Pull powerpc updates from Ben Herrenschmidt: "So here's my next branch for powerpc. A bit late as I was on vacation last week. It's mostly the same stuff that was in next already, I just added two patches today which are the wiring up of lockref for powerpc, which for some reason fell through the cracks last time and is trivial. The highlights are, in addition to a bunch of bug fixes: - Reworked Machine Check handling on kernels running without a hypervisor (or acting as a hypervisor). Provides hooks to handle some errors in real mode such as TLB errors, handle SLB errors, etc... - Support for retrieving memory error information from the service processor on IBM servers running without a hypervisor and routing them to the memory poison infrastructure. - _PAGE_NUMA support on server processors - 32-bit BookE relocatable kernel support - FSL e6500 hardware tablewalk support - A bunch of new/revived board support - FSL e6500 deeper idle states and altivec powerdown support You'll notice a generic mm change here, it has been acked by the relevant authorities and is a pre-req for our _PAGE_NUMA support" * 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (121 commits) powerpc: Implement arch_spin_is_locked() using arch_spin_value_unlocked() powerpc: Add support for the optimised lockref implementation powerpc/powernv: Call OPAL sync before kexec'ing powerpc/eeh: Escalate error on non-existing PE powerpc/eeh: Handle multiple EEH errors powerpc: Fix transactional FP/VMX/VSX unavailable handlers powerpc: Don't corrupt transactional state when using FP/VMX in kernel powerpc: Reclaim two unused thread_info flag bits powerpc: Fix races with irq_work Move precessing of MCE queued event out from syscall exit path. pseries/cpuidle: Remove redundant call to ppc64_runlatch_off() in cpu idle routines powerpc: Make add_system_ram_resources() __init powerpc: add SATA_MV to ppc64_defconfig powerpc/powernv: Increase candidate fw image size powerpc: Add debug checks to catch invalid cpu-to-node mappings powerpc: Fix the setup of CPU-to-Node mappings during CPU online powerpc/iommu: Don't detach device without IOMMU group powerpc/eeh: Hotplug improvement powerpc/eeh: Call opal_pci_reinit() on powernv for restoring config space powerpc/eeh: Add restore_config operation ...
309 lines
6.5 KiB
C
309 lines
6.5 KiB
C
/*
|
|
* processor_idle - idle state cpuidle driver.
|
|
* Adapted from drivers/idle/intel_idle.c and
|
|
* drivers/acpi/processor_idle.c
|
|
*
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <linux/moduleparam.h>
|
|
#include <linux/cpuidle.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/notifier.h>
|
|
|
|
#include <asm/paca.h>
|
|
#include <asm/reg.h>
|
|
#include <asm/machdep.h>
|
|
#include <asm/firmware.h>
|
|
#include <asm/plpar_wrappers.h>
|
|
|
|
struct cpuidle_driver pseries_idle_driver = {
|
|
.name = "pseries_idle",
|
|
.owner = THIS_MODULE,
|
|
};
|
|
|
|
#define MAX_IDLE_STATE_COUNT 2
|
|
|
|
static int max_idle_state = MAX_IDLE_STATE_COUNT - 1;
|
|
static struct cpuidle_state *cpuidle_state_table;
|
|
|
|
static inline void idle_loop_prolog(unsigned long *in_purr)
|
|
{
|
|
*in_purr = mfspr(SPRN_PURR);
|
|
/*
|
|
* Indicate to the HV that we are idle. Now would be
|
|
* a good time to find other work to dispatch.
|
|
*/
|
|
get_lppaca()->idle = 1;
|
|
}
|
|
|
|
static inline void idle_loop_epilog(unsigned long in_purr)
|
|
{
|
|
u64 wait_cycles;
|
|
|
|
wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
|
|
wait_cycles += mfspr(SPRN_PURR) - in_purr;
|
|
get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
|
|
get_lppaca()->idle = 0;
|
|
}
|
|
|
|
static int snooze_loop(struct cpuidle_device *dev,
|
|
struct cpuidle_driver *drv,
|
|
int index)
|
|
{
|
|
unsigned long in_purr;
|
|
int cpu = dev->cpu;
|
|
|
|
idle_loop_prolog(&in_purr);
|
|
local_irq_enable();
|
|
set_thread_flag(TIF_POLLING_NRFLAG);
|
|
|
|
while ((!need_resched()) && cpu_online(cpu)) {
|
|
HMT_low();
|
|
HMT_very_low();
|
|
}
|
|
|
|
HMT_medium();
|
|
clear_thread_flag(TIF_POLLING_NRFLAG);
|
|
smp_mb();
|
|
|
|
idle_loop_epilog(in_purr);
|
|
|
|
return index;
|
|
}
|
|
|
|
static void check_and_cede_processor(void)
|
|
{
|
|
/*
|
|
* Ensure our interrupt state is properly tracked,
|
|
* also checks if no interrupt has occurred while we
|
|
* were soft-disabled
|
|
*/
|
|
if (prep_irq_for_idle()) {
|
|
cede_processor();
|
|
#ifdef CONFIG_TRACE_IRQFLAGS
|
|
/* Ensure that H_CEDE returns with IRQs on */
|
|
if (WARN_ON(!(mfmsr() & MSR_EE)))
|
|
__hard_irq_enable();
|
|
#endif
|
|
}
|
|
}
|
|
|
|
static int dedicated_cede_loop(struct cpuidle_device *dev,
|
|
struct cpuidle_driver *drv,
|
|
int index)
|
|
{
|
|
unsigned long in_purr;
|
|
|
|
idle_loop_prolog(&in_purr);
|
|
get_lppaca()->donate_dedicated_cpu = 1;
|
|
|
|
HMT_medium();
|
|
check_and_cede_processor();
|
|
|
|
get_lppaca()->donate_dedicated_cpu = 0;
|
|
|
|
idle_loop_epilog(in_purr);
|
|
|
|
return index;
|
|
}
|
|
|
|
static int shared_cede_loop(struct cpuidle_device *dev,
|
|
struct cpuidle_driver *drv,
|
|
int index)
|
|
{
|
|
unsigned long in_purr;
|
|
|
|
idle_loop_prolog(&in_purr);
|
|
|
|
/*
|
|
* Yield the processor to the hypervisor. We return if
|
|
* an external interrupt occurs (which are driven prior
|
|
* to returning here) or if a prod occurs from another
|
|
* processor. When returning here, external interrupts
|
|
* are enabled.
|
|
*/
|
|
check_and_cede_processor();
|
|
|
|
idle_loop_epilog(in_purr);
|
|
|
|
return index;
|
|
}
|
|
|
|
/*
|
|
* States for dedicated partition case.
|
|
*/
|
|
static struct cpuidle_state dedicated_states[MAX_IDLE_STATE_COUNT] = {
|
|
{ /* Snooze */
|
|
.name = "snooze",
|
|
.desc = "snooze",
|
|
.flags = CPUIDLE_FLAG_TIME_VALID,
|
|
.exit_latency = 0,
|
|
.target_residency = 0,
|
|
.enter = &snooze_loop },
|
|
{ /* CEDE */
|
|
.name = "CEDE",
|
|
.desc = "CEDE",
|
|
.flags = CPUIDLE_FLAG_TIME_VALID,
|
|
.exit_latency = 10,
|
|
.target_residency = 100,
|
|
.enter = &dedicated_cede_loop },
|
|
};
|
|
|
|
/*
|
|
* States for shared partition case.
|
|
*/
|
|
static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = {
|
|
{ /* Shared Cede */
|
|
.name = "Shared Cede",
|
|
.desc = "Shared Cede",
|
|
.flags = CPUIDLE_FLAG_TIME_VALID,
|
|
.exit_latency = 0,
|
|
.target_residency = 0,
|
|
.enter = &shared_cede_loop },
|
|
};
|
|
|
|
void update_smt_snooze_delay(int cpu, int residency)
|
|
{
|
|
struct cpuidle_driver *drv = cpuidle_get_driver();
|
|
struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
|
|
|
|
if (cpuidle_state_table != dedicated_states)
|
|
return;
|
|
|
|
if (residency < 0) {
|
|
/* Disable the Nap state on that cpu */
|
|
if (dev)
|
|
dev->states_usage[1].disable = 1;
|
|
} else
|
|
if (drv)
|
|
drv->states[1].target_residency = residency;
|
|
}
|
|
|
|
static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n,
|
|
unsigned long action, void *hcpu)
|
|
{
|
|
int hotcpu = (unsigned long)hcpu;
|
|
struct cpuidle_device *dev =
|
|
per_cpu_ptr(cpuidle_devices, hotcpu);
|
|
|
|
if (dev && cpuidle_get_driver()) {
|
|
switch (action) {
|
|
case CPU_ONLINE:
|
|
case CPU_ONLINE_FROZEN:
|
|
cpuidle_pause_and_lock();
|
|
cpuidle_enable_device(dev);
|
|
cpuidle_resume_and_unlock();
|
|
break;
|
|
|
|
case CPU_DEAD:
|
|
case CPU_DEAD_FROZEN:
|
|
cpuidle_pause_and_lock();
|
|
cpuidle_disable_device(dev);
|
|
cpuidle_resume_and_unlock();
|
|
break;
|
|
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
}
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
static struct notifier_block setup_hotplug_notifier = {
|
|
.notifier_call = pseries_cpuidle_add_cpu_notifier,
|
|
};
|
|
|
|
/*
|
|
* pseries_cpuidle_driver_init()
|
|
*/
|
|
static int pseries_cpuidle_driver_init(void)
|
|
{
|
|
int idle_state;
|
|
struct cpuidle_driver *drv = &pseries_idle_driver;
|
|
|
|
drv->state_count = 0;
|
|
|
|
for (idle_state = 0; idle_state < MAX_IDLE_STATE_COUNT; ++idle_state) {
|
|
|
|
if (idle_state > max_idle_state)
|
|
break;
|
|
|
|
/* is the state not enabled? */
|
|
if (cpuidle_state_table[idle_state].enter == NULL)
|
|
continue;
|
|
|
|
drv->states[drv->state_count] = /* structure copy */
|
|
cpuidle_state_table[idle_state];
|
|
|
|
drv->state_count += 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* pseries_idle_probe()
|
|
* Choose state table for shared versus dedicated partition
|
|
*/
|
|
static int pseries_idle_probe(void)
|
|
{
|
|
|
|
if (!firmware_has_feature(FW_FEATURE_SPLPAR))
|
|
return -ENODEV;
|
|
|
|
if (cpuidle_disable != IDLE_NO_OVERRIDE)
|
|
return -ENODEV;
|
|
|
|
if (max_idle_state == 0) {
|
|
printk(KERN_DEBUG "pseries processor idle disabled.\n");
|
|
return -EPERM;
|
|
}
|
|
|
|
if (lppaca_shared_proc(get_lppaca()))
|
|
cpuidle_state_table = shared_states;
|
|
else
|
|
cpuidle_state_table = dedicated_states;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int __init pseries_processor_idle_init(void)
|
|
{
|
|
int retval;
|
|
|
|
retval = pseries_idle_probe();
|
|
if (retval)
|
|
return retval;
|
|
|
|
pseries_cpuidle_driver_init();
|
|
retval = cpuidle_register(&pseries_idle_driver, NULL);
|
|
if (retval) {
|
|
printk(KERN_DEBUG "Registration of pseries driver failed.\n");
|
|
return retval;
|
|
}
|
|
|
|
register_cpu_notifier(&setup_hotplug_notifier);
|
|
printk(KERN_DEBUG "pseries_idle_driver registered\n");
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void __exit pseries_processor_idle_exit(void)
|
|
{
|
|
|
|
unregister_cpu_notifier(&setup_hotplug_notifier);
|
|
cpuidle_unregister(&pseries_idle_driver);
|
|
|
|
return;
|
|
}
|
|
|
|
module_init(pseries_processor_idle_init);
|
|
module_exit(pseries_processor_idle_exit);
|
|
|
|
MODULE_AUTHOR("Deepthi Dharwar <deepthi@linux.vnet.ibm.com>");
|
|
MODULE_DESCRIPTION("Cpuidle driver for POWER");
|
|
MODULE_LICENSE("GPL");
|