@@ -389,9 +389,9 @@ extern int powersave_nap; /* set if nap mode can be used in idle loop */
extern void power7_nap(void);
#ifdef CONFIG_PSERIES_IDLE
-extern void update_smt_snooze_delay(int snooze);
+extern void update_smt_snooze_delay(int cpu, int residency);
#else
-static inline void update_smt_snooze_delay(int snooze) {}
+static inline void update_smt_snooze_delay(int cpu, int residency) {}
#endif
extern void flush_instruction_cache(void);
@@ -50,7 +50,7 @@ static ssize_t store_smt_snooze_delay(struct device *dev,
return -EINVAL;
per_cpu(smt_snooze_delay, cpu->dev.id) = snooze;
- update_smt_snooze_delay(snooze);
+ update_smt_snooze_delay(cpu->dev.id, snooze);
return count;
}
@@ -33,13 +33,6 @@ static int max_idle_state = MAX_IDLE_STATE_COUNT - 1;
static struct cpuidle_device __percpu *pseries_cpuidle_devices;
static struct cpuidle_state *cpuidle_state_table;
-void update_smt_snooze_delay(int snooze)
-{
- struct cpuidle_driver *drv = cpuidle_get_driver();
- if (drv)
- drv->states[0].target_residency = snooze;
-}
-
static inline void idle_loop_prolog(unsigned long *in_purr, ktime_t *kt_before)
{
@@ -190,6 +183,23 @@ static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = {
.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[0].target_residency = residency;
+}
+
static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n,
unsigned long action, void *hcpu)
{
smt_snooze_delay was designed to delay idle loop's nap entry in the native idle code before it got ported over to use as part of the cpuidle framework. A -ve value assigned to smt_snooze_delay should result in busy looping, in other words disabling the entry to nap state. - https://lists.ozlabs.org/pipermail/linuxppc-dev/2010-May/082450.html This particular functionality can be achieved currently by echo 1 > /sys/devices/system/cpu/cpu*/state1/disable but it is broken when one assigns -ve value to the smt_snooze_delay variable either via sysfs entry or ppc64_cpu util. This patch aims to fix this, by disabling nap state when smt_snooze_delay variable is set to -ve value. Signed-off-by: Deepthi Dharwar <deepthi@linux.vnet.ibm.com> --- arch/powerpc/include/asm/processor.h | 4 ++-- arch/powerpc/kernel/sysfs.c | 2 +- arch/powerpc/platforms/pseries/processor_idle.c | 24 ++++++++++++++++------- 3 files changed, 20 insertions(+), 10 deletions(-)