linux-sg2042/drivers/idle/intel_idle.c

708 lines
18 KiB
C
Raw Normal View History

/*
* 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 <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,
cpuidle: Measure idle state durations with monotonic clock Many cpuidle drivers measure their time spent in an idle state by reading the wallclock time before and after idling and calculating the difference. This leads to erroneous results when the wallclock time gets updated by another processor in the meantime, adding that clock adjustment to the idle state's time counter. If the clock adjustment was negative, the result is even worse due to an erroneous cast from int to unsigned long long of the last_residency variable. The negative 32 bit integer will zero-extend and result in a forward time jump of roughly four billion milliseconds or 1.3 hours on the idle state residency counter. This patch changes all affected cpuidle drivers to either use the monotonic clock for their measurements or make use of the generic time measurement wrapper in cpuidle.c, which was already working correctly. Some superfluous CLIs/STIs in the ACPI code are removed (interrupts should always already be disabled before entering the idle function, and not get reenabled until the generic wrapper has performed its second measurement). It also removes the erroneous cast, making sure that negative residency values are applied correctly even though they should not appear anymore. Signed-off-by: Julius Werner <jwerner@chromium.org> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Tested-by: Daniel Lezcano <daniel.lezcano@linaro.org> Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org> Acked-by: Len Brown <len.brown@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2012-11-27 21:17:58 +08:00
.en_core_tk_irqen = 1,
};
/* intel_idle.max_cstate=0 disables driver */
static int max_cstate = CPUIDLE_STATE_MAX - 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;
bool disable_promotion_to_c1e;
};
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 int intel_idle_cpu_init(int cpu);
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
/*
* MWAIT takes an 8-bit "hint" in EAX "suggesting"
* the C-state (top nibble) and sub-state (bottom nibble)
* 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc.
*
* We store the hint at the top of our "flags" for each state.
*/
#define flg2MWAIT(flags) (((flags) >> 24) & 0xFF)
#define MWAIT2flg(eax) ((eax & 0xFF) << 24)
/*
* 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[CPUIDLE_STATE_MAX] = {
{
.name = "C1-NHM",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 3,
.target_residency = 6,
.enter = &intel_idle },
{
.name = "C1E-NHM",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 20,
.enter = &intel_idle },
{
.name = "C3-NHM",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 20,
.target_residency = 80,
.enter = &intel_idle },
{
.name = "C6-NHM",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 200,
.target_residency = 800,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state snb_cstates[CPUIDLE_STATE_MAX] = {
{
.name = "C1-SNB",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 2,
.target_residency = 2,
.enter = &intel_idle },
{
.name = "C1E-SNB",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 20,
.enter = &intel_idle },
{
.name = "C3-SNB",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 80,
.target_residency = 211,
.enter = &intel_idle },
{
.name = "C6-SNB",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 104,
.target_residency = 345,
.enter = &intel_idle },
{
.name = "C7-SNB",
.desc = "MWAIT 0x30",
.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 109,
.target_residency = 345,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state ivb_cstates[CPUIDLE_STATE_MAX] = {
{
.name = "C1-IVB",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 1,
.target_residency = 1,
.enter = &intel_idle },
{
.name = "C1E-IVB",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 20,
.enter = &intel_idle },
{
.name = "C3-IVB",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 59,
.target_residency = 156,
.enter = &intel_idle },
{
.name = "C6-IVB",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 80,
.target_residency = 300,
.enter = &intel_idle },
{
.name = "C7-IVB",
.desc = "MWAIT 0x30",
.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 87,
.target_residency = 300,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state hsw_cstates[CPUIDLE_STATE_MAX] = {
{
.name = "C1-HSW",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 2,
.target_residency = 2,
.enter = &intel_idle },
{
.name = "C1E-HSW",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 20,
.enter = &intel_idle },
{
.name = "C3-HSW",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 33,
.target_residency = 100,
.enter = &intel_idle },
{
.name = "C6-HSW",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 133,
.target_residency = 400,
.enter = &intel_idle },
{
.name = "C7s-HSW",
.desc = "MWAIT 0x32",
.flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 166,
.target_residency = 500,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state atom_cstates[CPUIDLE_STATE_MAX] = {
{
.name = "C1E-ATM",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 20,
.enter = &intel_idle },
{
.name = "C2-ATM",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 20,
.target_residency = 80,
.enter = &intel_idle },
{
.name = "C4-ATM",
.desc = "MWAIT 0x30",
.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 100,
.target_residency = 400,
.enter = &intel_idle },
{
.name = "C6-ATM",
.desc = "MWAIT 0x52",
.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 140,
.target_residency = 560,
.enter = &intel_idle },
{
.enter = NULL }
};
/**
* 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];
unsigned long eax = flg2MWAIT(state->flags);
unsigned int cstate;
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);
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();
if (!(lapic_timer_reliable_states & (1 << (cstate))))
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
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 cpu_hotplug_notify(struct notifier_block *n,
unsigned long action, void *hcpu)
{
int hotcpu = (unsigned long)hcpu;
struct cpuidle_device *dev;
switch (action & 0xf) {
case CPU_ONLINE:
if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE)
smp_call_function_single(hotcpu, __setup_broadcast_timer,
(void *)true, 1);
/*
* Some systems can hotplug a cpu at runtime after
* the kernel has booted, we have to initialize the
* driver in this case
*/
dev = per_cpu_ptr(intel_idle_cpuidle_devices, hotcpu);
if (!dev->registered)
intel_idle_cpu_init(hotcpu);
break;
}
return NOTIFY_OK;
}
static struct notifier_block cpu_hotplug_notifier = {
.notifier_call = cpu_hotplug_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 void c1e_promotion_disable(void *dummy)
{
unsigned long long msr_bits;
rdmsrl(MSR_IA32_POWER_CTL, msr_bits);
msr_bits &= ~0x2;
wrmsrl(MSR_IA32_POWER_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,
.disable_promotion_to_c1e = true,
};
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,
.disable_promotion_to_c1e = true,
};
static const struct idle_cpu idle_cpu_ivb = {
.state_table = ivb_cstates,
.disable_promotion_to_c1e = true,
};
static const struct idle_cpu idle_cpu_hsw = {
.state_table = hsw_cstates,
.disable_promotion_to_c1e = true,
};
#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),
ICPU(0x3a, idle_cpu_ivb),
ICPU(0x3e, idle_cpu_ivb),
ICPU(0x3c, idle_cpu_hsw),
ICPU(0x3f, idle_cpu_hsw),
ICPU(0x45, idle_cpu_hsw),
ICPU(0x46, idle_cpu_hsw),
{}
};
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);
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 = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) {
int num_substates, mwait_hint, mwait_cstate, mwait_substate;
if (cpuidle_state_table[cstate].enter == NULL)
break;
if (cstate + 1 > max_cstate) {
printk(PREFIX "max_cstate %d reached\n",
max_cstate);
break;
}
mwait_hint = flg2MWAIT(cpuidle_state_table[cstate].flags);
mwait_cstate = MWAIT_HINT2CSTATE(mwait_hint);
mwait_substate = MWAIT_HINT2SUBSTATE(mwait_hint);
/* does the state exist in CPUID.MWAIT? */
num_substates = (mwait_substates >> ((mwait_cstate + 1) * 4))
& MWAIT_SUBSTATE_MASK;
/* if sub-state in table is not enumerated by CPUID */
if ((mwait_substate + 1) > num_substates)
continue;
if (((mwait_cstate + 1) > 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);
if (icpu->disable_promotion_to_c1e) /* each-cpu is redundant */
on_each_cpu(c1e_promotion_disable, NULL, 1);
return 0;
}
/*
* intel_idle_cpu_init()
* allocate, initialize, register cpuidle_devices
* @cpu: cpu/core to initialize
*/
static 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 = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) {
int num_substates, mwait_hint, mwait_cstate, mwait_substate;
if (cpuidle_state_table[cstate].enter == NULL)
continue;
if (cstate + 1 > max_cstate) {
printk(PREFIX "max_cstate %d reached\n", max_cstate);
break;
}
mwait_hint = flg2MWAIT(cpuidle_state_table[cstate].flags);
mwait_cstate = MWAIT_HINT2CSTATE(mwait_hint);
mwait_substate = MWAIT_HINT2SUBSTATE(mwait_hint);
/* does the state exist in CPUID.MWAIT? */
num_substates = (mwait_substates >> ((mwait_cstate + 1) * 4))
& MWAIT_SUBSTATE_MASK;
/* if sub-state in table is not enumerated by CPUID */
if ((mwait_substate + 1) > num_substates)
continue;
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;
}
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) {
struct cpuidle_driver *drv = cpuidle_get_driver();
printk(KERN_DEBUG PREFIX "intel_idle yielding to %s",
drv ? drv->name : "none");
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;
}
}
intel_idle: Don't register CPU notifier if we are not running. The 'intel_idle_probe' probes the CPU and sets the CPU notifier. But if later on during the module initialization we fail (say in cpuidle_register_driver), we stop loading, but we neglect to unregister the CPU notifier. This means that during CPU hotplug events the system will fail: calling intel_idle_init+0x0/0x326 @ 1 intel_idle: MWAIT substates: 0x1120 intel_idle: v0.4 model 0x2A intel_idle: lapic_timer_reliable_states 0xffffffff intel_idle: intel_idle yielding to none initcall intel_idle_init+0x0/0x326 returned -19 after 14 usecs ... some time later, offlining and onlining a CPU: cpu 3 spinlock event irq 62 BUG: unable to ] __cpuidle_register_device+0x1c/0x120 PGD 99b8b067 PUD 99b95067 PMD 0 Oops: 0000 [#1] SMP Modules linked in: xen_evtchn nouveau mxm_wmi wmi radeon ttm i915 fbcon tileblit font atl1c bitblit softcursor drm_kms_helper video xen_blkfront xen_netfront fb_sys_fops sysimgblt sysfillrect syscopyarea xenfs xen_privcmd mperf CPU 0 Pid: 2302, comm: udevd Not tainted 3.8.0-rc3upstream-00249-g09ad159 #1 MSI MS-7680/H61M-P23 (MS-7680) RIP: e030:[<ffffffff814d956c>] [<ffffffff814d956c>] __cpuidle_register_device+0x1c/0x120 RSP: e02b:ffff88009dacfcb8 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff880105380000 RCX: 000000000000001c RDX: 0000000000000000 RSI: 0000000000000055 RDI: ffff880105380000 RBP: ffff88009dacfce8 R08: ffffffff81a4f048 R09: 0000000000000008 R10: 0000000000000008 R11: 0000000000000000 R12: ffff880105380000 R13: 00000000ffffffdd R14: 0000000000000000 R15: ffffffff81a523d0 FS: 00007f37bd83b7a0(0000) GS:ffff880105200000(0000) knlGS:0000000000000000 CS: e033 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 00000000a09ea000 CR4: 0000000000042660 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process udevd (pid: 2302, threadinfo ffff88009dace000, task ffff88009afb47f0) Stack: ffffffff8107f2d0 ffffffff810c2fb7 ffff88009dacfce8 00000000ffffffea ffff880105380000 00000000ffffffdd ffff88009dacfd08 ffffffff814d9882 0000000000000003 ffff880105380000 ffff88009dacfd28 ffffffff81340afd Call Trace: [<ffffffff8107f2d0>] ? collect_cpu_info_local+0x30/0x30 [<ffffffff810c2fb7>] ? __might_sleep+0xe7/0x100 [<ffffffff814d9882>] cpuidle_register_device+0x32/0x70 [<ffffffff81340afd>] intel_idle_cpu_init+0xad/0x110 [<ffffffff81340bc8>] cpu_hotplug_notify+0x68/0x80 [<ffffffff8166023d>] notifier_call_chain+0x4d/0x70 [<ffffffff810bc369>] __raw_notifier_call_chain+0x9/0x10 [<ffffffff81094a4b>] __cpu_notify+0x1b/0x30 [<ffffffff81652cf7>] _cpu_up+0x103/0x14b [<ffffffff81652e18>] cpu_up+0xd9/0xec [<ffffffff8164a254>] store_online+0x94/0xd0 [<ffffffff814122fb>] dev_attr_store+0x1b/0x20 [<ffffffff81216404>] sysfs_write_file+0xf4/0x170 [<ffffffff811a1024>] vfs_write+0xb4/0x130 [<ffffffff811a17ea>] sys_write+0x5a/0xa0 [<ffffffff816643a9>] system_call_fastpath+0x16/0x1b Code: 03 18 00 c9 c3 66 2e 0f 1f 84 00 00 00 00 00 55 48 89 e5 48 83 ec 30 48 89 5d e8 4c 89 65 f0 48 89 fb 4c 89 6d f8 e8 84 08 00 00 <48> 8b 78 08 49 89 c4 e8 f8 7f c1 ff 89 c2 b8 ea ff ff ff 84 d2 RIP [<ffffffff814d956c>] __cpuidle_register_device+0x1c/0x120 RSP <ffff88009dacfcb8> This patch fixes that by moving the CPU notifier registration as the last item to be done by the module. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: 3.6+ <stable@vger.kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-01-17 06:40:01 +08:00
register_cpu_notifier(&cpu_hotplug_notifier);
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(&cpu_hotplug_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");