linux/drivers/idle/intel_idle.c
Marcos Paulo de Souza dc716e96f5 drivers/idle/intel_idle.c: fix confusing code identation
Fix a code indentation in the function intel_idle_cpu_init that looks
confusing.o

Suggested-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Marcos Paulo de Souza <marcos.mage@gmail.com>
Cc: "Brown, Len" <len.brown@intel.com>
Cc: Len Brown <lenb@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 17:54:54 -07:00

600 lines
15 KiB
C

/*
* intel_idle.c - native hardware idle loop for modern Intel processors
*
* Copyright (c) 2010, Intel Corporation.
* Len Brown <len.brown@intel.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
*/
/*
* intel_idle is a cpuidle driver that loads on specific Intel processors
* in lieu of the legacy ACPI processor_idle driver. The intent is to
* make Linux more efficient on these processors, as intel_idle knows
* more than ACPI, as well as make Linux more immune to ACPI BIOS bugs.
*/
/*
* Design Assumptions
*
* All CPUs have same idle states as boot CPU
*
* Chipset BM_STS (bus master status) bit is a NOP
* for preventing entry into deep C-stats
*/
/*
* Known limitations
*
* The driver currently initializes for_each_online_cpu() upon modprobe.
* It it unaware of subsequent processors hot-added to the system.
* This means that if you boot with maxcpus=n and later online
* processors above n, those processors will use C1 only.
*
* ACPI has a .suspend hack to turn off deep c-statees during suspend
* to avoid complications with the lapic timer workaround.
* Have not seen issues with suspend, but may need same workaround here.
*
* There is currently no kernel-based automatic probing/loading mechanism
* if the driver is built as a module.
*/
/* un-comment DEBUG to enable pr_debug() statements */
#define DEBUG
#include <linux/kernel.h>
#include <linux/cpuidle.h>
#include <linux/clockchips.h>
#include <linux/hrtimer.h> /* ktime_get_real() */
#include <trace/events/power.h>
#include <linux/sched.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/module.h>
#include <asm/cpu_device_id.h>
#include <asm/mwait.h>
#include <asm/msr.h>
#define INTEL_IDLE_VERSION "0.4"
#define PREFIX "intel_idle: "
static struct cpuidle_driver intel_idle_driver = {
.name = "intel_idle",
.owner = THIS_MODULE,
};
/* intel_idle.max_cstate=0 disables driver */
static int max_cstate = MWAIT_MAX_NUM_CSTATES - 1;
static unsigned int mwait_substates;
#define LAPIC_TIMER_ALWAYS_RELIABLE 0xFFFFFFFF
/* Reliable LAPIC Timer States, bit 1 for C1 etc. */
static unsigned int lapic_timer_reliable_states = (1 << 1); /* Default to only C1 */
struct idle_cpu {
struct cpuidle_state *state_table;
/*
* Hardware C-state auto-demotion may not always be optimal.
* Indicate which enable bits to clear here.
*/
unsigned long auto_demotion_disable_flags;
};
static const struct idle_cpu *icpu;
static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
static int intel_idle(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index);
static struct cpuidle_state *cpuidle_state_table;
/*
* Set this flag for states where the HW flushes the TLB for us
* and so we don't need cross-calls to keep it consistent.
* If this flag is set, SW flushes the TLB, so even if the
* HW doesn't do the flushing, this flag is safe to use.
*/
#define CPUIDLE_FLAG_TLB_FLUSHED 0x10000
/*
* States are indexed by the cstate number,
* which is also the index into the MWAIT hint array.
* Thus C0 is a dummy.
*/
static struct cpuidle_state nehalem_cstates[MWAIT_MAX_NUM_CSTATES] = {
{ /* MWAIT C0 */ },
{ /* MWAIT C1 */
.name = "C1-NHM",
.desc = "MWAIT 0x00",
.flags = CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 3,
.target_residency = 6,
.enter = &intel_idle },
{ /* MWAIT C2 */
.name = "C3-NHM",
.desc = "MWAIT 0x10",
.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 20,
.target_residency = 80,
.enter = &intel_idle },
{ /* MWAIT C3 */
.name = "C6-NHM",
.desc = "MWAIT 0x20",
.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 200,
.target_residency = 800,
.enter = &intel_idle },
};
static struct cpuidle_state snb_cstates[MWAIT_MAX_NUM_CSTATES] = {
{ /* MWAIT C0 */ },
{ /* MWAIT C1 */
.name = "C1-SNB",
.desc = "MWAIT 0x00",
.flags = CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 1,
.target_residency = 1,
.enter = &intel_idle },
{ /* MWAIT C2 */
.name = "C3-SNB",
.desc = "MWAIT 0x10",
.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 80,
.target_residency = 211,
.enter = &intel_idle },
{ /* MWAIT C3 */
.name = "C6-SNB",
.desc = "MWAIT 0x20",
.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 104,
.target_residency = 345,
.enter = &intel_idle },
{ /* MWAIT C4 */
.name = "C7-SNB",
.desc = "MWAIT 0x30",
.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 109,
.target_residency = 345,
.enter = &intel_idle },
};
static struct cpuidle_state atom_cstates[MWAIT_MAX_NUM_CSTATES] = {
{ /* MWAIT C0 */ },
{ /* MWAIT C1 */
.name = "C1-ATM",
.desc = "MWAIT 0x00",
.flags = CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 1,
.target_residency = 4,
.enter = &intel_idle },
{ /* MWAIT C2 */
.name = "C2-ATM",
.desc = "MWAIT 0x10",
.flags = CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 20,
.target_residency = 80,
.enter = &intel_idle },
{ /* MWAIT C3 */ },
{ /* MWAIT C4 */
.name = "C4-ATM",
.desc = "MWAIT 0x30",
.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 100,
.target_residency = 400,
.enter = &intel_idle },
{ /* MWAIT C5 */ },
{ /* MWAIT C6 */
.name = "C6-ATM",
.desc = "MWAIT 0x52",
.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 140,
.target_residency = 560,
.enter = &intel_idle },
};
static long get_driver_data(int cstate)
{
int driver_data;
switch (cstate) {
case 1: /* MWAIT C1 */
driver_data = 0x00;
break;
case 2: /* MWAIT C2 */
driver_data = 0x10;
break;
case 3: /* MWAIT C3 */
driver_data = 0x20;
break;
case 4: /* MWAIT C4 */
driver_data = 0x30;
break;
case 5: /* MWAIT C5 */
driver_data = 0x40;
break;
case 6: /* MWAIT C6 */
driver_data = 0x52;
break;
default:
driver_data = 0x00;
}
return driver_data;
}
/**
* intel_idle
* @dev: cpuidle_device
* @drv: cpuidle driver
* @index: index of cpuidle state
*
* Must be called under local_irq_disable().
*/
static int intel_idle(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
{
unsigned long ecx = 1; /* break on interrupt flag */
struct cpuidle_state *state = &drv->states[index];
struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
unsigned long eax = (unsigned long)cpuidle_get_statedata(state_usage);
unsigned int cstate;
ktime_t kt_before, kt_after;
s64 usec_delta;
int cpu = smp_processor_id();
cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) + 1;
/*
* leave_mm() to avoid costly and often unnecessary wakeups
* for flushing the user TLB's associated with the active mm.
*/
if (state->flags & CPUIDLE_FLAG_TLB_FLUSHED)
leave_mm(cpu);
if (!(lapic_timer_reliable_states & (1 << (cstate))))
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
kt_before = ktime_get_real();
stop_critical_timings();
if (!need_resched()) {
__monitor((void *)&current_thread_info()->flags, 0, 0);
smp_mb();
if (!need_resched())
__mwait(eax, ecx);
}
start_critical_timings();
kt_after = ktime_get_real();
usec_delta = ktime_to_us(ktime_sub(kt_after, kt_before));
local_irq_enable();
if (!(lapic_timer_reliable_states & (1 << (cstate))))
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
/* Update cpuidle counters */
dev->last_residency = (int)usec_delta;
return index;
}
static void __setup_broadcast_timer(void *arg)
{
unsigned long reason = (unsigned long)arg;
int cpu = smp_processor_id();
reason = reason ?
CLOCK_EVT_NOTIFY_BROADCAST_ON : CLOCK_EVT_NOTIFY_BROADCAST_OFF;
clockevents_notify(reason, &cpu);
}
static int setup_broadcast_cpuhp_notify(struct notifier_block *n,
unsigned long action, void *hcpu)
{
int hotcpu = (unsigned long)hcpu;
switch (action & 0xf) {
case CPU_ONLINE:
smp_call_function_single(hotcpu, __setup_broadcast_timer,
(void *)true, 1);
break;
}
return NOTIFY_OK;
}
static struct notifier_block setup_broadcast_notifier = {
.notifier_call = setup_broadcast_cpuhp_notify,
};
static void auto_demotion_disable(void *dummy)
{
unsigned long long msr_bits;
rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
msr_bits &= ~(icpu->auto_demotion_disable_flags);
wrmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
}
static const struct idle_cpu idle_cpu_nehalem = {
.state_table = nehalem_cstates,
.auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE,
};
static const struct idle_cpu idle_cpu_atom = {
.state_table = atom_cstates,
};
static const struct idle_cpu idle_cpu_lincroft = {
.state_table = atom_cstates,
.auto_demotion_disable_flags = ATM_LNC_C6_AUTO_DEMOTE,
};
static const struct idle_cpu idle_cpu_snb = {
.state_table = snb_cstates,
};
#define ICPU(model, cpu) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT, (unsigned long)&cpu }
static const struct x86_cpu_id intel_idle_ids[] = {
ICPU(0x1a, idle_cpu_nehalem),
ICPU(0x1e, idle_cpu_nehalem),
ICPU(0x1f, idle_cpu_nehalem),
ICPU(0x25, idle_cpu_nehalem),
ICPU(0x2c, idle_cpu_nehalem),
ICPU(0x2e, idle_cpu_nehalem),
ICPU(0x1c, idle_cpu_atom),
ICPU(0x26, idle_cpu_lincroft),
ICPU(0x2f, idle_cpu_nehalem),
ICPU(0x2a, idle_cpu_snb),
ICPU(0x2d, idle_cpu_snb),
{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids);
/*
* intel_idle_probe()
*/
static int intel_idle_probe(void)
{
unsigned int eax, ebx, ecx;
const struct x86_cpu_id *id;
if (max_cstate == 0) {
pr_debug(PREFIX "disabled\n");
return -EPERM;
}
id = x86_match_cpu(intel_idle_ids);
if (!id) {
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
boot_cpu_data.x86 == 6)
pr_debug(PREFIX "does not run on family %d model %d\n",
boot_cpu_data.x86, boot_cpu_data.x86_model);
return -ENODEV;
}
if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
return -ENODEV;
cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates);
if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
!(ecx & CPUID5_ECX_INTERRUPT_BREAK) ||
!mwait_substates)
return -ENODEV;
pr_debug(PREFIX "MWAIT substates: 0x%x\n", mwait_substates);
icpu = (const struct idle_cpu *)id->driver_data;
cpuidle_state_table = icpu->state_table;
if (boot_cpu_has(X86_FEATURE_ARAT)) /* Always Reliable APIC Timer */
lapic_timer_reliable_states = LAPIC_TIMER_ALWAYS_RELIABLE;
else {
on_each_cpu(__setup_broadcast_timer, (void *)true, 1);
register_cpu_notifier(&setup_broadcast_notifier);
}
pr_debug(PREFIX "v" INTEL_IDLE_VERSION
" model 0x%X\n", boot_cpu_data.x86_model);
pr_debug(PREFIX "lapic_timer_reliable_states 0x%x\n",
lapic_timer_reliable_states);
return 0;
}
/*
* intel_idle_cpuidle_devices_uninit()
* unregister, free cpuidle_devices
*/
static void intel_idle_cpuidle_devices_uninit(void)
{
int i;
struct cpuidle_device *dev;
for_each_online_cpu(i) {
dev = per_cpu_ptr(intel_idle_cpuidle_devices, i);
cpuidle_unregister_device(dev);
}
free_percpu(intel_idle_cpuidle_devices);
return;
}
/*
* intel_idle_cpuidle_driver_init()
* allocate, initialize cpuidle_states
*/
static int intel_idle_cpuidle_driver_init(void)
{
int cstate;
struct cpuidle_driver *drv = &intel_idle_driver;
drv->state_count = 1;
for (cstate = 1; cstate < MWAIT_MAX_NUM_CSTATES; ++cstate) {
int num_substates;
if (cstate > max_cstate) {
printk(PREFIX "max_cstate %d reached\n",
max_cstate);
break;
}
/* does the state exist in CPUID.MWAIT? */
num_substates = (mwait_substates >> ((cstate) * 4))
& MWAIT_SUBSTATE_MASK;
if (num_substates == 0)
continue;
/* is the state not enabled? */
if (cpuidle_state_table[cstate].enter == NULL) {
/* does the driver not know about the state? */
if (*cpuidle_state_table[cstate].name == '\0')
pr_debug(PREFIX "unaware of model 0x%x"
" MWAIT %d please"
" contact lenb@kernel.org",
boot_cpu_data.x86_model, cstate);
continue;
}
if ((cstate > 2) &&
!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
mark_tsc_unstable("TSC halts in idle"
" states deeper than C2");
drv->states[drv->state_count] = /* structure copy */
cpuidle_state_table[cstate];
drv->state_count += 1;
}
if (icpu->auto_demotion_disable_flags)
on_each_cpu(auto_demotion_disable, NULL, 1);
return 0;
}
/*
* intel_idle_cpu_init()
* allocate, initialize, register cpuidle_devices
* @cpu: cpu/core to initialize
*/
int intel_idle_cpu_init(int cpu)
{
int cstate;
struct cpuidle_device *dev;
dev = per_cpu_ptr(intel_idle_cpuidle_devices, cpu);
dev->state_count = 1;
for (cstate = 1; cstate < MWAIT_MAX_NUM_CSTATES; ++cstate) {
int num_substates;
if (cstate > max_cstate) {
printk(PREFIX "max_cstate %d reached\n", max_cstate);
break;
}
/* does the state exist in CPUID.MWAIT? */
num_substates = (mwait_substates >> ((cstate) * 4))
& MWAIT_SUBSTATE_MASK;
if (num_substates == 0)
continue;
/* is the state not enabled? */
if (cpuidle_state_table[cstate].enter == NULL)
continue;
dev->states_usage[dev->state_count].driver_data =
(void *)get_driver_data(cstate);
dev->state_count += 1;
}
dev->cpu = cpu;
if (cpuidle_register_device(dev)) {
pr_debug(PREFIX "cpuidle_register_device %d failed!\n", cpu);
intel_idle_cpuidle_devices_uninit();
return -EIO;
}
if (icpu->auto_demotion_disable_flags)
smp_call_function_single(cpu, auto_demotion_disable, NULL, 1);
return 0;
}
EXPORT_SYMBOL_GPL(intel_idle_cpu_init);
static int __init intel_idle_init(void)
{
int retval, i;
/* Do not load intel_idle at all for now if idle= is passed */
if (boot_option_idle_override != IDLE_NO_OVERRIDE)
return -ENODEV;
retval = intel_idle_probe();
if (retval)
return retval;
intel_idle_cpuidle_driver_init();
retval = cpuidle_register_driver(&intel_idle_driver);
if (retval) {
printk(KERN_DEBUG PREFIX "intel_idle yielding to %s",
cpuidle_get_driver()->name);
return retval;
}
intel_idle_cpuidle_devices = alloc_percpu(struct cpuidle_device);
if (intel_idle_cpuidle_devices == NULL)
return -ENOMEM;
for_each_online_cpu(i) {
retval = intel_idle_cpu_init(i);
if (retval) {
cpuidle_unregister_driver(&intel_idle_driver);
return retval;
}
}
return 0;
}
static void __exit intel_idle_exit(void)
{
intel_idle_cpuidle_devices_uninit();
cpuidle_unregister_driver(&intel_idle_driver);
if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE) {
on_each_cpu(__setup_broadcast_timer, (void *)false, 1);
unregister_cpu_notifier(&setup_broadcast_notifier);
}
return;
}
module_init(intel_idle_init);
module_exit(intel_idle_exit);
module_param(max_cstate, int, 0444);
MODULE_AUTHOR("Len Brown <len.brown@intel.com>");
MODULE_DESCRIPTION("Cpuidle driver for Intel Hardware v" INTEL_IDLE_VERSION);
MODULE_LICENSE("GPL");