Hi!

quoted

So we seem to have thermal or ACPI regression in v4.9-rc3.

To me, there are two problems,
the first one is a 4.9-rc regression that BIOS limit stops working,
results in overheating because of high cpu frequency. I agree with
Srinivas to check acpi_cpufreq driver code for this one.

Ok.

the second problem is that thermal passive cooling can not prevent the
system from overheating, when there is no BIOS limit. To debug this,
you can enable thermal dynamic debug by
echo 'module thermal_sys +fp' > /sys/kernel/debug/dynamic_debug/control

How is thermal passive cooling different from BIOS limit?

Is this related?

pavel@duo:/sys/class/thermal/cooling_device1$ grep -r . .
./cur_state:0
./power/runtime_active_kids:0
./power/runtime_suspended_time:0
grep: ./power/autosuspend_delay_ms: Input/output error
./power/runtime_enabled:disabled
./power/runtime_active_time:0
./power/control:auto
./power/async:disabled
./power/runtime_usage:0
./power/runtime_status:unsupported
./type:Processor
./max_state:10

Hmm. I seem to get _some_ throttling, even when bios_limit is still
1.8GHz, but I don't understand where it comes from. And yes,
'thermal_sys +fp' seems to produce some output.

[I did not get absolute records in >100C range this time, but still
there are "THERMAL EMERGENCY:" messages from thinkpad_acpi already...]

[14049.733423] thinkpad_acpi: THERMAL EMERGENCY: a sensor reports something is extremely hot!
[14049.735412] thinkpad_acpi: temperatures (Celsius): 92 50 N/A 80 32 N/A 32 N/A 50 59 N/A N/A N/A N/A N/A N/A
[14049.736557] update_temperature: thermal thermal_zone1: last_temperature=92000, current_temperature=93000
[14049.736570] thermal_zone_trip_update: thermal thermal_zone1: Trip1[type=1,temp=92500]:trend=1,throttle=1
[14049.736577] get_target_state: thermal cooling_device2: cur_state=0
[14049.736580] thermal_zone_trip_update: thermal cooling_device2: old_target=0, target=1
[14049.736586] get_target_state: thermal cooling_device1: cur_state=0
[14049.736589] thermal_zone_trip_update: thermal cooling_device1: old_target=0, target=1
[14049.736593] thermal_cdev_update: thermal cooling_device2: zone1->target=1
[14049.736643] thermal_cdev_update: thermal cooling_device2: set to state 1
[14049.736647] thermal_cdev_update: thermal cooling_device1: zone1->target=1
[14049.736666] thermal_cdev_update: thermal cooling_device1: set to state 1
[14049.808333] update_temperature: thermal thermal_zone1: last_temperature=93000, current_temperature=91000
[14049.808352] thermal_zone_trip_update: thermal thermal_zone1: Trip1[type=1,temp=92500]:trend=2,throttle=0
[14049.808360] get_target_state: thermal cooling_device2: cur_state=1
[14049.808364] thermal_zone_trip_update: thermal cooling_device2: old_target=1, target=0
[14049.808371] get_target_state: thermal cooling_device1: cur_state=1
[14049.808375] thermal_zone_trip_update: thermal cooling_device1: old_target=1, target=0
[14049.808381] thermal_cdev_update: thermal cooling_device2: zone1->target=0
[14049.808409] thermal_cdev_update: thermal cooling_device2: set to state 0
[14049.808414] thermal_cdev_update: thermal cooling_device1: zone1->target=0
[14049.808432] thermal_cdev_update: thermal cooling_device1: set to state 0
[14049.888385] update_temperature: thermal thermal_zone1: last_temperature=91000, current_temperature=92000
[14049.888401] thermal_zone_trip_update: thermal thermal_zone1: Trip1[type=1,temp=92500]:trend=1,throttle=0
[14049.888408] get_target_state: thermal cooling_device2: cur_state=0
[14049.888411] thermal_zone_trip_update: thermal cooling_device2: old_target=0, target=0
[14049.888416] get_target_state: thermal cooling_device1: cur_state=0
[14049.888419] thermal_zone_trip_update: thermal cooling_device1: old_target=0, target=0
[14051.312646] thinkpad_acpi: THERMAL EMERGENCY: a sensor reports something is extremely hot!
[14051.314442] thinkpad_acpi: temperatures (Celsius): 93 50 N/A 80 32 N/A 32 N/A 50 59 N/A N/A N/A N/A N/A N/A
[14051.315544] update_temperature: thermal thermal_zone1: last_temperature=92000, current_temperature=94000
[14051.315557] thermal_zone_trip_update: thermal thermal_zone1: Trip1[type=1,temp=92500]:trend=1,throttle=1
[14051.315564] get_target_state: thermal cooling_device2: cur_state=0
[14051.315567] thermal_zone_trip_update: thermal cooling_device2: old_target=0, target=1
[14051.315572] get_target_state: thermal cooling_device1: cur_state=0
[14051.315575] thermal_zone_trip_update: thermal cooling_device1: old_target=0, target=1
[14051.315579] thermal_cdev_update: thermal cooling_device2: zone1->target=1
[14051.315629] thermal_cdev_update: thermal cooling_device2: set to state 1
[14051.315633] thermal_cdev_update: thermal cooling_device1: zone1->target=1
[14051.315652] thermal_cdev_update: thermal cooling_device1: set to state 1
[14051.334873] thinkpad_acpi: THERMAL EMERGENCY: a sensor reports something is extremely hot!
[14051.337322] thinkpad_acpi: temperatures (Celsius): 93 50 N/A 80 32 N/A 32 N/A 50 59 N/A N/A N/A N/A N/A N/A
[14051.338746] update_temperature: thermal thermal_zone1: last_temperature=94000, current_temperature=93000
[14051.338760] thermal_zone_trip_update: thermal thermal_zone1: Trip1[type=1,temp=92500]:trend=2,throttle=1
[14051.338767] get_target_state: thermal cooling_device2: cur_state=1
[14051.338770] thermal_zone_trip_update: thermal cooling_device2: old_target=1, target=0
[14051.338777] get_target_state: thermal cooling_device1: cur_state=1
[14051.338781] thermal_zone_trip_update: thermal cooling_device1: old_target=1, target=0
[14051.338787] thermal_cdev_update: thermal cooling_device2: zone1->target=0
[14051.338811] thermal_cdev_update: thermal cooling_device2: set to state 0
[14051.338815] thermal_cdev_update: thermal cooling_device1: zone1->target=0
[14051.338834] thermal_cdev_update: thermal cooling_device1: set to state 0
[14051.454544] thinkpad_acpi: THERMAL EMERGENCY: a sensor reports something is extremely hot!
[14051.456827] thinkpad_acpi: temperatures (Celsius): 93 50 N/A 80 32 N/A 32 N/A 50 59 N/A N/A N/A N/A N/A N/A
[14051.457944] update_temperature: thermal thermal_zone1: last_temperature=93000, current_temperature=94000
[14051.457957] thermal_zone_trip_update: thermal thermal_zone1: Trip1[type=1,temp=92500]:trend=1,throttle=1
[14051.457964] get_target_state: thermal cooling_device2: cur_state=0
[14051.457967] thermal_zone_trip_update: thermal cooling_device2: old_target=0, target=1
[14051.457973] get_target_state: thermal cooling_device1: cur_state=0

...

									Pavel
-- 
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html