1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
|
// SPDX-License-Identifier: GPL-2.0
/*
* cpuidle-pseries - 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/runlatch.h>
#include <asm/plpar_wrappers.h>
struct cpuidle_driver pseries_idle_driver = {
.name = "pseries_idle",
.owner = THIS_MODULE,
};
static int max_idle_state __read_mostly;
static struct cpuidle_state *cpuidle_state_table __read_mostly;
static u64 snooze_timeout __read_mostly;
static bool snooze_timeout_en __read_mostly;
static inline void idle_loop_prolog(unsigned long *in_purr)
{
ppc64_runlatch_off();
*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;
ppc64_runlatch_on();
}
static int snooze_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
unsigned long in_purr;
u64 snooze_exit_time;
set_thread_flag(TIF_POLLING_NRFLAG);
idle_loop_prolog(&in_purr);
local_irq_enable();
snooze_exit_time = get_tb() + snooze_timeout;
while (!need_resched()) {
HMT_low();
HMT_very_low();
if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time) {
/*
* Task has not woken up but we are exiting the polling
* loop anyway. Require a barrier after polling is
* cleared to order subsequent test of need_resched().
*/
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb();
break;
}
}
HMT_medium();
clear_thread_flag(TIF_POLLING_NRFLAG);
local_irq_disable();
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();
local_irq_disable();
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();
local_irq_disable();
idle_loop_epilog(in_purr);
return index;
}
/*
* States for dedicated partition case.
*/
static struct cpuidle_state dedicated_states[] = {
{ /* Snooze */
.name = "snooze",
.desc = "snooze",
.exit_latency = 0,
.target_residency = 0,
.enter = &snooze_loop },
{ /* CEDE */
.name = "CEDE",
.desc = "CEDE",
.exit_latency = 10,
.target_residency = 100,
.enter = &dedicated_cede_loop },
};
/*
* States for shared partition case.
*/
static struct cpuidle_state shared_states[] = {
{ /* Snooze */
.name = "snooze",
.desc = "snooze",
.exit_latency = 0,
.target_residency = 0,
.enter = &snooze_loop },
{ /* Shared Cede */
.name = "Shared Cede",
.desc = "Shared Cede",
.exit_latency = 10,
.target_residency = 100,
.enter = &shared_cede_loop },
};
static int pseries_cpuidle_cpu_online(unsigned int cpu)
{
struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
if (dev && cpuidle_get_driver()) {
cpuidle_pause_and_lock();
cpuidle_enable_device(dev);
cpuidle_resume_and_unlock();
}
return 0;
}
static int pseries_cpuidle_cpu_dead(unsigned int cpu)
{
struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
if (dev && cpuidle_get_driver()) {
cpuidle_pause_and_lock();
cpuidle_disable_device(dev);
cpuidle_resume_and_unlock();
}
return 0;
}
/*
* 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; ++idle_state) {
/* 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 (cpuidle_disable != IDLE_NO_OVERRIDE)
return -ENODEV;
if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
/*
* Use local_paca instead of get_lppaca() since
* preemption is not disabled, and it is not required in
* fact, since lppaca_ptr does not need to be the value
* associated to the current CPU, it can be from any CPU.
*/
if (lppaca_shared_proc(local_paca->lppaca_ptr)) {
cpuidle_state_table = shared_states;
max_idle_state = ARRAY_SIZE(shared_states);
} else {
cpuidle_state_table = dedicated_states;
max_idle_state = ARRAY_SIZE(dedicated_states);
}
} else
return -ENODEV;
if (max_idle_state > 1) {
snooze_timeout_en = true;
snooze_timeout = cpuidle_state_table[1].target_residency *
tb_ticks_per_usec;
}
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;
}
retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
"cpuidle/pseries:online",
pseries_cpuidle_cpu_online, NULL);
WARN_ON(retval < 0);
retval = cpuhp_setup_state_nocalls(CPUHP_CPUIDLE_DEAD,
"cpuidle/pseries:DEAD", NULL,
pseries_cpuidle_cpu_dead);
WARN_ON(retval < 0);
printk(KERN_DEBUG "pseries_idle_driver registered\n");
return 0;
}
device_initcall(pseries_processor_idle_init);
|