habanalabs: set TPC Icache to 16 cache lines

Reduce latency to memory during TPC kernel execution.
Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: NTomer Tayar <ttayar@habana.ai>

drivers/misc/habanalabs/goya/goya.c

@@ -1457,6 +1457,9 @@ static void goya_init_golden_registers(struct hl_device *hdev)
 				1 << TPC0_NRTR_SCRAMB_EN_VAL_SHIFT);
 		WREG32(mmTPC0_NRTR_NON_LIN_SCRAMB + offset,
 				1 << TPC0_NRTR_NON_LIN_SCRAMB_EN_SHIFT);
+
+		WREG32_FIELD(TPC0_CFG_MSS_CONFIG, offset,
+				ICACHE_FETCH_LINE_NUM, 2);
 	}
 
 	WREG32(mmDMA_NRTR_SCRAMB_EN, 1 << DMA_NRTR_SCRAMB_EN_VAL_SHIFT);

drivers/misc/habanalabs/habanalabs.h

@@ -1062,9 +1062,10 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
 
 #define REG_FIELD_SHIFT(reg, field) reg##_##field##_SHIFT
 #define REG_FIELD_MASK(reg, field) reg##_##field##_MASK
-#define WREG32_FIELD(reg, field, val)	\
-	WREG32(mm##reg, (RREG32(mm##reg) & ~REG_FIELD_MASK(reg, field)) | \
-			(val) << REG_FIELD_SHIFT(reg, field))
+#define WREG32_FIELD(reg, offset, field, val)	\
+	WREG32(mm##reg + offset, (RREG32(mm##reg + offset) & \
+				~REG_FIELD_MASK(reg, field)) | \
+				(val) << REG_FIELD_SHIFT(reg, field))
 
 /* Timeout should be longer when working with simulator but cap the
  * increased timeout to some maximum