ixgbe: add AF_XDP zero-copy Rx support

This patch adds zero-copy Rx support for AF_XDP sockets. Instead of
allocating buffers of type MEM_TYPE_PAGE_SHARED, the Rx frames are
allocated as MEM_TYPE_ZERO_COPY when AF_XDP is enabled for a certain
queue.

All AF_XDP specific functions are added to a new file, ixgbe_xsk.c.

Note that when AF_XDP zero-copy is enabled, the XDP action XDP_PASS
will allocate a new buffer and copy the zero-copy frame prior passing
it to the kernel stack.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: William Tu <u9012063@gmail.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

drivers/net/ethernet/intel/ixgbe/Makefile

@@ -8,7 +8,8 @@ obj-$(CONFIG_IXGBE) += ixgbe.o
 
 ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
               ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
-              ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o
+              ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \
+              ixgbe_xsk.o
 
 ixgbe-$(CONFIG_IXGBE_DCB) +=  ixgbe_dcb.o ixgbe_dcb_82598.o \
                               ixgbe_dcb_82599.o ixgbe_dcb_nl.o

drivers/net/ethernet/intel/ixgbe/ixgbe.h

@@ -228,13 +228,17 @@ struct ixgbe_tx_buffer {
 struct ixgbe_rx_buffer {
 	struct sk_buff *skb;
 	dma_addr_t dma;
+	union {
+		struct {
 			struct page *page;
-#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
 			__u32 page_offset;
-#else
-	__u16 page_offset;
-#endif
 			__u16 pagecnt_bias;
+		};
+		struct {
+			void *addr;
+			u64 handle;
+		};
+	};
 };
 
 struct ixgbe_queue_stats {
@@ -348,6 +352,10 @@ struct ixgbe_ring {
 		struct ixgbe_rx_queue_stats rx_stats;
 	};
 	struct xdp_rxq_info xdp_rxq;
+	struct xdp_umem *xsk_umem;
+	struct zero_copy_allocator zca; /* ZC allocator anchor */
+	u16 ring_idx;		/* {rx,tx,xdp}_ring back reference idx */
+	u16 rx_buf_len;
 } ____cacheline_internodealigned_in_smp;
 
 enum ixgbe_ring_f_enum {
@@ -765,6 +773,11 @@ struct ixgbe_adapter {
 #ifdef CONFIG_XFRM_OFFLOAD
 	struct ixgbe_ipsec *ipsec;
 #endif /* CONFIG_XFRM_OFFLOAD */
+
+	/* AF_XDP zero-copy */
+	struct xdp_umem **xsk_umems;
+	u16 num_xsk_umems_used;
+	u16 num_xsk_umems;
 };
 
 static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)

drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c

@@ -1055,7 +1055,7 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter)
 	int txr_remaining = adapter->num_tx_queues;
 	int xdp_remaining = adapter->num_xdp_queues;
 	int rxr_idx = 0, txr_idx = 0, xdp_idx = 0, v_idx = 0;
-	int err;
+	int err, i;
 
 	/* only one q_vector if MSI-X is disabled. */
 	if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED))
@@ -1097,6 +1097,21 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter)
 		xdp_idx += xqpv;
 	}
 
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		if (adapter->rx_ring[i])
+			adapter->rx_ring[i]->ring_idx = i;
+	}
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		if (adapter->tx_ring[i])
+			adapter->tx_ring[i]->ring_idx = i;
+	}
+
+	for (i = 0; i < adapter->num_xdp_queues; i++) {
+		if (adapter->xdp_ring[i])
+			adapter->xdp_ring[i]->ring_idx = i;
+	}
+
 	return 0;
 
 err_out:

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -34,6 +34,7 @@
 #include <net/tc_act/tc_mirred.h>
 #include <net/vxlan.h>
 #include <net/mpls.h>
+#include <net/xdp_sock.h>
 
 #include "ixgbe.h"
 #include "ixgbe_common.h"
@@ -3176,7 +3177,10 @@ int ixgbe_poll(struct napi_struct *napi, int budget)
 		per_ring_budget = budget;
 
 	ixgbe_for_each_ring(ring, q_vector->rx) {
-		int cleaned = ixgbe_clean_rx_irq(q_vector, ring,
+		int cleaned = ring->xsk_umem ?
+			      ixgbe_clean_rx_irq_zc(q_vector, ring,
+						    per_ring_budget) :
+			      ixgbe_clean_rx_irq(q_vector, ring,
 						 per_ring_budget);
 
 		work_done += cleaned;
@@ -3704,10 +3708,27 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
 	srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT;
 
 	/* configure the packet buffer length */
-	if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state))
-		srrctl |= IXGBE_RXBUFFER_3K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+	if (rx_ring->xsk_umem) {
+		u32 xsk_buf_len = rx_ring->xsk_umem->chunk_size_nohr -
+				  XDP_PACKET_HEADROOM;
+
+		/* If the MAC support setting RXDCTL.RLPML, the
+		 * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and
+		 * RXDCTL.RLPML is set to the actual UMEM buffer
+		 * size. If not, then we are stuck with a 1k buffer
+		 * size resolution. In this case frames larger than
+		 * the UMEM buffer size viewed in a 1k resolution will
+		 * be dropped.
+		 */
+		if (hw->mac.type != ixgbe_mac_82599EB)
+			srrctl |= PAGE_SIZE >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
 		else
+			srrctl |= xsk_buf_len >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+	} else if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state)) {
+		srrctl |= IXGBE_RXBUFFER_3K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+	} else {
 		srrctl |= IXGBE_RXBUFFER_2K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+	}
 
 	/* configure descriptor type */
 	srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
@@ -4030,6 +4051,19 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 	u32 rxdctl;
 	u8 reg_idx = ring->reg_idx;
 
+	xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+	ring->xsk_umem = ixgbe_xsk_umem(adapter, ring);
+	if (ring->xsk_umem) {
+		ring->zca.free = ixgbe_zca_free;
+		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						   MEM_TYPE_ZERO_COPY,
+						   &ring->zca));
+
+	} else {
+		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						   MEM_TYPE_PAGE_SHARED, NULL));
+	}
+
 	/* disable queue to avoid use of these values while updating state */
 	rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
 	rxdctl &= ~IXGBE_RXDCTL_ENABLE;
@@ -4079,6 +4113,17 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 #endif
 	}
 
+	if (ring->xsk_umem && hw->mac.type != ixgbe_mac_82599EB) {
+		u32 xsk_buf_len = ring->xsk_umem->chunk_size_nohr -
+				  XDP_PACKET_HEADROOM;
+
+		rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK |
+			    IXGBE_RXDCTL_RLPML_EN);
+		rxdctl |= xsk_buf_len | IXGBE_RXDCTL_RLPML_EN;
+
+		ring->rx_buf_len = xsk_buf_len;
+	}
+
 	/* initialize rx_buffer_info */
 	memset(ring->rx_buffer_info, 0,
 	       sizeof(struct ixgbe_rx_buffer) * ring->count);
@@ -4092,6 +4137,9 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
 
 	ixgbe_rx_desc_queue_enable(adapter, ring);
+	if (ring->xsk_umem)
+		ixgbe_alloc_rx_buffers_zc(ring, ixgbe_desc_unused(ring));
+	else
 		ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring));
 }
 
@@ -5206,6 +5254,11 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 	u16 i = rx_ring->next_to_clean;
 	struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i];
 
+	if (rx_ring->xsk_umem) {
+		ixgbe_xsk_clean_rx_ring(rx_ring);
+		goto skip_free;
+	}
+
 	/* Free all the Rx ring sk_buffs */
 	while (i != rx_ring->next_to_alloc) {
 		if (rx_buffer->skb) {
@@ -5244,6 +5297,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 		}
 	}
 
+skip_free:
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
@@ -6439,7 +6493,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
 	struct device *dev = rx_ring->dev;
 	int orig_node = dev_to_node(dev);
 	int ring_node = -1;
-	int size, err;
+	int size;
 
 	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
 
@@ -6476,13 +6530,6 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
 			     rx_ring->queue_index) < 0)
 		goto err;
 
-	err = xdp_rxq_info_reg_mem_model(&rx_ring->xdp_rxq,
-					 MEM_TYPE_PAGE_SHARED, NULL);
-	if (err) {
-		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-		goto err;
-	}
-
 	rx_ring->xdp_prog = adapter->xdp_prog;
 
 	return 0;
@@ -10198,6 +10245,13 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		xdp->prog_id = adapter->xdp_prog ?
 			adapter->xdp_prog->aux->id : 0;
 		return 0;
+	case XDP_QUERY_XSK_UMEM:
+		return ixgbe_xsk_umem_query(adapter, &xdp->xsk.umem,
+					    xdp->xsk.queue_id);
+	case XDP_SETUP_XSK_UMEM:
+		return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem,
+					    xdp->xsk.queue_id);
+
 	default:
 		return -EINVAL;
 	}

drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h

@@ -23,4 +23,19 @@ void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
 void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring);
 void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring);
 
+struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
+				struct ixgbe_ring *ring);
+int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem,
+			 u16 qid);
+int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
+			 u16 qid);
+
+void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
+
+void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count);
+int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
+			  struct ixgbe_ring *rx_ring,
+			  const int budget);
+void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring);
+
 #endif /* #define _IXGBE_TXRX_COMMON_H_ */