diff mbox series

[02/14] accel/habanalabs/gaudi2: include block id in ECC error reporting

Message ID 20230918091321.855943-2-ogabbay@kernel.org (mailing list archive)
State New, archived
Headers show
Series [01/14] accel/habanalabs: improve etf configuration | expand

Commit Message

Oded Gabbay Sept. 18, 2023, 9:13 a.m. UTC 
From: Ofir Bitton <obitton@habana.ai>

During ECC event handling, Memory wrapper id was mistakenly
printed as block id. Fix the print and in addition fetch the actual
block-id from firmware.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/gaudi2/gaudi2.c      | 23 +++++++++++++++----
 .../habanalabs/include/common/cpucp_if.h      |  3 ++-
 2 files changed, 20 insertions(+), 6 deletions(-)
diff mbox series

Patch

diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index d60389b6700f..dca19be42d5f 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -7834,16 +7834,29 @@  static void gaudi2_print_event(struct hl_device *hdev, u16 event_type,
 static bool gaudi2_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 		struct hl_eq_ecc_data *ecc_data)
 {
-	u64 ecc_address = 0, ecc_syndrom = 0;
+	u64 ecc_address = 0, ecc_syndrome = 0;
 	u8 memory_wrapper_idx = 0;
+	bool has_block_id = false;
+	u16 block_id;
+
+	if (!hl_is_fw_sw_ver_below(hdev, 1, 12))
+		has_block_id = true;
 
 	ecc_address = le64_to_cpu(ecc_data->ecc_address);
-	ecc_syndrom = le64_to_cpu(ecc_data->ecc_syndrom);
+	ecc_syndrome = le64_to_cpu(ecc_data->ecc_syndrom);
 	memory_wrapper_idx = ecc_data->memory_wrapper_idx;
 
-	gaudi2_print_event(hdev, event_type, !ecc_data->is_critical,
-		"ECC error detected. address: %#llx. Syndrom: %#llx. block id %u. critical %u.",
-		ecc_address, ecc_syndrom, memory_wrapper_idx, ecc_data->is_critical);
+	if (has_block_id) {
+		block_id = le16_to_cpu(ecc_data->block_id);
+		gaudi2_print_event(hdev, event_type, !ecc_data->is_critical,
+			"ECC error detected. address: %#llx. Syndrome: %#llx. wrapper id %u. block id %#x. critical %u.",
+			ecc_address, ecc_syndrome, memory_wrapper_idx, block_id,
+			ecc_data->is_critical);
+	} else {
+		gaudi2_print_event(hdev, event_type, !ecc_data->is_critical,
+			"ECC error detected. address: %#llx. Syndrome: %#llx. wrapper id %u. critical %u.",
+			ecc_address, ecc_syndrome, memory_wrapper_idx, ecc_data->is_critical);
+	}
 
 	return !!ecc_data->is_critical;
 }
diff --git a/drivers/accel/habanalabs/include/common/cpucp_if.h b/drivers/accel/habanalabs/include/common/cpucp_if.h
index 33807b839c37..ef7d32224066 100644
--- a/drivers/accel/habanalabs/include/common/cpucp_if.h
+++ b/drivers/accel/habanalabs/include/common/cpucp_if.h
@@ -69,7 +69,8 @@  struct hl_eq_ecc_data {
 	__le64 ecc_syndrom;
 	__u8 memory_wrapper_idx;
 	__u8 is_critical;
-	__u8 pad[6];
+	__le16 block_id;
+	__u8 pad[4];
 };
 
 enum hl_sm_sei_cause {