habanalabs: skip DISABLE PCI packet to FW on heartbeat

if reset is due to heartbeat, device CPU is no responsive in which
case no point sending PCI disable message to it.

Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

1 files changed, 17 insertions, 23 deletions

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index eee9387c8a26..37e3f4cd05c0 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -7380,18 +7380,14 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 	case GAUDI_EVENT_MMU_DERR:
 		gaudi_print_irq_info(hdev, event_type, true);
 		gaudi_handle_ecc_event(hdev, event_type, &eq_entry->ecc_data);
-		if (hdev->hard_reset_on_fw_events)
-			hl_device_reset(hdev, true, false);
-		break;
+		goto reset_device;
 
 	case GAUDI_EVENT_GIC500:
 	case GAUDI_EVENT_AXI_ECC:
 	case GAUDI_EVENT_L2_RAM_ECC:
 	case GAUDI_EVENT_PLL0 ... GAUDI_EVENT_PLL17:
 		gaudi_print_irq_info(hdev, event_type, false);
-		if (hdev->hard_reset_on_fw_events)
-			hl_device_reset(hdev, true, false);
-		break;
+		goto reset_device;
 
 	case GAUDI_EVENT_HBM0_SPI_0:
 	case GAUDI_EVENT_HBM1_SPI_0:
@@ -7401,9 +7397,7 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 		gaudi_hbm_read_interrupts(hdev,
 				gaudi_hbm_event_to_dev(event_type),
 				&eq_entry->hbm_ecc_data);
-		if (hdev->hard_reset_on_fw_events)
-			hl_device_reset(hdev, true, false);
-		break;
+		goto reset_device;
 
 	case GAUDI_EVENT_HBM0_SPI_1:
 	case GAUDI_EVENT_HBM1_SPI_1:
@@ -7432,8 +7426,7 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 			dev_err(hdev->dev, "hard reset required due to %s\n",
 				gaudi_irq_map_table[event_type].name);
 
-			if (hdev->hard_reset_on_fw_events)
-				hl_device_reset(hdev, true, false);
+			goto reset_device;
 		} else {
 			hl_fw_unmask_irq(hdev, event_type);
 		}
@@ -7455,8 +7448,7 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 			dev_err(hdev->dev, "hard reset required due to %s\n",
 				gaudi_irq_map_table[event_type].name);
 
-			if (hdev->hard_reset_on_fw_events)
-				hl_device_reset(hdev, true, false);
+			goto reset_device;
 		} else {
 			hl_fw_unmask_irq(hdev, event_type);
 		}
@@ -7525,9 +7517,7 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 
 	case GAUDI_EVENT_RAZWI_OR_ADC_SW:
 		gaudi_print_irq_info(hdev, event_type, true);
-		if (hdev->hard_reset_on_fw_events)
-			hl_device_reset(hdev, true, false);
-		break;
+		goto reset_device;
 
 	case GAUDI_EVENT_TPC0_BMON_SPMU:
 	case GAUDI_EVENT_TPC1_BMON_SPMU:
@@ -7564,17 +7554,21 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 	case GAUDI_EVENT_PKT_QUEUE_OUT_SYNC:
 		gaudi_print_irq_info(hdev, event_type, false);
 		gaudi_print_out_of_sync_info(hdev, &eq_entry->pkt_sync_err);
-		if (hdev->hard_reset_on_fw_events)
-			hl_device_reset(hdev, true, false);
-		else
-			hl_fw_unmask_irq(hdev, event_type);
-		break;
+		goto reset_device;
 
 	default:
 		dev_err(hdev->dev, "Received invalid H/W interrupt %d\n",
 				event_type);
 		break;
 	}
+
+	return;
+
+reset_device:
+	if (hdev->hard_reset_on_fw_events)
+		hl_device_reset(hdev, HL_RESET_HARD);
+	else
+		hl_fw_unmask_irq(hdev, event_type);
 }
 
 static void *gaudi_get_events_stat(struct hl_device *hdev, bool aggregate,
@@ -7625,7 +7619,7 @@ static int gaudi_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard,
 	if (rc) {
 		dev_err_ratelimited(hdev->dev,
 					"MMU cache invalidation timeout\n");
-		hl_device_reset(hdev, true, false);
+		hl_device_reset(hdev, HL_RESET_HARD);
 	}
 
 	return rc;
@@ -7674,7 +7668,7 @@ static int gaudi_mmu_invalidate_cache_range(struct hl_device *hdev,
 	if (rc) {
 		dev_err_ratelimited(hdev->dev,
 					"MMU cache invalidation timeout\n");
-		hl_device_reset(hdev, true, false);
+		hl_device_reset(hdev, HL_RESET_HARD);
 	}
 
 	return rc;