qede: Add support for XDP_TX

Add support for forwarding via XDP. Once the eBPF is attached,
driver would allocate & configure a designated transmission queue
meant solely for forwarding packets. Said queue would share the
receive-queue's interrupt line, and would have it's own Tx statistics.

Infrastructure changes required for this [spread-out through the code]:
 - Determine the DMA direction of the receive buffers based on the presence
of the eBPF program.
 - Turn the sw Tx ring into a union, as regular/XDP queues have different
needs for releasing resources after completion [regular requires the SKB,
XDP requires the transmitted page].
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/qlogic/qede/qede.h

@@ -258,6 +258,7 @@ struct qede_rx_queue {
 	u16 sw_rx_prod;
 
 	u16 num_rx_buffers; /* Slowpath */
+	u8 data_direction;
 	u8 rxq_id;
 
 	u32 rx_buf_size;
@@ -294,6 +295,7 @@ struct sw_tx_bd {
 };
 
 struct qede_tx_queue {
+	u8 is_xdp;
 	bool is_legacy;
 	u16 sw_tx_cons;
 	u16 sw_tx_prod;
@@ -310,8 +312,18 @@ struct qede_tx_queue {
 	void __iomem *doorbell_addr;
 	union db_prod tx_db;
 	int index; /* Slowpath only */
+#define QEDE_TXQ_XDP_TO_IDX(edev, txq)	((txq)->index - \
+					 QEDE_MAX_TSS_CNT(edev))
+#define QEDE_TXQ_IDX_TO_XDP(edev, idx)	((idx) + QEDE_MAX_TSS_CNT(edev))
+
+	/* Regular Tx requires skb + metadata for release purpose,
+	 * while XDP requires only the pages themselves.
+	 */
+	union {
+		struct sw_tx_bd *skbs;
+		struct page **pages;
+	} sw_tx_ring;
 
-	struct sw_tx_bd *sw_tx_ring;
 	struct qed_chain tx_pbl;
 
 	/* Slowpath; Should be kept in end [unless missing padding] */
@@ -336,10 +348,12 @@ struct qede_fastpath {
 #define QEDE_FASTPATH_COMBINED	(QEDE_FASTPATH_TX | QEDE_FASTPATH_RX)
 	u8			type;
 	u8			id;
+	u8			xdp_xmit;
 	struct napi_struct	napi;
 	struct qed_sb_info	*sb_info;
 	struct qede_rx_queue	*rxq;
 	struct qede_tx_queue	*txq;
+	struct qede_tx_queue	*xdp_tx;
 
 #define VEC_NAME_SIZE	(sizeof(((struct net_device *)0)->name) + 8)
 	char	name[VEC_NAME_SIZE];

drivers/net/ethernet/qlogic/qede/qede_ethtool.c

@@ -165,6 +165,11 @@ static void qede_get_strings_stats_txq(struct qede_dev *edev,
 	int i;
 
 	for (i = 0; i < QEDE_NUM_TQSTATS; i++) {
+		if (txq->is_xdp)
+			sprintf(*buf, "%d [XDP]: %s",
+				QEDE_TXQ_XDP_TO_IDX(edev, txq),
+				qede_tqstats_arr[i].string);
+		else
 			sprintf(*buf, "%d: %s", txq->index,
 				qede_tqstats_arr[i].string);
 		*buf += ETH_GSTRING_LEN;
@@ -195,6 +200,9 @@ static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf)
 		if (fp->type & QEDE_FASTPATH_RX)
 			qede_get_strings_stats_rxq(edev, fp->rxq, &buf);
 
+		if (fp->type & QEDE_FASTPATH_XDP)
+			qede_get_strings_stats_txq(edev, fp->xdp_tx, &buf);
+
 		if (fp->type & QEDE_FASTPATH_TX)
 			qede_get_strings_stats_txq(edev, fp->txq, &buf);
 	}
@@ -268,6 +276,9 @@ static void qede_get_ethtool_stats(struct net_device *dev,
 		if (fp->type & QEDE_FASTPATH_RX)
 			qede_get_ethtool_stats_rxq(fp->rxq, &buf);
 
+		if (fp->type & QEDE_FASTPATH_XDP)
+			qede_get_ethtool_stats_txq(fp->xdp_tx, &buf);
+
 		if (fp->type & QEDE_FASTPATH_TX)
 			qede_get_ethtool_stats_txq(fp->txq, &buf);
 	}
@@ -305,6 +316,9 @@ static int qede_get_sset_count(struct net_device *dev, int stringset)
 		/* Account for the Regular Rx statistics */
 		num_stats += QEDE_RSS_COUNT(edev) * QEDE_NUM_RQSTATS;
 
+		/* Account for XDP statistics [if needed] */
+		if (edev->xdp_prog)
+			num_stats += QEDE_RSS_COUNT(edev) * QEDE_NUM_TQSTATS;
 		return num_stats;
 
 	case ETH_SS_PRIV_FLAGS:
@@ -1216,7 +1230,7 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev,
 
 	/* Fill the entry in the SW ring and the BDs in the FW ring */
 	idx = txq->sw_tx_prod & NUM_TX_BDS_MAX;
-	txq->sw_tx_ring[idx].skb = skb;
+	txq->sw_tx_ring.skbs[idx].skb = skb;
 	first_bd = qed_chain_produce(&txq->tx_pbl);
 	memset(first_bd, 0, sizeof(*first_bd));
 	val = 1 << ETH_TX_1ST_BD_FLAGS_START_BD_SHIFT;
@@ -1270,7 +1284,7 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev,
 	dma_unmap_single(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
 			 BD_UNMAP_LEN(first_bd), DMA_TO_DEVICE);
 	txq->sw_tx_cons++;
-	txq->sw_tx_ring[idx].skb = NULL;
+	txq->sw_tx_ring.skbs[idx].skb = NULL;
 
 	return 0;
 }