From bd30d075eedce159fd5a42e772b903facaa3c47c Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Thu, 19 May 2022 22:35:08 +0800 Subject: [PATCH] thermal: intel: pch: improve the cooling delay log Previously, during suspend, intel_pch_thermal driver logs for every cooling iteration, about the current PCH temperature and number of cooling iterations that have been tried, like below [ 100.955526] intel_pch_thermal 0000:00:14.2: CPU-PCH current temp [53C] higher than the threshold temp [50C], sleep 1 times for 100 ms duration [ 101.064156] intel_pch_thermal 0000:00:14.2: CPU-PCH current temp [53C] higher than the threshold temp [50C], sleep 2 times for 100 ms duration After changing the default delay_cnt to 600, in practice, it is common to see tens of the above messages if the system is suspended when PCH overheats. Thus, change this log message from dev_warn to dev_dbg because it is only useful when we want to check the temperature trend. At the same time, there is always a one-line message given by the driver with the patch applied, with below four possibilities. 1. PCH is cool, no cooling delay needed [ 1791.902853] intel_pch_thermal 0000:00:12.0: CPU-PCH is cool [48C] 2. PCH overheats and becomes cool after the cooling delays [ 1475.511617] intel_pch_thermal 0000:00:12.0: CPU-PCH is cool [49C] after 30700 ms delay 3. PCH still overheats after the overall cooling timeout [ 2250.157487] intel_pch_thermal 0000:00:12.0: CPU-PCH is hot [60C] after 60000 ms delay. S0ix might fail 4. PCH aborts cooling because of wakeup event detected during the delay [ 1933.639509] intel_pch_thermal 0000:00:12.0: Wakeup event detected, abort cooling Signed-off-by: Zhang Rui Tested-by: Sumeet Pawnikar Signed-off-by: Rafael J. Wysocki --- drivers/thermal/intel/intel_pch_thermal.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-) diff --git a/drivers/thermal/intel/intel_pch_thermal.c b/drivers/thermal/intel/intel_pch_thermal.c index b7b32e2..c1fa2b2 100644 --- a/drivers/thermal/intel/intel_pch_thermal.c +++ b/drivers/thermal/intel/intel_pch_thermal.c @@ -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; - int pch_delay_cnt = 1; + int pch_delay_cnt = 0; u16 pch_thr_temp, pch_cur_temp; /* Shutdown the thermal sensor if it is not enabled by BIOS */ @@ -233,29 +233,38 @@ static int pch_wpt_suspend(struct pch_thermal_device *ptd) * temperature stays above threshold, notify the warning message * which helps to indentify the reason why S0ix entry was rejected. */ - while (pch_delay_cnt <= delay_cnt) { + while (pch_delay_cnt < delay_cnt) { if (pch_cur_temp < pch_thr_temp) break; - if (pm_wakeup_pending()) - break; + if (pm_wakeup_pending()) { + dev_warn(&ptd->pdev->dev, "Wakeup event detected, abort cooling\n"); + return 0; + } - dev_warn(&ptd->pdev->dev, + pch_delay_cnt++; + dev_dbg(&ptd->pdev->dev, "CPU-PCH current temp [%dC] higher than the threshold temp [%dC], sleep %d times for %d ms duration\n", pch_cur_temp, pch_thr_temp, pch_delay_cnt, delay_timeout); msleep(delay_timeout); /* Read the PCH current temperature for next cycle. */ pch_cur_temp = GET_PCH_TEMP(WPT_TEMP_TSR & readw(ptd->hw_base + WPT_TEMP)); - pch_delay_cnt++; } 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); - else - dev_info(&ptd->pdev->dev, - "CPU-PCH is cool [%dC], continue to suspend\n", pch_cur_temp); + "CPU-PCH is hot [%dC] after %d ms delay. S0ix might fail\n", + pch_cur_temp, pch_delay_cnt * delay_timeout); + else { + if (pch_delay_cnt) + dev_info(&ptd->pdev->dev, + "CPU-PCH is cool [%dC] after %d ms delay\n", + pch_cur_temp, pch_delay_cnt * delay_timeout); + else + dev_info(&ptd->pdev->dev, + "CPU-PCH is cool [%dC]\n", + pch_cur_temp); + } return 0; } -- 2.7.4