From fe8d70873c4919086d5929c49e1c6cd6bb7d1de3 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sat, 13 Nov 2021 17:58:43 +0200 Subject: [PATCH] habanalabs: prevent false heartbeat message If a device reset has started, there is a chance that the heartbeat function will fail because the device is disabled at the beginning of the reset function. In that case, we don't want the error message to appear in the log. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/device.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index 0da5a55..ca74d78 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -543,7 +543,9 @@ static void hl_device_heartbeat(struct work_struct *work) if (!hdev->asic_funcs->send_heartbeat(hdev)) goto reschedule; - dev_err(hdev->dev, "Device heartbeat failed!\n"); + if (hl_device_operational(hdev, NULL)) + dev_err(hdev->dev, "Device heartbeat failed!\n"); + hl_device_reset(hdev, HL_DRV_RESET_HARD | HL_DRV_RESET_HEARTBEAT); return; -- 2.7.4