[PATCH v16 net-next 05/11] net/nebula-matrix: add channel layer

@@ -3,7 +3,8 @@
 
 obj-$(CONFIG_NBL) := nbl.o
 
-nbl-objs +=       nbl_channel/nbl_channel.o \
+nbl-objs +=       nbl_common/nbl_common.o \
+				nbl_channel/nbl_channel.o \
 				nbl_hw/nbl_hw_leonis/nbl_hw_leonis.o \
 				nbl_hw/nbl_hw_leonis/nbl_resource_leonis.o \
 				nbl_hw/nbl_hw_leonis/nbl_hw_leonis_regs.o \

@@ -2,12 +2,878 @@
 /*
  * Copyright (c) 2025 Nebula Matrix Limited.
  */
-
+#include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/pci.h>
+#include <linux/bits.h>
+#include <linux/dma-mapping.h>
 #include "nbl_channel.h"
 
+static int nbl_chan_add_msg_handler(struct nbl_channel_mgt *chan_mgt,
+				    u16 msg_type, nbl_chan_resp func,
+				    void *priv)
+{
+	struct nbl_chan_msg_node_data handler = { 0 };
+	int ret;
+
+	handler.func = func;
+	handler.priv = priv;
+	ret = nbl_common_alloc_hash_node(chan_mgt->handle_hash_tbl, &msg_type,
+					 &handler, NULL);
+
+	return ret;
+}
+
+static int nbl_chan_init_msg_handler(struct nbl_channel_mgt *chan_mgt)
+{
+	struct nbl_common_info *common = chan_mgt->common;
+	struct nbl_hash_tbl_key tbl_key = {0};
+
+	tbl_key.dev = common->dev;
+	tbl_key.key_size = sizeof(u16);
+	tbl_key.data_size = sizeof(struct nbl_chan_msg_node_data);
+	tbl_key.bucket_size = NBL_CHAN_HANDLER_TBL_BUCKET_SIZE;
+
+	chan_mgt->handle_hash_tbl = nbl_common_init_hash_table(&tbl_key);
+	if (!chan_mgt->handle_hash_tbl)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void nbl_chan_remove_msg_handler(struct nbl_channel_mgt *chan_mgt)
+{
+	nbl_common_remove_hash_table(chan_mgt->handle_hash_tbl, NULL);
+
+	chan_mgt->handle_hash_tbl = NULL;
+}
+
+static void nbl_chan_init_queue_param(struct nbl_chan_info *chan_info,
+				      u16 num_txq_entries, u16 num_rxq_entries,
+				      u16 txq_buf_size, u16 rxq_buf_size)
+{
+	mutex_init(&chan_info->txq_lock);
+	mutex_init(&chan_info->rxq_lock);
+	chan_info->num_txq_entries = num_txq_entries;
+	chan_info->num_rxq_entries = num_rxq_entries;
+	chan_info->txq_buf_size = txq_buf_size;
+	chan_info->rxq_buf_size = rxq_buf_size;
+}
+
+static int nbl_chan_init_tx_queue(struct nbl_common_info *common,
+				  struct nbl_chan_info *chan_info)
+{
+	struct nbl_chan_ring *txq = &chan_info->txq;
+	struct device *dev = common->dev;
+	size_t size =
+		chan_info->num_txq_entries * sizeof(struct nbl_chan_tx_desc);
+	int i;
+
+	txq->desc.tx_desc = dmam_alloc_coherent(dev, size, &txq->dma,
+						GFP_KERNEL);
+	if (!txq->desc.tx_desc)
+		return -ENOMEM;
+
+	chan_info->wait = devm_kcalloc(dev, chan_info->num_txq_entries,
+				       sizeof(*chan_info->wait),
+				       GFP_KERNEL);
+	if (!chan_info->wait)
+		return -ENOMEM;
+	for (i = 0; i < chan_info->num_txq_entries; i++) {
+		init_waitqueue_head(&chan_info->wait[i].wait_queue);
+		atomic_set(&chan_info->wait[i].status, NBL_MBX_STATUS_IDLE);
+	}
+
+	txq->buf = devm_kcalloc(dev, chan_info->num_txq_entries,
+				sizeof(*txq->buf), GFP_KERNEL);
+	if (!txq->buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int nbl_chan_init_rx_queue(struct nbl_common_info *common,
+				  struct nbl_chan_info *chan_info)
+{
+	struct nbl_chan_ring *rxq = &chan_info->rxq;
+	struct device *dev = common->dev;
+	size_t size =
+		chan_info->num_rxq_entries * sizeof(struct nbl_chan_rx_desc);
+
+	rxq->desc.rx_desc = dmam_alloc_coherent(dev, size, &rxq->dma,
+						GFP_KERNEL);
+	if (!rxq->desc.rx_desc) {
+		dev_err(dev,
+			"Allocate DMA for chan rx descriptor ring failed\n");
+		return -ENOMEM;
+	}
+
+	rxq->buf = devm_kcalloc(dev, chan_info->num_rxq_entries,
+				sizeof(*rxq->buf), GFP_KERNEL);
+	if (!rxq->buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int nbl_chan_init_queue(struct nbl_common_info *common,
+			       struct nbl_chan_info *chan_info)
+{
+	int err;
+
+	err = nbl_chan_init_tx_queue(common, chan_info);
+	if (err)
+		return err;
+
+	err = nbl_chan_init_rx_queue(common, chan_info);
+
+	return err;
+}
+
+static void nbl_chan_config_queue(struct nbl_channel_mgt *chan_mgt,
+				  struct nbl_chan_info *chan_info, bool tx)
+{
+	struct nbl_hw_ops *hw_ops = chan_mgt->hw_ops_tbl->ops;
+	struct nbl_hw_mgt *p = chan_mgt->hw_ops_tbl->priv;
+	int size_bwid;
+	struct nbl_chan_ring *ring;
+	dma_addr_t dma_addr;
+
+	if (tx)
+		ring = &chan_info->txq;
+	else
+		ring = &chan_info->rxq;
+	dma_addr = ring->dma;
+	if (tx) {
+		size_bwid = ilog2(chan_info->num_txq_entries);
+		hw_ops->config_mailbox_txq(p, dma_addr, size_bwid);
+	} else {
+		size_bwid = ilog2(chan_info->num_rxq_entries);
+		hw_ops->config_mailbox_rxq(p, dma_addr, size_bwid);
+	}
+}
+
+static int nbl_chan_alloc_all_tx_bufs(struct nbl_channel_mgt *chan_mgt,
+				      struct nbl_chan_info *chan_info)
+{
+	struct nbl_chan_ring *txq = &chan_info->txq;
+	struct device *dev = chan_mgt->common->dev;
+	struct nbl_chan_buf *buf;
+	u16 i;
+
+	for (i = 0; i < chan_info->num_txq_entries; i++) {
+		buf = &txq->buf[i];
+		buf->va = dmam_alloc_coherent(dev, chan_info->txq_buf_size,
+					      &buf->pa,
+					      GFP_KERNEL);
+		if (!buf->va) {
+			dev_err(dev,
+				"Allocate buffer for chan tx queue failed\n");
+			return -ENOMEM;
+		}
+	}
+
+	txq->next_to_clean = 0;
+	txq->next_to_use = 0;
+	txq->tail_ptr = 0;
+
+	return 0;
+}
+
+static void nbl_chan_cfg_qinfo_map_table(struct nbl_channel_mgt *chan_mgt)
+{
+	struct nbl_hw_ops *hw_ops = chan_mgt->hw_ops_tbl->ops;
+	struct nbl_common_info *common = chan_mgt->common;
+	struct nbl_hw_mgt *p = chan_mgt->hw_ops_tbl->priv;
+	u8 func_id;
+	u32 pf_mask;
+
+	pf_mask = hw_ops->get_host_pf_mask(p);
+	for (func_id = 0; func_id < NBL_MAX_PF; func_id++) {
+		if (!(pf_mask & (1 << func_id)))
+			hw_ops->cfg_mailbox_qinfo(p, func_id, common->hw_bus,
+						  common->devid,
+						  common->function + func_id);
+	}
+}
+
+#define NBL_UPDATE_QUEUE_TAIL_PTR(chan_info, hw_ops, chan_mgt, tail_ptr, qid)\
+do {									\
+	(void)(chan_info);						\
+	typeof(hw_ops) _hw_ops = (hw_ops);				\
+	typeof(chan_mgt) _chan_mgt = (chan_mgt);			\
+	typeof(tail_ptr) _tail_ptr = (tail_ptr);			\
+	typeof(qid) _qid = (qid);					\
+	(_hw_ops)->update_mailbox_queue_tail_ptr(			\
+		_chan_mgt->hw_ops_tbl->priv, _tail_ptr, _qid);	\
+} while (0)
+
+static int nbl_chan_alloc_all_rx_bufs(struct nbl_channel_mgt *chan_mgt,
+				      struct nbl_chan_info *chan_info)
+{
+	struct nbl_hw_ops *hw_ops = chan_mgt->hw_ops_tbl->ops;
+	struct nbl_chan_ring *rxq = &chan_info->rxq;
+	struct device *dev = chan_mgt->common->dev;
+	struct nbl_chan_rx_desc *desc;
+	struct nbl_chan_buf *buf;
+	u16 i;
+
+	for (i = 0; i < chan_info->num_rxq_entries; i++) {
+		buf = &rxq->buf[i];
+		buf->va = dmam_alloc_coherent(dev, chan_info->rxq_buf_size,
+					      &buf->pa,
+					      GFP_KERNEL);
+		if (!buf->va) {
+			dev_err(dev,
+				"Allocate buffer for chan rx queue failed\n");
+			goto err;
+		}
+	}
+
+	desc = rxq->desc.rx_desc;
+	for (i = 0; i < chan_info->num_rxq_entries - 1; i++) {
+		buf = &rxq->buf[i];
+		desc[i].buf_addr = cpu_to_le64(buf->pa);
+		desc[i].buf_len = cpu_to_le32(chan_info->rxq_buf_size);
+		desc[i].flags = cpu_to_le16(BIT(NBL_CHAN_RX_DESC_AVAIL));
+	}
+
+	rxq->next_to_clean = 0;
+	rxq->next_to_use = chan_info->num_rxq_entries - 1;
+	rxq->tail_ptr = chan_info->num_rxq_entries - 1;
+
+	NBL_UPDATE_QUEUE_TAIL_PTR(chan_info, hw_ops, chan_mgt, rxq->tail_ptr,
+				  NBL_MB_RX_QID);
+
+	return 0;
+err:
+	return -ENOMEM;
+}
+
+static int nbl_chan_alloc_all_bufs(struct nbl_channel_mgt *chan_mgt,
+				   struct nbl_chan_info *chan_info)
+{
+	int err;
+
+	err = nbl_chan_alloc_all_tx_bufs(chan_mgt, chan_info);
+	if (err)
+		return err;
+	err = nbl_chan_alloc_all_rx_bufs(chan_mgt, chan_info);
+
+	return err;
+}
+
+static void nbl_chan_stop_queue(struct nbl_channel_mgt *chan_mgt)
+{
+	struct nbl_hw_ops *hw_ops = chan_mgt->hw_ops_tbl->ops;
+
+	hw_ops->stop_mailbox_rxq(chan_mgt->hw_ops_tbl->priv);
+	hw_ops->stop_mailbox_txq(chan_mgt->hw_ops_tbl->priv);
+}
+
+static int nbl_chan_teardown_queue(struct nbl_channel_mgt *chan_mgt,
+				   u8 chan_type)
+{
+	struct nbl_chan_info *chan_info = chan_mgt->chan_info[chan_type];
+
+	nbl_chan_stop_queue(chan_mgt);
+	if (chan_info->clean_task)
+		cancel_work_sync(chan_info->clean_task);
+	mutex_destroy(&chan_info->txq_lock);
+	mutex_destroy(&chan_info->rxq_lock);
+
+	return 0;
+}
+
+static int nbl_chan_setup_queue(struct nbl_channel_mgt *chan_mgt, u8 chan_type)
+{
+	struct nbl_chan_info *chan_info = chan_mgt->chan_info[chan_type];
+	struct nbl_common_info *common = chan_mgt->common;
+	int err;
+
+	nbl_chan_init_queue_param(chan_info, NBL_CHAN_QUEUE_LEN,
+				  NBL_CHAN_QUEUE_LEN, NBL_CHAN_BUF_LEN,
+				  NBL_CHAN_BUF_LEN);
+	err = nbl_chan_init_queue(common, chan_info);
+	if (err)
+		return err;
+
+	nbl_chan_config_queue(chan_mgt, chan_info, true); /* tx */
+	nbl_chan_config_queue(chan_mgt, chan_info, false); /* rx */
+
+	err = nbl_chan_alloc_all_bufs(chan_mgt, chan_info);
+	if (err)
+		goto chan_q_setup_fail;
+
+	return 0;
+
+chan_q_setup_fail:
+	nbl_chan_teardown_queue(chan_mgt, chan_type);
+	return err;
+}
+
+static int nbl_chan_update_txqueue(struct nbl_channel_mgt *chan_mgt,
+				   struct nbl_chan_info *chan_info,
+				   struct nbl_chan_tx_param *param)
+{
+	struct nbl_chan_ring *txq = &chan_info->txq;
+	struct nbl_chan_tx_desc *tx_desc =
+		NBL_CHAN_TX_RING_TO_DESC(txq, txq->next_to_use);
+	struct nbl_chan_buf *tx_buf =
+		NBL_CHAN_TX_RING_TO_BUF(txq, txq->next_to_use);
+
+	if (param->arg_len > NBL_CHAN_BUF_LEN - sizeof(*tx_desc))
+		return -EINVAL;
+
+	tx_desc->dstid = cpu_to_le16(param->dstid);
+	tx_desc->msg_type = cpu_to_le16(param->msg_type);
+	tx_desc->msgid = cpu_to_le16(param->msgid);
+
+	if (param->arg_len > NBL_CHAN_TX_DESC_EMBEDDED_DATA_LEN) {
+		memcpy(tx_buf->va, param->arg, param->arg_len);
+		tx_desc->buf_addr = cpu_to_le64(tx_buf->pa);
+		tx_desc->buf_len = cpu_to_le16(param->arg_len);
+		tx_desc->data_len = 0;
+	} else {
+		memcpy(tx_desc->data, param->arg, param->arg_len);
+		tx_desc->buf_len = 0;
+		tx_desc->data_len = cpu_to_le16(param->arg_len);
+	}
+	/* Ensure desc body is visible to DMA before writing AVAIL flag */
+	dma_wmb();
+	tx_desc->flags = cpu_to_le16(BIT(NBL_CHAN_TX_DESC_AVAIL));
+
+	txq->next_to_use =
+		NBL_NEXT_ID(txq->next_to_use, chan_info->num_txq_entries - 1);
+	txq->tail_ptr++;
+
+	return 0;
+}
+
+static int nbl_chan_kick_tx_ring(struct nbl_channel_mgt *chan_mgt,
+				 struct nbl_chan_info *chan_info)
+{
+	struct nbl_hw_ops *hw_ops = chan_mgt->hw_ops_tbl->ops;
+	struct nbl_chan_ring *txq = &chan_info->txq;
+	struct device *dev = chan_mgt->common->dev;
+	int max_retries = NBL_CHAN_TX_WAIT_TIMES;
+	struct nbl_chan_tx_desc *tx_desc;
+	int retry_count = 0;
+
+	NBL_UPDATE_QUEUE_TAIL_PTR(chan_info, hw_ops, chan_mgt, txq->tail_ptr,
+				  NBL_MB_TX_QID);
+
+	tx_desc = NBL_CHAN_TX_RING_TO_DESC(txq, txq->next_to_clean);
+	while (retry_count < max_retries) {
+		if (le16_to_cpu(READ_ONCE(tx_desc->flags)) &
+		    BIT(NBL_CHAN_TX_DESC_USED)) {
+			dma_rmb();
+			break;
+		}
+
+		if (!(retry_count % NBL_CHAN_TX_REKICK_WAIT_TIMES))
+			NBL_UPDATE_QUEUE_TAIL_PTR(chan_info, hw_ops, chan_mgt,
+						  txq->tail_ptr, NBL_MB_TX_QID);
+		retry_count++;
+
+		usleep_range(NBL_CHAN_TX_WAIT_US, NBL_CHAN_TX_WAIT_US_MAX);
+	}
+
+	txq->next_to_clean = txq->next_to_use;
+	if (retry_count >= max_retries) {
+		dev_err(dev, "chan send message type: %d timeout\n",
+			le16_to_cpu(READ_ONCE(tx_desc->msg_type)));
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static void nbl_chan_recv_ack_msg(void *priv, u16 srcid, u16 msgid, void *data,
+				  u32 data_len)
+{
+	struct nbl_channel_mgt *chan_mgt = (struct nbl_channel_mgt *)priv;
+	struct nbl_chan_waitqueue_head *wait_head = NULL;
+	union nbl_chan_msg_id ack_msgid = { { 0 } };
+	struct device *dev = chan_mgt->common->dev;
+	struct nbl_chan_info *chan_info =
+		chan_mgt->chan_info[NBL_CHAN_TYPE_MAILBOX];
+	u32 *payload = data;
+	u32 ack_datalen, ack_msgtype = 0;
+	u32 copy_len;
+
+	if (data_len > NBL_CHAN_BUF_LEN ||
+	    data_len < NBL_CHAN_ACK_HEAD_LEN * sizeof(u32)) {
+		dev_err(dev, "Invalid ACK data_len: %u\n", data_len);
+		return;
+	}
+	ack_datalen = data_len - NBL_CHAN_ACK_HEAD_LEN * sizeof(u32);
+	ack_msgtype = le16_to_cpu(*(__le16 *)(payload + NBL_CHAN_MSG_TYPE_POS));
+	ack_msgid.id = le16_to_cpu(*(__le16 *)(payload + NBL_CHAN_MSG_ID_POS));
+	if (ack_msgid.info.loc >= NBL_CHAN_QUEUE_LEN) {
+		dev_err(dev, "chan recv msg loc: %d err\n", ack_msgid.info.loc);
+		return;
+	}
+	wait_head = &chan_info->wait[ack_msgid.info.loc];
+	preempt_disable();
+	if (wait_head->msg_type != ack_msgtype) {
+		preempt_enable();
+		dev_err(dev, "Skip ack msg type donot match, wait_head msgtype:%u msg_index:%u status:%d ack_data_len:%d, ack msgtype:%u msgid:%u datalen:%d\n",
+			wait_head->msg_type, wait_head->msg_index,
+			atomic_read(&wait_head->status),
+			wait_head->ack_data_len, ack_msgtype,
+			ack_msgid.id, ack_datalen);
+		return;
+	}
+	if (ack_msgid.info.index != wait_head->msg_index) {
+		preempt_enable();
+		dev_err(dev, "Stale ACK: expected index=%u, got %u for loc=%u\n",
+			wait_head->msg_index, ack_msgid.info.index,
+			ack_msgid.info.loc);
+		return;
+	}
+
+	wait_head->ack_err =
+		le32_to_cpu(*(__le32 *)(payload + NBL_CHAN_ACK_RET_POS));
+	preempt_enable();
+	if (atomic_cmpxchg(&wait_head->status, NBL_MBX_STATUS_WAITING,
+			   NBL_MBX_STATUS_ACKD) != NBL_MBX_STATUS_WAITING) {
+		dev_err(dev, "Skip ack with invalid status, wait_head msgtype:%u msg_index:%u status:%d ack_data_len:%d, ack msgtype:%u msgid:%u datalen:%d\n",
+			wait_head->msg_type, wait_head->msg_index,
+			atomic_read(&wait_head->status),
+			wait_head->ack_data_len, ack_msgtype,
+			ack_msgid.id, ack_datalen);
+		return;
+	}
+
+	copy_len = min_t(u32, wait_head->ack_data_len, ack_datalen);
+	if (wait_head->ack_err >= 0 && copy_len > 0) {
+		if (NBL_CHAN_ACK_HEAD_LEN * sizeof(u32) + copy_len > data_len) {
+			dev_err(dev, "ACK payload overflow\n");
+			goto ack_done;
+			return;
+		}
+		memcpy((char *)wait_head->ack_data,
+		       payload + NBL_CHAN_ACK_HEAD_LEN, copy_len);
+		wait_head->ack_data_len = (u16)copy_len;
+	} else {
+		wait_head->ack_data_len = 0;
+	}
+ack_done:
+	/*
+	 * Ensure all writes to ack_data and ack_data_len are completed
+	 * before setting the 'acked' flag. This prevents other threads
+	 * from observing stale or partially updated data.
+	 */
+	wmb();
+	wait_head->acked = 1;
+	wait_head->ack_data = NULL;
+	if (wait_head->need_waked)
+		wake_up(&wait_head->wait_queue);
+}
+
+static void nbl_chan_recv_msg(struct nbl_channel_mgt *chan_mgt, void *data)
+{
+	struct device *dev = chan_mgt->common->dev;
+	struct nbl_chan_msg_node_data *msg_handler;
+	u16 msg_type, payload_len, srcid, msgid;
+	struct nbl_chan_tx_desc *tx_desc;
+	void *payload;
+
+	tx_desc = data;
+	msg_type = le16_to_cpu(tx_desc->msg_type);
+	dev_dbg(dev, "recv msg_type: %d\n", msg_type);
+
+	srcid = le16_to_cpu(tx_desc->srcid);
+	msgid = le16_to_cpu(tx_desc->msgid);
+	/* Only check if the value exceeds the maximum, relying on the hash
+	 * table to filter invalid message IDs.
+	 * The gap values are reserved for future protocol extensions.
+	 */
+	if (msg_type >= NBL_CHAN_MSG_MAILBOX_MAX)
+		return;
+
+	if (tx_desc->data_len) {
+		payload_len = le16_to_cpu(tx_desc->data_len);
+		if (payload_len > NBL_CHAN_TX_DESC_EMBEDDED_DATA_LEN) {
+			dev_err(dev, "data_len=%u exceeds embedded buffer size=%u\n",
+				payload_len,
+				NBL_CHAN_TX_DESC_EMBEDDED_DATA_LEN);
+			return;
+		}
+		payload = tx_desc->data;
+	} else {
+		payload_len = le16_to_cpu(tx_desc->buf_len);
+		if (payload_len > NBL_CHAN_BUF_LEN - sizeof(*tx_desc)) {
+			dev_err(dev, "buf_len=%u exceeds external buffer size=%zu\n",
+				payload_len,
+				NBL_CHAN_BUF_LEN - sizeof(*tx_desc));
+			return;
+		}
+		payload = tx_desc + 1;
+	}
+
+	msg_handler =
+		nbl_common_get_hash_node(chan_mgt->handle_hash_tbl, &msg_type);
+	if (!msg_handler || !msg_handler->func) {
+		dev_err(dev, "No handler for msg_type: %u (srcid=%u, msgid=%u)\n",
+			msg_type, srcid, msgid);
+		return;
+	}
+	msg_handler->func(msg_handler->priv, srcid, msgid, payload,
+			  payload_len);
+}
+
+static void nbl_chan_advance_rx_ring(struct nbl_channel_mgt *chan_mgt,
+				     struct nbl_chan_info *chan_info,
+				     struct nbl_chan_ring *rxq)
+{
+	struct nbl_hw_ops *hw_ops = chan_mgt->hw_ops_tbl->ops;
+	struct nbl_chan_rx_desc *rx_desc;
+	struct nbl_chan_buf *rx_buf;
+	u16 next_to_use;
+
+	next_to_use = rxq->next_to_use;
+	rx_desc = NBL_CHAN_RX_RING_TO_DESC(rxq, next_to_use);
+	rx_buf = NBL_CHAN_RX_RING_TO_BUF(rxq, next_to_use);
+
+	rx_desc->buf_addr = cpu_to_le64(rx_buf->pa);
+	rx_desc->buf_len = cpu_to_le32(chan_info->rxq_buf_size);
+
+	/*
+	 * DMA Write Memory Barrier:
+	 * Ensures all previous DMA-mapped writes (buffer address/length)
+	 * are completed before the descriptor flags are updated.
+	 * This prevents hardware from seeing a partially updated descriptor
+	 * where flags are set but buffer info isn't ready yet.
+	 */
+	dma_wmb();
+
+	rx_desc->flags = cpu_to_le16(BIT(NBL_CHAN_RX_DESC_AVAIL));
+
+	/*
+	 * CPU Write Memory Barrier:
+	 * Ensures the descriptor flags update is visible to other CPUs
+	 * before we update the tail pointer. This is important for:
+	 * 1. Software cleaning threads that might be checking the tail pointer
+	 * 2. Maintaining proper memory ordering in multi-core systems
+	 */
+	wmb();
+	rxq->next_to_use++;
+	if (rxq->next_to_use == chan_info->num_rxq_entries)
+		rxq->next_to_use = 0;
+	rxq->tail_ptr++;
+
+	NBL_UPDATE_QUEUE_TAIL_PTR(chan_info, hw_ops, chan_mgt, rxq->tail_ptr,
+				  NBL_MB_RX_QID);
+}
+
+static void nbl_chan_clean_queue(struct nbl_channel_mgt *chan_mgt,
+				 struct nbl_chan_info *chan_info)
+{
+	struct nbl_chan_ring *rxq = &chan_info->rxq;
+	struct device *dev = chan_mgt->common->dev;
+	struct nbl_chan_rx_desc *rx_desc;
+	struct nbl_chan_buf *rx_buf;
+	u16 next_to_clean;
+	void *va;
+
+	mutex_lock(&chan_info->rxq_lock);
+	next_to_clean = rxq->next_to_clean;
+	rx_desc = NBL_CHAN_RX_RING_TO_DESC(rxq, next_to_clean);
+	rx_buf = NBL_CHAN_RX_RING_TO_BUF(rxq, next_to_clean);
+	while (le16_to_cpu(rx_desc->flags) & BIT(NBL_CHAN_RX_DESC_USED)) {
+		if (!(le16_to_cpu(rx_desc->flags) &
+		    BIT(NBL_CHAN_RX_DESC_WRITE)))
+			dev_dbg(dev,
+				"mailbox rx flag 0x%x has no NBL_CHAN_RX_DESC_WRITE\n",
+				le16_to_cpu(rx_desc->flags));
+
+		dma_rmb();
+		va = rx_buf->va;
+		next_to_clean =
+			(next_to_clean + 1) % chan_info->num_rxq_entries;
+		rx_desc = NBL_CHAN_RX_RING_TO_DESC(rxq, next_to_clean);
+		rx_buf = NBL_CHAN_RX_RING_TO_BUF(rxq, next_to_clean);
+
+		mutex_unlock(&chan_info->rxq_lock);
+
+		nbl_chan_recv_msg(chan_mgt, va);
+
+		mutex_lock(&chan_info->rxq_lock);
+		rxq->next_to_clean = next_to_clean;
+		nbl_chan_advance_rx_ring(chan_mgt, chan_info, rxq);
+	}
+	mutex_unlock(&chan_info->rxq_lock);
+}
+
+static void nbl_chan_clean_queue_subtask(struct nbl_channel_mgt *chan_mgt,
+					 u8 chan_type)
+{
+	struct nbl_chan_info *chan_info = chan_mgt->chan_info[chan_type];
+
+	if (!test_bit(NBL_CHAN_INTERRUPT_READY, chan_info->state) ||
+	    test_bit(NBL_CHAN_RESETTING, chan_info->state))
+		return;
+
+	nbl_chan_clean_queue(chan_mgt, chan_info);
+}
+
+static int nbl_chan_get_msg_id(struct nbl_chan_info *chan_info,
+			       union nbl_chan_msg_id *msgid)
+{
+	int valid_loc = chan_info->wait_head_index, i;
+	struct nbl_chan_waitqueue_head *wait = NULL;
+	int status;
+
+	for (i = 0; i < NBL_CHAN_QUEUE_LEN; i++) {
+		wait = &chan_info->wait[valid_loc];
+		status = atomic_read(&wait->status);
+		if (status == NBL_MBX_STATUS_IDLE ||
+		    status == NBL_MBX_STATUS_TIMEOUT) {
+			wait->msg_index = NBL_NEXT_ID(wait->msg_index,
+						      NBL_CHAN_MSG_INDEX_MAX);
+			msgid->info.index = wait->msg_index;
+			msgid->info.loc = valid_loc;
+			valid_loc = NBL_NEXT_ID(valid_loc,
+						chan_info->num_txq_entries - 1);
+			chan_info->wait_head_index = valid_loc;
+			return 0;
+		}
+
+		valid_loc =
+			NBL_NEXT_ID(valid_loc, chan_info->num_txq_entries - 1);
+	}
+
+	/*
+	 * the current NBL_CHAN_QUEUE_LEN configuration meets the design
+	 * requirements and theoretically should not return errors, the
+	 * following scenarios may still cause the waiting queue to
+	 * become full:
+	 * High-concurrency scenarios:
+	 * If the sender (calling nbl_chan_send_msg()) generates messages
+	 * at a rate far exceeding the receiver's ability to process
+	 * acknowledgments (ACKs),the waiting queue may become fully occupied.
+	 * Delayed or failed ACK handling by the receiver:
+	 * The receiver may fail to send ACKs in a timely manner due to
+	 * processing delays, blocking, or faults, causing the sender's
+	 * waiting queue slots to remain occupied for an extended period.
+	 */
+	return -EAGAIN;
+}
+
+static int nbl_chan_send_msg(struct nbl_channel_mgt *chan_mgt,
+			     struct nbl_chan_send_info *chan_send)
+{
+	struct nbl_common_info *common = chan_mgt->common;
+	struct nbl_chan_waitqueue_head *wait_head;
+	struct nbl_chan_tx_param tx_param = { 0 };
+	union nbl_chan_msg_id msgid = { { 0 } };
+	int i = NBL_CHAN_TX_WAIT_ACK_TIMES, ret;
+	struct nbl_chan_info *chan_info =
+		chan_mgt->chan_info[NBL_CHAN_TYPE_MAILBOX];
+	struct device *dev = common->dev;
+
+	if (test_bit(NBL_CHAN_ABNORMAL, chan_info->state))
+		return -EIO;
+
+	mutex_lock(&chan_info->txq_lock);
+
+	ret = nbl_chan_get_msg_id(chan_info, &msgid);
+	if (ret) {
+		mutex_unlock(&chan_info->txq_lock);
+		dev_err(dev,
+			"Channel tx wait head full, send msgtype:%u to dstid:%u failed\n",
+			chan_send->msg_type, chan_send->dstid);
+		return ret;
+	}
+
+	tx_param.msg_type = chan_send->msg_type;
+	tx_param.arg = chan_send->arg;
+	tx_param.arg_len = chan_send->arg_len;
+	tx_param.dstid = chan_send->dstid;
+	tx_param.msgid = msgid.id;
+
+	ret = nbl_chan_update_txqueue(chan_mgt, chan_info, &tx_param);
+	if (ret) {
+		mutex_unlock(&chan_info->txq_lock);
+		dev_err(dev,
+			"Channel tx queue full, send msgtype:%u to dstid:%u failed\n",
+			chan_send->msg_type, chan_send->dstid);
+		return ret;
+	}
+
+	wait_head = &chan_info->wait[msgid.info.loc];
+	wait_head->acked = 0;
+	wait_head->ack_data = chan_send->resp;
+	wait_head->ack_data_len = chan_send->resp_len;
+	wait_head->msg_type = chan_send->msg_type;
+	wait_head->need_waked = chan_send->ack;
+	wait_head->msg_index = msgid.info.index;
+	atomic_set(&wait_head->status, chan_send->ack ? NBL_MBX_STATUS_WAITING :
+		   NBL_MBX_STATUS_IDLE);
+
+	ret = nbl_chan_kick_tx_ring(chan_mgt, chan_info);
+	mutex_unlock(&chan_info->txq_lock);
+	if (ret) {
+		mutex_lock(&chan_info->txq_lock);
+		atomic_set(&wait_head->status, NBL_MBX_STATUS_TIMEOUT);
+		mutex_unlock(&chan_info->txq_lock);
+		return ret;
+	}
+
+	if (!chan_send->ack)
+		return 0;
+
+	if (test_bit(NBL_CHAN_INTERRUPT_READY, chan_info->state)) {
+wait_again:
+		ret = wait_event_timeout(wait_head->wait_queue,
+					 wait_head->acked,
+					 NBL_CHAN_ACK_WAIT_TIME);
+		if (!ret) {
+			if (atomic_cmpxchg(&wait_head->status,
+					   NBL_MBX_STATUS_WAITING,
+					   NBL_MBX_STATUS_TIMEOUT)
+					   != NBL_MBX_STATUS_WAITING)
+				goto wait_again;
+
+			dev_err(dev,
+				"Channel waiting ack failed, message type: %d, msg id: %u\n",
+				chan_send->msg_type, msgid.id);
+			wait_head->acked = 0;
+			wait_head->ack_data = NULL;
+			wait_head->ack_data_len = 0;
+			ret = -ETIMEDOUT;
+		} else {
+			/*
+			 * ensure that after observing 'acked == 1', all
+			 * subsequent reads (ack_data_len, ack_err) observe
+			 * the latest values written by the sender
+			 * (nbl_chan_recv_ack_msg()). This prevents stale reads
+			 * of ACK data or status.
+			 */
+			smp_rmb();
+			chan_send->ack_len = wait_head->ack_data_len;
+			wait_head->acked = 0;
+			atomic_set(&wait_head->status, NBL_MBX_STATUS_IDLE);
+			ret = READ_ONCE(wait_head->ack_err);
+		}
+		return ret;
+	}
+
+	/*polling wait mailbox ack*/
+
+	while (i--) {
+		nbl_chan_clean_queue(chan_mgt, chan_info);
+
+		/* Acquire load: ensure we see the latest 'acked' value */
+		if (smp_load_acquire(&wait_head->acked)) {
+			/*
+			 * ensure that after observing 'acked == 1', all
+			 * subsequent reads (ack_data_len, ack_err) observe
+			 * the latest values written by the sender
+			 * (nbl_chan_recv_ack_msg()). This prevents stale reads
+			 * of ACK data or status.
+			 */
+			smp_rmb();
+			chan_send->ack_len = wait_head->ack_data_len;
+			wait_head->acked = 0;
+			atomic_set(&wait_head->status, NBL_MBX_STATUS_IDLE);
+			ret = READ_ONCE(wait_head->ack_err);
+			return ret;
+		}
+		usleep_range(NBL_CHAN_TX_WAIT_ACK_US_MIN,
+			     NBL_CHAN_TX_WAIT_ACK_US_MAX);
+	}
+	wait_head->acked = 0;
+	wait_head->ack_data = NULL;
+	wait_head->ack_data_len = 0;
+	atomic_set(&wait_head->status, NBL_MBX_STATUS_TIMEOUT);
+	dev_err(dev,
+		"Channel polling ack failed, message type: %d msg id: %u\n",
+		chan_send->msg_type, msgid.id);
+	return -ETIMEDOUT;
+}
+
+static int nbl_chan_send_ack(struct nbl_channel_mgt *chan_mgt,
+			     struct nbl_chan_ack_info *chan_ack)
+{
+	size_t head_len = NBL_CHAN_ACK_HEAD_LEN * sizeof(u32);
+	size_t data_len = chan_ack->data_len;
+	struct nbl_chan_send_info chan_send;
+	__le32 *tmp;
+	size_t len;
+	int ret;
+
+	if (data_len > NBL_CHAN_BUF_LEN - head_len)
+		return -EINVAL;
+
+	len = head_len + data_len;
+	tmp = kzalloc(len, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	*(__le16 *)&tmp[NBL_CHAN_MSG_TYPE_POS] =
+		cpu_to_le16(chan_ack->msg_type);
+	*(__le16 *)&tmp[NBL_CHAN_MSG_ID_POS] = cpu_to_le16(chan_ack->msgid);
+	tmp[NBL_CHAN_ACK_RET_POS] = cpu_to_le32(chan_ack->err);
+	if (chan_ack->data && chan_ack->data_len)
+		memcpy(&tmp[NBL_CHAN_ACK_HEAD_LEN], chan_ack->data,
+		       chan_ack->data_len);
+
+	NBL_CHAN_SEND(chan_send, chan_ack->dstid, NBL_CHAN_MSG_ACK, tmp, len,
+		      NULL, 0, 0);
+	ret = nbl_chan_send_msg(chan_mgt, &chan_send);
+	kfree(tmp);
+
+	return ret;
+}
+
+static int nbl_chan_register_msg(struct nbl_channel_mgt *chan_mgt, u16 msg_type,
+				 nbl_chan_resp func, void *callback)
+{
+	return nbl_chan_add_msg_handler(chan_mgt, msg_type, func, callback);
+}
+
+static bool nbl_chan_check_queue_exist(struct nbl_channel_mgt *chan_mgt,
+				       u8 chan_type)
+{
+	struct nbl_chan_info *chan_info = chan_mgt->chan_info[chan_type];
+
+	return chan_info ? true : false;
+}
+
+static void nbl_chan_register_chan_task(struct nbl_channel_mgt *chan_mgt,
+					u8 chan_type, struct work_struct *task)
+{
+	struct nbl_chan_info *chan_info = chan_mgt->chan_info[chan_type];
+
+	chan_info->clean_task = task;
+}
+
+static void nbl_chan_set_queue_state(struct nbl_channel_mgt *chan_mgt,
+				     enum nbl_chan_state state, u8 chan_type,
+				     u8 set)
+{
+	struct nbl_chan_info *chan_info = chan_mgt->chan_info[chan_type];
+
+	if (set)
+		set_bit(state, chan_info->state);
+	else
+		clear_bit(state, chan_info->state);
+}
+
 static struct nbl_channel_ops chan_ops = {
+	.send_msg			= nbl_chan_send_msg,
+	.send_ack			= nbl_chan_send_ack,
+	.register_msg			= nbl_chan_register_msg,
+	.cfg_chan_qinfo_map_table	= nbl_chan_cfg_qinfo_map_table,
+	.check_queue_exist		= nbl_chan_check_queue_exist,
+	.setup_queue			= nbl_chan_setup_queue,
+	.teardown_queue			= nbl_chan_teardown_queue,
+	.clean_queue_subtask		= nbl_chan_clean_queue_subtask,
+	.register_chan_task		= nbl_chan_register_chan_task,
+	.set_queue_state		= nbl_chan_set_queue_state,
 };
 
 static struct nbl_channel_mgt *