habanalabs: add support for getting device total energy

Add driver implementation for reading the total energy consumption
from the device ARM FW.

Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 61f5edc96e1627f78d7887945b5d097929a4436c..eb66ff532c6a66c721327bf759811f79e45f62dd 100644 (file)
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -411,6 +411,30 @@ int hl_fw_armcp_pci_counters_get(struct hl_device *hdev,
        return rc;
 }
 
+int hl_fw_armcp_total_energy_get(struct hl_device *hdev,
+                       u64 *total_energy)
+{
+       struct armcp_packet pkt = {};
+       long result;
+       int rc;
+
+       pkt.ctl = cpu_to_le32(ARMCP_PACKET_TOTAL_ENERGY_GET <<
+                       ARMCP_PKT_CTL_OPCODE_SHIFT);
+
+       rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+                                       HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+       if (rc) {
+               dev_err(hdev->dev,
+                       "Failed to handle ArmCP total energy pkt, error %d\n",
+                               rc);
+               return rc;
+       }
+
+       *total_energy = result;
+
+       return rc;
+}
+
 static void fw_read_errors(struct hl_device *hdev, u32 boot_err0_reg)
 {
        u32 err_val;

diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 5ef487a3b843b38347b6fcd15243af2b84f70f22..6577a73e3227dac1951173024d1404adcb71e124 100644 (file)
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -1852,6 +1852,8 @@ int hl_fw_armcp_info_get(struct hl_device *hdev);
 int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size);
 int hl_fw_armcp_pci_counters_get(struct hl_device *hdev,
                struct hl_info_pci_counters *counters);
+int hl_fw_armcp_total_energy_get(struct hl_device *hdev,
+                       u64 *total_energy);
 int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
                        u32 msg_to_cpu_reg, u32 cpu_msg_status_reg,
                        u32 boot_err0_reg, bool skip_bmc,

diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index a9480001424332e0e712cced02f38af60c93f230..18ee14b4b0e19bb1342a12caf08bb3d5a3b32264 100644 (file)
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -357,6 +357,27 @@ static int sync_manager_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
                        sizeof(sm_info))) ? -EFAULT : 0;
 }
 
+static int total_energy_consumption_info(struct hl_fpriv *hpriv,
+                       struct hl_info_args *args)
+{
+       struct hl_device *hdev = hpriv->hdev;
+       struct hl_info_energy total_energy = {0};
+       u32 max_size = args->return_size;
+       void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+       int rc;
+
+       if ((!max_size) || (!out))
+               return -EINVAL;
+
+       rc = hl_fw_armcp_total_energy_get(hdev,
+                       &total_energy.total_energy_consumption);
+       if (rc)
+               return rc;
+
+       return copy_to_user(out, &total_energy,
+               min((size_t) max_size, sizeof(total_energy))) ? -EFAULT : 0;
+}
+
 static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
                                struct device *dev)
 {
@@ -429,6 +450,9 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
        case HL_INFO_SYNC_MANAGER:
                return sync_manager_info(hpriv, args);
 
+       case HL_INFO_TOTAL_ENERGY:
+               return total_energy_consumption_info(hpriv, args);
+
        default:
                dev_err(dev, "Invalid request %d\n", args->op);
                rc = -ENOTTY;

diff --git a/drivers/misc/habanalabs/include/common/armcp_if.h b/drivers/misc/habanalabs/include/common/armcp_if.h
index 1403c937253c93c9e57e4b34d9299a7a4ab39f8c..4d78898524e9a63bee87a1d14b839653cdf92c59 100644 (file)
--- a/drivers/misc/habanalabs/include/common/armcp_if.h
+++ b/drivers/misc/habanalabs/include/common/armcp_if.h
@@ -245,6 +245,7 @@ enum armcp_packet_id {
        ARMCP_PACKET_CURRENT_SET,               /* sysfs */
        ARMCP_PACKET_PCIE_THROUGHPUT_GET,       /* internal */
        ARMCP_PACKET_PCIE_REPLAY_CNT_GET,       /* internal */
+       ARMCP_PACKET_TOTAL_ENERGY_GET,          /* internal */
 };
 
 #define ARMCP_PACKET_FENCE_VAL 0xFE8CE7A5

diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index 693081728ef390b3e727703698b1b7da8b4d735f..6803991726e88876091b7cb9dbc80cc396edd35d 100644 (file)
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -267,6 +267,7 @@ enum hl_device_status {
  * HL_INFO_PCI_COUNTERS  - Retrieve PCI counters
  * HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason
  * HL_INFO_SYNC_MANAGER  - Retrieve sync manager info per dcore
+ * HL_INFO_TOTAL_ENERGY  - Retrieve total energy consumption
  */
 #define HL_INFO_HW_IP_INFO             0
 #define HL_INFO_HW_EVENTS              1
@@ -282,6 +283,7 @@ enum hl_device_status {
 #define HL_INFO_PCI_COUNTERS           12
 #define HL_INFO_CLK_THROTTLE_REASON    13
 #define HL_INFO_SYNC_MANAGER           14
+#define HL_INFO_TOTAL_ENERGY           15
 
 #define HL_INFO_VERSION_MAX_LEN        128
 #define HL_INFO_CARD_NAME_MAX_LEN      16
@@ -375,6 +377,14 @@ struct hl_info_clk_throttle {
        __u32 clk_throttling_reason;
 };
 
+/**
+ * struct hl_info_energy - device energy information
+ * @total_energy_consumption: total device energy consumption
+ */
+struct hl_info_energy {
+       __u64 total_energy_consumption;
+};
+
 /**
  * struct hl_info_sync_manager - sync manager information
  * @first_available_sync_object: first available sob