[04/10] accel/habanalabs: fix EQ heartbeat mechanism

Commit Message

Oded Gabbay Nov. 15, 2023, 4:39 p.m. UTC

From: Farah Kassabri <[e-mail]>

Stop rescheduling another heartbeat check when EQ heartbeat check fails
as it generates confusing logs in dmesg that the heartbeat fails.

Signed-off-by: Farah Kassabri <[e-mail]>
Reviewed-by: Oded Gabbay <[e-mail]>
Signed-off-by: Oded Gabbay <[e-mail]>
---
 drivers/accel/habanalabs/common/device.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

Patch

diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index d9447aeb3937..6bf5f1d0d005 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -1044,20 +1044,21 @@  static bool is_pci_link_healthy(struct hl_device *hdev)
 	return (vendor_id == PCI_VENDOR_ID_HABANALABS);
 }
 
-static void hl_device_eq_heartbeat(struct hl_device *hdev)
+static int hl_device_eq_heartbeat_check(struct hl_device *hdev)
 {
-	u64 event_mask = HL_NOTIFIER_EVENT_DEVICE_RESET | HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE;
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 
 	if (!prop->cpucp_info.eq_health_check_supported)
-		return;
+		return 0;
 
 	if (hdev->eq_heartbeat_received) {
 		hdev->eq_heartbeat_received = false;
 	} else {
 		dev_err(hdev->dev, "EQ heartbeat event was not received!\n");
-		hl_device_cond_reset(hdev, HL_DRV_RESET_HARD, event_mask);
+		return -EIO;
 	}
+
+	return 0;
 }
 
 static void hl_device_heartbeat(struct work_struct *work)
@@ -1074,10 +1075,9 @@  static void hl_device_heartbeat(struct work_struct *work)
 	/*
 	 * For EQ health check need to check if driver received the heartbeat eq event
 	 * in order to validate the eq is working.
+	 * Only if both the EQ is healthy and we managed to send the next heartbeat reschedule.
 	 */
-	hl_device_eq_heartbeat(hdev);
-
-	if (!hdev->asic_funcs->send_heartbeat(hdev))
+	if ((!hl_device_eq_heartbeat_check(hdev)) && (!hdev->asic_funcs->send_heartbeat(hdev)))
 		goto reschedule;
 
 	if (hl_device_operational(hdev, NULL))