
smp_mb();
if (!need_resched())
__mwait(power_saving_mwait_eax, 1);
start_critical_timings();
if (lapic_marked_unstable)
clockevents_notify(
CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
local_irq_enable();
if (jiffies > expire_time) {
do_sleep = 1;
break;
}
}
/*
* current sched_rt has threshold for rt task running time.
* When a rt task uses 95% CPU time, the rt thread will be
* scheduled out for 5% CPU time to not starve other tasks. But
* the mechanism only works when all CPUs have RT task running,
* as if one CPU hasn't RT task, RT task from other CPUs will
* borrow CPU time from this CPU and cause RT task use > 95%
* CPU time. To make 'avoid starvation' work, takes a nap here.
*/
if (do_sleep)
schedule_timeout_killable(HZ * idle_pct / 100);
}
exit_round_robin(tsk_index);
return 0;
}
static struct task_struct *ps_tsks[NR_CPUS];
static unsigned int ps_tsk_num;
static int create_power_saving_task(void)
{
int rc = -ENOMEM;
ps_tsks[ps_tsk_num] = kthread_run(power_saving_thread,
(void *)(unsigned long)ps_tsk_num,
"acpi_pad/%d", ps_tsk_num);
rc = PTR_RET(ps_tsks[ps_tsk_num]);
if (!rc)
ps_tsk_num++;
else
ps_tsks[ps_tsk_num] = NULL;
return rc;
}
/*
* Source CPU calls into this - it waits for the freshly booted
* target CPU to arrive and then starts the measurement:
*/
void __cpuinit check_tsc_sync_source(int cpu)
{
int cpus = 2;
/*
* No need to check if we already know that the TSC is not
* synchronized:
*/
if (unsynchronized_tsc())
return;
if (tsc_clocksource_reliable) {
if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING)
pr_info(
"Skipped synchronization checks as TSC is reliable.\n");
return;
}
/*
* Reset it - in case this is a second bootup:
*/
atomic_set(&stop_count, 0);
/*
* Wait for the target to arrive:
*/
while (atomic_read(&start_count) != cpus-1)
cpu_relax();
/*
* Trigger the target to continue into the measurement too:
*/
atomic_inc(&start_count);
check_tsc_warp(loop_timeout(cpu));
while (atomic_read(&stop_count) != cpus-1)
cpu_relax();
if (nr_warps) {
pr_warning("TSC synchronization [CPU#%d -> CPU#%d]:\n",
smp_processor_id(), cpu);
pr_warning("Measured %Ld cycles TSC warp between CPUs, "
"turning off TSC clock.\n", max_warp);
mark_tsc_unstable("check_tsc_sync_source failed");
} else {
pr_debug("TSC synchronization [CPU#%d -> CPU#%d]: passed\n",
smp_processor_id(), cpu);
}
/*
* Reset it - just in case we boot another CPU later:
*/
atomic_set(&start_count, 0);
nr_warps = 0;
max_warp = 0;
last_tsc = 0;
/*
* Let the target continue with the bootup:
*/
atomic_inc(&stop_count);
}