@@ -70,8 +70,8 @@ static unsigned int delay_timeout = 100;
module_param(delay_timeout, int, 0644);
MODULE_PARM_DESC(delay_timeout, "amount of time delay for each iteration.");
-/* Number of iterations for cooling delay, 10 counts by default for now */
-static unsigned int delay_cnt = 10;
+/* Number of iterations for cooling delay, 600 counts by default for now */
+static unsigned int delay_cnt = 600;
module_param(delay_cnt, int, 0644);
MODULE_PARM_DESC(delay_cnt, "total number of iterations for time delay.");
@@ -197,7 +197,7 @@ static int pch_wpt_get_temp(struct pch_thermal_device *ptd, int *temp)
static int pch_wpt_suspend(struct pch_thermal_device *ptd)
{
u8 tsel;
- u8 pch_delay_cnt = 1;
+ int pch_delay_cnt = 1;
u16 pch_thr_temp, pch_cur_temp;
/* Shutdown the thermal sensor if it is not enabled by BIOS */
@@ -234,7 +234,10 @@ static int pch_wpt_suspend(struct pch_thermal_device *ptd)
* which helps to indentify the reason why S0ix entry was rejected.
*/
while (pch_delay_cnt <= delay_cnt) {
- if (pch_cur_temp <= pch_thr_temp)
+ if (pch_cur_temp < pch_thr_temp)
+ break;
+
+ if (pm_wakeup_pending())
break;
dev_warn(&ptd->pdev->dev,
@@ -246,7 +249,7 @@ static int pch_wpt_suspend(struct pch_thermal_device *ptd)
pch_delay_cnt++;
}
- if (pch_cur_temp > pch_thr_temp)
+ if (pch_cur_temp >= pch_thr_temp)
dev_warn(&ptd->pdev->dev,
"CPU-PCH is hot [%dC] even after delay, continue to suspend. S0ix might fail\n",
pch_cur_temp);
Commit ef63b043ac86 ("thermal: intel: pch: fix S0ix failure due to PCH temperature above threshold") introduces delay loop mechanism that allows PCH temperature to go down below threshold during suspend so it won't block S0ix. And the default overall delay timeout is 1 second. However, in practice, we found that the time it takes to cool the PCH down below threshold highly depends on the initial PCH temperature when the delay starts, as well as the ambient temperature. And in some cases, the 1 second delay is not sufficient. As a result, the system stays in a shallower power state like PCx instead of S0ix, and drains the battery power, without user' notice. To make sure S0ix is not blocked by the PCH overheating, we 1. expand the default overall timeout to 60 seconds. 2. make sure the temperature is below threshold rather than equal to it. At the same time, as the cooling delay can be much longer and many wakeup events (ACPI Power Button press, USB mouse move, etc) becomes valid in the suspend_noirq phase, add detection of wakeup event so that the driver does not delay blindly when the system suspend is likely to abort soon. This patch may introduce longer suspend time, but only in the cases when the system overheats and Linux used to enter a shallower S2idle state, say, PCx instead of S0ix. Signed-off-by: Zhang Rui <rui.zhang@intel.com> Tested-by: Sumeet Pawnikar <sumeet.r.pawnikar@intel.com> --- drivers/thermal/intel/intel_pch_thermal.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-)