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, 164 insertions, 6 deletions

diff --git a/util/ectool.c b/util/ectool.c
index 0ee39dcb9e..b25edb88b8 100644
--- a/util/ectool.c
+++ b/util/ectool.c
@@ -140,10 +140,10 @@ const char help_str[] =
 	"      Print temperature.\n"
 	"  tempsinfo <sensorid>\n"
 	"      Print temperature sensor info.\n"
-	"  thermalget <sensor_id> <threshold_id>\n"
-	"      Get the threshold temperature value from thermal engine.\n"
-	"  thermalset <sensor_id> <threshold_id> <value>\n"
-	"      Set the threshold temperature value for thermal engine.\n"
+	"  thermalget <platform-specific args>\n"
+	"      Get the threshold temperature values from the thermal engine.\n"
+	"  thermalset <platform-specific args>\n"
+	"      Set the threshold temperature values for the thermal engine.\n"
 	"  tmp006cal <tmp006_index> [<S0> <b0> <b1> <b2>]\n"
 	"      Get/set TMP006 calibration\n"
 	"  usbchargemode <port> <mode>\n"
@@ -859,7 +859,7 @@ int cmd_temp_sensor_info(int argc, char *argv[])
 }
 
 
-int cmd_thermal_get_threshold(int argc, char *argv[])
+int cmd_thermal_get_threshold_v0(int argc, char *argv[])
 {
 	struct ec_params_thermal_get_threshold p;
 	struct ec_response_thermal_get_threshold r;
@@ -899,7 +899,7 @@ int cmd_thermal_get_threshold(int argc, char *argv[])
 }
 
 
-int cmd_thermal_set_threshold(int argc, char *argv[])
+int cmd_thermal_set_threshold_v0(int argc, char *argv[])
 {
 	struct ec_params_thermal_set_threshold p;
 	char *e;
@@ -942,6 +942,164 @@ int cmd_thermal_set_threshold(int argc, char *argv[])
 }
 
 
+int cmd_thermal_get_threshold_v1(int argc, char *argv[])
+{
+	struct ec_params_thermal_get_threshold_v1 p;
+	struct ec_thermal_config r;
+	struct ec_params_temp_sensor_get_info pi;
+	struct ec_response_temp_sensor_get_info ri;
+	int rv;
+	int i;
+
+	printf("sensor  warn  high  halt   fan_off fan_max   name\n");
+	for (i = 0; i < 99; i++) {	/* number of sensors is unknown */
+
+		/* ask for one */
+		p.sensor_num = i;
+		rv = ec_command(EC_CMD_THERMAL_GET_THRESHOLD, 1,
+				&p, sizeof(p), &r, sizeof(r));
+		if (rv <= 0)		/* stop on first failure */
+			break;
+
+		/* ask for its name, too */
+		pi.id = i;
+		rv = ec_command(EC_CMD_TEMP_SENSOR_GET_INFO, 0,
+				&pi, sizeof(pi), &ri, sizeof(ri));
+
+		/* print what we know */
+		printf(" %2d      %3d   %3d    %3d    %3d     %3d     %s\n",
+		       i,
+		       r.temp_host[EC_TEMP_THRESH_WARN],
+		       r.temp_host[EC_TEMP_THRESH_HIGH],
+		       r.temp_host[EC_TEMP_THRESH_HALT],
+		       r.temp_fan_off, r.temp_fan_max,
+		       rv > 0 ? ri.sensor_name : "?");
+	}
+	if (i)
+		printf("(all temps in degrees Kelvin)\n");
+
+	return 0;
+}
+
+int cmd_thermal_set_threshold_v1(int argc, char *argv[])
+{
+	struct ec_params_thermal_get_threshold_v1 p;
+	struct ec_thermal_config r;
+	struct ec_params_thermal_set_threshold_v1 s;
+	int i, n, val, rv;
+	char *e;
+
+	if (argc < 3 || argc > 7) {
+		printf("Usage: %s"
+		       " sensor warn [high [shutdown [fan_off [fan_max]]]]\n",
+		       argv[0]);
+		return 1;
+	}
+
+	n = strtod(argv[1], &e);
+	if (e && *e) {
+		printf("arg %d is invalid\n", 1);
+		return 1;
+	}
+
+	p.sensor_num = n;
+	rv = ec_command(EC_CMD_THERMAL_GET_THRESHOLD, 1,
+			&p, sizeof(p), &r, sizeof(r));
+	if (rv <= 0)
+		return rv;
+
+	s.sensor_num = n;
+	s.cfg = r;
+
+	for (i = 2; i < argc; i++) {
+		val = strtod(argv[i], &e);
+		if (e && *e) {
+			printf("arg %d is invalid\n", i);
+			return 1;
+		}
+
+		if (val < 0)
+			continue;
+		switch (i) {
+		case 2:
+		case 3:
+		case 4:
+			s.cfg.temp_host[i-2] = val;
+			break;
+		case 5:
+			s.cfg.temp_fan_off = val;
+			break;
+		case 6:
+			s.cfg.temp_fan_max = val;
+			break;
+		}
+	}
+
+	rv = ec_command(EC_CMD_THERMAL_SET_THRESHOLD, 1,
+			&s, sizeof(s), NULL, 0);
+
+	return rv;
+}
+
+
+static int thermal_threshold_version(void)
+{
+	struct ec_params_thermal_get_threshold v0_p;
+	struct ec_response_thermal_get_threshold v0_r;
+	struct ec_params_thermal_get_threshold_v1 v1_p;
+	struct ec_thermal_config v1_r;
+	int rv;
+
+	v1_p.sensor_num = 0;
+	rv = ec_command(EC_CMD_THERMAL_GET_THRESHOLD, 1,
+			&v1_p, sizeof(v1_p), &v1_r, sizeof(v1_r));
+	/* FIXME: Verson 1 will only return these responses */
+	/* FIXME: if (??? == EC_RES_SUCCESS || ??? == EC_RES_INVALID_PARAM) */
+	if (rv > 0)
+		return 1;
+
+	v0_p.sensor_type = 0;
+	v0_p.threshold_id = 0;
+	rv = ec_command(EC_CMD_THERMAL_GET_THRESHOLD, 0,
+			&v0_p, sizeof(v0_p), &v0_r, sizeof(v0_r));
+	/* FIXME: Verson 0 will only return these responses */
+	/* FIXME: if (??? == EC_RES_SUCCESS || ??? == EC_RES_ERROR) */
+	if (rv > 0)
+		return 0;
+
+	/* Anything else is most likely EC_RES_INVALID_COMMAND,
+	 * but we don't care because it's nothing we can use.
+	 */
+	return -1;
+}
+
+int cmd_thermal_get_threshold(int argc, char *argv[])
+{
+	switch (thermal_threshold_version()) {
+	case 0:
+		return cmd_thermal_get_threshold_v0(argc, argv);
+	case 1:
+		return cmd_thermal_get_threshold_v1(argc, argv);
+	default:
+		printf("I got nuthin.\n");
+		return -1;
+	}
+}
+
+int cmd_thermal_set_threshold(int argc, char *argv[])
+{
+	switch (thermal_threshold_version()) {
+	case 0:
+		return cmd_thermal_set_threshold_v0(argc, argv);
+	case 1:
+		return cmd_thermal_set_threshold_v1(argc, argv);
+	default:
+		printf("I got nuthin.\n");
+		return -1;
+	}
+}
+
+
 int cmd_thermal_auto_fan_ctrl(int argc, char *argv[])
 {
 	int rv;