linux-hardened/drivers/cpuidle/cpuidle-powernv.c
Gautham R. Shenoy 09206b600c powernv: Pass PSSCR value and mask to power9_idle_stop
The power9_idle_stop method currently takes only the requested stop
level as a parameter and picks up the rest of the PSSCR bits from a
hand-coded macro. This is not a very flexible design, especially when
the firmware has the capability to communicate the psscr value and the
mask associated with a particular stop state via device tree.

This patch modifies the power9_idle_stop API to take as parameters the
PSSCR value and the PSSCR mask corresponding to the stop state that
needs to be set. These PSSCR value and mask are respectively obtained
by parsing the "ibm,cpu-idle-state-psscr" and
"ibm,cpu-idle-state-psscr-mask" fields from the device tree.

In addition to this, the patch adds support for handling stop states
for which ESL and EC bits in the PSSCR are zero. As per the
architecture, a wakeup from these stop states resumes execution from
the subsequent instruction as opposed to waking up at the System
Vector.

The older firmware sets only the Requested Level (RL) field in the
psscr and psscr-mask exposed in the device tree. For older firmware
where psscr-mask=0xf, this patch will set the default sane values that
the set for for remaining PSSCR fields (i.e PSLL, MTL, ESL, EC, and
TR). For the new firmware, the patch will validate that the invariants
required by the ISA for the psscr values are maintained by the
firmware.

This skiboot patch that exports fully populated PSSCR values and the
mask for all the stop states can be found here:
https://lists.ozlabs.org/pipermail/skiboot/2016-September/004869.html

[Optimize the number of instructions before entering STOP with
ESL=EC=0, validate the PSSCR values provided by the firimware
maintains the invariants required as per the ISA suggested by Balbir
Singh]

Acked-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-01-31 08:32:13 +11:00

407 lines
10 KiB
C

/*
* cpuidle-powernv - idle state cpuidle driver.
* Adapted from drivers/cpuidle/cpuidle-pseries
*
*/
#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 <linux/clockchips.h>
#include <linux/of.h>
#include <linux/slab.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
#include <asm/opal.h>
#include <asm/runlatch.h>
#include <asm/cpuidle.h>
/*
* Expose only those Hardware idle states via the cpuidle framework
* that have latency value below POWERNV_THRESHOLD_LATENCY_NS.
*/
#define POWERNV_THRESHOLD_LATENCY_NS 200000
static struct cpuidle_driver powernv_idle_driver = {
.name = "powernv_idle",
.owner = THIS_MODULE,
};
static int max_idle_state;
static struct cpuidle_state *cpuidle_state_table;
struct stop_psscr_table {
u64 val;
u64 mask;
};
static struct stop_psscr_table stop_psscr_table[CPUIDLE_STATE_MAX];
static u64 snooze_timeout;
static bool snooze_timeout_en;
static int snooze_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
u64 snooze_exit_time;
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
snooze_exit_time = get_tb() + snooze_timeout;
ppc64_runlatch_off();
while (!need_resched()) {
HMT_low();
HMT_very_low();
if (snooze_timeout_en && get_tb() > snooze_exit_time)
break;
}
HMT_medium();
ppc64_runlatch_on();
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb();
return index;
}
static int nap_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
ppc64_runlatch_off();
power7_idle();
ppc64_runlatch_on();
return index;
}
/* Register for fastsleep only in oneshot mode of broadcast */
#ifdef CONFIG_TICK_ONESHOT
static int fastsleep_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
unsigned long old_lpcr = mfspr(SPRN_LPCR);
unsigned long new_lpcr;
if (unlikely(system_state < SYSTEM_RUNNING))
return index;
new_lpcr = old_lpcr;
/* Do not exit powersave upon decrementer as we've setup the timer
* offload.
*/
new_lpcr &= ~LPCR_PECE1;
mtspr(SPRN_LPCR, new_lpcr);
power7_sleep();
mtspr(SPRN_LPCR, old_lpcr);
return index;
}
#endif
static int stop_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
ppc64_runlatch_off();
power9_idle_stop(stop_psscr_table[index].val,
stop_psscr_table[index].mask);
ppc64_runlatch_on();
return index;
}
/*
* States for dedicated partition case.
*/
static struct cpuidle_state powernv_states[CPUIDLE_STATE_MAX] = {
{ /* Snooze */
.name = "snooze",
.desc = "snooze",
.exit_latency = 0,
.target_residency = 0,
.enter = snooze_loop },
};
static int powernv_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 powernv_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;
}
/*
* powernv_cpuidle_driver_init()
*/
static int powernv_cpuidle_driver_init(void)
{
int idle_state;
struct cpuidle_driver *drv = &powernv_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;
}
static inline void add_powernv_state(int index, const char *name,
unsigned int flags,
int (*idle_fn)(struct cpuidle_device *,
struct cpuidle_driver *,
int),
unsigned int target_residency,
unsigned int exit_latency,
u64 psscr_val, u64 psscr_mask)
{
strlcpy(powernv_states[index].name, name, CPUIDLE_NAME_LEN);
strlcpy(powernv_states[index].desc, name, CPUIDLE_NAME_LEN);
powernv_states[index].flags = flags;
powernv_states[index].target_residency = target_residency;
powernv_states[index].exit_latency = exit_latency;
powernv_states[index].enter = idle_fn;
stop_psscr_table[index].val = psscr_val;
stop_psscr_table[index].mask = psscr_mask;
}
static int powernv_add_idle_states(void)
{
struct device_node *power_mgt;
int nr_idle_states = 1; /* Snooze */
int dt_idle_states;
u32 latency_ns[CPUIDLE_STATE_MAX];
u32 residency_ns[CPUIDLE_STATE_MAX];
u32 flags[CPUIDLE_STATE_MAX];
u64 psscr_val[CPUIDLE_STATE_MAX];
u64 psscr_mask[CPUIDLE_STATE_MAX];
const char *names[CPUIDLE_STATE_MAX];
u32 has_stop_states = 0;
int i, rc;
/* Currently we have snooze statically defined */
power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
if (!power_mgt) {
pr_warn("opal: PowerMgmt Node not found\n");
goto out;
}
/* Read values of any property to determine the num of idle states */
dt_idle_states = of_property_count_u32_elems(power_mgt, "ibm,cpu-idle-state-flags");
if (dt_idle_states < 0) {
pr_warn("cpuidle-powernv: no idle states found in the DT\n");
goto out;
}
/*
* Since snooze is used as first idle state, max idle states allowed is
* CPUIDLE_STATE_MAX -1
*/
if (dt_idle_states > CPUIDLE_STATE_MAX - 1) {
pr_warn("cpuidle-powernv: discovered idle states more than allowed");
dt_idle_states = CPUIDLE_STATE_MAX - 1;
}
if (of_property_read_u32_array(power_mgt,
"ibm,cpu-idle-state-flags", flags, dt_idle_states)) {
pr_warn("cpuidle-powernv : missing ibm,cpu-idle-state-flags in DT\n");
goto out;
}
if (of_property_read_u32_array(power_mgt,
"ibm,cpu-idle-state-latencies-ns", latency_ns,
dt_idle_states)) {
pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-latencies-ns in DT\n");
goto out;
}
if (of_property_read_string_array(power_mgt,
"ibm,cpu-idle-state-names", names, dt_idle_states) < 0) {
pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-names in DT\n");
goto out;
}
/*
* If the idle states use stop instruction, probe for psscr values
* and psscr mask which are necessary to specify required stop level.
*/
has_stop_states = (flags[0] &
(OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP));
if (has_stop_states) {
if (of_property_read_u64_array(power_mgt,
"ibm,cpu-idle-state-psscr", psscr_val, dt_idle_states)) {
pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n");
goto out;
}
if (of_property_read_u64_array(power_mgt,
"ibm,cpu-idle-state-psscr-mask",
psscr_mask, dt_idle_states)) {
pr_warn("cpuidle-powernv:Missing ibm,cpu-idle-state-psscr-mask in DT\n");
goto out;
}
}
rc = of_property_read_u32_array(power_mgt,
"ibm,cpu-idle-state-residency-ns", residency_ns, dt_idle_states);
for (i = 0; i < dt_idle_states; i++) {
unsigned int exit_latency, target_residency;
/*
* If an idle state has exit latency beyond
* POWERNV_THRESHOLD_LATENCY_NS then don't use it
* in cpu-idle.
*/
if (latency_ns[i] > POWERNV_THRESHOLD_LATENCY_NS)
continue;
/*
* Firmware passes residency and latency values in ns.
* cpuidle expects it in us.
*/
exit_latency = latency_ns[i] / 1000;
if (!rc)
target_residency = residency_ns[i] / 1000;
else
target_residency = 0;
if (has_stop_states) {
int err = validate_psscr_val_mask(&psscr_val[i],
&psscr_mask[i],
flags[i]);
if (err) {
report_invalid_psscr_val(psscr_val[i], err);
continue;
}
}
/*
* For nap and fastsleep, use default target_residency
* values if f/w does not expose it.
*/
if (flags[i] & OPAL_PM_NAP_ENABLED) {
if (!rc)
target_residency = 100;
/* Add NAP state */
add_powernv_state(nr_idle_states, "Nap",
CPUIDLE_FLAG_NONE, nap_loop,
target_residency, exit_latency, 0, 0);
} else if ((flags[i] & OPAL_PM_STOP_INST_FAST) &&
!(flags[i] & OPAL_PM_TIMEBASE_STOP)) {
add_powernv_state(nr_idle_states, names[i],
CPUIDLE_FLAG_NONE, stop_loop,
target_residency, exit_latency,
psscr_val[i], psscr_mask[i]);
}
/*
* All cpuidle states with CPUIDLE_FLAG_TIMER_STOP set must come
* within this config dependency check.
*/
#ifdef CONFIG_TICK_ONESHOT
if (flags[i] & OPAL_PM_SLEEP_ENABLED ||
flags[i] & OPAL_PM_SLEEP_ENABLED_ER1) {
if (!rc)
target_residency = 300000;
/* Add FASTSLEEP state */
add_powernv_state(nr_idle_states, "FastSleep",
CPUIDLE_FLAG_TIMER_STOP,
fastsleep_loop,
target_residency, exit_latency, 0, 0);
} else if ((flags[i] & OPAL_PM_STOP_INST_DEEP) &&
(flags[i] & OPAL_PM_TIMEBASE_STOP)) {
add_powernv_state(nr_idle_states, names[i],
CPUIDLE_FLAG_TIMER_STOP, stop_loop,
target_residency, exit_latency,
psscr_val[i], psscr_mask[i]);
}
#endif
nr_idle_states++;
}
out:
return nr_idle_states;
}
/*
* powernv_idle_probe()
* Choose state table for shared versus dedicated partition
*/
static int powernv_idle_probe(void)
{
if (cpuidle_disable != IDLE_NO_OVERRIDE)
return -ENODEV;
if (firmware_has_feature(FW_FEATURE_OPAL)) {
cpuidle_state_table = powernv_states;
/* Device tree can indicate more idle states */
max_idle_state = powernv_add_idle_states();
if (max_idle_state > 1) {
snooze_timeout_en = true;
snooze_timeout = powernv_states[1].target_residency *
tb_ticks_per_usec;
}
} else
return -ENODEV;
return 0;
}
static int __init powernv_processor_idle_init(void)
{
int retval;
retval = powernv_idle_probe();
if (retval)
return retval;
powernv_cpuidle_driver_init();
retval = cpuidle_register(&powernv_idle_driver, NULL);
if (retval) {
printk(KERN_DEBUG "Registration of powernv driver failed.\n");
return retval;
}
retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
"cpuidle/powernv:online",
powernv_cpuidle_cpu_online, NULL);
WARN_ON(retval < 0);
retval = cpuhp_setup_state_nocalls(CPUHP_CPUIDLE_DEAD,
"cpuidle/powernv:dead", NULL,
powernv_cpuidle_cpu_dead);
WARN_ON(retval < 0);
printk(KERN_DEBUG "powernv_idle_driver registered\n");
return 0;
}
device_initcall(powernv_processor_idle_init);