Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:6 as permitted sender) client-ip=2620:137:e000::3:6;
From:   Justin Lai <justinlai0215@realtek.com>
To:     <kuba@kernel.org>
CC:     <davem@davemloft.net>, <edumazet@google.com>, <pabeni@redhat.com>,
        <linux-kernel@vger.kernel.org>, <netdev@vger.kernel.org>,
        <andrew@lunn.ch>, Justin Lai <justinlai0215@realtek.com>
Subject: [PATCH net-next v7 02/13] net:ethernet:realtek:rtase: Implement the .ndo_open function
Date:   Tue, 12 Sep 2023 17:18:19 +0800
Message-ID: <20230912091830.338164-3-justinlai0215@realtek.com>
In-Reply-To: <20230912091830.338164-1-justinlai0215@realtek.com>
References: <20230912091830.338164-1-justinlai0215@realtek.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

Implement the .ndo_open function to set default hardware settings
and initialize the descriptor ring and interrupts. Among them,
when requesting irq, because the first group of interrupts needs to
process more events, the overall structure will be different from
other groups of interrupts, so it needs to be processed separately.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
---
 .../net/ethernet/realtek/rtase/rtase_main.c   | 414 ++++++++++++++++++
 1 file changed, 414 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index e2fc2fff9c32..d3d2570a3429 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -129,6 +129,282 @@ static u32 rtase_r32(const struct rtase_private *tp, u16 reg)
 	return readl(tp->mmio_addr + reg);
 }
 
+static void rtase_set_rxbufsize(struct rtase_private *tp,
+				const struct net_device *dev)
+{
+	u32 mtu = dev->mtu;
+
+	tp->rx_buf_sz = (mtu > ETH_DATA_LEN) ?
+			(mtu + ETH_HLEN + 8 + 1) : RX_BUF_SIZE;
+}
+
+static int rtase_alloc_desc(struct rtase_private *tp)
+{
+	struct pci_dev *pdev = tp->pdev;
+	u32 i;
+
+	/* rx and tx descriptors needs 256 bytes alignment.
+	 * dma_alloc_coherent provides more.
+	 */
+	for (i = 0; i < tp->func_tx_queue_num; i++) {
+		tp->tx_ring[i].desc = dma_alloc_coherent(&pdev->dev,
+							 RTASE_TX_RING_DESC_SIZE,
+							 &tp->tx_ring[i].phy_addr,
+							 GFP_KERNEL);
+		if (!tp->tx_ring[i].desc)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < tp->func_rx_queue_num; i++) {
+		tp->rx_ring[i].desc =
+			dma_alloc_coherent(&pdev->dev, RTASE_RX_RING_DESC_SIZE,
+					   &tp->rx_ring[i].phy_addr,
+					   GFP_KERNEL);
+		if (!tp->rx_ring[i].desc)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void rtase_free_desc(struct rtase_private *tp)
+{
+	struct pci_dev *pdev = tp->pdev;
+	u32 i;
+
+	for (i = 0; i < tp->func_tx_queue_num; i++) {
+		if (!tp->tx_ring[i].desc)
+			continue;
+
+		dma_free_coherent(&pdev->dev, RTASE_TX_RING_DESC_SIZE,
+				  tp->tx_ring[i].desc,
+				  tp->tx_ring[i].phy_addr);
+		tp->tx_ring[i].desc = NULL;
+	}
+
+	for (i = 0; i < tp->func_rx_queue_num; i++) {
+		if (!tp->rx_ring[i].desc)
+			continue;
+
+		dma_free_coherent(&pdev->dev, RTASE_RX_RING_DESC_SIZE,
+				  tp->rx_ring[i].desc,
+				  tp->rx_ring[i].phy_addr);
+		tp->rx_ring[i].desc = NULL;
+	}
+}
+
+static void rtase_mark_to_asic(union rx_desc *desc, u32 rx_buf_sz)
+{
+	u32 eor = le32_to_cpu(desc->desc_cmd.opts1) & RING_END;
+
+	desc->desc_status.opts2 = 0;
+	/* force memory writes to complete before releasing descriptor */
+	dma_wmb();
+	WRITE_ONCE(desc->desc_cmd.opts1,
+		   cpu_to_le32(DESC_OWN | eor | rx_buf_sz));
+}
+
+static void rtase_tx_desc_init(struct rtase_private *tp, u16 idx)
+{
+	struct rtase_ring *ring = &tp->tx_ring[idx];
+	struct tx_desc *desc;
+	u32 i;
+
+	memset(ring->desc, 0x0, RTASE_TX_RING_DESC_SIZE);
+	memset(ring->skbuff, 0x0, sizeof(ring->skbuff));
+	ring->cur_idx = 0;
+	ring->dirty_idx = 0;
+	ring->index = idx;
+
+	for (i = 0; i < NUM_DESC; i++) {
+		ring->mis.len[i] = 0;
+		if ((NUM_DESC - 1) == i) {
+			desc = ring->desc + sizeof(struct tx_desc) * i;
+			desc->opts1 = cpu_to_le32(RING_END);
+		}
+	}
+
+	ring->ring_handler = tx_handler;
+	if (idx < 4) {
+		ring->ivec = &tp->int_vector[idx];
+		list_add_tail(&ring->ring_entry,
+			      &tp->int_vector[idx].ring_list);
+	} else {
+		ring->ivec = &tp->int_vector[0];
+		list_add_tail(&ring->ring_entry, &tp->int_vector[0].ring_list);
+	}
+}
+
+static void rtase_map_to_asic(union rx_desc *desc, dma_addr_t mapping,
+			      u32 rx_buf_sz)
+{
+	desc->desc_cmd.addr = cpu_to_le64(mapping);
+	/* make sure the physical address has been updated */
+	wmb();
+	rtase_mark_to_asic(desc, rx_buf_sz);
+}
+
+static void rtase_make_unusable_by_asic(union rx_desc *desc)
+{
+	desc->desc_cmd.addr = RTK_MAGIC_NUMBER;
+	desc->desc_cmd.opts1 &= ~cpu_to_le32(DESC_OWN | RSVD_MASK);
+}
+
+static int rtase_alloc_rx_skb(const struct rtase_ring *ring,
+			      struct sk_buff **p_sk_buff, union rx_desc *desc,
+			      dma_addr_t *rx_phy_addr, u32 rx_buf_sz,
+			      u8 in_intr)
+{
+	struct rtase_int_vector *ivec = ring->ivec;
+	const struct rtase_private *tp = ivec->tp;
+	struct sk_buff *skb = NULL;
+	dma_addr_t mapping;
+	int ret = 0;
+
+	if (in_intr)
+		skb = napi_alloc_skb(&ivec->napi, (rx_buf_sz + RTK_RX_ALIGN));
+	else
+		skb = dev_alloc_skb(rx_buf_sz + RTK_RX_ALIGN);
+
+	if (unlikely(!skb))
+		goto err_out;
+
+	skb_reserve(skb, RTK_RX_ALIGN);
+
+	mapping = dma_map_single(&tp->pdev->dev, skb->data, rx_buf_sz,
+				 DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(&tp->pdev->dev, mapping))) {
+		if (unlikely(net_ratelimit()))
+			netdev_err(tp->dev, "Failed to map RX DMA!\n");
+
+		goto err_out;
+	}
+
+	*p_sk_buff = skb;
+	*rx_phy_addr = mapping;
+	rtase_map_to_asic(desc, mapping, rx_buf_sz);
+
+	return ret;
+
+err_out:
+	if (skb)
+		dev_kfree_skb(skb);
+
+	ret = -ENOMEM;
+	rtase_make_unusable_by_asic(desc);
+
+	return ret;
+}
+
+static u32 rtase_rx_ring_fill(struct rtase_ring *ring, u32 ring_start,
+			      u32 ring_end, u8 in_intr)
+{
+	const struct rtase_private *tp = ring->ivec->tp;
+	union rx_desc *desc_base = ring->desc;
+	u32 cur;
+
+	for (cur = ring_start; ring_end - cur > 0; cur++) {
+		u32 i = cur % NUM_DESC;
+		union rx_desc *desc = desc_base + i;
+		int ret;
+
+		if (ring->skbuff[i])
+			continue;
+
+		ret = rtase_alloc_rx_skb(ring, &ring->skbuff[i], desc,
+					 &ring->mis.data_phy_addr[i],
+					 tp->rx_buf_sz, in_intr);
+		if (ret)
+			break;
+	}
+
+	return cur - ring_start;
+}
+
+static void rtase_mark_as_last_descriptor(union rx_desc *desc)
+{
+	desc->desc_cmd.opts1 |= cpu_to_le32(RING_END);
+}
+
+static void rtase_rx_ring_clear(struct rtase_ring *ring)
+{
+	const struct rtase_private *tp = ring->ivec->tp;
+	union rx_desc *desc;
+	u32 i;
+
+	for (i = 0; i < NUM_DESC; i++) {
+		desc = ring->desc + sizeof(union rx_desc) * i;
+
+		if (!ring->skbuff[i])
+			continue;
+
+		dma_unmap_single(&tp->pdev->dev,
+				 ring->mis.data_phy_addr[i],
+				 tp->rx_buf_sz,
+				 DMA_FROM_DEVICE);
+
+		dev_kfree_skb(ring->skbuff[i]);
+
+		ring->skbuff[i] = NULL;
+
+		rtase_make_unusable_by_asic(desc);
+	}
+}
+
+static void rtase_rx_desc_init(struct rtase_private *tp, u16 idx)
+{
+	struct rtase_ring *ring = &tp->rx_ring[idx];
+	u16 i;
+
+	memset(ring->desc, 0x0, RTASE_RX_RING_DESC_SIZE);
+	memset(ring->skbuff, 0x0, sizeof(ring->skbuff));
+	ring->cur_idx = 0;
+	ring->dirty_idx = 0;
+	ring->index = idx;
+
+	for (i = 0; i < NUM_DESC; i++)
+		ring->mis.data_phy_addr[i] = 0;
+
+	ring->ring_handler = rx_handler;
+	ring->ivec = &tp->int_vector[idx];
+	list_add_tail(&ring->ring_entry, &tp->int_vector[idx].ring_list);
+}
+
+void rtase_rx_clear(struct rtase_private *tp)
+{
+	u32 i;
+
+	for (i = 0; i < tp->func_rx_queue_num; i++)
+		rtase_rx_ring_clear(&tp->rx_ring[i]);
+}
+
+static int rtase_init_ring(const struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	u32 num;
+	u16 i;
+
+	for (i = 0; i < tp->func_tx_queue_num; i++)
+		rtase_tx_desc_init(tp, i);
+
+	for (i = 0; i < tp->func_rx_queue_num; i++) {
+		rtase_rx_desc_init(tp, i);
+		num = rtase_rx_ring_fill(&tp->rx_ring[i], 0, NUM_DESC, 0);
+		if (num != NUM_DESC)
+			goto err_out;
+
+		rtase_mark_as_last_descriptor(tp->rx_ring[i].desc +
+					      sizeof(union rx_desc) *
+					      (NUM_DESC - 1));
+	}
+
+	return 0;
+
+err_out:
+	rtase_rx_clear(tp);
+	return -ENOMEM;
+}
+
 static void rtase_tally_counter_clear(const struct rtase_private *tp)
 {
 	u32 cmd = lower_32_bits(le64_to_cpu(tp->tally_paddr));
@@ -137,6 +413,134 @@ static void rtase_tally_counter_clear(const struct rtase_private *tp)
 	rtase_w32(tp, RTASE_DTCCR0, cmd | COUNTER_RESET);
 }
 
+static void rtase_nic_enable(const struct net_device *dev)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	u16 rcr = rtase_r16(tp, RTASE_RX_CONFIG_1);
+	u8 val;
+
+	/* PCIe PLA reload */
+	rtase_w16(tp, RTASE_RX_CONFIG_1, rcr & ~PCIE_RELOAD_En);
+	rtase_w16(tp, RTASE_RX_CONFIG_1, rcr | PCIE_RELOAD_En);
+
+	/* set PCIe TE & RE */
+	val = rtase_r8(tp, RTASE_CHIP_CMD);
+	rtase_w8(tp, RTASE_CHIP_CMD, val | TE | RE);
+
+	/* clear rxdv_gated_en */
+	val = rtase_r8(tp, RTASE_MISC);
+	rtase_w8(tp, RTASE_MISC, val & ~RX_DV_GATE_EN);
+}
+
+static void rtase_enable_hw_interrupt(const struct rtase_private *tp)
+{
+	const struct rtase_int_vector *ivec = &tp->int_vector[0];
+	u32 i;
+
+	rtase_w32(tp, ivec->imr_addr, ivec->imr);
+
+	for (i = 1; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		rtase_w16(tp, ivec->imr_addr, ivec->imr);
+	}
+}
+
+void rtase_hw_start(const struct net_device *dev)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+
+	rtase_nic_enable(dev);
+	rtase_enable_hw_interrupt(tp);
+}
+
+static int rtase_open(struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	struct rtase_int_vector *ivec = &tp->int_vector[0];
+	const struct pci_dev *pdev = tp->pdev;
+	int ret;
+	u16 i;
+
+	rtase_set_rxbufsize(tp, dev);
+
+	ret = rtase_alloc_desc(tp);
+	if (ret)
+		goto err_free_all_allocated_mem;
+
+	ret = rtase_init_ring(dev);
+	if (ret)
+		goto err_free_all_allocated_mem;
+
+	INIT_DELAYED_WORK(&tp->task, NULL);
+
+	rtase_hw_config(dev);
+
+	if (tp->sw_flag & SWF_MSIX_ENABLED) {
+		ret = request_irq(ivec->irq, rtase_interrupt, 0,
+				  dev->name, ivec);
+
+		/* request other interrupts to handle multiqueue */
+		for (i = 1; i < tp->int_nums; i++) {
+			if (ret)
+				continue;
+
+			ivec = &tp->int_vector[i];
+			if (ivec->status != 1)
+				continue;
+
+			sprintf((char *)&ivec->name, "%s_int%i", dev->name, i);
+			ret = request_irq(ivec->irq, rtase_q_interrupt, 0,
+					  (char *)&ivec->name, ivec);
+		}
+	} else if (tp->sw_flag & SWF_MSI_ENABLED) {
+		ret = request_irq(pdev->irq, rtase_interrupt, 0, dev->name,
+				  ivec);
+	} else {
+		ret = request_irq(pdev->irq, rtase_interrupt, IRQF_SHARED,
+				  dev->name, ivec);
+	}
+
+	if (ret != 0) {
+		netdev_err(dev, "can't request MSIX interrupt. Error: %d", ret);
+		goto err_free_all_allocated_mem;
+	}
+
+	rtase_hw_start(dev);
+
+	netif_carrier_on(dev);
+	netif_wake_queue(dev);
+	netdev_info(dev, "link up\n");
+
+	goto out;
+
+err_free_all_allocated_mem:
+	rtase_free_desc(tp);
+
+out:
+	return ret;
+}
+
+static int rtase_close(struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	const struct pci_dev *pdev = tp->pdev;
+	u32 i;
+
+	rtase_down(dev);
+
+	if (tp->sw_flag & SWF_MSIX_ENABLED) {
+		for (i = 0; i < tp->int_nums; i++)
+			free_irq(tp->int_vector[i].irq, &tp->int_vector[i]);
+
+	} else {
+		free_irq(pdev->irq, &tp->int_vector[0]);
+	}
+
+	rtase_free_desc(tp);
+
+	return 0;
+}
+
 static void rtase_enable_eem_write(const struct rtase_private *tp)
 {
 	u8 val;
@@ -169,6 +573,11 @@ static void rtase_rar_set(const struct rtase_private *tp, const u8 *addr)
 	rtase_w16(tp, RTASE_LBK_CTRL, LBK_ATLD | LBK_CLR);
 }
 
+static const struct net_device_ops rtase_netdev_ops = {
+	.ndo_open = rtase_open,
+	.ndo_stop = rtase_close,
+};
+
 static void rtase_get_mac_address(struct net_device *dev)
 {
 	struct rtase_private *tp = netdev_priv(dev);
@@ -192,6 +601,11 @@ static void rtase_get_mac_address(struct net_device *dev)
 	ether_addr_copy(dev->perm_addr, dev->dev_addr);
 }
 
+static void rtase_init_netdev_ops(struct net_device *dev)
+{
+	dev->netdev_ops = &rtase_netdev_ops;
+}
+
 static void rtase_reset_interrupt(struct pci_dev *pdev,
 				  const struct rtase_private *tp)
 {
-- 
2.34.1