igb: Add AF_XDP zero-copy Rx support

Add support for AF_XDP zero-copy receive path.

When AF_XDP zero-copy is enabled, the rx buffers are allocated from the
xsk buff pool using igb_alloc_rx_buffers_zc().

Use xsk_pool_get_rx_frame_size() to set SRRCTL rx buf size when zero-copy
is enabled.

Signed-off-by: Sriram Yagnaraman <[email protected]>
[Kurt: Port to v6.12 and provide napi_id for xdp_rxq_info_reg(),
       RCT, remove NETDEV_XDP_ACT_XSK_ZEROCOPY, update NTC handling,
       READ_ONCE() xsk_pool, likelyfy for XDP_REDIRECT case]
Signed-off-by: Kurt Kanzenbach <[email protected]>
Acked-by: Maciej Fijalkowski <[email protected]>
Tested-by: George Kuruvinakunnel <[email protected]>
Signed-off-by: Tony Nguyen <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: sriramy

drivers/net/ethernet/intel/igb/igb.h

@@ -88,6 +88,7 @@ struct igb_adapter;
 #define IGB_XDP_CONSUMED	BIT(0)
 #define IGB_XDP_TX		BIT(1)
 #define IGB_XDP_REDIR		BIT(2)
+#define IGB_XDP_EXIT		BIT(3)
 
 struct vf_data_storage {
 	unsigned char vf_mac_addresses[ETH_ALEN];
@@ -853,6 +854,11 @@ struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter,
 int igb_xsk_pool_setup(struct igb_adapter *adapter,
 		       struct xsk_buff_pool *pool,
 		       u16 qid);
+bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring,
+			     struct xsk_buff_pool *xsk_pool, u16 count);
+void igb_clean_rx_ring_zc(struct igb_ring *rx_ring);
+int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector,
+			struct xsk_buff_pool *xsk_pool, const int budget);
 int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags);
 
 #endif /* _IGB_H_ */

drivers/net/ethernet/intel/igb/igb_main.c

@@ -472,12 +472,17 @@ static void igb_dump(struct igb_adapter *adapter)
 
 		for (i = 0; i < rx_ring->count; i++) {
 			const char *next_desc;
-			struct igb_rx_buffer *buffer_info;
-			buffer_info = &rx_ring->rx_buffer_info[i];
+			dma_addr_t dma = (dma_addr_t)0;
+			struct igb_rx_buffer *buffer_info = NULL;
 			rx_desc = IGB_RX_DESC(rx_ring, i);
 			u0 = (struct my_u0 *)rx_desc;
 			staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
 
+			if (!rx_ring->xsk_pool) {
+				buffer_info = &rx_ring->rx_buffer_info[i];
+				dma = buffer_info->dma;
+			}
+
 			if (i == rx_ring->next_to_use)
 				next_desc = " NTU";
 			else if (i == rx_ring->next_to_clean)
@@ -497,11 +502,11 @@ static void igb_dump(struct igb_adapter *adapter)
 					"R  ", i,
 					le64_to_cpu(u0->a),
 					le64_to_cpu(u0->b),
-					(u64)buffer_info->dma,
+					(u64)dma,
 					next_desc);
 
 				if (netif_msg_pktdata(adapter) &&
-				    buffer_info->dma && buffer_info->page) {
+				    buffer_info && dma && buffer_info->page) {
 					print_hex_dump(KERN_INFO, "",
 					  DUMP_PREFIX_ADDRESS,
 					  16, 1,
@@ -1987,7 +1992,11 @@ static void igb_configure(struct igb_adapter *adapter)
 	 */
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		struct igb_ring *ring = adapter->rx_ring[i];
-		igb_alloc_rx_buffers(ring, igb_desc_unused(ring));
+		if (ring->xsk_pool)
+			igb_alloc_rx_buffers_zc(ring, ring->xsk_pool,
+						igb_desc_unused(ring));
+		else
+			igb_alloc_rx_buffers(ring, igb_desc_unused(ring));
 	}
 }
 
@@ -4409,7 +4418,8 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
 	if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-			       rx_ring->queue_index, 0);
+			       rx_ring->queue_index,
+			       rx_ring->q_vector->napi.napi_id);
 	if (res < 0) {
 		dev_err(dev, "Failed to register xdp_rxq index %u\n",
 			rx_ring->queue_index);
@@ -4705,12 +4715,17 @@ void igb_setup_srrctl(struct igb_adapter *adapter, struct igb_ring *ring)
 	struct e1000_hw *hw = &adapter->hw;
 	int reg_idx = ring->reg_idx;
 	u32 srrctl = 0;
+	u32 buf_size;
 
-	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
-	if (ring_uses_large_buffer(ring))
-		srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+	if (ring->xsk_pool)
+		buf_size = xsk_pool_get_rx_frame_size(ring->xsk_pool);
+	else if (ring_uses_large_buffer(ring))
+		buf_size = IGB_RXBUFFER_3072;
 	else
-		srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+		buf_size = IGB_RXBUFFER_2048;
+
+	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
+	srrctl |= buf_size >> E1000_SRRCTL_BSIZEPKT_SHIFT;
 	srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
 	if (hw->mac.type >= e1000_82580)
 		srrctl |= E1000_SRRCTL_TIMESTAMP;
@@ -4742,9 +4757,17 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	u32 rxdctl = 0;
 
 	xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
-	WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-					   MEM_TYPE_PAGE_SHARED, NULL));
 	WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring));
+	if (ring->xsk_pool) {
+		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						   MEM_TYPE_XSK_BUFF_POOL,
+						   NULL));
+		xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
+	} else {
+		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						   MEM_TYPE_PAGE_SHARED,
+						   NULL));
+	}
 
 	/* disable the queue */
 	wr32(E1000_RXDCTL(reg_idx), 0);
@@ -4771,9 +4794,12 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	rxdctl |= IGB_RX_HTHRESH << 8;
 	rxdctl |= IGB_RX_WTHRESH << 16;
 
-	/* initialize rx_buffer_info */
-	memset(ring->rx_buffer_info, 0,
-	       sizeof(struct igb_rx_buffer) * ring->count);
+	if (ring->xsk_pool)
+		memset(ring->rx_buffer_info_zc, 0,
+		       sizeof(*ring->rx_buffer_info_zc) * ring->count);
+	else
+		memset(ring->rx_buffer_info, 0,
+		       sizeof(*ring->rx_buffer_info) * ring->count);
 
 	/* initialize Rx descriptor 0 */
 	rx_desc = IGB_RX_DESC(ring, 0);
@@ -4961,8 +4987,13 @@ void igb_free_rx_resources(struct igb_ring *rx_ring)
 
 	rx_ring->xdp_prog = NULL;
 	xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-	vfree(rx_ring->rx_buffer_info);
-	rx_ring->rx_buffer_info = NULL;
+	if (rx_ring->xsk_pool) {
+		vfree(rx_ring->rx_buffer_info_zc);
+		rx_ring->rx_buffer_info_zc = NULL;
+	} else {
+		vfree(rx_ring->rx_buffer_info);
+		rx_ring->rx_buffer_info = NULL;
+	}
 
 	/* if not set, then don't free */
 	if (!rx_ring->desc)
@@ -5000,6 +5031,11 @@ void igb_clean_rx_ring(struct igb_ring *rx_ring)
 	dev_kfree_skb(rx_ring->skb);
 	rx_ring->skb = NULL;
 
+	if (rx_ring->xsk_pool) {
+		igb_clean_rx_ring_zc(rx_ring);
+		goto skip_for_xsk;
+	}
+
 	/* Free all the Rx ring sk_buffs */
 	while (i != rx_ring->next_to_alloc) {
 		struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i];
@@ -5027,6 +5063,7 @@ void igb_clean_rx_ring(struct igb_ring *rx_ring)
 			i = 0;
 	}
 
+skip_for_xsk:
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
@@ -8181,6 +8218,7 @@ static int igb_poll(struct napi_struct *napi, int budget)
 	struct igb_q_vector *q_vector = container_of(napi,
 						     struct igb_q_vector,
 						     napi);
+	struct xsk_buff_pool *xsk_pool;
 	bool clean_complete = true;
 	int work_done = 0;
 
@@ -8192,7 +8230,12 @@ static int igb_poll(struct napi_struct *napi, int budget)
 		clean_complete = igb_clean_tx_irq(q_vector, budget);
 
 	if (q_vector->rx.ring) {
-		int cleaned = igb_clean_rx_irq(q_vector, budget);
+		int cleaned;
+
+		xsk_pool = READ_ONCE(q_vector->rx.ring->xsk_pool);
+		cleaned = xsk_pool ?
+			igb_clean_rx_irq_zc(q_vector, xsk_pool, budget) :
+			igb_clean_rx_irq(q_vector, budget);
 
 		work_done += cleaned;
 		if (cleaned >= budget)