i40e: add support for XDP_TX action

This patch adds proper XDP_TX action support. For each Tx ring, an
additional XDP Tx ring is allocated and setup. This version does the
DMA mapping in the fast-path, which will penalize performance for
IOMMU enabled systems. Further, debugfs support is not wired up for
the XDP Tx rings.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

drivers/net/ethernet/intel/i40e/i40e.h

@@ -629,6 +629,7 @@ struct i40e_vsi {
 	/* These are containers of ring pointers, allocated at run-time */
 	struct i40e_ring **rx_rings;
 	struct i40e_ring **tx_rings;
+	struct i40e_ring **xdp_rings; /* XDP Tx rings */
 
 	u32  active_filters;
 	u32  promisc_threshold;

drivers/net/ethernet/intel/i40e/i40e_ethtool.c

@@ -1299,6 +1299,17 @@ static void i40e_get_ringparam(struct net_device *netdev,
 	ring->rx_jumbo_pending = 0;
 }
 
+static bool i40e_active_tx_ring_index(struct i40e_vsi *vsi, u16 index)
+{
+	if (i40e_enabled_xdp_vsi(vsi)) {
+		return index < vsi->num_queue_pairs ||
+			(index >= vsi->alloc_queue_pairs &&
+			 index < vsi->alloc_queue_pairs + vsi->num_queue_pairs);
+	}
+
+	return index < vsi->num_queue_pairs;
+}
+
 static int i40e_set_ringparam(struct net_device *netdev,
 			      struct ethtool_ringparam *ring)
 {
@@ -1308,6 +1319,7 @@ static int i40e_set_ringparam(struct net_device *netdev,
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
 	u32 new_rx_count, new_tx_count;
+	u16 tx_alloc_queue_pairs;
 	int timeout = 50;
 	int i, err = 0;
 
@@ -1345,6 +1357,8 @@ static int i40e_set_ringparam(struct net_device *netdev,
 		for (i = 0; i < vsi->num_queue_pairs; i++) {
 			vsi->tx_rings[i]->count = new_tx_count;
 			vsi->rx_rings[i]->count = new_rx_count;
+			if (i40e_enabled_xdp_vsi(vsi))
+				vsi->xdp_rings[i]->count = new_tx_count;
 		}
 		goto done;
 	}
@@ -1354,20 +1368,24 @@ static int i40e_set_ringparam(struct net_device *netdev,
 	 * to the Tx and Rx ring structs.
 	 */
 
-	/* alloc updated Tx resources */
+	/* alloc updated Tx and XDP Tx resources */
+	tx_alloc_queue_pairs = vsi->alloc_queue_pairs *
+			       (i40e_enabled_xdp_vsi(vsi) ? 2 : 1);
 	if (new_tx_count != vsi->tx_rings[0]->count) {
 		netdev_info(netdev,
 			    "Changing Tx descriptor count from %d to %d.\n",
 			    vsi->tx_rings[0]->count, new_tx_count);
-		tx_rings = kcalloc(vsi->alloc_queue_pairs,
+		tx_rings = kcalloc(tx_alloc_queue_pairs,
 				   sizeof(struct i40e_ring), GFP_KERNEL);
 		if (!tx_rings) {
 			err = -ENOMEM;
 			goto done;
 		}
 
-		for (i = 0; i < vsi->num_queue_pairs; i++) {
-			/* clone ring and setup updated count */
+		for (i = 0; i < tx_alloc_queue_pairs; i++) {
+			if (!i40e_active_tx_ring_index(vsi, i))
+				continue;
+
 			tx_rings[i] = *vsi->tx_rings[i];
 			tx_rings[i].count = new_tx_count;
 			/* the desc and bi pointers will be reallocated in the
@@ -1379,6 +1397,8 @@ static int i40e_set_ringparam(struct net_device *netdev,
 			if (err) {
 				while (i) {
 					i--;
+					if (!i40e_active_tx_ring_index(vsi, i))
+						continue;
 					i40e_free_tx_resources(&tx_rings[i]);
 				}
 				kfree(tx_rings);
@@ -1446,10 +1466,12 @@ static int i40e_set_ringparam(struct net_device *netdev,
 	i40e_down(vsi);
 
 	if (tx_rings) {
-		for (i = 0; i < vsi->num_queue_pairs; i++) {
+		for (i = 0; i < tx_alloc_queue_pairs; i++) {
+			if (i40e_active_tx_ring_index(vsi, i)) {
 				i40e_free_tx_resources(vsi->tx_rings[i]);
 				*vsi->tx_rings[i] = tx_rings[i];
 			}
+		}
 		kfree(tx_rings);
 		tx_rings = NULL;
 	}
@@ -1479,8 +1501,10 @@ static int i40e_set_ringparam(struct net_device *netdev,
 free_tx:
 	/* error cleanup if the Rx allocations failed after getting Tx */
 	if (tx_rings) {
-		for (i = 0; i < vsi->num_queue_pairs; i++)
-			i40e_free_tx_resources(&tx_rings[i]);
+		for (i = 0; i < tx_alloc_queue_pairs; i++) {
+			if (i40e_active_tx_ring_index(vsi, i))
+				i40e_free_tx_resources(vsi->tx_rings[i]);
+		}
 		kfree(tx_rings);
 		tx_rings = NULL;
 	}

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -630,6 +630,8 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
 	if (tx_buffer->skb) {
 		if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB)
 			kfree(tx_buffer->raw_buf);
+		else if (ring_is_xdp(ring))
+			page_frag_free(tx_buffer->raw_buf);
 		else
 			dev_kfree_skb_any(tx_buffer->skb);
 		if (dma_unmap_len(tx_buffer, len))
@@ -771,7 +773,10 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		total_bytes += tx_buf->bytecount;
 		total_packets += tx_buf->gso_segs;
 
-		/* free the skb */
+		/* free the skb/XDP data */
+		if (ring_is_xdp(tx_ring))
+			page_frag_free(tx_buf->raw_buf);
+		else
 			napi_consume_skb(tx_buf->skb, napi_budget);
 
 		/* unmap skb header data */
@@ -848,6 +853,9 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 			tx_ring->arm_wb = true;
 	}
 
+	if (ring_is_xdp(tx_ring))
+		return !!budget;
+
 	/* notify netdev of completed buffers */
 	netdev_tx_completed_queue(txring_txq(tx_ring),
 				  total_packets, total_bytes);
@@ -1969,6 +1977,10 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring,
 
 #define I40E_XDP_PASS 0
 #define I40E_XDP_CONSUMED 1
+#define I40E_XDP_TX 2
+
+static int i40e_xmit_xdp_ring(struct xdp_buff *xdp,
+			      struct i40e_ring *xdp_ring);
 
 /**
  * i40e_run_xdp - run an XDP program
@@ -1979,6 +1991,7 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
 				    struct xdp_buff *xdp)
 {
 	int result = I40E_XDP_PASS;
+	struct i40e_ring *xdp_ring;
 	struct bpf_prog *xdp_prog;
 	u32 act;
 
@@ -1992,9 +2005,12 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
 	switch (act) {
 	case XDP_PASS:
 		break;
+	case XDP_TX:
+		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
+		result = i40e_xmit_xdp_ring(xdp, xdp_ring);
+		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
-	case XDP_TX:
 	case XDP_ABORTED:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		/* fallthrough -- handle aborts by dropping packet */
@@ -2007,6 +2023,27 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
 	return ERR_PTR(-result);
 }
 
+/**
+ * i40e_rx_buffer_flip - adjusted rx_buffer to point to an unused region
+ * @rx_ring: Rx ring
+ * @rx_buffer: Rx buffer to adjust
+ * @size: Size of adjustment
+ **/
+static void i40e_rx_buffer_flip(struct i40e_ring *rx_ring,
+				struct i40e_rx_buffer *rx_buffer,
+				unsigned int size)
+{
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+
+	rx_buffer->page_offset ^= truesize;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(i40e_rx_offset(rx_ring) + size);
+
+	rx_buffer->page_offset += truesize;
+#endif
+}
+
 /**
  * i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: rx descriptor ring to transact packets on
@@ -2024,7 +2061,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	struct sk_buff *skb = rx_ring->skb;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
-	bool failure = false;
+	bool failure = false, xdp_xmit = false;
 
 	while (likely(total_rx_packets < budget)) {
 		struct i40e_rx_buffer *rx_buffer;
@@ -2081,9 +2118,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		}
 
 		if (IS_ERR(skb)) {
+			if (PTR_ERR(skb) == -I40E_XDP_TX) {
+				xdp_xmit = true;
+				i40e_rx_buffer_flip(rx_ring, rx_buffer, size);
+			} else {
+				rx_buffer->pagecnt_bias++;
+			}
 			total_rx_bytes += size;
 			total_rx_packets++;
-			rx_buffer->pagecnt_bias++;
 		} else if (skb) {
 			i40e_add_rx_frag(rx_ring, rx_buffer, skb, size);
 		} else if (ring_uses_build_skb(rx_ring)) {
@@ -2131,6 +2173,19 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		total_rx_packets++;
 	}
 
+	if (xdp_xmit) {
+		struct i40e_ring *xdp_ring;
+
+		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
+
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch.
+		 */
+		wmb();
+
+		writel(xdp_ring->next_to_use, xdp_ring->tail);
+	}
+
 	rx_ring->skb = skb;
 
 	u64_stats_update_begin(&rx_ring->syncp);
@@ -3187,6 +3242,59 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	return -1;
 }
 
+/**
+ * i40e_xmit_xdp_ring - transmits an XDP buffer to an XDP Tx ring
+ * @xdp: data to transmit
+ * @xdp_ring: XDP Tx ring
+ **/
+static int i40e_xmit_xdp_ring(struct xdp_buff *xdp,
+			      struct i40e_ring *xdp_ring)
+{
+	u32 size = xdp->data_end - xdp->data;
+	u16 i = xdp_ring->next_to_use;
+	struct i40e_tx_buffer *tx_bi;
+	struct i40e_tx_desc *tx_desc;
+	dma_addr_t dma;
+
+	if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) {
+		xdp_ring->tx_stats.tx_busy++;
+		return I40E_XDP_CONSUMED;
+	}
+
+	dma = dma_map_single(xdp_ring->dev, xdp->data, size, DMA_TO_DEVICE);
+	if (dma_mapping_error(xdp_ring->dev, dma))
+		return I40E_XDP_CONSUMED;
+
+	tx_bi = &xdp_ring->tx_bi[i];
+	tx_bi->bytecount = size;
+	tx_bi->gso_segs = 1;
+	tx_bi->raw_buf = xdp->data;
+
+	/* record length, and DMA address */
+	dma_unmap_len_set(tx_bi, len, size);
+	dma_unmap_addr_set(tx_bi, dma, dma);
+
+	tx_desc = I40E_TX_DESC(xdp_ring, i);
+	tx_desc->buffer_addr = cpu_to_le64(dma);
+	tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC
+						  | I40E_TXD_CMD,
+						  0, size, 0);
+
+	/* Make certain all of the status bits have been updated
+	 * before next_to_watch is written.
+	 */
+	smp_wmb();
+
+	i++;
+	if (i == xdp_ring->count)
+		i = 0;
+
+	tx_bi->next_to_watch = tx_desc;
+	xdp_ring->next_to_use = i;
+
+	return I40E_XDP_TX;
+}
+
 /**
  * i40e_xmit_frame_ring - Sends buffer on Tx ring
  * @skb:     send buffer

drivers/net/ethernet/intel/i40e/i40e_txrx.h

@@ -396,6 +396,7 @@ struct i40e_ring {
 	u16 flags;
 #define I40E_TXR_FLAGS_WB_ON_ITR		BIT(0)
 #define I40E_RXR_FLAGS_BUILD_SKB_ENABLED	BIT(1)
+#define I40E_TXR_FLAGS_XDP			BIT(2)
 
 	/* stats structs */
 	struct i40e_queue_stats	stats;
@@ -438,6 +439,16 @@ static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring)
 	ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
 }
 
+static inline bool ring_is_xdp(struct i40e_ring *ring)
+{
+	return !!(ring->flags & I40E_TXR_FLAGS_XDP);
+}
+
+static inline void set_ring_xdp(struct i40e_ring *ring)
+{
+	ring->flags |= I40E_TXR_FLAGS_XDP;
+}
+
 enum i40e_latency_range {
 	I40E_LOWEST_LATENCY = 0,
 	I40E_LOW_LATENCY = 1,