linux/drivers/cpuidle/cpuidle-powernv.c

483 lines
12 KiB
C
Raw Normal View History

/*
* 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>
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>
2017-01-25 16:36:28 +08:00
#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;
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>
2017-01-25 16:36:28 +08:00
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();
HMT_very_low();
while (!need_resched()) {
if (likely(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;
}
tick/idle/powerpc: Do not register idle states with CPUIDLE_FLAG_TIMER_STOP set in periodic mode On some archs, the local clockevent device stops in deep cpuidle states. The broadcast framework is used to wakeup cpus in these idle states, in which either an external clockevent device is used to send wakeup ipis or the hrtimer broadcast framework kicks in in the absence of such a device. One cpu is nominated as the broadcast cpu and this cpu sends wakeup ipis to sleeping cpus at the appropriate time. This is the implementation in the oneshot mode of broadcast. In periodic mode of broadcast however, the presence of such cpuidle states results in the cpuidle driver calling tick_broadcast_enable() which shuts down the local clockevent devices of all the cpus and appoints the tick broadcast device as the clockevent device for each of them. This works on those archs where the tick broadcast device is a real clockevent device. But on archs which depend on the hrtimer mode of broadcast, the tick broadcast device hapens to be a pseudo device. The consequence is that the local clockevent devices of all cpus are shutdown and the kernel hangs at boot time in periodic mode. Let us thus not register the cpuidle states which have CPUIDLE_FLAG_TIMER_STOP flag set, on archs which depend on the hrtimer mode of broadcast in periodic mode. This patch takes care of doing this on powerpc. The cpus would not have entered into such deep cpuidle states in periodic mode on powerpc anyway. So there is no loss here. Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: 3.19+ <stable@vger.kernel.org> # 3.19+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-06-24 14:48:01 +08:00
/* 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;
}
tick/idle/powerpc: Do not register idle states with CPUIDLE_FLAG_TIMER_STOP set in periodic mode On some archs, the local clockevent device stops in deep cpuidle states. The broadcast framework is used to wakeup cpus in these idle states, in which either an external clockevent device is used to send wakeup ipis or the hrtimer broadcast framework kicks in in the absence of such a device. One cpu is nominated as the broadcast cpu and this cpu sends wakeup ipis to sleeping cpus at the appropriate time. This is the implementation in the oneshot mode of broadcast. In periodic mode of broadcast however, the presence of such cpuidle states results in the cpuidle driver calling tick_broadcast_enable() which shuts down the local clockevent devices of all the cpus and appoints the tick broadcast device as the clockevent device for each of them. This works on those archs where the tick broadcast device is a real clockevent device. But on archs which depend on the hrtimer mode of broadcast, the tick broadcast device hapens to be a pseudo device. The consequence is that the local clockevent devices of all cpus are shutdown and the kernel hangs at boot time in periodic mode. Let us thus not register the cpuidle states which have CPUIDLE_FLAG_TIMER_STOP flag set, on archs which depend on the hrtimer mode of broadcast in periodic mode. This patch takes care of doing this on powerpc. The cpus would not have entered into such deep cpuidle states in periodic mode on powerpc anyway. So there is no loss here. Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: 3.19+ <stable@vger.kernel.org> # 3.19+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-06-24 14:48:01 +08:00
#endif
static int stop_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
ppc64_runlatch_off();
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>
2017-01-25 16:36:28 +08:00
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;
}
cpuidle: powernv: Pass correct drv->cpumask for registration drv->cpumask defaults to cpu_possible_mask in __cpuidle_driver_init(). On PowerNV platform cpu_present could be less than cpu_possible in cases where firmware detects the cpu, but it is not available to the OS. When CONFIG_HOTPLUG_CPU=n, such cpus are not hotplugable at runtime and hence we skip creating cpu_device. This breaks cpuidle on powernv where register_cpu() is not called for cpus in cpu_possible_mask that cannot be hot-added at runtime. Trying cpuidle_register_device() on cpu without cpu_device will cause crash like this: cpu 0xf: Vector: 380 (Data SLB Access) at [c000000ff1503490] pc: c00000000022c8bc: string+0x34/0x60 lr: c00000000022ed78: vsnprintf+0x284/0x42c sp: c000000ff1503710 msr: 9000000000009033 dar: 6000000060000000 current = 0xc000000ff1480000 paca = 0xc00000000fe82d00 softe: 0 irq_happened: 0x01 pid = 1, comm = swapper/8 Linux version 4.11.0-rc2 (sv@sagarika) (gcc version 4.9.4 (Buildroot 2017.02-00004-gc28573e) ) #15 SMP Fri Mar 17 19:32:02 IST 2017 enter ? for help [link register ] c00000000022ed78 vsnprintf+0x284/0x42c [c000000ff1503710] c00000000022ebb8 vsnprintf+0xc4/0x42c (unreliable) [c000000ff1503800] c00000000022ef40 vscnprintf+0x20/0x44 [c000000ff1503830] c0000000000ab61c vprintk_emit+0x94/0x2cc [c000000ff15038a0] c0000000000acc9c vprintk_func+0x60/0x74 [c000000ff15038c0] c000000000619694 printk+0x38/0x4c [c000000ff15038e0] c000000000224950 kobject_get+0x40/0x60 [c000000ff1503950] c00000000022507c kobject_add_internal+0x60/0x2c4 [c000000ff15039e0] c000000000225350 kobject_init_and_add+0x70/0x78 [c000000ff1503a60] c00000000053c288 cpuidle_add_sysfs+0x9c/0xe0 [c000000ff1503ae0] c00000000053aeac cpuidle_register_device+0xd4/0x12c [c000000ff1503b30] c00000000053b108 cpuidle_register+0x98/0xcc [c000000ff1503bc0] c00000000085eaf0 powernv_processor_idle_init+0x140/0x1e0 [c000000ff1503c60] c00000000000cd60 do_one_initcall+0xc0/0x15c [c000000ff1503d20] c000000000833e84 kernel_init_freeable+0x1a0/0x25c [c000000ff1503dc0] c00000000000d478 kernel_init+0x24/0x12c [c000000ff1503e30] c00000000000b564 ret_from_kernel_thread+0x5c/0x78 This patch fixes the bug by passing correct cpumask from powernv-cpuidle driver. Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> [ rjw: Comment massage ] Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-03-23 23:22:46 +08:00
/*
* On the PowerNV platform cpu_present may be less than cpu_possible in
* cases when firmware detects the CPU, but it is not available to the
* OS. If CONFIG_HOTPLUG_CPU=n, then such CPUs are not hotplugable at
* run time and hence cpu_devices are not created for those CPUs by the
* generic topology_init().
*
* drv->cpumask defaults to cpu_possible_mask in
* __cpuidle_driver_init(). This breaks cpuidle on PowerNV where
* cpu_devices are not created for CPUs in cpu_possible_mask that
* cannot be hot-added later at run time.
*
* Trying cpuidle_register_device() on a CPU without a cpu_device is
* incorrect, so pass a correct CPU mask to the generic cpuidle driver.
*/
drv->cpumask = (struct cpumask *)cpu_present_mask;
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,
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>
2017-01-25 16:36:28 +08:00
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;
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>
2017-01-25 16:36:28 +08:00
stop_psscr_table[index].val = psscr_val;
stop_psscr_table[index].mask = psscr_mask;
}
/*
* Returns 0 if prop1_len == prop2_len. Else returns -1
*/
static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len,
const char *prop2, int prop2_len)
{
if (prop1_len == prop2_len)
return 0;
pr_warn("cpuidle-powernv: array sizes don't match for %s and %s\n",
prop1, prop2);
return -1;
}
static int powernv_add_idle_states(void)
{
struct device_node *power_mgt;
int nr_idle_states = 1; /* Snooze */
int dt_idle_states, count;
u32 latency_ns[CPUIDLE_STATE_MAX];
u32 residency_ns[CPUIDLE_STATE_MAX];
u32 flags[CPUIDLE_STATE_MAX];
u64 psscr_val[CPUIDLE_STATE_MAX];
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>
2017-01-25 16:36:28 +08:00
u64 psscr_mask[CPUIDLE_STATE_MAX];
const char *names[CPUIDLE_STATE_MAX];
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>
2017-01-25 16:36:28 +08:00
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;
}
count = of_property_count_u32_elems(power_mgt,
"ibm,cpu-idle-state-latencies-ns");
if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", dt_idle_states,
"ibm,cpu-idle-state-latencies-ns",
count) != 0)
goto out;
count = of_property_count_strings(power_mgt,
"ibm,cpu-idle-state-names");
if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", dt_idle_states,
"ibm,cpu-idle-state-names",
count) != 0)
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
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>
2017-01-25 16:36:28 +08:00
* and psscr mask which are necessary to specify required stop level.
*/
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>
2017-01-25 16:36:28 +08:00
has_stop_states = (flags[0] &
(OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP));
if (has_stop_states) {
count = of_property_count_u64_elems(power_mgt,
"ibm,cpu-idle-state-psscr");
if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
dt_idle_states,
"ibm,cpu-idle-state-psscr",
count) != 0)
goto out;
count = of_property_count_u64_elems(power_mgt,
"ibm,cpu-idle-state-psscr-mask");
if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
dt_idle_states,
"ibm,cpu-idle-state-psscr-mask",
count) != 0)
goto out;
if (of_property_read_u64_array(power_mgt,
"ibm,cpu-idle-state-psscr", psscr_val, dt_idle_states)) {
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>
2017-01-25 16:36:28 +08:00
pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n");
goto out;
}
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>
2017-01-25 16:36:28 +08:00
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;
}
}
count = of_property_count_u32_elems(power_mgt,
"ibm,cpu-idle-state-residency-ns");
if (count < 0) {
rc = count;
} else if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
dt_idle_states,
"ibm,cpu-idle-state-residency-ns",
count) != 0) {
goto out;
} else {
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;
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>
2017-01-25 16:36:28 +08:00
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,
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>
2017-01-25 16:36:28 +08:00
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,
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>
2017-01-25 16:36:28 +08:00
psscr_val[i], psscr_mask[i]);
tick/idle/powerpc: Do not register idle states with CPUIDLE_FLAG_TIMER_STOP set in periodic mode On some archs, the local clockevent device stops in deep cpuidle states. The broadcast framework is used to wakeup cpus in these idle states, in which either an external clockevent device is used to send wakeup ipis or the hrtimer broadcast framework kicks in in the absence of such a device. One cpu is nominated as the broadcast cpu and this cpu sends wakeup ipis to sleeping cpus at the appropriate time. This is the implementation in the oneshot mode of broadcast. In periodic mode of broadcast however, the presence of such cpuidle states results in the cpuidle driver calling tick_broadcast_enable() which shuts down the local clockevent devices of all the cpus and appoints the tick broadcast device as the clockevent device for each of them. This works on those archs where the tick broadcast device is a real clockevent device. But on archs which depend on the hrtimer mode of broadcast, the tick broadcast device hapens to be a pseudo device. The consequence is that the local clockevent devices of all cpus are shutdown and the kernel hangs at boot time in periodic mode. Let us thus not register the cpuidle states which have CPUIDLE_FLAG_TIMER_STOP flag set, on archs which depend on the hrtimer mode of broadcast in periodic mode. This patch takes care of doing this on powerpc. The cpus would not have entered into such deep cpuidle states in periodic mode on powerpc anyway. So there is no loss here. Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: 3.19+ <stable@vger.kernel.org> # 3.19+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-06-24 14:48:01 +08:00
}
/*
* 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,
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>
2017-01-25 16:36:28 +08:00
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,
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>
2017-01-25 16:36:28 +08:00
psscr_val[i], psscr_mask[i]);
}
tick/idle/powerpc: Do not register idle states with CPUIDLE_FLAG_TIMER_STOP set in periodic mode On some archs, the local clockevent device stops in deep cpuidle states. The broadcast framework is used to wakeup cpus in these idle states, in which either an external clockevent device is used to send wakeup ipis or the hrtimer broadcast framework kicks in in the absence of such a device. One cpu is nominated as the broadcast cpu and this cpu sends wakeup ipis to sleeping cpus at the appropriate time. This is the implementation in the oneshot mode of broadcast. In periodic mode of broadcast however, the presence of such cpuidle states results in the cpuidle driver calling tick_broadcast_enable() which shuts down the local clockevent devices of all the cpus and appoints the tick broadcast device as the clockevent device for each of them. This works on those archs where the tick broadcast device is a real clockevent device. But on archs which depend on the hrtimer mode of broadcast, the tick broadcast device hapens to be a pseudo device. The consequence is that the local clockevent devices of all cpus are shutdown and the kernel hangs at boot time in periodic mode. Let us thus not register the cpuidle states which have CPUIDLE_FLAG_TIMER_STOP flag set, on archs which depend on the hrtimer mode of broadcast in periodic mode. This patch takes care of doing this on powerpc. The cpus would not have entered into such deep cpuidle states in periodic mode on powerpc anyway. So there is no loss here. Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: 3.19+ <stable@vger.kernel.org> # 3.19+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-06-24 14:48:01 +08:00
#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);