accel/habanalabs: fix handling of arc farm sei event

There is only single eq entry for arc farm sei event which aggregates
events from the four arc farms.
Fix the code to handle this event according to this behavior.

Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index da1b2e6dd6839459ceecaab2499ceb4129409dcb..b318c67dae134e2d20d12d94ad34bc4a3bab7cd6 100644 (file)
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -8490,23 +8490,28 @@ static int gaudi2_handle_qman_err(struct hl_device *hdev, u16 event_type, u64 *e
 
 static int gaudi2_handle_arc_farm_sei_err(struct hl_device *hdev, u16 event_type)
 {
-       u32 i, sts_val, sts_clr_val = 0, error_count = 0;
+       u32 i, sts_val, sts_clr_val, error_count = 0, arc_farm;
 
-       sts_val = RREG32(mmARC_FARM_ARC0_AUX_ARC_SEI_INTR_STS);
+       for (arc_farm = 0 ; arc_farm < NUM_OF_ARC_FARMS_ARC ; arc_farm++) {
+               sts_clr_val = 0;
+               sts_val = RREG32(mmARC_FARM_ARC0_AUX_ARC_SEI_INTR_STS +
+                               (arc_farm * ARC_FARM_OFFSET));
 
-       for (i = 0 ; i < GAUDI2_NUM_OF_ARC_SEI_ERR_CAUSE ; i++) {
-               if (sts_val & BIT(i)) {
-                       gaudi2_print_event(hdev, event_type, true,
-                               "err cause: %s", gaudi2_arc_sei_error_cause[i]);
-                       sts_clr_val |= BIT(i);
-                       error_count++;
+               for (i = 0 ; i < GAUDI2_NUM_OF_ARC_SEI_ERR_CAUSE ; i++) {
+                       if (sts_val & BIT(i)) {
+                               gaudi2_print_event(hdev, event_type, true,
+                                               "ARC FARM ARC %u err cause: %s",
+                                               arc_farm, gaudi2_arc_sei_error_cause[i]);
+                               sts_clr_val |= BIT(i);
+                               error_count++;
+                       }
                }
+               WREG32(mmARC_FARM_ARC0_AUX_ARC_SEI_INTR_CLR + (arc_farm * ARC_FARM_OFFSET),
+                               sts_clr_val);
        }
 
        hl_check_for_glbl_errors(hdev);
 
-       WREG32(mmARC_FARM_ARC0_AUX_ARC_SEI_INTR_CLR, sts_clr_val);
-
        return error_count;
 }
 

diff --git a/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h b/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
index 452b379f39f68d069ac13e20e7d2654cb06b0879..6c58af614236446929ccf3c5dfba52bb47b4ff5a 100644 (file)
--- a/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
+++ b/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0
  *
- * Copyright 2020-2022 HabanaLabs, Ltd.
+ * Copyright 2020-2023 HabanaLabs, Ltd.
  * All Rights Reserved.
  *
  */
@@ -543,6 +543,8 @@
 #define HBM_MC_SPI_IEEE1500_COMP_MASK          BIT(3)
 #define HBM_MC_SPI_IEEE1500_PAUSED_MASK                BIT(4)
 
+#define ARC_FARM_OFFSET (mmARC_FARM_ARC1_AUX_BASE - mmARC_FARM_ARC0_AUX_BASE)
+
 #include "nic0_qpc0_regs.h"
 #include "nic0_qm0_regs.h"
 #include "nic0_qm_arc_aux0_regs.h"