From 246d8b6cfb80a31e3cc287e3c1db6a5515b7c20a Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Mon, 25 Dec 2023 00:28:36 +0200 Subject: [PATCH] accel/habanalabs: abort device reset for consecutive heartbeat failures The mechanism of aborting device reset for consecutive fatal errors is currently only for fatal errors that are reported by FW. A non-responsive FW and consecutive heartbeat failures is also considered fatal, so add them as well to this mechanism to avoid recurring device reset in such a case. Signed-off-by: Tomer Tayar Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/accel/habanalabs/common/device.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c index 5c46826e3659..cf004baf5e62 100644 --- a/drivers/accel/habanalabs/common/device.c +++ b/drivers/accel/habanalabs/common/device.c @@ -1769,14 +1769,16 @@ kill_processes: hdev->device_cpu_disabled = false; hdev->reset_info.hard_reset_pending = false; + /* + * Put the device in an unusable state if there are 2 back to back resets due to + * fatal errors. + */ if (hdev->reset_info.reset_trigger_repeated && - (hdev->reset_info.prev_reset_trigger == - HL_DRV_RESET_FW_FATAL_ERR)) { - /* if there 2 back to back resets from FW, - * ensure driver puts the driver in a unusable state - */ + (hdev->reset_info.prev_reset_trigger == HL_DRV_RESET_FW_FATAL_ERR || + hdev->reset_info.prev_reset_trigger == + HL_DRV_RESET_HEARTBEAT)) { dev_crit(hdev->dev, - "%s Consecutive FW fatal errors received, stopping hard reset\n", + "%s Consecutive fatal errors, stopping hard reset\n", dev_name(&(hdev)->pdev->dev)); rc = -EIO; goto out_err;