[PATCH 4.4 046/105] cpuidle: powernv: Fix promotion from snooze if next state disabled

[Greg Kroah-Hartman]

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Gautham R. Shenoy <ego@xxxxxxxxxxxxxxxxxx>

commit 0a4ec6aa035a52c422eceb2ed51ed88392a3d6c2 upstream.

The commit 78eaa10f027c ("cpuidle: powernv/pseries: Auto-promotion of
snooze to deeper idle state") introduced a timeout for the snooze idle
state so that it could be eventually be promoted to a deeper idle
state. The snooze timeout value is static and set to the target
residency of the next idle state, which would train the cpuidle
governor to pick the next idle state eventually.

The unfortunate side-effect of this is that if the next idle state(s)
is disabled, the CPU will forever remain in snooze, despite the fact
that the system is completely idle, and other deeper idle states are
available.

This patch fixes the issue by dynamically setting the snooze timeout
to the target residency of the next enabled state on the device.

Before Patch:
  POWER8 : Only nap disabled.
  $ cpupower monitor sleep 30
  sleep took 30.01297 seconds and exited with status 0
                |Idle_Stats
  PKG |CORE|CPU | snoo | Nap  | Fast
     0|   8|   0| 96.41|  0.00|  0.00
     0|   8|   1| 96.43|  0.00|  0.00
     0|   8|   2| 96.47|  0.00|  0.00
     0|   8|   3| 96.35|  0.00|  0.00
     0|   8|   4| 96.37|  0.00|  0.00
     0|   8|   5| 96.37|  0.00|  0.00
     0|   8|   6| 96.47|  0.00|  0.00
     0|   8|   7| 96.47|  0.00|  0.00

  POWER9: Shallow states (stop0lite, stop1lite, stop2lite, stop0, stop1,
  stop2) disabled:
  $ cpupower monitor sleep 30
  sleep took 30.05033 seconds and exited with status 0
                |Idle_Stats
  PKG |CORE|CPU | snoo | stop | stop | stop | stop | stop | stop | stop | stop
     0|  16|   0| 89.79|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00
     0|  16|   1| 90.12|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00
     0|  16|   2| 90.21|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00
     0|  16|   3| 90.29|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00

After Patch:
  POWER8 : Only nap disabled.
  $ cpupower monitor sleep 30
  sleep took 30.01200 seconds and exited with status 0
                |Idle_Stats
  PKG |CORE|CPU | snoo | Nap  | Fast
     0|   8|   0| 16.58|  0.00| 77.21
     0|   8|   1| 18.42|  0.00| 75.38
     0|   8|   2|  4.70|  0.00| 94.09
     0|   8|   3| 17.06|  0.00| 81.73
     0|   8|   4|  3.06|  0.00| 95.73
     0|   8|   5|  7.00|  0.00| 96.80
     0|   8|   6|  1.00|  0.00| 98.79
     0|   8|   7|  5.62|  0.00| 94.17

  POWER9: Shallow states (stop0lite, stop1lite, stop2lite, stop0, stop1,
  stop2) disabled:

  $ cpupower monitor sleep 30
  sleep took 30.02110 seconds and exited with status 0
                |Idle_Stats
  PKG |CORE|CPU | snoo | stop | stop | stop | stop | stop | stop | stop | stop
     0|   0|   0|  0.69|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  9.39| 89.70
     0|   0|   1|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.05| 93.21
     0|   0|   2|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00| 89.93
     0|   0|   3|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00|  0.00| 93.26

Fixes: 78eaa10f027c ("cpuidle: powernv/pseries: Auto-promotion of snooze to deeper idle state")
Cc: stable@xxxxxxxxxxxxxxx # v4.2+
Signed-off-by: Gautham R. Shenoy <ego@xxxxxxxxxxxxxxxxxx>
Reviewed-by: Balbir Singh <bsingharora@xxxxxxxxx>
Signed-off-by: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>


---
 drivers/cpuidle/cpuidle-powernv.c |   32 ++++++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 6 deletions(-)

--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -29,9 +29,31 @@ struct cpuidle_driver powernv_idle_drive
 
 static int max_idle_state;
 static struct cpuidle_state *cpuidle_state_table;
-static u64 snooze_timeout;
+static u64 default_snooze_timeout;
 static bool snooze_timeout_en;
 
+static u64 get_snooze_timeout(struct cpuidle_device *dev,
+			      struct cpuidle_driver *drv,
+			      int index)
+{
+	int i;
+
+	if (unlikely(!snooze_timeout_en))
+		return default_snooze_timeout;
+
+	for (i = index + 1; i < drv->state_count; i++) {
+		struct cpuidle_state *s = &drv->states[i];
+		struct cpuidle_state_usage *su = &dev->states_usage[i];
+
+		if (s->disabled || su->disable)
+			continue;
+
+		return s->target_residency * tb_ticks_per_usec;
+	}
+
+	return default_snooze_timeout;
+}
+
 static int snooze_loop(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv,
 			int index)
@@ -41,7 +63,7 @@ static int snooze_loop(struct cpuidle_de
 	local_irq_enable();
 	set_thread_flag(TIF_POLLING_NRFLAG);
 
-	snooze_exit_time = get_tb() + snooze_timeout;
+	snooze_exit_time = get_tb() + get_snooze_timeout(dev, drv, index);
 	ppc64_runlatch_off();
 	while (!need_resched()) {
 		HMT_low();
@@ -286,11 +308,9 @@ static int powernv_idle_probe(void)
 		cpuidle_state_table = powernv_states;
 		/* Device tree can indicate more idle states */
 		max_idle_state = powernv_add_idle_states();
-		if (max_idle_state > 1) {
+		default_snooze_timeout = TICK_USEC * tb_ticks_per_usec;
+		if (max_idle_state > 1)
 			snooze_timeout_en = true;
-			snooze_timeout = powernv_states[1].target_residency *
-					 tb_ticks_per_usec;
-		}
  	} else
  		return -ENODEV;