ice: Implement transmit and NAPI support

This patch implements ice_start_xmit (the handler for ndo_start_xmit) and
related functions. ice_start_xmit ultimately calls ice_tx_map, where the
Tx descriptor is built and posted to the hardware by bumping the ring tail.

This patch also implements ice_napi_poll, which is invoked when there's an
interrupt on the VSI's queues. The interrupt can be due to either a
completed Tx or an Rx event. In case of a completed Tx/Rx event, resources
are reclaimed. Additionally, in case of an Rx event, the skb is fetched
and passed up to the network stack.

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

drivers/net/ethernet/intel/ice/ice.h

@@ -60,6 +60,7 @@
 		(((val) << ICE_AQ_VSI_UP_TABLE_UP##i##_S) & \
 		  ICE_AQ_VSI_UP_TABLE_UP##i##_M)
 
+#define ICE_TX_DESC(R, i) (&(((struct ice_tx_desc *)((R)->desc))[i]))
 #define ICE_RX_DESC(R, i) (&(((union ice_32b_rx_flex_desc *)((R)->desc))[i]))
 
 #define ice_for_each_txq(vsi, i) \

drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h

@@ -131,6 +131,33 @@ enum ice_rx_flg64_bits {
 	ICE_RXFLG_RSVD		= 63
 };
 
+/* for ice_32byte_rx_flex_desc.ptype_flexi_flags0 member */
+#define ICE_RX_FLEX_DESC_PTYPE_M	(0x3FF) /* 10-bits */
+
+/* for ice_32byte_rx_flex_desc.pkt_length member */
+#define ICE_RX_FLX_DESC_PKT_LEN_M	(0x3FFF) /* 14-bits */
+
+enum ice_rx_flex_desc_status_error_0_bits {
+	/* Note: These are predefined bit offsets */
+	ICE_RX_FLEX_DESC_STATUS0_DD_S = 0,
+	ICE_RX_FLEX_DESC_STATUS0_EOF_S,
+	ICE_RX_FLEX_DESC_STATUS0_HBO_S,
+	ICE_RX_FLEX_DESC_STATUS0_L3L4P_S,
+	ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S,
+	ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S,
+	ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S,
+	ICE_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S,
+	ICE_RX_FLEX_DESC_STATUS0_LPBK_S,
+	ICE_RX_FLEX_DESC_STATUS0_IPV6EXADD_S,
+	ICE_RX_FLEX_DESC_STATUS0_RXE_S,
+	ICE_RX_FLEX_DESC_STATUS0_CRCP_S,
+	ICE_RX_FLEX_DESC_STATUS0_RSS_VALID_S,
+	ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S,
+	ICE_RX_FLEX_DESC_STATUS0_XTRMD0_VALID_S,
+	ICE_RX_FLEX_DESC_STATUS0_XTRMD1_VALID_S,
+	ICE_RX_FLEX_DESC_STATUS0_LAST /* this entry must be last!!! */
+};
+
 #define ICE_RXQ_CTX_SIZE_DWORDS		8
 #define ICE_RXQ_CTX_SZ			(ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32))
 
@@ -201,6 +228,25 @@ struct ice_tx_desc {
 	__le64 cmd_type_offset_bsz;
 };
 
+enum ice_tx_desc_dtype_value {
+	ICE_TX_DESC_DTYPE_DATA		= 0x0,
+	ICE_TX_DESC_DTYPE_CTX		= 0x1,
+	/* DESC_DONE - HW has completed write-back of descriptor */
+	ICE_TX_DESC_DTYPE_DESC_DONE	= 0xF,
+};
+
+#define ICE_TXD_QW1_CMD_S	4
+#define ICE_TXD_QW1_CMD_M	(0xFFFUL << ICE_TXD_QW1_CMD_S)
+
+enum ice_tx_desc_cmd_bits {
+	ICE_TX_DESC_CMD_EOP			= 0x0001,
+	ICE_TX_DESC_CMD_RS			= 0x0002,
+};
+
+#define ICE_TXD_QW1_OFFSET_S	16
+#define ICE_TXD_QW1_TX_BUF_SZ_S	34
+#define ICE_TXD_QW1_L2TAG1_S	48
+
 #define ICE_LAN_TXQ_MAX_QGRPS	127
 #define ICE_LAN_TXQ_MAX_QDIS	1023
 

drivers/net/ethernet/intel/ice/ice_main.c

@@ -1258,6 +1258,23 @@ err_txrings:
 	return -ENOMEM;
 }
 
+/**
+ * ice_msix_clean_rings - MSIX mode Interrupt Handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ */
+static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data)
+{
+	struct ice_q_vector *q_vector = (struct ice_q_vector *)data;
+
+	if (!q_vector->tx.ring && !q_vector->rx.ring)
+		return IRQ_HANDLED;
+
+	napi_schedule(&q_vector->napi);
+
+	return IRQ_HANDLED;
+}
+
 /**
  * ice_vsi_alloc - Allocates the next available struct vsi in the PF
  * @pf: board private structure
@@ -1298,6 +1315,8 @@ static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type)
 		if (ice_vsi_alloc_arrays(vsi, true))
 			goto err_rings;
 
+		/* Setup default MSIX irq handler for VSI */
+		vsi->irq_handler = ice_msix_clean_rings;
 		break;
 	default:
 		dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type);
@@ -1741,6 +1760,9 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx)
 	if (cpu_online(v_idx))
 		cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
 
+	if (vsi->netdev)
+		netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll,
+			       NAPI_POLL_WEIGHT);
 	/* tie q_vector and vsi together */
 	vsi->q_vectors[v_idx] = q_vector;
 
@@ -2914,6 +2936,21 @@ static int ice_vsi_stop_tx_rx_rings(struct ice_vsi *vsi)
 	return 0;
 }
 
+/**
+ * ice_napi_enable_all - Enable NAPI for all q_vectors in the VSI
+ * @vsi: the VSI being configured
+ */
+static void ice_napi_enable_all(struct ice_vsi *vsi)
+{
+	int q_idx;
+
+	if (!vsi->netdev)
+		return;
+
+	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
+		napi_enable(&vsi->q_vectors[q_idx]->napi);
+}
+
 /**
  * ice_up_complete - Finish the last steps of bringing up a connection
  * @vsi: The VSI being configured
@@ -2939,6 +2976,7 @@ static int ice_up_complete(struct ice_vsi *vsi)
 		return err;
 
 	clear_bit(__ICE_DOWN, vsi->state);
+	ice_napi_enable_all(vsi);
 	ice_vsi_ena_irq(vsi);
 
 	if (vsi->port_info &&
@@ -2954,6 +2992,21 @@ static int ice_up_complete(struct ice_vsi *vsi)
 	return err;
 }
 
+/**
+ * ice_napi_disable_all - Disable NAPI for all q_vectors in the VSI
+ * @vsi: VSI having NAPI disabled
+ */
+static void ice_napi_disable_all(struct ice_vsi *vsi)
+{
+	int q_idx;
+
+	if (!vsi->netdev)
+		return;
+
+	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
+		napi_disable(&vsi->q_vectors[q_idx]->napi);
+}
+
 /**
  * ice_down - Shutdown the connection
  * @vsi: The VSI being stopped
@@ -2972,6 +3025,7 @@ static int ice_down(struct ice_vsi *vsi)
 
 	ice_vsi_dis_irq(vsi);
 	err = ice_vsi_stop_tx_rx_rings(vsi);
+	ice_napi_disable_all(vsi);
 
 	ice_for_each_txq(vsi, i)
 		ice_clean_tx_ring(vsi->tx_rings[i]);
@@ -3251,4 +3305,5 @@ static int ice_stop(struct net_device *netdev)
 static const struct net_device_ops ice_netdev_ops = {
 	.ndo_open = ice_open,
 	.ndo_stop = ice_stop,
+	.ndo_start_xmit = ice_start_xmit,
 };

drivers/net/ethernet/intel/ice/ice_txrx.h

@@ -7,8 +7,23 @@
 #define ICE_DFLT_IRQ_WORK	256
 #define ICE_RXBUF_2048		2048
 #define ICE_MAX_CHAINED_RX_BUFS	5
+#define ICE_MAX_BUF_TXD		8
+#define ICE_MIN_TX_LEN		17
+
+/* The size limit for a transmit buffer in a descriptor is (16K - 1).
+ * In order to align with the read requests we will align the value to
+ * the nearest 4K which represents our maximum read request size.
+ */
+#define ICE_MAX_READ_REQ_SIZE	4096
+#define ICE_MAX_DATA_PER_TXD	(16 * 1024 - 1)
+#define ICE_MAX_DATA_PER_TXD_ALIGNED \
+	(~(ICE_MAX_READ_REQ_SIZE - 1) & ICE_MAX_DATA_PER_TXD)
+
+#define ICE_RX_BUF_WRITE	16	/* Must be power of 2 */
 #define ICE_MAX_TXQ_PER_TXQG	128
 
+/* Tx Descriptors needed, worst case */
+#define DESC_NEEDED (MAX_SKB_FRAGS + 4)
 #define ICE_DESC_UNUSED(R)	\
 	((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
 	(R)->next_to_clean - (R)->next_to_use - 1)
@@ -30,6 +45,24 @@ struct ice_rx_buf {
 	unsigned int page_offset;
 };
 
+struct ice_q_stats {
+	u64 pkts;
+	u64 bytes;
+};
+
+struct ice_txq_stats {
+	u64 restart_q;
+	u64 tx_busy;
+	u64 tx_linearize;
+};
+
+struct ice_rxq_stats {
+	u64 non_eop_descs;
+	u64 alloc_page_failed;
+	u64 alloc_buf_failed;
+	u64 page_reuse_count;
+};
+
 /* this enum matches hardware bits and is meant to be used by DYN_CTLN
  * registers and QINT registers or more generally anywhere in the manual
  * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any
@@ -94,6 +127,15 @@ struct ice_ring {
 	u16 next_to_clean;
 
 	bool ring_active;		/* is ring online or not */
+
+	/* stats structs */
+	struct ice_q_stats	stats;
+	struct u64_stats_sync syncp;
+	union {
+		struct ice_txq_stats tx_stats;
+		struct ice_rxq_stats rx_stats;
+	};
+
 	unsigned int size;		/* length of descriptor ring in bytes */
 	dma_addr_t dma;			/* physical address of ring */
 	struct rcu_head rcu;		/* to avoid race on free */
@@ -121,10 +163,13 @@ struct ice_ring_container {
 	for (pos = (head).ring; pos; pos = pos->next)
 
 bool ice_alloc_rx_bufs(struct ice_ring *rxr, u16 cleaned_count);
+netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev);
 void ice_clean_tx_ring(struct ice_ring *tx_ring);
 void ice_clean_rx_ring(struct ice_ring *rx_ring);
 int ice_setup_tx_ring(struct ice_ring *tx_ring);
 int ice_setup_rx_ring(struct ice_ring *rx_ring);
 void ice_free_tx_ring(struct ice_ring *tx_ring);
 void ice_free_rx_ring(struct ice_ring *rx_ring);
+int ice_napi_poll(struct napi_struct *napi, int budget);
+
 #endif /* _ICE_TXRX_H_ */