habanalabs: Update the device idle check

The patch updates the device idle check:
- Add reading the DMA core status register, because it is possible that
  a QMAN has finished its work but the DMA itself is still running.
- Remove the MME shadow status check, as the MME ARCH status register
  includes the status of all MME shadows.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

3 files changed, 425 insertions, 4 deletions

diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index ce127a6f606f..8653aa914724 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -4893,17 +4893,22 @@ int goya_armcp_info_get(struct hl_device *hdev)
 
 static bool goya_is_device_idle(struct hl_device *hdev, char *buf, size_t size)
 {
-	u64 offset, dma_qm_reg, tpc_qm_reg, tpc_cmdq_reg, tpc_cfg_reg;
+	u64 offset, dma_qm_reg, tpc_qm_reg, tpc_cmdq_reg, tpc_cfg_reg,
+		dma_core_sts;
 	int i;
 
 	offset = mmDMA_QM_1_GLBL_STS0 - mmDMA_QM_0_GLBL_STS0;
 
 	for (i = 0 ; i < DMA_MAX_NUM ; i++) {
 		dma_qm_reg = mmDMA_QM_0_GLBL_STS0 + i * offset;
+		dma_core_sts = mmDMA_CH_0_STS0 + i * offset;
 
 		if ((RREG32(dma_qm_reg) & DMA_QM_IDLE_MASK) !=
 				DMA_QM_IDLE_MASK)
 			return HL_ENG_BUSY(buf, size, "DMA%d_QM", i);
+
+		if (RREG32(dma_core_sts) & DMA_CH_0_STS0_DMA_BUSY_MASK)
+			return HL_ENG_BUSY(buf, size, "DMA%d_CORE", i);
 	}
 
 	offset = mmTPC1_QM_GLBL_STS0 - mmTPC0_QM_GLBL_STS0;
@@ -4938,9 +4943,6 @@ static bool goya_is_device_idle(struct hl_device *hdev, char *buf, size_t size)
 			MME_ARCH_IDLE_MASK)
 		return HL_ENG_BUSY(buf, size, "MME_ARCH");
 
-	if (RREG32(mmMME_SHADOW_0_STATUS) & MME_SHADOW_IDLE_MASK)
-		return HL_ENG_BUSY(buf, size, "MME");
-
 	return true;
 }
 
diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_0_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_0_masks.h
new file mode 100644
index 000000000000..028143408401
--- /dev/null
+++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_0_masks.h
@@ -0,0 +1,418 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright 2016-2018 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ *
+ */
+
+/************************************
+ ** This is an auto-generated file **
+ **       DO NOT EDIT BELOW        **
+ ************************************/
+
+#ifndef ASIC_REG_DMA_CH_0_MASKS_H_
+#define ASIC_REG_DMA_CH_0_MASKS_H_
+
+/*
+ *****************************************
+ *   DMA_CH_0 (Prototype: DMA_CH)
+ *****************************************
+ */
+
+/* DMA_CH_0_CFG0 */
+#define DMA_CH_0_CFG0_RD_MAX_OUTSTAND_SHIFT                          0
+#define DMA_CH_0_CFG0_RD_MAX_OUTSTAND_MASK                           0x3FF
+#define DMA_CH_0_CFG0_WR_MAX_OUTSTAND_SHIFT                          16
+#define DMA_CH_0_CFG0_WR_MAX_OUTSTAND_MASK                           0xFFF0000
+
+/* DMA_CH_0_CFG1 */
+#define DMA_CH_0_CFG1_RD_BUF_MAX_SIZE_SHIFT                          0
+#define DMA_CH_0_CFG1_RD_BUF_MAX_SIZE_MASK                           0x3FF
+
+/* DMA_CH_0_ERRMSG_ADDR_LO */
+#define DMA_CH_0_ERRMSG_ADDR_LO_VAL_SHIFT                            0
+#define DMA_CH_0_ERRMSG_ADDR_LO_VAL_MASK                             0xFFFFFFFF
+
+/* DMA_CH_0_ERRMSG_ADDR_HI */
+#define DMA_CH_0_ERRMSG_ADDR_HI_VAL_SHIFT                            0
+#define DMA_CH_0_ERRMSG_ADDR_HI_VAL_MASK                             0xFFFFFFFF
+
+/* DMA_CH_0_ERRMSG_WDATA */
+#define DMA_CH_0_ERRMSG_WDATA_VAL_SHIFT                              0
+#define DMA_CH_0_ERRMSG_WDATA_VAL_MASK                               0xFFFFFFFF
+
+/* DMA_CH_0_RD_COMP_ADDR_LO */
+#define DMA_CH_0_RD_COMP_ADDR_LO_VAL_SHIFT                           0
+#define DMA_CH_0_RD_COMP_ADDR_LO_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_RD_COMP_ADDR_HI */
+#define DMA_CH_0_RD_COMP_ADDR_HI_VAL_SHIFT                           0
+#define DMA_CH_0_RD_COMP_ADDR_HI_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_RD_COMP_WDATA */
+#define DMA_CH_0_RD_COMP_WDATA_VAL_SHIFT                             0
+#define DMA_CH_0_RD_COMP_WDATA_VAL_MASK                              0xFFFFFFFF
+
+/* DMA_CH_0_WR_COMP_ADDR_LO */
+#define DMA_CH_0_WR_COMP_ADDR_LO_VAL_SHIFT                           0
+#define DMA_CH_0_WR_COMP_ADDR_LO_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_WR_COMP_ADDR_HI */
+#define DMA_CH_0_WR_COMP_ADDR_HI_VAL_SHIFT                           0
+#define DMA_CH_0_WR_COMP_ADDR_HI_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_WR_COMP_WDATA */
+#define DMA_CH_0_WR_COMP_WDATA_VAL_SHIFT                             0
+#define DMA_CH_0_WR_COMP_WDATA_VAL_MASK                              0xFFFFFFFF
+
+/* DMA_CH_0_LDMA_SRC_ADDR_LO */
+#define DMA_CH_0_LDMA_SRC_ADDR_LO_VAL_SHIFT                          0
+#define DMA_CH_0_LDMA_SRC_ADDR_LO_VAL_MASK                           0xFFFFFFFF
+
+/* DMA_CH_0_LDMA_SRC_ADDR_HI */
+#define DMA_CH_0_LDMA_SRC_ADDR_HI_VAL_SHIFT                          0
+#define DMA_CH_0_LDMA_SRC_ADDR_HI_VAL_MASK                           0xFFFFFFFF
+
+/* DMA_CH_0_LDMA_DST_ADDR_LO */
+#define DMA_CH_0_LDMA_DST_ADDR_LO_VAL_SHIFT                          0
+#define DMA_CH_0_LDMA_DST_ADDR_LO_VAL_MASK                           0xFFFFFFFF
+
+/* DMA_CH_0_LDMA_DST_ADDR_HI */
+#define DMA_CH_0_LDMA_DST_ADDR_HI_VAL_SHIFT                          0
+#define DMA_CH_0_LDMA_DST_ADDR_HI_VAL_MASK                           0xFFFFFFFF
+
+/* DMA_CH_0_LDMA_TSIZE */
+#define DMA_CH_0_LDMA_TSIZE_VAL_SHIFT                                0
+#define DMA_CH_0_LDMA_TSIZE_VAL_MASK                                 0xFFFFFFFF
+
+/* DMA_CH_0_COMIT_TRANSFER */
+#define DMA_CH_0_COMIT_TRANSFER_PCI_UPS_WKORDR_SHIFT                 0
+#define DMA_CH_0_COMIT_TRANSFER_PCI_UPS_WKORDR_MASK                  0x1
+#define DMA_CH_0_COMIT_TRANSFER_RD_COMP_EN_SHIFT                     1
+#define DMA_CH_0_COMIT_TRANSFER_RD_COMP_EN_MASK                      0x2
+#define DMA_CH_0_COMIT_TRANSFER_WR_COMP_EN_SHIFT                     2
+#define DMA_CH_0_COMIT_TRANSFER_WR_COMP_EN_MASK                      0x4
+#define DMA_CH_0_COMIT_TRANSFER_NOSNOOP_SHIFT                        3
+#define DMA_CH_0_COMIT_TRANSFER_NOSNOOP_MASK                         0x8
+#define DMA_CH_0_COMIT_TRANSFER_SRC_ADDR_INC_DIS_SHIFT               4
+#define DMA_CH_0_COMIT_TRANSFER_SRC_ADDR_INC_DIS_MASK                0x10
+#define DMA_CH_0_COMIT_TRANSFER_DST_ADDR_INC_DIS_SHIFT               5
+#define DMA_CH_0_COMIT_TRANSFER_DST_ADDR_INC_DIS_MASK                0x20
+#define DMA_CH_0_COMIT_TRANSFER_MEM_SET_SHIFT                        6
+#define DMA_CH_0_COMIT_TRANSFER_MEM_SET_MASK                         0x40
+#define DMA_CH_0_COMIT_TRANSFER_MOD_TENSOR_SHIFT                     15
+#define DMA_CH_0_COMIT_TRANSFER_MOD_TENSOR_MASK                      0x8000
+#define DMA_CH_0_COMIT_TRANSFER_CTL_SHIFT                            16
+#define DMA_CH_0_COMIT_TRANSFER_CTL_MASK                             0xFFFF0000
+
+/* DMA_CH_0_STS0 */
+#define DMA_CH_0_STS0_DMA_BUSY_SHIFT                                 0
+#define DMA_CH_0_STS0_DMA_BUSY_MASK                                  0x1
+#define DMA_CH_0_STS0_RD_STS_CTX_FULL_SHIFT                          1
+#define DMA_CH_0_STS0_RD_STS_CTX_FULL_MASK                           0x2
+#define DMA_CH_0_STS0_WR_STS_CTX_FULL_SHIFT                          2
+#define DMA_CH_0_STS0_WR_STS_CTX_FULL_MASK                           0x4
+
+/* DMA_CH_0_STS1 */
+#define DMA_CH_0_STS1_RD_STS_CTX_CNT_SHIFT                           0
+#define DMA_CH_0_STS1_RD_STS_CTX_CNT_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_STS2 */
+#define DMA_CH_0_STS2_WR_STS_CTX_CNT_SHIFT                           0
+#define DMA_CH_0_STS2_WR_STS_CTX_CNT_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_STS3 */
+#define DMA_CH_0_STS3_RD_STS_TRN_CNT_SHIFT                           0
+#define DMA_CH_0_STS3_RD_STS_TRN_CNT_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_STS4 */
+#define DMA_CH_0_STS4_WR_STS_TRN_CNT_SHIFT                           0
+#define DMA_CH_0_STS4_WR_STS_TRN_CNT_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_SRC_ADDR_LO_STS */
+#define DMA_CH_0_SRC_ADDR_LO_STS_VAL_SHIFT                           0
+#define DMA_CH_0_SRC_ADDR_LO_STS_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_SRC_ADDR_HI_STS */
+#define DMA_CH_0_SRC_ADDR_HI_STS_VAL_SHIFT                           0
+#define DMA_CH_0_SRC_ADDR_HI_STS_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_SRC_TSIZE_STS */
+#define DMA_CH_0_SRC_TSIZE_STS_VAL_SHIFT                             0
+#define DMA_CH_0_SRC_TSIZE_STS_VAL_MASK                              0xFFFFFFFF
+
+/* DMA_CH_0_DST_ADDR_LO_STS */
+#define DMA_CH_0_DST_ADDR_LO_STS_VAL_SHIFT                           0
+#define DMA_CH_0_DST_ADDR_LO_STS_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_DST_ADDR_HI_STS */
+#define DMA_CH_0_DST_ADDR_HI_STS_VAL_SHIFT                           0
+#define DMA_CH_0_DST_ADDR_HI_STS_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_DST_TSIZE_STS */
+#define DMA_CH_0_DST_TSIZE_STS_VAL_SHIFT                             0
+#define DMA_CH_0_DST_TSIZE_STS_VAL_MASK                              0xFFFFFFFF
+
+/* DMA_CH_0_RD_RATE_LIM_EN */
+#define DMA_CH_0_RD_RATE_LIM_EN_VAL_SHIFT                            0
+#define DMA_CH_0_RD_RATE_LIM_EN_VAL_MASK                             0x1
+
+/* DMA_CH_0_RD_RATE_LIM_RST_TOKEN */
+#define DMA_CH_0_RD_RATE_LIM_RST_TOKEN_VAL_SHIFT                     0
+#define DMA_CH_0_RD_RATE_LIM_RST_TOKEN_VAL_MASK                      0xFFFF
+
+/* DMA_CH_0_RD_RATE_LIM_SAT */
+#define DMA_CH_0_RD_RATE_LIM_SAT_VAL_SHIFT                           0
+#define DMA_CH_0_RD_RATE_LIM_SAT_VAL_MASK                            0xFFFF
+
+/* DMA_CH_0_RD_RATE_LIM_TOUT */
+#define DMA_CH_0_RD_RATE_LIM_TOUT_VAL_SHIFT                          0
+#define DMA_CH_0_RD_RATE_LIM_TOUT_VAL_MASK                           0x7FFFFFFF
+
+/* DMA_CH_0_WR_RATE_LIM_EN */
+#define DMA_CH_0_WR_RATE_LIM_EN_VAL_SHIFT                            0
+#define DMA_CH_0_WR_RATE_LIM_EN_VAL_MASK                             0x1
+
+/* DMA_CH_0_WR_RATE_LIM_RST_TOKEN */
+#define DMA_CH_0_WR_RATE_LIM_RST_TOKEN_VAL_SHIFT                     0
+#define DMA_CH_0_WR_RATE_LIM_RST_TOKEN_VAL_MASK                      0xFFFF
+
+/* DMA_CH_0_WR_RATE_LIM_SAT */
+#define DMA_CH_0_WR_RATE_LIM_SAT_VAL_SHIFT                           0
+#define DMA_CH_0_WR_RATE_LIM_SAT_VAL_MASK                            0xFFFF
+
+/* DMA_CH_0_WR_RATE_LIM_TOUT */
+#define DMA_CH_0_WR_RATE_LIM_TOUT_VAL_SHIFT                          0
+#define DMA_CH_0_WR_RATE_LIM_TOUT_VAL_MASK                           0x7FFFFFFF
+
+/* DMA_CH_0_CFG2 */
+#define DMA_CH_0_CFG2_FORCE_WORD_SHIFT                               0
+#define DMA_CH_0_CFG2_FORCE_WORD_MASK                                0x1
+
+/* DMA_CH_0_TDMA_CTL */
+#define DMA_CH_0_TDMA_CTL_DTYPE_SHIFT                                0
+#define DMA_CH_0_TDMA_CTL_DTYPE_MASK                                 0x7
+
+/* DMA_CH_0_TDMA_SRC_BASE_ADDR_LO */
+#define DMA_CH_0_TDMA_SRC_BASE_ADDR_LO_VAL_SHIFT                     0
+#define DMA_CH_0_TDMA_SRC_BASE_ADDR_LO_VAL_MASK                      0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_BASE_ADDR_HI */
+#define DMA_CH_0_TDMA_SRC_BASE_ADDR_HI_VAL_SHIFT                     0
+#define DMA_CH_0_TDMA_SRC_BASE_ADDR_HI_VAL_MASK                      0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_BASE_0 */
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_0_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_0_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_SIZE_0 */
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_0_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_0_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_0 */
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_0_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_0_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_START_OFFSET_0 */
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_0_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_0_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_STRIDE_0 */
+#define DMA_CH_0_TDMA_SRC_STRIDE_0_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_SRC_STRIDE_0_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_BASE_1 */
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_1_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_1_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_SIZE_1 */
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_1_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_1_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_1 */
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_1_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_1_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_START_OFFSET_1 */
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_1_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_1_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_STRIDE_1 */
+#define DMA_CH_0_TDMA_SRC_STRIDE_1_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_SRC_STRIDE_1_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_BASE_2 */
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_2_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_2_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_SIZE_2 */
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_2_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_2_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_2 */
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_2_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_2_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_START_OFFSET_2 */
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_2_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_2_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_STRIDE_2 */
+#define DMA_CH_0_TDMA_SRC_STRIDE_2_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_SRC_STRIDE_2_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_BASE_3 */
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_3_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_3_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_SIZE_3 */
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_3_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_3_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_3 */
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_3_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_3_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_START_OFFSET_3 */
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_3_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_3_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_STRIDE_3 */
+#define DMA_CH_0_TDMA_SRC_STRIDE_3_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_SRC_STRIDE_3_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_BASE_4 */
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_4_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_4_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_SIZE_4 */
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_4_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_4_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_4 */
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_4_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_4_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_START_OFFSET_4 */
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_4_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_4_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_STRIDE_4 */
+#define DMA_CH_0_TDMA_SRC_STRIDE_4_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_SRC_STRIDE_4_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_BASE_ADDR_LO */
+#define DMA_CH_0_TDMA_DST_BASE_ADDR_LO_VAL_SHIFT                     0
+#define DMA_CH_0_TDMA_DST_BASE_ADDR_LO_VAL_MASK                      0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_BASE_ADDR_HI */
+#define DMA_CH_0_TDMA_DST_BASE_ADDR_HI_VAL_SHIFT                     0
+#define DMA_CH_0_TDMA_DST_BASE_ADDR_HI_VAL_MASK                      0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_BASE_0 */
+#define DMA_CH_0_TDMA_DST_ROI_BASE_0_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_BASE_0_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_SIZE_0 */
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_0_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_0_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_VALID_ELEMENTS_0 */
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_0_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_0_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_START_OFFSET_0 */
+#define DMA_CH_0_TDMA_DST_START_OFFSET_0_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_DST_START_OFFSET_0_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_STRIDE_0 */
+#define DMA_CH_0_TDMA_DST_STRIDE_0_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_DST_STRIDE_0_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_BASE_1 */
+#define DMA_CH_0_TDMA_DST_ROI_BASE_1_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_BASE_1_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_SIZE_1 */
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_1_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_1_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_VALID_ELEMENTS_1 */
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_1_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_1_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_START_OFFSET_1 */
+#define DMA_CH_0_TDMA_DST_START_OFFSET_1_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_DST_START_OFFSET_1_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_STRIDE_1 */
+#define DMA_CH_0_TDMA_DST_STRIDE_1_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_DST_STRIDE_1_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_BASE_2 */
+#define DMA_CH_0_TDMA_DST_ROI_BASE_2_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_BASE_2_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_SIZE_2 */
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_2_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_2_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_VALID_ELEMENTS_2 */
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_2_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_2_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_START_OFFSET_2 */
+#define DMA_CH_0_TDMA_DST_START_OFFSET_2_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_DST_START_OFFSET_2_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_STRIDE_2 */
+#define DMA_CH_0_TDMA_DST_STRIDE_2_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_DST_STRIDE_2_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_BASE_3 */
+#define DMA_CH_0_TDMA_DST_ROI_BASE_3_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_BASE_3_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_SIZE_3 */
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_3_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_3_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_VALID_ELEMENTS_3 */
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_3_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_3_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_START_OFFSET_3 */
+#define DMA_CH_0_TDMA_DST_START_OFFSET_3_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_DST_START_OFFSET_3_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_STRIDE_3 */
+#define DMA_CH_0_TDMA_DST_STRIDE_3_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_DST_STRIDE_3_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_BASE_4 */
+#define DMA_CH_0_TDMA_DST_ROI_BASE_4_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_BASE_4_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_SIZE_4 */
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_4_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_4_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_VALID_ELEMENTS_4 */
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_4_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_4_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_START_OFFSET_4 */
+#define DMA_CH_0_TDMA_DST_START_OFFSET_4_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_DST_START_OFFSET_4_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_STRIDE_4 */
+#define DMA_CH_0_TDMA_DST_STRIDE_4_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_DST_STRIDE_4_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_MEM_INIT_BUSY */
+#define DMA_CH_0_MEM_INIT_BUSY_SBC_DATA_SHIFT                        0
+#define DMA_CH_0_MEM_INIT_BUSY_SBC_DATA_MASK                         0xFF
+#define DMA_CH_0_MEM_INIT_BUSY_SBC_MD_SHIFT                          8
+#define DMA_CH_0_MEM_INIT_BUSY_SBC_MD_MASK                           0x100
+
+#endif /* ASIC_REG_DMA_CH_0_MASKS_H_ */
diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h
index 506e71e201e1..19b0f0ef1d0b 100644
--- a/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h
+++ b/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h
@@ -88,6 +88,7 @@
 #include "psoc_global_conf_masks.h"
 #include "dma_macro_masks.h"
 #include "dma_qm_0_masks.h"
+#include "dma_ch_0_masks.h"
 #include "tpc0_qm_masks.h"
 #include "tpc0_cmdq_masks.h"
 #include "mme_qm_masks.h"