[PATCH 8/8] dma/odm: add remaining ops

[Anoob Joseph <anoobj@marvell.com>]

From: Vidya Sagar Velumuri <vvelumuri@marvell.com>

Add all remaining ops such as fill, burst_capacity etc. Also update the
documentation.

Signed-off-by: Anoob Joseph <anoobj@marvell.com>
Signed-off-by: Gowrishankar Muthukrishnan <gmuthukrishn@marvell.com>
Signed-off-by: Vidya Sagar Velumuri <vvelumuri@marvell.com>
---
 MAINTAINERS                  |   1 +
 doc/guides/dmadevs/index.rst |   1 +
 doc/guides/dmadevs/odm.rst   |  92 +++++++++++++
 drivers/dma/odm/odm.h        |   4 +
 drivers/dma/odm/odm_dmadev.c | 246 +++++++++++++++++++++++++++++++++++
 5 files changed, 344 insertions(+)
 create mode 100644 doc/guides/dmadevs/odm.rst

diff --git a/MAINTAINERS b/MAINTAINERS
index b8d2f7b3d8..38293008aa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1273,6 +1273,7 @@ M: Gowrishankar Muthukrishnan <gmuthukrishn@marvell.com>
 M: Vidya Sagar Velumuri <vvelumuri@marvell.com>
 T: git://dpdk.org/next/dpdk-next-net-mrvl
 F: drivers/dma/odm/
+F: doc/guides/dmadevs/odm.rst
 
 NXP DPAA DMA
 M: Gagandeep Singh <g.singh@nxp.com>
diff --git a/doc/guides/dmadevs/index.rst b/doc/guides/dmadevs/index.rst
index 5bd25b32b9..ce9f6eb260 100644
--- a/doc/guides/dmadevs/index.rst
+++ b/doc/guides/dmadevs/index.rst
@@ -17,3 +17,4 @@ an application through DMA API.
    hisilicon
    idxd
    ioat
+   odm
diff --git a/doc/guides/dmadevs/odm.rst b/doc/guides/dmadevs/odm.rst
new file mode 100644
index 0000000000..a2eaab59a0
--- /dev/null
+++ b/doc/guides/dmadevs/odm.rst
@@ -0,0 +1,92 @@
+.. SPDX-License-Identifier: BSD-3-Clause
+   Copyright(c) 2024 Marvell.
+
+Odyssey ODM DMA Device Driver
+=============================
+
+The ``odm`` DMA device driver provides a poll-mode driver (PMD) for Marvell Odyssey
+DMA Hardware Accelerator block found in Odyssey SoC. The block supports only mem
+to mem DMA transfers.
+
+ODM DMA device can support up to 32 queues and 16 VFs.
+
+Prerequisites and Compilation procedure
+---------------------------------------
+
+Device Setup
+-------------
+
+ODM DMA device is initialized by kernel PF driver. The PF kernel driver is part
+of Marvell software packages for Odyssey.
+
+Kernel module can be inserted as in below example::
+
+    $ sudo insmod odyssey_odm.ko
+
+ODM DMA device can support up to 16 VFs::
+
+    $ sudo echo 16 > /sys/bus/pci/devices/0000\:08\:00.0/sriov_numvfs
+
+Above command creates 16 VFs with 2 queues each.
+
+The ``dpdk-devbind.py`` script, included with DPDK, can be used to show the
+presence of supported hardware. Running ``dpdk-devbind.py --status-dev dma``
+will show all the Odyssey ODM DMA devices.
+
+Devices using VFIO drivers
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The HW devices to be used will need to be bound to a user-space IO driver.
+The ``dpdk-devbind.py`` script can be used to view the state of the devices
+and to bind them to a suitable DPDK-supported driver, such as ``vfio-pci``.
+For example::
+
+     $ dpdk-devbind.py -b vfio-pci 0000:08:00.1
+
+Device Probing and Initialization
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+To use the devices from an application, the dmadev API can be used.
+
+Once configured, the device can then be made ready for use
+by calling the ``rte_dma_start()`` API.
+
+Performing Data Copies
+~~~~~~~~~~~~~~~~~~~~~~
+
+Refer to the :ref:`Enqueue / Dequeue APIs <dmadev_enqueue_dequeue>` section
+of the dmadev library documentation for details on operation enqueue and
+submission API usage.
+
+Performance Tuning Parameters
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+To achieve higher performance, DMA device needs to be tuned using PF kernel
+driver module parameters.
+
+Following options are exposed by kernel PF driver via devlink interface for
+tuning performance.
+
+``eng_sel``
+
+  ODM DMA device has 2 engines internally. Engine to queue mapping is decided
+  by a hardware register which can be configured as below::
+
+    $ /sbin/devlink dev param set pci/0000:08:00.0 name eng_sel value 3435973836 cmode runtime
+
+  Each bit in the register corresponds to one queue. Each queue would be
+  associated with one engine. If the value of the bit corresponding to the queue
+  is 0, then engine 0 would be picked. If it is 1, then engine 1 would be
+  picked.
+
+  In the above command, the register value is set as
+  ``1100 1100 1100 1100 1100 1100 1100 1100`` which allows for alternate engines
+  to be used with alternate VFs (assuming the system has 16 VFs with 2 queues
+  each).
+
+``max_load_request``
+
+  Specifies maximum outstanding load requests on internal bus. Values can range
+  from 1 to 512. Set to 512 for maximum requests in flight.::
+
+    $ /sbin/devlink dev param set pci/0000:08:00.0 name max_load_request value 512 cmode runtime
diff --git a/drivers/dma/odm/odm.h b/drivers/dma/odm/odm.h
index e1373e0c7f..1d60d2d11a 100644
--- a/drivers/dma/odm/odm.h
+++ b/drivers/dma/odm/odm.h
@@ -75,6 +75,10 @@ extern int odm_logtype;
 	rte_log(RTE_LOG_INFO, odm_logtype,                                                         \
 		RTE_FMT("%s(): %u" RTE_FMT_HEAD(__VA_ARGS__, ), __func__, __LINE__,                \
 			RTE_FMT_TAIL(__VA_ARGS__, )))
+#define odm_debug(...)                                                                             \
+	rte_log(RTE_LOG_DEBUG, odm_logtype,                                                        \
+		RTE_FMT("%s(): %u" RTE_FMT_HEAD(__VA_ARGS__, ), __func__, __LINE__,                \
+			RTE_FMT_TAIL(__VA_ARGS__, )))
 
 #define ODM_MEMZONE_FLAGS                                                                          \
 	(RTE_MEMZONE_1GB | RTE_MEMZONE_16MB | RTE_MEMZONE_16GB | RTE_MEMZONE_256MB |               \
diff --git a/drivers/dma/odm/odm_dmadev.c b/drivers/dma/odm/odm_dmadev.c
index 327692426f..04286e3bf7 100644
--- a/drivers/dma/odm/odm_dmadev.c
+++ b/drivers/dma/odm/odm_dmadev.c
@@ -317,6 +317,247 @@ odm_dmadev_copy_sg(void *dev_private, uint16_t vchan, const struct rte_dma_sge *
 	return vq->desc_idx++;
 }
 
+static int
+odm_dmadev_fill(void *dev_private, uint16_t vchan, uint64_t pattern, rte_iova_t dst,
+		uint32_t length, uint64_t flags)
+{
+	uint16_t pending_submit_len, pending_submit_cnt, iring_sz_available, iring_head;
+	const int num_words = ODM_IRING_ENTRY_SIZE_MIN;
+	struct odm_dev *odm = dev_private;
+	uint64_t *iring_head_ptr;
+	struct odm_queue *vq;
+	uint64_t h;
+
+	vq = &odm->vq[vchan];
+
+	union odm_instr_hdr_s hdr = {
+		.s.ct = ODM_HDR_CT_CW_NC,
+		.s.nfst = 0,
+		.s.nlst = 1,
+	};
+
+	h = (uint64_t)length;
+
+	switch (pattern) {
+	case 0:
+		hdr.s.xtype = ODM_XTYPE_FILL0;
+		break;
+	case 0xffffffffffffffff:
+		hdr.s.xtype = ODM_XTYPE_FILL1;
+		break;
+	default:
+		return -ENOTSUP;
+	}
+
+	const uint16_t max_iring_words = vq->iring_max_words;
+
+	iring_sz_available = vq->iring_sz_available;
+	pending_submit_len = vq->pending_submit_len;
+	pending_submit_cnt = vq->pending_submit_cnt;
+	iring_head_ptr = vq->iring_mz->addr;
+	iring_head = vq->iring_head;
+
+	if (iring_sz_available < num_words)
+		return -ENOSPC;
+
+	if ((iring_head + num_words) >= max_iring_words) {
+
+		iring_head_ptr[iring_head] = hdr.u;
+		iring_head = (iring_head + 1) % max_iring_words;
+
+		iring_head_ptr[iring_head] = h;
+		iring_head = (iring_head + 1) % max_iring_words;
+
+		iring_head_ptr[iring_head] = dst;
+		iring_head = (iring_head + 1) % max_iring_words;
+
+		iring_head_ptr[iring_head] = 0;
+		iring_head = (iring_head + 1) % max_iring_words;
+	} else {
+		iring_head_ptr[iring_head] = hdr.u;
+		iring_head_ptr[iring_head + 1] = h;
+		iring_head_ptr[iring_head + 2] = dst;
+		iring_head_ptr[iring_head + 3] = 0;
+		iring_head += num_words;
+	}
+
+	pending_submit_len += num_words;
+
+	if (flags & RTE_DMA_OP_FLAG_SUBMIT) {
+		rte_wmb();
+		odm_write64(pending_submit_len, odm->rbase + ODM_VDMA_DBELL(vchan));
+		vq->stats.submitted += pending_submit_cnt + 1;
+		vq->pending_submit_len = 0;
+		vq->pending_submit_cnt = 0;
+	} else {
+		vq->pending_submit_len = pending_submit_len;
+		vq->pending_submit_cnt++;
+	}
+
+	vq->iring_head = iring_head;
+	vq->iring_sz_available = iring_sz_available - num_words;
+
+	/* No extra space to save. Skip entry in extra space ring. */
+	vq->ins_ring_head = (vq->ins_ring_head + 1) % vq->cring_max_entry;
+
+	vq->iring_sz_available = iring_sz_available - num_words;
+
+	return vq->desc_idx++;
+}
+
+static uint16_t
+odm_dmadev_completed(void *dev_private, uint16_t vchan, const uint16_t nb_cpls, uint16_t *last_idx,
+		     bool *has_error)
+{
+	const union odm_cmpl_ent_s cmpl_zero = {0};
+	uint16_t cring_head, iring_sz_available;
+	struct odm_dev *odm = dev_private;
+	union odm_cmpl_ent_s cmpl;
+	struct odm_queue *vq;
+	uint64_t nb_err = 0;
+	uint32_t *cmpl_ptr;
+	int cnt;
+
+	vq = &odm->vq[vchan];
+	const uint32_t *base_addr = vq->cring_mz->addr;
+	const uint16_t cring_max_entry = vq->cring_max_entry;
+
+	cring_head = vq->cring_head;
+	iring_sz_available = vq->iring_sz_available;
+
+	if (unlikely(vq->stats.submitted == vq->stats.completed)) {
+		*last_idx = (vq->stats.completed_offset + vq->stats.completed - 1) & 0xFFFF;
+		return 0;
+	}
+
+	for (cnt = 0; cnt < nb_cpls; cnt++) {
+		cmpl_ptr = RTE_PTR_ADD(base_addr, cring_head * sizeof(cmpl));
+		cmpl.u = rte_atomic_load_explicit(cmpl_ptr, rte_memory_order_relaxed);
+		if (!cmpl.s.valid)
+			break;
+
+		if (cmpl.s.cmp_code)
+			nb_err++;
+
+		/* Free space for enqueue */
+		iring_sz_available += 4 + vq->extra_ins_sz[cring_head];
+
+		/* Clear instruction extra space */
+		vq->extra_ins_sz[cring_head] = 0;
+
+		rte_atomic_store_explicit(cmpl_ptr, cmpl_zero.u, rte_memory_order_relaxed);
+		cring_head = (cring_head + 1) % cring_max_entry;
+	}
+
+	vq->stats.errors += nb_err;
+
+	if (unlikely(has_error != NULL && nb_err))
+		*has_error = true;
+
+	vq->cring_head = cring_head;
+	vq->iring_sz_available = iring_sz_available;
+
+	vq->stats.completed += cnt;
+
+	*last_idx = (vq->stats.completed_offset + vq->stats.completed - 1) & 0xFFFF;
+
+	return cnt;
+}
+
+static uint16_t
+odm_dmadev_completed_status(void *dev_private, uint16_t vchan, const uint16_t nb_cpls,
+			    uint16_t *last_idx, enum rte_dma_status_code *status)
+{
+	const union odm_cmpl_ent_s cmpl_zero = {0};
+	uint16_t cring_head, iring_sz_available;
+	struct odm_dev *odm = dev_private;
+	union odm_cmpl_ent_s cmpl;
+	struct odm_queue *vq;
+	uint32_t *cmpl_ptr;
+	int cnt;
+
+	vq = &odm->vq[vchan];
+	const uint32_t *base_addr = vq->cring_mz->addr;
+	const uint16_t cring_max_entry = vq->cring_max_entry;
+
+	cring_head = vq->cring_head;
+	iring_sz_available = vq->iring_sz_available;
+
+	if (vq->stats.submitted == vq->stats.completed) {
+		*last_idx = (vq->stats.completed_offset + vq->stats.completed - 1) & 0xFFFF;
+		return 0;
+	}
+
+#ifdef ODM_DEBUG
+	odm_debug("cring_head: 0x%" PRIx16, cring_head);
+	odm_debug("Submitted: 0x%" PRIx64, vq->stats.submitted);
+	odm_debug("Completed: 0x%" PRIx64, vq->stats.completed);
+	odm_debug("Hardware count: 0x%" PRIx64, odm_read64(odm->rbase + ODM_VDMA_CNT(vchan)));
+#endif
+
+	for (cnt = 0; cnt < nb_cpls; cnt++) {
+		cmpl_ptr = RTE_PTR_ADD(base_addr, cring_head * sizeof(cmpl));
+		cmpl.u = rte_atomic_load_explicit(cmpl_ptr, rte_memory_order_relaxed);
+		if (!cmpl.s.valid)
+			break;
+
+		status[cnt] = cmpl.s.cmp_code;
+
+		if (cmpl.s.cmp_code)
+			vq->stats.errors++;
+
+		/* Free space for enqueue */
+		iring_sz_available += 4 + vq->extra_ins_sz[cring_head];
+
+		/* Clear instruction extra space */
+		vq->extra_ins_sz[cring_head] = 0;
+
+		rte_atomic_store_explicit(cmpl_ptr, cmpl_zero.u, rte_memory_order_relaxed);
+		cring_head = (cring_head + 1) % cring_max_entry;
+	}
+
+	vq->cring_head = cring_head;
+	vq->iring_sz_available = iring_sz_available;
+
+	vq->stats.completed += cnt;
+
+	*last_idx = (vq->stats.completed_offset + vq->stats.completed - 1) & 0xFFFF;
+
+	return cnt;
+}
+
+static int
+odm_dmadev_submit(void *dev_private, uint16_t vchan)
+{
+	struct odm_dev *odm = dev_private;
+	uint16_t pending_submit_len;
+	struct odm_queue *vq;
+
+	vq = &odm->vq[vchan];
+	pending_submit_len = vq->pending_submit_len;
+
+	if (pending_submit_len == 0)
+		return 0;
+
+	rte_wmb();
+	odm_write64(pending_submit_len, odm->rbase + ODM_VDMA_DBELL(vchan));
+	vq->pending_submit_len = 0;
+	vq->stats.submitted += vq->pending_submit_cnt;
+	vq->pending_submit_cnt = 0;
+
+	return 0;
+}
+
+static uint16_t
+odm_dmadev_burst_capacity(const void *dev_private, uint16_t vchan __rte_unused)
+{
+	const struct odm_dev *odm = dev_private;
+	const struct odm_queue *vq;
+
+	vq = &odm->vq[vchan];
+	return (vq->iring_sz_available / ODM_IRING_ENTRY_SIZE_MIN);
+}
+
 static int
 odm_stats_get(const struct rte_dma_dev *dev, uint16_t vchan, struct rte_dma_stats *rte_stats,
 	      uint32_t size)
@@ -416,6 +657,11 @@ odm_dmadev_probe(struct rte_pci_driver *pci_drv __rte_unused, struct rte_pci_dev
 
 	dmadev->fp_obj->copy = odm_dmadev_copy;
 	dmadev->fp_obj->copy_sg = odm_dmadev_copy_sg;
+	dmadev->fp_obj->fill = odm_dmadev_fill;
+	dmadev->fp_obj->submit = odm_dmadev_submit;
+	dmadev->fp_obj->completed = odm_dmadev_completed;
+	dmadev->fp_obj->completed_status = odm_dmadev_completed_status;
+	dmadev->fp_obj->burst_capacity = odm_dmadev_burst_capacity;
 
 	odm->pci_dev = pci_dev;
 
-- 
2.25.1