Completely new thermal/fan implementation

Problems with existing thermal control loop:
* Not multi-board friendly. thermal.c only supports Link and needs
  refactoring. Temp thresholds and fan speeds are hard-coded.
* Only the PECI temp is used to determine the fan speed. Other temp sensors
  are ignored.
* Has confusing data structures. Values in the CPU temp thresholds array mix
  ACPI thresholds with fan step values.

With this change, the thermal task monitors all temp sensors in order to
perform two completely independent functions:

Function one: Determine if the host needs to be throttled by or informed of
              any thermal events.

For thermal events, each temp sensor will have three threshold levels.

TEMP_HOST_WARN
* When any sensor goes above this level, host_throttle_cpu(1) will be called
  to ask the CPU to slow itself down.
* When all sensors drop below this level, host_throttle_cpu(0) will be called.
* Exactly AT this level, nothing happens (this provides hysteresis).

TEMP_HOST_HIGH
* When any sensor goes above this level, chipset_throttle_cpu(1) will be
  called to slow the CPU down whether it wants to or not.
* When all sensors drop below this level, chipset_throttle_cpu(0) will be
  called.
* Exactly AT this level, nothing happens (this provides hysteresis).

TEMP_HOST_SHUTDOWN
* When any sensor is above this level, chipset_force_shutdown() will be
  called to halt the CPU.
* Nothing turns the CPU back on again - the user just has to wait for things
  to cool off. Pressing the power button too soon will just trigger shutdown
  again as soon as the EC can read the host temp.

Function two: Determine the amount of fan cooling needed

For fan cooling, each temp sensor will have two levels.

TEMP_FAN_OFF
* At or below this temperature, no active cooling is needed.

TEMP_FAN_MAX
* At or above this temperature, active cooling should be running at maximum.

The highest level of all temp sensors will be used to request the amount of
active cooling needed. The function pwm_fan_percent_to_rpm() is invoked to
convert the amount of cooling to the target fan RPM.

The default pwm_fan_percent_to_rpm() function converts smoothly between the
configured CONFIG_PWM_FAN_RPM_MIN and CONFIG_PWM_FAN_RPM_MAX for percentages
between 1 and 100. 0% means "off".

The default function probably provide the smoothest and quietest behavior,
but individual boards can provide their own pwm_fan_percent_to_rpm() to
implement whatever curves, hysteresis, feedback, or other hackery they wish.

BUG=chrome-os-partner:20805
BRANCH=none
TEST=manual

Compile-time test with

  make BOARD=falco runtests

On the EC console, the existing fan commands should work correctly:

  faninfo       - display the fan state
  fanduty NUM   - force the fan PWM to the specified percentage (0-100)
  fanset RPM    - force the fan to the specified RPM
  fanset NUM%   - force the fan to the specified percentage (0-100) between
                  its configured minimum and maximum speeds from board.h
                  (CONFIG_PWM_FAN_RPM_MIN and CONFIG_PWM_FAN_RPM_MAX)
  fanauto       - let the EC control the fan automatically

You can test the default pwm_fan_percent_to_rpm() with

  fanset 1%
  faninfo

The fan should be turning at CONFIG_PWM_FAN_RPM_MIN. Let the EC control it
automatically again with

  fanauto

Also on the EC console, the thermal settings can be examined or changed:

  > temps
  PECI                : 327 K = 54 C
  ECInternal          : 320 K = 47 C
  G781Internal        : 319 K = 46 C
  G781External        : 318 K = 45 C
  >
  > thermalget
  sensor  warn  high  shutdown   fan_off fan_max   name
    0      373   387    383        333     363     PECI
    1        0     0      0          0       0     ECInternal
    2        0     0      0          0       0     G781Internal
    3        0     0      0          0       0     G781External
  >
  > help thermalset
  Usage: thermalset sensor warn [high [shutdown [fan_off [fan_max]]]]
  set thermal parameters (-1 to skip)
  >
  > thermalset 2 -1 -1 999
  sensor  warn  high  shutdown   fan_off fan_max   name
    0      373   387    383        333     363     PECI
    1        0     0      0          0       0     ECInternal
    2        0     0    999          0       0     G781Internal
    3        0     0      0          0       0     G781External
  >

From the host, ectool can be used to get and set these parameters with
nearly identical commands:

  ectool thermalget
  ectool thermalset 2 -1 -1 999

Change-Id: Idb27977278f766826045fb7d41929953ec6b1cca
Signed-off-by: Bill Richardson <wfrichar@chromium.org>
Reviewed-on: https://gerrit.chromium.org/gerrit/66688
Reviewed-by: Randall Spangler <rspangler@chromium.org>

1 files changed, 47 insertions, 5 deletions

diff --git a/include/ec_commands.h b/include/ec_commands.h
index 019c1ab88f..08fb20a996 100644
--- a/include/ec_commands.h
+++ b/include/ec_commands.h
@@ -1169,20 +1169,27 @@ struct ec_response_port80_last_boot {
 } __packed;
 
 /*****************************************************************************/
-/* Thermal engine commands */
+/* Thermal engine commands. Note that there are two implementations. We'll
+ * reuse the command number, but the data and behavior is incompatible.
+ * Version 0 is what originally shipped on Link.
+ * Version 1 separates the CPU thermal limits from the fan control.
+ */
 
-/* Set thershold value */
 #define EC_CMD_THERMAL_SET_THRESHOLD 0x50
+#define EC_CMD_THERMAL_GET_THRESHOLD 0x51
 
+/* The version 0 structs are opaque. You have to know what they are for
+ * the get/set commands to make any sense.
+ */
+
+/* Version 0 - set */
 struct ec_params_thermal_set_threshold {
 	uint8_t sensor_type;
 	uint8_t threshold_id;
 	uint16_t value;
 } __packed;
 
-/* Get threshold value */
-#define EC_CMD_THERMAL_GET_THRESHOLD 0x51
-
+/* Version 0 - get */
 struct ec_params_thermal_get_threshold {
 	uint8_t sensor_type;
 	uint8_t threshold_id;
@@ -1192,6 +1199,41 @@ struct ec_response_thermal_get_threshold {
 	uint16_t value;
 } __packed;
 
+
+/* The version 1 structs are visible. */
+enum ec_temp_thresholds {
+	EC_TEMP_THRESH_WARN = 0,
+	EC_TEMP_THRESH_HIGH,
+	EC_TEMP_THRESH_HALT,
+
+	EC_TEMP_THRESH_COUNT
+};
+
+/* Thermal configuration for one temperature sensor. Temps are in degrees K.
+ * Zero values will be silently ignored by the thermal task.
+ */
+struct ec_thermal_config {
+	uint32_t temp_host[EC_TEMP_THRESH_COUNT]; /* levels of hotness */
+	uint32_t temp_fan_off;		/* no active cooling needed */
+	uint32_t temp_fan_max;		/* max active cooling needed */
+} __packed;
+
+/* Version 1 - get config for one sensor. */
+struct ec_params_thermal_get_threshold_v1 {
+	uint32_t sensor_num;
+} __packed;
+/* This returns a struct ec_thermal_config */
+
+/* Version 1 - set config for one sensor.
+ * Use read-modify-write for best results! */
+struct ec_params_thermal_set_threshold_v1 {
+	uint32_t sensor_num;
+	struct ec_thermal_config cfg;
+} __packed;
+/* This returns no data */
+
+/****************************************************************************/
+
 /* Toggle automatic fan control */
 #define EC_CMD_THERMAL_AUTO_FAN_CTRL 0x52