Merge branch 'net-fec-improve-xdp-copy-mode-and-add-af_xdp-zero-copy-support'

Wei Fang says:

====================
net: fec: improve XDP copy mode and add AF_XDP zero-copy support

This patch set optimizes the XDP copy mode logic as follows.

1. Separate the processing of RX XDP frames from fec_enet_rx_queue(),
and adds a separate function fec_enet_rx_queue_xdp() for handling XDP
frames.

2. For TX XDP packets, using the batch sending method to avoid frequent
MMIO writes.

3. Use the switch statement to check the tx_buf type instead of the
if...else... statement, making the cleanup logic of TX BD ring cleared
and more efficient.

We compared the performance of XDP copy mode before and after applying
this patch set, and the results show that the performance has improved.

Before applying this patch set.
root@imx93evk:~# ./xdp-bench tx eth0
Summary                   396,868 rx/s                  0 err,drop/s
Summary                   396,024 rx/s                  0 err,drop/s

root@imx93evk:~# ./xdp-bench drop eth0
Summary                   684,781 rx/s                  0 err/s
Summary                   675,746 rx/s                  0 err/s

root@imx93evk:~# ./xdp-bench pass eth0
Summary                   208,552 rx/s                  0 err,drop/s
Summary                   208,654 rx/s                  0 err,drop/s

root@imx93evk:~# ./xdp-bench redirect eth0 eth0
eth0->eth0                311,210 rx/s                  0 err,drop/s      311,208 xmit/s
eth0->eth0                310,808 rx/s                  0 err,drop/s      310,809 xmit/s

After applying this patch set.
root@imx93evk:~# ./xdp-bench tx eth0
Summary                   425,778 rx/s                  0 err,drop/s
Summary                   426,042 rx/s                  0 err,drop/s

root@imx93evk:~# ./xdp-bench drop eth0
Summary                   698,351 rx/s                  0 err/s
Summary                   701,882 rx/s                  0 err/s

root@imx93evk:~# ./xdp-bench pass eth0
Summary                   210,348 rx/s                  0 err,drop/s
Summary                   210,016 rx/s                  0 err,drop/s

root@imx93evk:~# ./xdp-bench redirect eth0 eth0
eth0->eth0                354,407 rx/s                  0 err,drop/s      354,401 xmit/s
eth0->eth0                350,381 rx/s                  0 err,drop/s      350,389 xmit/s

This patch set also addes the AF_XDP zero-copy support, and we tested
the performance on i.MX93 platform with xdpsock tool. The following is
the performance comparison of copy mode and zero-copy mode. It can be
seen that the performance of zero-copy mode is better than that of copy
mode.

1. MAC swap L2 forwarding
1.1 Zero-copy mode
root@imx93evk:~# ./xdpsock -i eth0 -l -z
 sock0@eth0:0 l2fwd xdp-drv
                   pps            pkts           1.00
rx                 414715         415455
tx                 414715         415455

1.2 Copy mode
root@imx93evk:~# ./xdpsock -i eth0 -l -c
 sock0@eth0:0 l2fwd xdp-drv
                   pps            pkts           1.00
rx                 356396         356609
tx                 356396         356609

2. TX only
2.1 Zero-copy mode
root@imx93evk:~# ./xdpsock -i eth0 -t -s 64 -z
 sock0@eth0:0 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 1119573        1126720

2.2 Copy mode
root@imx93evk:~# ./xdpsock -i eth0 -t -s 64 -c
sock0@eth0:0 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 406864         407616
====================

Link: https://patch.msgid.link/20260205085742.2685134-1-wei.fang@nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Author: Paolo Abeni

drivers/net/ethernet/freescale/fec.h

@@ -340,6 +340,7 @@ struct bufdesc_ex {
 #define FEC_ENET_TX_FRPPG	(PAGE_SIZE / FEC_ENET_TX_FRSIZE)
 #define TX_RING_SIZE		1024	/* Must be power of two */
 #define TX_RING_MOD_MASK	511	/*   for this to work */
+#define FEC_XSK_TX_BUDGET_MAX	256
 
 #define BD_ENET_RX_INT		0x00800000
 #define BD_ENET_RX_PTP		((ushort)0x0400)
@@ -528,6 +529,8 @@ enum fec_txbuf_type {
 	FEC_TXBUF_T_SKB,
 	FEC_TXBUF_T_XDP_NDO,
 	FEC_TXBUF_T_XDP_TX,
+	FEC_TXBUF_T_XSK_XMIT,
+	FEC_TXBUF_T_XSK_TX,
 };
 
 struct fec_tx_buffer {
@@ -539,6 +542,7 @@ struct fec_enet_priv_tx_q {
 	struct bufdesc_prop bd;
 	unsigned char *tx_bounce[TX_RING_SIZE];
 	struct fec_tx_buffer tx_buf[TX_RING_SIZE];
+	struct xsk_buff_pool *xsk_pool;
 
 	unsigned short tx_stop_threshold;
 	unsigned short tx_wake_threshold;
@@ -548,9 +552,16 @@ struct fec_enet_priv_tx_q {
 	dma_addr_t tso_hdrs_dma;
 };
 
+union fec_rx_buffer {
+	void *buf_p;
+	struct page *page;
+	struct xdp_buff *xdp;
+};
+
 struct fec_enet_priv_rx_q {
 	struct bufdesc_prop bd;
-	struct page *rx_buf[RX_RING_SIZE];
+	union fec_rx_buffer rx_buf[RX_RING_SIZE];
+	struct xsk_buff_pool *xsk_pool;
 
 	/* page_pool */
 	struct page_pool *page_pool;
@@ -643,6 +654,7 @@ struct fec_enet_private {
 	struct pm_qos_request pm_qos_req;
 
 	unsigned int tx_align;
+	unsigned int rx_shift;
 
 	/* hw interrupt coalesce */
 	unsigned int rx_pkts_itr;