[v2 12/30] dma/dpaa2: move the qdma header to common place

[Gagandeep Singh <g.singh@nxp.com>]

From: Jun Yang <jun.yang@nxp.com>

Include rte_pmd_dpaax_qdma.h instead of rte_pmd_dpaa2_qdma.h
and change code accordingly.

Signed-off-by: Jun Yang <jun.yang@nxp.com>
---
 doc/api/doxy-api-index.md                 |  2 +-
 doc/api/doxy-api.conf.in                  |  2 +-
 drivers/common/dpaax/meson.build          |  3 +-
 drivers/common/dpaax/rte_pmd_dpaax_qdma.h | 23 +++++++
 drivers/dma/dpaa2/dpaa2_qdma.c            | 84 +++++++++++------------
 drivers/dma/dpaa2/dpaa2_qdma.h            | 10 +--
 drivers/dma/dpaa2/meson.build             |  4 +-
 drivers/dma/dpaa2/rte_pmd_dpaa2_qdma.h    | 23 -------
 8 files changed, 72 insertions(+), 79 deletions(-)
 create mode 100644 drivers/common/dpaax/rte_pmd_dpaax_qdma.h
 delete mode 100644 drivers/dma/dpaa2/rte_pmd_dpaa2_qdma.h

diff --git a/doc/api/doxy-api-index.md b/doc/api/doxy-api-index.md
index f9283154f8..ab42440733 100644
--- a/doc/api/doxy-api-index.md
+++ b/doc/api/doxy-api-index.md
@@ -57,7 +57,7 @@ The public API headers are grouped by topics:
   [mlx5](@ref rte_pmd_mlx5.h),
   [dpaa2_mempool](@ref rte_dpaa2_mempool.h),
   [dpaa2_cmdif](@ref rte_pmd_dpaa2_cmdif.h),
-  [dpaa2_qdma](@ref rte_pmd_dpaa2_qdma.h),
+  [dpaax](@ref rte_pmd_dpaax_qdma.h),
   [crypto_scheduler](@ref rte_cryptodev_scheduler.h),
   [dlb2](@ref rte_pmd_dlb2.h),
   [ifpga](@ref rte_pmd_ifpga.h)
diff --git a/doc/api/doxy-api.conf.in b/doc/api/doxy-api.conf.in
index a8823c046f..33250d867c 100644
--- a/doc/api/doxy-api.conf.in
+++ b/doc/api/doxy-api.conf.in
@@ -8,7 +8,7 @@ INPUT                   = @TOPDIR@/doc/api/doxy-api-index.md \
                           @TOPDIR@/drivers/bus/vdev \
                           @TOPDIR@/drivers/crypto/cnxk \
                           @TOPDIR@/drivers/crypto/scheduler \
-                          @TOPDIR@/drivers/dma/dpaa2 \
+                          @TOPDIR@/drivers/common/dpaax \
                           @TOPDIR@/drivers/event/dlb2 \
                           @TOPDIR@/drivers/event/cnxk \
                           @TOPDIR@/drivers/mempool/cnxk \
diff --git a/drivers/common/dpaax/meson.build b/drivers/common/dpaax/meson.build
index a162779116..db61b76ce3 100644
--- a/drivers/common/dpaax/meson.build
+++ b/drivers/common/dpaax/meson.build
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: BSD-3-Clause
-# Copyright(c) 2018 NXP
+# Copyright 2018, 2024 NXP
 
 if not is_linux
     build = false
@@ -16,3 +16,4 @@ endif
 if cc.has_argument('-Wno-pointer-arith')
     cflags += '-Wno-pointer-arith'
 endif
+headers = files('rte_pmd_dpaax_qdma.h')
diff --git a/drivers/common/dpaax/rte_pmd_dpaax_qdma.h b/drivers/common/dpaax/rte_pmd_dpaax_qdma.h
new file mode 100644
index 0000000000..2552a4adfb
--- /dev/null
+++ b/drivers/common/dpaax/rte_pmd_dpaax_qdma.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2021-2024 NXP
+ */
+
+#ifndef _RTE_PMD_DPAAX_QDMA_H_
+#define _RTE_PMD_DPAAX_QDMA_H_
+
+#include <rte_compat.h>
+
+#define RTE_DPAAX_QDMA_COPY_IDX_OFFSET 8
+#define RTE_DPAAX_QDMA_SG_IDX_ADDR_ALIGN \
+	RTE_BIT64(RTE_DPAAX_QDMA_COPY_IDX_OFFSET)
+#define RTE_DPAAX_QDMA_SG_IDX_ADDR_MASK \
+	(RTE_DPAAX_QDMA_SG_IDX_ADDR_ALIGN - 1)
+#define RTE_DPAAX_QDMA_SG_SUBMIT(idx_addr, flag) \
+	(((uint64_t)idx_addr) | (flag))
+
+#define RTE_DPAAX_QDMA_COPY_SUBMIT(idx, flag) \
+	((idx << RTE_DPAAX_QDMA_COPY_IDX_OFFSET) | (flag))
+
+#define RTE_DPAAX_QDMA_JOB_SUBMIT_MAX 64
+#define RTE_DMA_CAPA_DPAAX_QDMA_FLAGS_INDEX RTE_BIT64(63)
+#endif /* _RTE_PMD_DPAAX_QDMA_H_ */
diff --git a/drivers/dma/dpaa2/dpaa2_qdma.c b/drivers/dma/dpaa2/dpaa2_qdma.c
index b70750fede..19d8af9416 100644
--- a/drivers/dma/dpaa2/dpaa2_qdma.c
+++ b/drivers/dma/dpaa2/dpaa2_qdma.c
@@ -10,7 +10,7 @@
 
 #include <mc/fsl_dpdmai.h>
 
-#include "rte_pmd_dpaa2_qdma.h"
+#include <rte_pmd_dpaax_qdma.h>
 #include "dpaa2_qdma.h"
 #include "dpaa2_qdma_logs.h"
 
@@ -212,16 +212,16 @@ fle_sdd_pre_populate(struct qdma_cntx_fle_sdd *fle_sdd,
 	}
 	/* source frame list to source buffer */
 	DPAA2_SET_FLE_ADDR(&fle[DPAA2_QDMA_SRC_FLE], src);
-#ifdef RTE_LIBRTE_DPAA2_USE_PHYS_IOVA
-	DPAA2_SET_FLE_BMT(&fle[DPAA2_QDMA_SRC_FLE]);
-#endif
+	/** IOMMU is always on for either VA or PA mode,
+	 * so Bypass Memory Translation should be disabled.
+	 *
+	 * DPAA2_SET_FLE_BMT(&fle[DPAA2_QDMA_SRC_FLE]);
+	 * DPAA2_SET_FLE_BMT(&fle[DPAA2_QDMA_DST_FLE]);
+	 */
 	fle[DPAA2_QDMA_SRC_FLE].word4.fmt = fmt;
 
 	/* destination frame list to destination buffer */
 	DPAA2_SET_FLE_ADDR(&fle[DPAA2_QDMA_DST_FLE], dest);
-#ifdef RTE_LIBRTE_DPAA2_USE_PHYS_IOVA
-	DPAA2_SET_FLE_BMT(&fle[DPAA2_QDMA_DST_FLE]);
-#endif
 	fle[DPAA2_QDMA_DST_FLE].word4.fmt = fmt;
 
 	/* Final bit: 1, for last frame list */
@@ -235,23 +235,21 @@ sg_entry_pre_populate(struct qdma_cntx_sg *sg_cntx)
 	struct qdma_sg_entry *src_sge = sg_cntx->sg_src_entry;
 	struct qdma_sg_entry *dst_sge = sg_cntx->sg_dst_entry;
 
-	for (i = 0; i < RTE_DPAA2_QDMA_JOB_SUBMIT_MAX; i++) {
+	for (i = 0; i < RTE_DPAAX_QDMA_JOB_SUBMIT_MAX; i++) {
 		/* source SG */
 		src_sge[i].ctrl.sl = QDMA_SG_SL_LONG;
 		src_sge[i].ctrl.fmt = QDMA_SG_FMT_SDB;
-#ifdef RTE_LIBRTE_DPAA2_USE_PHYS_IOVA
-		src_sge[i].ctrl.bmt = QDMA_SG_BMT_ENABLE;
-#else
+		/** IOMMU is always on for either VA or PA mode,
+		 * so Bypass Memory Translation should be disabled.
+		 */
 		src_sge[i].ctrl.bmt = QDMA_SG_BMT_DISABLE;
-#endif
 		/* destination SG */
 		dst_sge[i].ctrl.sl = QDMA_SG_SL_LONG;
 		dst_sge[i].ctrl.fmt = QDMA_SG_FMT_SDB;
-#ifdef RTE_LIBRTE_DPAA2_USE_PHYS_IOVA
-		dst_sge[i].ctrl.bmt = QDMA_SG_BMT_ENABLE;
-#else
+		/** IOMMU is always on for either VA or PA mode,
+		 * so Bypass Memory Translation should be disabled.
+		 */
 		dst_sge[i].ctrl.bmt = QDMA_SG_BMT_DISABLE;
-#endif
 	}
 }
 
@@ -350,21 +348,19 @@ sg_entry_populate(const struct rte_dma_sge *src,
 		src_sge->data_len.data_len_sl0 = src[i].length;
 		src_sge->ctrl.sl = QDMA_SG_SL_LONG;
 		src_sge->ctrl.fmt = QDMA_SG_FMT_SDB;
-#ifdef RTE_LIBRTE_DPAA2_USE_PHYS_IOVA
-		src_sge->ctrl.bmt = QDMA_SG_BMT_ENABLE;
-#else
+		/** IOMMU is always on for either VA or PA mode,
+		 * so Bypass Memory Translation should be disabled.
+		 */
 		src_sge->ctrl.bmt = QDMA_SG_BMT_DISABLE;
-#endif
 		dst_sge->addr_lo = (uint32_t)dst[i].addr;
 		dst_sge->addr_hi = (dst[i].addr >> 32);
 		dst_sge->data_len.data_len_sl0 = dst[i].length;
 		dst_sge->ctrl.sl = QDMA_SG_SL_LONG;
 		dst_sge->ctrl.fmt = QDMA_SG_FMT_SDB;
-#ifdef RTE_LIBRTE_DPAA2_USE_PHYS_IOVA
-		dst_sge->ctrl.bmt = QDMA_SG_BMT_ENABLE;
-#else
+		/** IOMMU is always on for either VA or PA mode,
+		 * so Bypass Memory Translation should be disabled.
+		 */
 		dst_sge->ctrl.bmt = QDMA_SG_BMT_DISABLE;
-#endif
 		total_len += src[i].length;
 
 		if (i == (nb_sge - 1)) {
@@ -444,17 +440,16 @@ fle_populate(struct qbman_fle fle[],
 	}
 	/* source frame list to source buffer */
 	DPAA2_SET_FLE_ADDR(&fle[DPAA2_QDMA_SRC_FLE], src_iova);
-#ifdef RTE_LIBRTE_DPAA2_USE_PHYS_IOVA
-	DPAA2_SET_FLE_BMT(&fle[DPAA2_QDMA_SRC_FLE]);
-#endif
+	/** IOMMU is always on for either VA or PA mode,
+	 * so Bypass Memory Translation should be disabled.
+	 * DPAA2_SET_FLE_BMT(&fle[DPAA2_QDMA_SRC_FLE]);
+	 * DPAA2_SET_FLE_BMT(&fle[DPAA2_QDMA_DST_FLE]);
+	 */
 	fle[DPAA2_QDMA_SRC_FLE].word4.fmt = fmt;
 	DPAA2_SET_FLE_LEN(&fle[DPAA2_QDMA_SRC_FLE], len);
 
 	/* destination frame list to destination buffer */
 	DPAA2_SET_FLE_ADDR(&fle[DPAA2_QDMA_DST_FLE], dst_iova);
-#ifdef RTE_LIBRTE_DPAA2_USE_PHYS_IOVA
-	DPAA2_SET_FLE_BMT(&fle[DPAA2_QDMA_DST_FLE]);
-#endif
 	fle[DPAA2_QDMA_DST_FLE].word4.fmt = fmt;
 	DPAA2_SET_FLE_LEN(&fle[DPAA2_QDMA_DST_FLE], len);
 
@@ -560,7 +555,7 @@ dpaa2_qdma_long_fmt_dump(const struct qbman_fle *fle)
 		DPAA2_QDMA_INFO("long format/SG format, job number:%d",
 			cntx_sg->job_nb);
 		if (!cntx_sg->job_nb ||
-			cntx_sg->job_nb > RTE_DPAA2_QDMA_JOB_SUBMIT_MAX) {
+			cntx_sg->job_nb > RTE_DPAAX_QDMA_JOB_SUBMIT_MAX) {
 			DPAA2_QDMA_ERR("Invalid SG job number:%d",
 				cntx_sg->job_nb);
 			return;
@@ -610,9 +605,9 @@ dpaa2_qdma_copy_sg(void *dev_private,
 		return -EINVAL;
 	}
 
-	if (unlikely(nb_src > RTE_DPAA2_QDMA_JOB_SUBMIT_MAX)) {
+	if (unlikely(nb_src > RTE_DPAAX_QDMA_JOB_SUBMIT_MAX)) {
 		DPAA2_QDMA_ERR("SG entry number(%d) > MAX(%d)",
-			nb_src, RTE_DPAA2_QDMA_JOB_SUBMIT_MAX);
+			nb_src, RTE_DPAAX_QDMA_JOB_SUBMIT_MAX);
 		return -EINVAL;
 	}
 
@@ -631,11 +626,7 @@ dpaa2_qdma_copy_sg(void *dev_private,
 			cntx_sg->cntx_idx[i] = idx_addr[i];
 	}
 
-#ifdef RTE_LIBRTE_DPAA2_USE_PHYS_IOVA
-	cntx_iova = rte_mempool_virt2iova(cntx_sg);
-#else
-	cntx_iova = DPAA2_VADDR_TO_IOVA(cntx_sg);
-#endif
+	cntx_iova = (uint64_t)cntx_sg - qdma_vq->fle_iova2va_offset;
 
 	fle = cntx_sg->fle_sdd.fle;
 	fle_iova = cntx_iova +
@@ -667,8 +658,7 @@ dpaa2_qdma_copy_sg(void *dev_private,
 			offsetof(struct qdma_cntx_sg, sg_src_entry);
 		dst_sge_iova = cntx_iova +
 			offsetof(struct qdma_cntx_sg, sg_dst_entry);
-		len = sg_entry_populate(src, dst,
-			cntx_sg, nb_src);
+		len = sg_entry_populate(src, dst, cntx_sg, nb_src);
 
 		fle_populate(fle, sdd, sdd_iova,
 			&qdma_vq->rbp, src_sge_iova, dst_sge_iova, len,
@@ -1011,7 +1001,7 @@ dpaa2_qdma_dequeue(void *dev_private,
 			q_storage->last_num_pkts);
 		qbman_pull_desc_set_fq(&pulldesc, fqid);
 		qbman_pull_desc_set_storage(&pulldesc, dq_storage,
-			(size_t)(DPAA2_VADDR_TO_IOVA(dq_storage)), 1);
+			DPAA2_VADDR_TO_IOVA(dq_storage), 1);
 		if (check_swp_active_dqs(DPAA2_PER_LCORE_DPIO->index)) {
 			while (!qbman_check_command_complete(
 			       get_swp_active_dqs(
@@ -1046,7 +1036,7 @@ dpaa2_qdma_dequeue(void *dev_private,
 	qbman_pull_desc_set_numframes(&pulldesc, pull_size);
 	qbman_pull_desc_set_fq(&pulldesc, fqid);
 	qbman_pull_desc_set_storage(&pulldesc, dq_storage1,
-		(size_t)(DPAA2_VADDR_TO_IOVA(dq_storage1)), 1);
+		DPAA2_VADDR_TO_IOVA(dq_storage1), 1);
 
 	/* Check if the previous issued command is completed.
 	 * Also seems like the SWP is shared between the Ethernet Driver
@@ -1078,7 +1068,7 @@ dpaa2_qdma_dequeue(void *dev_private,
 		}
 		fd = qbman_result_DQ_fd(dq_storage);
 		ret = dpaa2_qdma_dq_fd(fd, qdma_vq, &free_space, &fle_elem_nb);
-		if (ret || free_space < RTE_DPAA2_QDMA_JOB_SUBMIT_MAX)
+		if (ret || free_space < RTE_DPAAX_QDMA_JOB_SUBMIT_MAX)
 			pending = 0;
 
 		dq_storage++;
@@ -1131,11 +1121,11 @@ dpaa2_qdma_info_get(const struct rte_dma_dev *dev,
 		RTE_DMA_CAPA_SILENT |
 		RTE_DMA_CAPA_OPS_COPY |
 		RTE_DMA_CAPA_OPS_COPY_SG;
-	dev_info->dev_capa |= RTE_DMA_CAPA_DPAA2_QDMA_FLAGS_INDEX;
+	dev_info->dev_capa |= RTE_DMA_CAPA_DPAAX_QDMA_FLAGS_INDEX;
 	dev_info->max_vchans = dpdmai_dev->num_queues;
 	dev_info->max_desc = DPAA2_QDMA_MAX_DESC;
 	dev_info->min_desc = DPAA2_QDMA_MIN_DESC;
-	dev_info->max_sges = RTE_DPAA2_QDMA_JOB_SUBMIT_MAX;
+	dev_info->max_sges = RTE_DPAAX_QDMA_JOB_SUBMIT_MAX;
 	dev_info->dev_name = dev->device->name;
 	if (dpdmai_dev->qdma_dev)
 		dev_info->nb_vchans = dpdmai_dev->qdma_dev->num_vqs;
@@ -1317,6 +1307,7 @@ dpaa2_qdma_vchan_setup(struct rte_dma_dev *dev, uint16_t vchan,
 	char pool_name[64];
 	int ret;
 	char *env = NULL;
+	uint64_t iova, va;
 
 	DPAA2_QDMA_FUNC_TRACE();
 
@@ -1359,6 +1350,9 @@ dpaa2_qdma_vchan_setup(struct rte_dma_dev *dev, uint16_t vchan,
 		DPAA2_QDMA_ERR("%s create failed", pool_name);
 		return -ENOMEM;
 	}
+	iova = qdma_dev->vqs[vchan].fle_pool->mz->iova;
+	va = qdma_dev->vqs[vchan].fle_pool->mz->addr_64;
+	qdma_dev->vqs[vchan].fle_iova2va_offset = va - iova;
 
 	if (qdma_dev->is_silent) {
 		ret = rte_mempool_get_bulk(qdma_dev->vqs[vchan].fle_pool,
diff --git a/drivers/dma/dpaa2/dpaa2_qdma.h b/drivers/dma/dpaa2/dpaa2_qdma.h
index 250c83c83c..0fd1debaf8 100644
--- a/drivers/dma/dpaa2/dpaa2_qdma.h
+++ b/drivers/dma/dpaa2/dpaa2_qdma.h
@@ -220,18 +220,18 @@ struct qdma_cntx_fle_sdd {
 
 struct qdma_cntx_sg {
 	struct qdma_cntx_fle_sdd fle_sdd;
-	struct qdma_sg_entry sg_src_entry[RTE_DPAA2_QDMA_JOB_SUBMIT_MAX];
-	struct qdma_sg_entry sg_dst_entry[RTE_DPAA2_QDMA_JOB_SUBMIT_MAX];
-	uint16_t cntx_idx[RTE_DPAA2_QDMA_JOB_SUBMIT_MAX];
+	struct qdma_sg_entry sg_src_entry[RTE_DPAAX_QDMA_JOB_SUBMIT_MAX];
+	struct qdma_sg_entry sg_dst_entry[RTE_DPAAX_QDMA_JOB_SUBMIT_MAX];
+	uint16_t cntx_idx[RTE_DPAAX_QDMA_JOB_SUBMIT_MAX];
 	uint16_t job_nb;
 	uint16_t rsv[3];
 } __rte_packed;
 
 #define DPAA2_QDMA_IDXADDR_FROM_SG_FLAG(flag) \
-	((void *)(uintptr_t)((flag) - ((flag) & RTE_DPAA2_QDMA_SG_IDX_ADDR_MASK)))
+	((void *)(uintptr_t)((flag) - ((flag) & RTE_DPAAX_QDMA_SG_IDX_ADDR_MASK)))
 
 #define DPAA2_QDMA_IDX_FROM_FLAG(flag) \
-	((flag) >> RTE_DPAA2_QDMA_COPY_IDX_OFFSET)
+	((flag) >> RTE_DPAAX_QDMA_COPY_IDX_OFFSET)
 
 /** Represents a DPDMAI device */
 struct dpaa2_dpdmai_dev {
diff --git a/drivers/dma/dpaa2/meson.build b/drivers/dma/dpaa2/meson.build
index a99151e2a5..a523f5edb4 100644
--- a/drivers/dma/dpaa2/meson.build
+++ b/drivers/dma/dpaa2/meson.build
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: BSD-3-Clause
-# Copyright 2021 NXP
+# Copyright 2021, 2024 NXP
 
 if not is_linux
     build = false
@@ -14,5 +14,3 @@ sources = files('dpaa2_qdma.c')
 if cc.has_argument('-Wno-pointer-arith')
     cflags += '-Wno-pointer-arith'
 endif
-
-headers = files('rte_pmd_dpaa2_qdma.h')
diff --git a/drivers/dma/dpaa2/rte_pmd_dpaa2_qdma.h b/drivers/dma/dpaa2/rte_pmd_dpaa2_qdma.h
deleted file mode 100644
index df21b39cae..0000000000
--- a/drivers/dma/dpaa2/rte_pmd_dpaa2_qdma.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright 2021-2023 NXP
- */
-
-#ifndef _RTE_PMD_DPAA2_QDMA_H_
-#define _RTE_PMD_DPAA2_QDMA_H_
-
-#include <rte_compat.h>
-
-#define RTE_DPAA2_QDMA_COPY_IDX_OFFSET 8
-#define RTE_DPAA2_QDMA_SG_IDX_ADDR_ALIGN \
-	RTE_BIT64(RTE_DPAA2_QDMA_COPY_IDX_OFFSET)
-#define RTE_DPAA2_QDMA_SG_IDX_ADDR_MASK \
-	(RTE_DPAA2_QDMA_SG_IDX_ADDR_ALIGN - 1)
-#define RTE_DPAA2_QDMA_SG_SUBMIT(idx_addr, flag) \
-	(((uint64_t)idx_addr) | (flag))
-
-#define RTE_DPAA2_QDMA_COPY_SUBMIT(idx, flag) \
-	((idx << RTE_DPAA2_QDMA_COPY_IDX_OFFSET) | (flag))
-
-#define RTE_DPAA2_QDMA_JOB_SUBMIT_MAX (32 + 8)
-#define RTE_DMA_CAPA_DPAA2_QDMA_FLAGS_INDEX RTE_BIT64(63)
-#endif /* _RTE_PMD_DPAA2_QDMA_H_ */
-- 
2.25.1