powercap: Add Power Limit4 support

Modern Intel Mobile platforms support power limit4 (PL4), which is
the SoC package level maximum power limit (in Watts). It can be used
to preemptively limits potential SoC power to prevent power spikes
from tripping the power adapter and battery over-current protection.
This patch enables this feature by exposing package level peak power
capping control to userspace via RAPL sysfs interface. With this,
application like DTPF can modify PL4 power limit, the similar way
of other package power limit (PL1).
As this feature is not tested on previous generations, here it is
enabled only for the platform that has been verified to work,
for safety concerns.

Signed-off-by: Sumeet Pawnikar <sumeet.r.pawnikar@intel.com>
Co-developed-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Reviewed-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Tested-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

2 files changed, 67 insertions, 2 deletions

diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index b739ce4f390d..6f55aaef8afc 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -39,6 +39,8 @@
 #define POWER_HIGH_LOCK         BIT_ULL(63)
 #define POWER_LOW_LOCK          BIT(31)
 
+#define POWER_LIMIT4_MASK		0x1FFF
+
 #define TIME_WINDOW1_MASK       (0x7FULL<<17)
 #define TIME_WINDOW2_MASK       (0x7FULL<<49)
 
@@ -82,6 +84,7 @@ enum unit_type {
 
 static const char pl1_name[] = "long_term";
 static const char pl2_name[] = "short_term";
+static const char pl4_name[] = "peak_power";
 
 #define power_zone_to_rapl_domain(_zone) \
 	container_of(_zone, struct rapl_domain, power_zone)
@@ -338,6 +341,9 @@ static int set_power_limit(struct powercap_zone *power_zone, int cid,
 	case PL2_ENABLE:
 		rapl_write_data_raw(rd, POWER_LIMIT2, power_limit);
 		break;
+	case PL4_ENABLE:
+		rapl_write_data_raw(rd, POWER_LIMIT4, power_limit);
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -372,6 +378,9 @@ static int get_current_power_limit(struct powercap_zone *power_zone, int cid,
 	case PL2_ENABLE:
 		prim = POWER_LIMIT2;
 		break;
+	case PL4_ENABLE:
+		prim = POWER_LIMIT4;
+		break;
 	default:
 		put_online_cpus();
 		return -EINVAL;
@@ -441,6 +450,13 @@ static int get_time_window(struct powercap_zone *power_zone, int cid,
 	case PL2_ENABLE:
 		ret = rapl_read_data_raw(rd, TIME_WINDOW2, true, &val);
 		break;
+	case PL4_ENABLE:
+		/*
+		 * Time window parameter is not applicable for PL4 entry
+		 * so assigining '0' as default value.
+		 */
+		val = 0;
+		break;
 	default:
 		put_online_cpus();
 		return -EINVAL;
@@ -484,6 +500,9 @@ static int get_max_power(struct powercap_zone *power_zone, int id, u64 *data)
 	case PL2_ENABLE:
 		prim = MAX_POWER;
 		break;
+	case PL4_ENABLE:
+		prim = MAX_POWER;
+		break;
 	default:
 		put_online_cpus();
 		return -EINVAL;
@@ -493,6 +512,10 @@ static int get_max_power(struct powercap_zone *power_zone, int id, u64 *data)
 	else
 		*data = val;
 
+	/* As a generalization rule, PL4 would be around two times PL2. */
+	if (rd->rpl[id].prim_id == PL4_ENABLE)
+		*data = *data * 2;
+
 	put_online_cpus();
 
 	return ret;
@@ -525,12 +548,22 @@ static void rapl_init_domains(struct rapl_package *rp)
 		rd->id = i;
 		rd->rpl[0].prim_id = PL1_ENABLE;
 		rd->rpl[0].name = pl1_name;
-		/* some domain may support two power limits */
-		if (rp->priv->limits[i] == 2) {
+
+		/*
+		 * The PL2 power domain is applicable for limits two
+		 * and limits three
+		 */
+		if (rp->priv->limits[i] >= 2) {
 			rd->rpl[1].prim_id = PL2_ENABLE;
 			rd->rpl[1].name = pl2_name;
 		}
 
+		/* Enable PL4 domain if the total power limits are three */
+		if (rp->priv->limits[i] == 3) {
+			rd->rpl[2].prim_id = PL4_ENABLE;
+			rd->rpl[2].name = pl4_name;
+		}
+
 		for (j = 0; j < RAPL_DOMAIN_REG_MAX; j++)
 			rd->regs[j] = rp->priv->regs[i][j];
 
@@ -599,6 +632,8 @@ static struct rapl_primitive_info rpi[] = {
 			    RAPL_DOMAIN_REG_LIMIT, POWER_UNIT, 0),
 	PRIMITIVE_INFO_INIT(POWER_LIMIT2, POWER_LIMIT2_MASK, 32,
 			    RAPL_DOMAIN_REG_LIMIT, POWER_UNIT, 0),
+	PRIMITIVE_INFO_INIT(POWER_LIMIT4, POWER_LIMIT4_MASK, 0,
+				RAPL_DOMAIN_REG_PL4, POWER_UNIT, 0),
 	PRIMITIVE_INFO_INIT(FW_LOCK, POWER_LOW_LOCK, 31,
 			    RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0),
 	PRIMITIVE_INFO_INIT(PL1_ENABLE, POWER_LIMIT1_ENABLE, 15,
@@ -609,6 +644,8 @@ static struct rapl_primitive_info rpi[] = {
 			    RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0),
 	PRIMITIVE_INFO_INIT(PL2_CLAMP, POWER_LIMIT2_CLAMP, 48,
 			    RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0),
+	PRIMITIVE_INFO_INIT(PL4_ENABLE, POWER_LIMIT4_MASK, 0,
+				RAPL_DOMAIN_REG_PL4, ARBITRARY_UNIT, 0),
 	PRIMITIVE_INFO_INIT(TIME_WINDOW1, TIME_WINDOW1_MASK, 17,
 			    RAPL_DOMAIN_REG_LIMIT, TIME_UNIT, 0),
 	PRIMITIVE_INFO_INIT(TIME_WINDOW2, TIME_WINDOW2_MASK, 49,
@@ -1273,6 +1310,7 @@ void rapl_remove_package(struct rapl_package *rp)
 		if (find_nr_power_limit(rd) > 1) {
 			rapl_write_data_raw(rd, PL2_ENABLE, 0);
 			rapl_write_data_raw(rd, PL2_CLAMP, 0);
+			rapl_write_data_raw(rd, PL4_ENABLE, 0);
 		}
 		if (rd->id == RAPL_DOMAIN_PACKAGE) {
 			rd_package = rd;
@@ -1381,6 +1419,13 @@ static void power_limit_state_save(void)
 				if (ret)
 					rd->rpl[i].last_power_limit = 0;
 				break;
+			case PL4_ENABLE:
+				ret = rapl_read_data_raw(rd,
+						 POWER_LIMIT4, true,
+						 &rd->rpl[i].last_power_limit);
+				if (ret)
+					rd->rpl[i].last_power_limit = 0;
+				break;
 			}
 		}
 	}
@@ -1411,6 +1456,11 @@ static void power_limit_state_restore(void)
 					rapl_write_data_raw(rd, POWER_LIMIT2,
 					    rd->rpl[i].last_power_limit);
 				break;
+			case PL4_ENABLE:
+				if (rd->rpl[i].last_power_limit)
+					rapl_write_data_raw(rd, POWER_LIMIT4,
+					    rd->rpl[i].last_power_limit);
+				break;
 			}
 		}
 	}
diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c
index d5487965bdfe..d2a2627507a9 100644
--- a/drivers/powercap/intel_rapl_msr.c
+++ b/drivers/powercap/intel_rapl_msr.c
@@ -28,6 +28,7 @@
 
 /* Local defines */
 #define MSR_PLATFORM_POWER_LIMIT	0x0000065C
+#define MSR_VR_CURRENT_CONFIG		0x00000601
 
 /* private data for RAPL MSR Interface */
 static struct rapl_if_priv rapl_msr_priv = {
@@ -123,13 +124,27 @@ static int rapl_msr_write_raw(int cpu, struct reg_action *ra)
 	return ra->err;
 }
 
+/* List of verified CPUs. */
+static const struct x86_cpu_id pl4_support_ids[] = {
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_TIGERLAKE_L, X86_FEATURE_ANY },
+	{}
+};
+
 static int rapl_msr_probe(struct platform_device *pdev)
 {
+	const struct x86_cpu_id *id = x86_match_cpu(pl4_support_ids);
 	int ret;
 
 	rapl_msr_priv.read_raw = rapl_msr_read_raw;
 	rapl_msr_priv.write_raw = rapl_msr_write_raw;
 
+	if (id) {
+		rapl_msr_priv.limits[RAPL_DOMAIN_PACKAGE] = 3;
+		rapl_msr_priv.regs[RAPL_DOMAIN_PACKAGE][RAPL_DOMAIN_REG_PL4] =
+			MSR_VR_CURRENT_CONFIG;
+		pr_info("PL4 support detected.\n");
+	}
+
 	rapl_msr_priv.control_type = powercap_register_control_type(NULL, "intel-rapl", NULL);
 	if (IS_ERR(rapl_msr_priv.control_type)) {
 		pr_debug("failed to register powercap control_type.\n");