cpufreq: powernv: Use PMCR to verify global and local pstate
As fast_switch() may get called with interrupt disable mode, we cannot
hold a mutex to update the global_pstate_info. So currently, fast_switch()
does not update the global_pstate_info and it will end up with stale data
whenever pstate is updated through fast_switch().
As the gpstate_timer can fire after fast_switch() has updated the pstates,
the timer handler cannot rely on the cached values of local and global
pstate and needs to read it from the PMCR.
Only gpstate_timer_handler() is affected by the stale cached pstate data
beacause either fast_switch() or target_index() routines will be called
for a given govenor, but gpstate_timer can fire after the governor has
changed to schedutil.
Signed-off-by: Akshay Adiga <akshay.adiga@linux.vnet.ibm.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 4a4380d..c82304b 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -42,6 +42,10 @@
#define PMSR_PSAFE_ENABLE (1UL << 30)
#define PMSR_SPR_EM_DISABLE (1UL << 31)
#define PMSR_MAX(x) ((x >> 32) & 0xFF)
+#define LPSTATE_SHIFT 48
+#define GPSTATE_SHIFT 56
+#define GET_LPSTATE(x) (((x) >> LPSTATE_SHIFT) & 0xFF)
+#define GET_GPSTATE(x) (((x) >> GPSTATE_SHIFT) & 0xFF)
#define MAX_RAMP_DOWN_TIME 5120
/*
@@ -592,7 +596,8 @@
{
struct cpufreq_policy *policy = (struct cpufreq_policy *)data;
struct global_pstate_info *gpstates = policy->driver_data;
- int gpstate_idx;
+ int gpstate_idx, lpstate_idx;
+ unsigned long val;
unsigned int time_diff = jiffies_to_msecs(jiffies)
- gpstates->last_sampled_time;
struct powernv_smp_call_data freq_data;
@@ -600,21 +605,36 @@
if (!spin_trylock(&gpstates->gpstate_lock))
return;
+ /*
+ * If PMCR was last updated was using fast_swtich then
+ * We may have wrong in gpstate->last_lpstate_idx
+ * value. Hence, read from PMCR to get correct data.
+ */
+ val = get_pmspr(SPRN_PMCR);
+ freq_data.gpstate_id = (s8)GET_GPSTATE(val);
+ freq_data.pstate_id = (s8)GET_LPSTATE(val);
+ if (freq_data.gpstate_id == freq_data.pstate_id) {
+ reset_gpstates(policy);
+ spin_unlock(&gpstates->gpstate_lock);
+ return;
+ }
+
gpstates->last_sampled_time += time_diff;
gpstates->elapsed_time += time_diff;
- freq_data.pstate_id = idx_to_pstate(gpstates->last_lpstate_idx);
- if ((gpstates->last_gpstate_idx == gpstates->last_lpstate_idx) ||
- (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME)) {
+ if (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME) {
gpstate_idx = pstate_to_idx(freq_data.pstate_id);
reset_gpstates(policy);
gpstates->highest_lpstate_idx = gpstate_idx;
} else {
+ lpstate_idx = pstate_to_idx(freq_data.pstate_id);
gpstate_idx = calc_global_pstate(gpstates->elapsed_time,
gpstates->highest_lpstate_idx,
- gpstates->last_lpstate_idx);
+ lpstate_idx);
}
-
+ freq_data.gpstate_id = idx_to_pstate(gpstate_idx);
+ gpstates->last_gpstate_idx = gpstate_idx;
+ gpstates->last_lpstate_idx = lpstate_idx;
/*
* If local pstate is equal to global pstate, rampdown is over
* So timer is not required to be queued.
@@ -622,10 +642,6 @@
if (gpstate_idx != gpstates->last_lpstate_idx)
queue_gpstate_timer(gpstates);
- freq_data.gpstate_id = idx_to_pstate(gpstate_idx);
- gpstates->last_gpstate_idx = pstate_to_idx(freq_data.gpstate_id);
- gpstates->last_lpstate_idx = pstate_to_idx(freq_data.pstate_id);
-
spin_unlock(&gpstates->gpstate_lock);
/* Timer may get migrated to a different cpu on cpu hot unplug */