From 988262ef2fb9b43719ce40af1efe9bfbc62b461c Mon Sep 17 00:00:00 2001 From: farah kassabri Date: Tue, 23 Aug 2022 17:41:52 +0300 Subject: [PATCH] habanalabs/gaudi2: log critical events with no rate limit When we have a storm of errors of HBM ECC SERR we can reach a situation where driver start hard reset flow without logging the error cause that caused the hard reset due to logs rate limiting. Signed-off-by: farah kassabri Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/gaudi2/gaudi2.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/misc/habanalabs/gaudi2/gaudi2.c b/drivers/misc/habanalabs/gaudi2/gaudi2.c index ff0f9e9..6bebd5e 100644 --- a/drivers/misc/habanalabs/gaudi2/gaudi2.c +++ b/drivers/misc/habanalabs/gaudi2/gaudi2.c @@ -8200,10 +8200,17 @@ static bool gaudi2_handle_hbm_mc_sei_err(struct hl_device *hdev, u16 event_type, return true; } - dev_err_ratelimited(hdev->dev, - "System Error Interrupt - HBM(%u) MC(%u) MC_CH(%u) MC_PC(%u). Critical(%u). Error cause: %s\n", - hbm_id, mc_id, sei_data->hdr.mc_channel, sei_data->hdr.mc_pseudo_channel, - sei_data->hdr.is_critical, hbm_mc_sei_cause[cause_idx]); + if (sei_data->hdr.is_critical) + dev_err(hdev->dev, + "System Critical Error Interrupt - HBM(%u) MC(%u) MC_CH(%u) MC_PC(%u). Error cause: %s\n", + hbm_id, mc_id, sei_data->hdr.mc_channel, sei_data->hdr.mc_pseudo_channel, + hbm_mc_sei_cause[cause_idx]); + + else + dev_err_ratelimited(hdev->dev, + "System Non-Critical Error Interrupt - HBM(%u) MC(%u) MC_CH(%u) MC_PC(%u). Error cause: %s\n", + hbm_id, mc_id, sei_data->hdr.mc_channel, sei_data->hdr.mc_pseudo_channel, + hbm_mc_sei_cause[cause_idx]); /* Print error-specific info */ switch (cause_idx) { -- 2.7.4