[PATCH 1/3] habanalabs: generalize COMMS message sending procedure

[PATCH 1/3] habanalabs: generalize COMMS message sending procedure

[Oded Gabbay]

From: Alon Mizrahi <amizrahi@habana.ai>

Instead of having dedicated function per message that we want to send
to the firmware in COMMS protocol, have a generic function that we can
call to from other parts of the driver

Signed-off-by: Alon Mizrahi <amizrahi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/misc/habanalabs/common/firmware_if.c | 28 +++++++++++++-------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 8d2568c63f19..4e68fb9d2a6b 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -2162,18 +2162,17 @@ static void hl_fw_linux_update_state(struct hl_device *hdev,
 }
 
 /**
- * hl_fw_dynamic_report_reset_cause - send a COMMS message with the cause
- *                                    of the newly triggered hard reset
+ * hl_fw_dynamic_send_msg - send a COMMS message with attached data
  *
  * @hdev: pointer to the habanalabs device structure
  * @fw_loader: managing structure for loading device's FW
- * @reset_cause: enumerated cause for the recent hard reset
+ * @msg_type: message type
+ * @data: data to be sent
  *
  * @return 0 on success, otherwise non-zero error code
  */
-static int hl_fw_dynamic_report_reset_cause(struct hl_device *hdev,
-		struct fw_load_mgr *fw_loader,
-		enum comms_reset_cause reset_cause)
+static int hl_fw_dynamic_send_msg(struct hl_device *hdev,
+		struct fw_load_mgr *fw_loader, u8 msg_type, void *data)
 {
 	struct lkd_msg_comms msg;
 	int rc;
@@ -2181,11 +2180,20 @@ static int hl_fw_dynamic_report_reset_cause(struct hl_device *hdev,
 	memset(&msg, 0, sizeof(msg));
 
 	/* create message to be sent */
-	msg.header.type = HL_COMMS_RESET_CAUSE_TYPE;
+	msg.header.type = msg_type;
 	msg.header.size = cpu_to_le16(sizeof(struct comms_msg_header));
 	msg.header.magic = cpu_to_le32(HL_COMMS_MSG_MAGIC);
 
-	msg.reset_cause = reset_cause;
+	switch (msg_type) {
+	case HL_COMMS_RESET_CAUSE_TYPE:
+		msg.reset_cause = *(__u8 *) data;
+		break;
+	default:
+		dev_err(hdev->dev,
+			"Send COMMS message - invalid message type %u\n",
+			msg_type);
+		return -EINVAL;
+	}
 
 	rc = hl_fw_dynamic_request_descriptor(hdev, fw_loader,
 			sizeof(struct lkd_msg_comms));
@@ -2252,8 +2260,8 @@ static int hl_fw_dynamic_init_cpu(struct hl_device *hdev,
 		goto protocol_err;
 
 	if (hdev->curr_reset_cause) {
-		rc = hl_fw_dynamic_report_reset_cause(hdev, fw_loader,
-				hdev->curr_reset_cause);
+		rc = hl_fw_dynamic_send_msg(hdev, fw_loader,
+				HL_COMMS_RESET_CAUSE_TYPE, &hdev->curr_reset_cause);
 		if (rc)
 			goto protocol_err;
 
-- 
2.17.1

[PATCH 2/3] habanalabs: enable power info via HWMON framework

[Oded Gabbay]

From: Rajaravi Krishna Katta <rkatta@habana.ai>

Add support to retrieve following power info via HWMON:
- instantaneous power value
- highest value since last reset
- reset the highest place holder

Signed-off-by: Rajaravi Krishna Katta <rkatta@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/misc/habanalabs/common/habanalabs.h   |  4 +
 drivers/misc/habanalabs/common/hwmon.c        | 94 +++++++++++++++++++
 .../misc/habanalabs/include/common/cpucp_if.h | 10 ++
 3 files changed, 108 insertions(+)

diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index bebebcb163ee..f8e23ca18a57 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -2956,6 +2956,10 @@ int hl_set_voltage(struct hl_device *hdev,
 			int sensor_index, u32 attr, long value);
 int hl_set_current(struct hl_device *hdev,
 			int sensor_index, u32 attr, long value);
+int hl_set_power(struct hl_device *hdev,
+			int sensor_index, u32 attr, long value);
+int hl_get_power(struct hl_device *hdev,
+			int sensor_index, u32 attr, long *value);
 void hw_sob_get(struct hl_hw_sob *hw_sob);
 void hw_sob_put(struct hl_hw_sob *hw_sob);
 void hl_encaps_handle_do_release(struct kref *ref);
diff --git a/drivers/misc/habanalabs/common/hwmon.c b/drivers/misc/habanalabs/common/hwmon.c
index 8f12d99fda09..e33f65be8a00 100644
--- a/drivers/misc/habanalabs/common/hwmon.c
+++ b/drivers/misc/habanalabs/common/hwmon.c
@@ -236,6 +236,23 @@ static int hl_read(struct device *dev, enum hwmon_sensor_types type,
 		else
 			rc = hl_get_pwm_info(hdev, channel, attr, val);
 		break;
+	case hwmon_power:
+		switch (attr) {
+		case hwmon_power_input:
+			cpucp_attr = CPUCP_POWER_INPUT;
+			break;
+		case hwmon_power_input_highest:
+			cpucp_attr = CPUCP_POWER_INPUT_HIGHEST;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		if (use_cpucp_enum)
+			rc = hl_get_power(hdev, channel, cpucp_attr, val);
+		else
+			rc = hl_get_power(hdev, channel, attr, val);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -316,6 +333,20 @@ static int hl_write(struct device *dev, enum hwmon_sensor_types type,
 		else
 			hl_set_current(hdev, channel, attr, val);
 		break;
+	case hwmon_power:
+		switch (attr) {
+		case hwmon_power_reset_history:
+			cpucp_attr = CPUCP_POWER_RESET_INPUT_HISTORY;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		if (use_cpucp_enum)
+			hl_set_power(hdev, channel, cpucp_attr, val);
+		else
+			hl_set_power(hdev, channel, attr, val);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -378,6 +409,15 @@ static umode_t hl_is_visible(const void *data, enum hwmon_sensor_types type,
 			return 0644;
 		}
 		break;
+	case hwmon_power:
+		switch (attr) {
+		case hwmon_power_input:
+		case hwmon_power_input_highest:
+			return 0444;
+		case hwmon_power_reset_history:
+			return 0200;
+		}
+		break;
 	default:
 		break;
 	}
@@ -633,6 +673,60 @@ int hl_set_current(struct hl_device *hdev,
 	return rc;
 }
 
+int hl_set_power(struct hl_device *hdev,
+			int sensor_index, u32 attr, long value)
+{
+	struct cpucp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_POWER_GET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.sensor_index = __cpu_to_le16(sensor_index);
+	pkt.type = __cpu_to_le16(attr);
+	pkt.value = __cpu_to_le64(value);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+						0, NULL);
+
+	if (rc)
+		dev_err(hdev->dev,
+			"Failed to set power of sensor %d, error %d\n",
+			sensor_index, rc);
+
+	return rc;
+}
+
+int hl_get_power(struct hl_device *hdev,
+			int sensor_index, u32 attr, long *value)
+{
+	struct cpucp_packet pkt;
+	u64 result;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_POWER_GET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.sensor_index = __cpu_to_le16(sensor_index);
+	pkt.type = __cpu_to_le16(attr);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+						0, &result);
+
+	*value = (long) result;
+
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to get power of sensor %d, error %d\n",
+			sensor_index, rc);
+		*value = 0;
+	}
+
+	return rc;
+}
+
 int hl_hwmon_init(struct hl_device *hdev)
 {
 	struct device *dev = hdev->pdev ? &hdev->pdev->dev : hdev->dev;
diff --git a/drivers/misc/habanalabs/include/common/cpucp_if.h b/drivers/misc/habanalabs/include/common/cpucp_if.h
index 9ff6a448f0d4..a6fa1cfa38a5 100644
--- a/drivers/misc/habanalabs/include/common/cpucp_if.h
+++ b/drivers/misc/habanalabs/include/common/cpucp_if.h
@@ -598,6 +598,16 @@ enum cpucp_pll_type_attributes {
 	cpucp_pll_pci,
 };
 
+/*
+ * cpucp_power_type aligns with hwmon_power_attributes
+ * defined in Linux kernel hwmon.h file
+ */
+enum cpucp_power_type {
+	CPUCP_POWER_INPUT = 8,
+	CPUCP_POWER_INPUT_HIGHEST = 9,
+	CPUCP_POWER_RESET_INPUT_HISTORY = 11
+};
+
 /*
  * MSI type enumeration table for all ASICs and future SW versions.
  * For future ASIC-LKD compatibility, we can only add new enumerations.
-- 
2.17.1

[PATCH 3/3] habanalabs: remove redundant cs validity checks

[Oded Gabbay]

From: Ofir Bitton <obitton@habana.ai>

During TDR handling, we check multiple times if CS is valid.
No need to perform this check as CS must be valid at all time
during the TDR handling.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/misc/habanalabs/common/command_submission.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index a4ed91ed991d..70bc00ff27f0 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -431,11 +431,10 @@ static void cs_handle_tdr(struct hl_device *hdev, struct hl_cs *cs)
 	/* Don't cancel TDR in case this CS was timedout because we might be
 	 * running from the TDR context
 	 */
-	if (cs && (cs->timedout ||
-			hdev->timeout_jiffies == MAX_SCHEDULE_TIMEOUT))
+	if (cs->timedout || hdev->timeout_jiffies == MAX_SCHEDULE_TIMEOUT)
 		return;
 
-	if (cs && cs->tdr_active)
+	if (cs->tdr_active)
 		cancel_delayed_work_sync(&cs->work_tdr);
 
 	spin_lock(&hdev->cs_mirror_lock);
-- 
2.17.1