Merge branch 'ionic-xdp-support'

Shannon Nelson says:

====================
ionic: add XDP support

This patchset is new support in ionic for XDP processing,
including basic XDP on Rx packets, TX and REDIRECT, and frags
for jumbo frames.

Since ionic has not yet been converted to use the page_pool APIs,
this uses the simple MEM_TYPE_PAGE_ORDER0 buffering.  There are plans
to convert the driver in the near future.

v4:
 - removed "inline" from short utility functions
 - changed to use "goto err_out" in ionic_xdp_register_rxq_info()
 - added "continue" to reduce nesting in ionic_xdp_queues_config()
 - used xdp_prog in ionic_rx_clean() to flag whether or not to sync
   the rx buffer after calling ionix_xdp_run()
 - swapped order of XDP_TX and XDP_REDIRECT cases in ionic_xdp_run()
   to make patch 6 a little cleaner

v3:
https://lore.kernel.org/netdev/20240210004827.53814-1-shannon.nelson@amd.com/
 - removed budget==0 patch, sent it separately to net

v2:
https://lore.kernel.org/netdev/20240208005725.65134-1-shannon.nelson@amd.com/
 - added calls to txq_trans_cond_update()
 - added a new patch to catch NAPI budget==0

v1:
https://lore.kernel.org/netdev/20240130013042.11586-1-shannon.nelson@amd.com/

RFC:
https://lore.kernel.org/netdev/20240118192500.58665-1-shannon.nelson@amd.com/
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/pensando/ionic/ionic_dev.h

@@ -8,6 +8,7 @@
 #include <linux/mutex.h>
 #include <linux/workqueue.h>
 #include <linux/skbuff.h>
+#include <linux/bpf_trace.h>
 
 #include "ionic_if.h"
 #include "ionic_regs.h"
@@ -195,6 +196,11 @@ typedef void (*ionic_desc_cb)(struct ionic_queue *q,
 #define IONIC_PAGE_GFP_MASK			(GFP_ATOMIC | __GFP_NOWARN |\
 						 __GFP_COMP | __GFP_MEMALLOC)
 
+#define IONIC_XDP_MAX_LINEAR_MTU	(IONIC_PAGE_SIZE -	\
+					 (VLAN_ETH_HLEN +	\
+					  XDP_PACKET_HEADROOM +	\
+					  SKB_DATA_ALIGN(sizeof(struct skb_shared_info))))
+
 struct ionic_buf_info {
 	struct page *page;
 	dma_addr_t dma_addr;
@@ -222,6 +228,8 @@ struct ionic_desc_info {
 	struct ionic_buf_info bufs[MAX_SKB_FRAGS + 1];
 	ionic_desc_cb cb;
 	void *cb_arg;
+	struct xdp_frame *xdpf;
+	enum xdp_action act;
 };
 
 #define IONIC_QUEUE_NAME_MAX_SZ		16
@@ -256,6 +264,9 @@ struct ionic_queue {
 		struct ionic_txq_sg_desc *txq_sgl;
 		struct ionic_rxq_sg_desc *rxq_sgl;
 	};
+	struct xdp_rxq_info *xdp_rxq_info;
+	struct ionic_queue *partner;
+	bool xdp_flush;
 	dma_addr_t base_pa;
 	dma_addr_t cmb_base_pa;
 	dma_addr_t sg_base_pa;

drivers/net/ethernet/pensando/ionic/ionic_ethtool.c

@@ -721,6 +721,11 @@ static int ionic_set_channels(struct net_device *netdev,
 
 	ionic_init_queue_params(lif, &qparam);
 
+	if ((ch->rx_count || ch->tx_count) && lif->xdp_prog) {
+		netdev_info(lif->netdev, "Split Tx/Rx interrupts not available when using XDP\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (ch->rx_count != ch->tx_count) {
 		netdev_info(netdev, "The rx and tx count must be equal\n");
 		return -EINVAL;

drivers/net/ethernet/pensando/ionic/ionic_lif.c

@@ -46,6 +46,9 @@ static int ionic_start_queues(struct ionic_lif *lif);
 static void ionic_stop_queues(struct ionic_lif *lif);
 static void ionic_lif_queue_identify(struct ionic_lif *lif);
 
+static int ionic_xdp_queues_config(struct ionic_lif *lif);
+static void ionic_xdp_unregister_rxq_info(struct ionic_queue *q);
+
 static void ionic_dim_work(struct work_struct *work)
 {
 	struct dim *dim = container_of(work, struct dim, work);
@@ -422,6 +425,7 @@ static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq)
 		qcq->sg_base_pa = 0;
 	}
 
+	ionic_xdp_unregister_rxq_info(&qcq->q);
 	ionic_qcq_intr_free(lif, qcq);
 
 	vfree(qcq->cq.info);
@@ -862,8 +866,7 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq)
 			.type = q->type,
 			.ver = lif->qtype_info[q->type].version,
 			.index = cpu_to_le32(q->index),
-			.flags = cpu_to_le16(IONIC_QINIT_F_IRQ |
-					     IONIC_QINIT_F_SG),
+			.flags = cpu_to_le16(IONIC_QINIT_F_IRQ),
 			.intr_index = cpu_to_le16(cq->bound_intr->index),
 			.pid = cpu_to_le16(q->pid),
 			.ring_size = ilog2(q->num_descs),
@@ -875,6 +878,13 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq)
 	};
 	int err;
 
+	q->partner = &lif->txqcqs[q->index]->q;
+	q->partner->partner = q;
+
+	if (!lif->xdp_prog ||
+	    (lif->xdp_prog->aux && lif->xdp_prog->aux->xdp_has_frags))
+		ctx.cmd.q_init.flags |= cpu_to_le16(IONIC_QINIT_F_SG);
+
 	if (qcq->flags & IONIC_QCQ_F_CMB_RINGS) {
 		ctx.cmd.q_init.flags |= cpu_to_le16(IONIC_QINIT_F_CMB);
 		ctx.cmd.q_init.ring_base = cpu_to_le64(qcq->cmb_q_base_pa);
@@ -1640,6 +1650,12 @@ static int ionic_init_nic_features(struct ionic_lif *lif)
 	netdev->priv_flags |= IFF_UNICAST_FLT |
 			      IFF_LIVE_ADDR_CHANGE;
 
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC    |
+			       NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_RX_SG    |
+			       NETDEV_XDP_ACT_NDO_XMIT |
+			       NETDEV_XDP_ACT_NDO_XMIT_SG;
+
 	return 0;
 }
 
@@ -1777,6 +1793,21 @@ static int ionic_start_queues_reconfig(struct ionic_lif *lif)
 	return err;
 }
 
+static bool ionic_xdp_is_valid_mtu(struct ionic_lif *lif, u32 mtu,
+				   struct bpf_prog *xdp_prog)
+{
+	if (!xdp_prog)
+		return true;
+
+	if (mtu <= IONIC_XDP_MAX_LINEAR_MTU)
+		return true;
+
+	if (xdp_prog->aux && xdp_prog->aux->xdp_has_frags)
+		return true;
+
+	return false;
+}
+
 static int ionic_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
@@ -1789,8 +1820,13 @@ static int ionic_change_mtu(struct net_device *netdev, int new_mtu)
 			.mtu = cpu_to_le32(new_mtu),
 		},
 	};
+	struct bpf_prog *xdp_prog;
 	int err;
 
+	xdp_prog = READ_ONCE(lif->xdp_prog);
+	if (!ionic_xdp_is_valid_mtu(lif, new_mtu, xdp_prog))
+		return -EINVAL;
+
 	err = ionic_adminq_post_wait(lif, &ctx);
 	if (err)
 		return err;
@@ -2166,6 +2202,10 @@ static int ionic_txrx_enable(struct ionic_lif *lif)
 	int derr = 0;
 	int i, err;
 
+	err = ionic_xdp_queues_config(lif);
+	if (err)
+		return err;
+
 	for (i = 0; i < lif->nxqs; i++) {
 		if (!(lif->rxqcqs[i] && lif->txqcqs[i])) {
 			dev_err(lif->ionic->dev, "%s: bad qcq %d\n", __func__, i);
@@ -2211,6 +2251,8 @@ static int ionic_txrx_enable(struct ionic_lif *lif)
 		derr = ionic_qcq_disable(lif, lif->rxqcqs[i], derr);
 	}
 
+	ionic_xdp_queues_config(lif);
+
 	return err;
 }
 
@@ -2668,11 +2710,151 @@ static void ionic_vf_attr_replay(struct ionic_lif *lif)
 	ionic_vf_start(ionic);
 }
 
+static void ionic_xdp_unregister_rxq_info(struct ionic_queue *q)
+{
+	struct xdp_rxq_info *xi;
+
+	if (!q->xdp_rxq_info)
+		return;
+
+	xi = q->xdp_rxq_info;
+	q->xdp_rxq_info = NULL;
+
+	xdp_rxq_info_unreg(xi);
+	kfree(xi);
+}
+
+static int ionic_xdp_register_rxq_info(struct ionic_queue *q, unsigned int napi_id)
+{
+	struct xdp_rxq_info *rxq_info;
+	int err;
+
+	rxq_info = kzalloc(sizeof(*rxq_info), GFP_KERNEL);
+	if (!rxq_info)
+		return -ENOMEM;
+
+	err = xdp_rxq_info_reg(rxq_info, q->lif->netdev, q->index, napi_id);
+	if (err) {
+		dev_err(q->dev, "Queue %d xdp_rxq_info_reg failed, err %d\n",
+			q->index, err);
+		goto err_out;
+	}
+
+	err = xdp_rxq_info_reg_mem_model(rxq_info, MEM_TYPE_PAGE_ORDER0, NULL);
+	if (err) {
+		dev_err(q->dev, "Queue %d xdp_rxq_info_reg_mem_model failed, err %d\n",
+			q->index, err);
+		xdp_rxq_info_unreg(rxq_info);
+		goto err_out;
+	}
+
+	q->xdp_rxq_info = rxq_info;
+
+	return 0;
+
+err_out:
+	kfree(rxq_info);
+	return err;
+}
+
+static int ionic_xdp_queues_config(struct ionic_lif *lif)
+{
+	unsigned int i;
+	int err;
+
+	if (!lif->rxqcqs)
+		return 0;
+
+	/* There's no need to rework memory if not going to/from NULL program.
+	 * If there is no lif->xdp_prog, there should also be no q.xdp_rxq_info
+	 * This way we don't need to keep an *xdp_prog in every queue struct.
+	 */
+	if (!lif->xdp_prog == !lif->rxqcqs[0]->q.xdp_rxq_info)
+		return 0;
+
+	for (i = 0; i < lif->ionic->nrxqs_per_lif && lif->rxqcqs[i]; i++) {
+		struct ionic_queue *q = &lif->rxqcqs[i]->q;
+
+		if (q->xdp_rxq_info) {
+			ionic_xdp_unregister_rxq_info(q);
+			continue;
+		}
+
+		err = ionic_xdp_register_rxq_info(q, lif->rxqcqs[i]->napi.napi_id);
+		if (err) {
+			dev_err(lif->ionic->dev, "failed to register RX queue %d info for XDP, err %d\n",
+				i, err);
+			goto err_out;
+		}
+	}
+
+	return 0;
+
+err_out:
+	for (i = 0; i < lif->ionic->nrxqs_per_lif && lif->rxqcqs[i]; i++)
+		ionic_xdp_unregister_rxq_info(&lif->rxqcqs[i]->q);
+
+	return err;
+}
+
+static int ionic_xdp_config(struct net_device *netdev, struct netdev_bpf *bpf)
+{
+	struct ionic_lif *lif = netdev_priv(netdev);
+	struct bpf_prog *old_prog;
+	u32 maxfs;
+
+	if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) {
+#define XDP_ERR_SPLIT "XDP not available with split Tx/Rx interrupts"
+		NL_SET_ERR_MSG_MOD(bpf->extack, XDP_ERR_SPLIT);
+		netdev_info(lif->netdev, XDP_ERR_SPLIT);
+		return -EOPNOTSUPP;
+	}
+
+	if (!ionic_xdp_is_valid_mtu(lif, netdev->mtu, bpf->prog)) {
+#define XDP_ERR_MTU "MTU is too large for XDP without frags support"
+		NL_SET_ERR_MSG_MOD(bpf->extack, XDP_ERR_MTU);
+		netdev_info(lif->netdev, XDP_ERR_MTU);
+		return -EINVAL;
+	}
+
+	maxfs = __le32_to_cpu(lif->identity->eth.max_frame_size) - VLAN_ETH_HLEN;
+	if (bpf->prog && !(bpf->prog->aux && bpf->prog->aux->xdp_has_frags))
+		maxfs = min_t(u32, maxfs, IONIC_XDP_MAX_LINEAR_MTU);
+	netdev->max_mtu = maxfs;
+
+	if (!netif_running(netdev)) {
+		old_prog = xchg(&lif->xdp_prog, bpf->prog);
+	} else {
+		mutex_lock(&lif->queue_lock);
+		ionic_stop_queues_reconfig(lif);
+		old_prog = xchg(&lif->xdp_prog, bpf->prog);
+		ionic_start_queues_reconfig(lif);
+		mutex_unlock(&lif->queue_lock);
+	}
+
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	return 0;
+}
+
+static int ionic_xdp(struct net_device *netdev, struct netdev_bpf *bpf)
+{
+	switch (bpf->command) {
+	case XDP_SETUP_PROG:
+		return ionic_xdp_config(netdev, bpf);
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops ionic_netdev_ops = {
 	.ndo_open               = ionic_open,
 	.ndo_stop               = ionic_stop,
 	.ndo_eth_ioctl		= ionic_eth_ioctl,
 	.ndo_start_xmit		= ionic_start_xmit,
+	.ndo_bpf		= ionic_xdp,
+	.ndo_xdp_xmit		= ionic_xdp_xmit,
 	.ndo_get_stats64	= ionic_get_stats64,
 	.ndo_set_rx_mode	= ionic_ndo_set_rx_mode,
 	.ndo_set_features	= ionic_set_features,
@@ -2755,6 +2937,8 @@ static void ionic_swap_queues(struct ionic_qcq *a, struct ionic_qcq *b)
 	swap(a->q.base,       b->q.base);
 	swap(a->q.base_pa,    b->q.base_pa);
 	swap(a->q.info,       b->q.info);
+	swap(a->q.xdp_rxq_info, b->q.xdp_rxq_info);
+	swap(a->q.partner,    b->q.partner);
 	swap(a->q_base,       b->q_base);
 	swap(a->q_base_pa,    b->q_base_pa);
 	swap(a->q_size,       b->q_size);
@@ -3391,9 +3575,12 @@ static int ionic_lif_adminq_init(struct ionic_lif *lif)
 
 	napi_enable(&qcq->napi);
 
-	if (qcq->flags & IONIC_QCQ_F_INTR)
+	if (qcq->flags & IONIC_QCQ_F_INTR) {
+		irq_set_affinity_hint(qcq->intr.vector,
+				      &qcq->intr.affinity_mask);
 		ionic_intr_mask(idev->intr_ctrl, qcq->intr.index,
 				IONIC_INTR_MASK_CLEAR);
+	}
 
 	qcq->flags |= IONIC_QCQ_F_INITED;
 

drivers/net/ethernet/pensando/ionic/ionic_lif.h

@@ -37,6 +37,7 @@ struct ionic_tx_stats {
 	u64 dma_map_err;
 	u64 hwstamp_valid;
 	u64 hwstamp_invalid;
+	u64 xdp_frames;
 };
 
 struct ionic_rx_stats {
@@ -51,6 +52,11 @@ struct ionic_rx_stats {
 	u64 alloc_err;
 	u64 hwstamp_valid;
 	u64 hwstamp_invalid;
+	u64 xdp_drop;
+	u64 xdp_aborted;
+	u64 xdp_pass;
+	u64 xdp_tx;
+	u64 xdp_redirect;
 };
 
 #define IONIC_QCQ_F_INITED		BIT(0)
@@ -135,6 +141,12 @@ struct ionic_lif_sw_stats {
 	u64 hw_rx_over_errors;
 	u64 hw_rx_missed_errors;
 	u64 hw_tx_aborted_errors;
+	u64 xdp_drop;
+	u64 xdp_aborted;
+	u64 xdp_pass;
+	u64 xdp_tx;
+	u64 xdp_redirect;
+	u64 xdp_frames;
 };
 
 enum ionic_lif_state_flags {
@@ -230,6 +242,7 @@ struct ionic_lif {
 	struct ionic_phc *phc;
 
 	struct dentry *dentry;
+	struct bpf_prog *xdp_prog;
 };
 
 struct ionic_phc {

drivers/net/ethernet/pensando/ionic/ionic_stats.c

@@ -27,6 +27,12 @@ static const struct ionic_stat_desc ionic_lif_stats_desc[] = {
 	IONIC_LIF_STAT_DESC(hw_rx_over_errors),
 	IONIC_LIF_STAT_DESC(hw_rx_missed_errors),
 	IONIC_LIF_STAT_DESC(hw_tx_aborted_errors),
+	IONIC_LIF_STAT_DESC(xdp_drop),
+	IONIC_LIF_STAT_DESC(xdp_aborted),
+	IONIC_LIF_STAT_DESC(xdp_pass),
+	IONIC_LIF_STAT_DESC(xdp_tx),
+	IONIC_LIF_STAT_DESC(xdp_redirect),
+	IONIC_LIF_STAT_DESC(xdp_frames),
 };
 
 static const struct ionic_stat_desc ionic_port_stats_desc[] = {
@@ -135,6 +141,7 @@ static const struct ionic_stat_desc ionic_tx_stats_desc[] = {
 	IONIC_TX_STAT_DESC(csum_none),
 	IONIC_TX_STAT_DESC(csum),
 	IONIC_TX_STAT_DESC(vlan_inserted),
+	IONIC_TX_STAT_DESC(xdp_frames),
 };
 
 static const struct ionic_stat_desc ionic_rx_stats_desc[] = {
@@ -149,6 +156,11 @@ static const struct ionic_stat_desc ionic_rx_stats_desc[] = {
 	IONIC_RX_STAT_DESC(hwstamp_invalid),
 	IONIC_RX_STAT_DESC(dropped),
 	IONIC_RX_STAT_DESC(vlan_stripped),
+	IONIC_RX_STAT_DESC(xdp_drop),
+	IONIC_RX_STAT_DESC(xdp_aborted),
+	IONIC_RX_STAT_DESC(xdp_pass),
+	IONIC_RX_STAT_DESC(xdp_tx),
+	IONIC_RX_STAT_DESC(xdp_redirect),
 };
 
 #define IONIC_NUM_LIF_STATS ARRAY_SIZE(ionic_lif_stats_desc)
@@ -171,6 +183,7 @@ static void ionic_add_lif_txq_stats(struct ionic_lif *lif, int q_num,
 	stats->tx_csum += txstats->csum;
 	stats->tx_hwstamp_valid += txstats->hwstamp_valid;
 	stats->tx_hwstamp_invalid += txstats->hwstamp_invalid;
+	stats->xdp_frames += txstats->xdp_frames;
 }
 
 static void ionic_add_lif_rxq_stats(struct ionic_lif *lif, int q_num,
@@ -185,6 +198,11 @@ static void ionic_add_lif_rxq_stats(struct ionic_lif *lif, int q_num,
 	stats->rx_csum_error += rxstats->csum_error;
 	stats->rx_hwstamp_valid += rxstats->hwstamp_valid;
 	stats->rx_hwstamp_invalid += rxstats->hwstamp_invalid;
+	stats->xdp_drop += rxstats->xdp_drop;
+	stats->xdp_aborted += rxstats->xdp_aborted;
+	stats->xdp_pass += rxstats->xdp_pass;
+	stats->xdp_tx += rxstats->xdp_tx;
+	stats->xdp_redirect += rxstats->xdp_redirect;
 }
 
 static void ionic_get_lif_stats(struct ionic_lif *lif,

drivers/net/ethernet/pensando/ionic/ionic_txrx.c

@@ -10,6 +10,23 @@
 #include "ionic_lif.h"
 #include "ionic_txrx.h"
 
+static int ionic_maybe_stop_tx(struct ionic_queue *q, int ndescs);
+
+static dma_addr_t ionic_tx_map_single(struct ionic_queue *q,
+				      void *data, size_t len);
+
+static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q,
+				    const skb_frag_t *frag,
+				    size_t offset, size_t len);
+
+static void ionic_tx_desc_unmap_bufs(struct ionic_queue *q,
+				     struct ionic_desc_info *desc_info);
+
+static void ionic_tx_clean(struct ionic_queue *q,
+			   struct ionic_desc_info *desc_info,
+			   struct ionic_cq_info *cq_info,
+			   void *cb_arg);
+
 static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell,
 				  ionic_desc_cb cb_func, void *cb_arg)
 {
@@ -88,6 +105,21 @@ static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q)
 	return netdev_get_tx_queue(q->lif->netdev, q->index);
 }
 
+static void *ionic_rx_buf_va(struct ionic_buf_info *buf_info)
+{
+	return page_address(buf_info->page) + buf_info->page_offset;
+}
+
+static dma_addr_t ionic_rx_buf_pa(struct ionic_buf_info *buf_info)
+{
+	return buf_info->dma_addr + buf_info->page_offset;
+}
+
+static unsigned int ionic_rx_buf_size(struct ionic_buf_info *buf_info)
+{
+	return min_t(u32, IONIC_MAX_BUF_LEN, IONIC_PAGE_SIZE - buf_info->page_offset);
+}
+
 static int ionic_rx_page_alloc(struct ionic_queue *q,
 			       struct ionic_buf_info *buf_info)
 {
@@ -162,7 +194,7 @@ static bool ionic_rx_buf_recycle(struct ionic_queue *q,
 	if (page_to_nid(buf_info->page) != numa_mem_id())
 		return false;
 
-	size = ALIGN(used, IONIC_PAGE_SPLIT_SZ);
+	size = ALIGN(used, q->xdp_rxq_info ? IONIC_PAGE_SIZE : IONIC_PAGE_SPLIT_SZ);
 	buf_info->page_offset += size;
 	if (buf_info->page_offset >= IONIC_PAGE_SIZE)
 		return false;
@@ -174,7 +206,10 @@ static bool ionic_rx_buf_recycle(struct ionic_queue *q,
 
 static struct sk_buff *ionic_rx_frags(struct ionic_queue *q,
 				      struct ionic_desc_info *desc_info,
-				      struct ionic_rxq_comp *comp)
+				      unsigned int headroom,
+				      unsigned int len,
+				      unsigned int num_sg_elems,
+				      bool synced)
 {
 	struct net_device *netdev = q->lif->netdev;
 	struct ionic_buf_info *buf_info;
@@ -183,12 +218,10 @@ static struct sk_buff *ionic_rx_frags(struct ionic_queue *q,
 	struct sk_buff *skb;
 	unsigned int i;
 	u16 frag_len;
-	u16 len;
 
 	stats = q_to_rx_stats(q);
 
 	buf_info = &desc_info->bufs[0];
-	len = le16_to_cpu(comp->len);
 
 	prefetchw(buf_info->page);
 
@@ -200,24 +233,26 @@ static struct sk_buff *ionic_rx_frags(struct ionic_queue *q,
 		return NULL;
 	}
 
-	i = comp->num_sg_elems + 1;
+	i = num_sg_elems + 1;
 	do {
 		if (unlikely(!buf_info->page)) {
 			dev_kfree_skb(skb);
 			return NULL;
 		}
 
-		frag_len = min_t(u16, len, min_t(u32, IONIC_MAX_BUF_LEN,
-						 IONIC_PAGE_SIZE - buf_info->page_offset));
+		if (headroom)
+			frag_len = min_t(u16, len, IONIC_XDP_MAX_LINEAR_MTU + VLAN_ETH_HLEN);
+		else
+			frag_len = min_t(u16, len, ionic_rx_buf_size(buf_info));
 		len -= frag_len;
 
-		dma_sync_single_for_cpu(dev,
-					buf_info->dma_addr + buf_info->page_offset,
-					frag_len, DMA_FROM_DEVICE);
+		if (!synced)
+			dma_sync_single_range_for_cpu(dev, ionic_rx_buf_pa(buf_info),
+						      headroom, frag_len, DMA_FROM_DEVICE);
 
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-				buf_info->page, buf_info->page_offset, frag_len,
-				IONIC_PAGE_SIZE);
+				buf_info->page, buf_info->page_offset + headroom,
+				frag_len, IONIC_PAGE_SIZE);
 
 		if (!ionic_rx_buf_recycle(q, buf_info, frag_len)) {
 			dma_unmap_page(dev, buf_info->dma_addr,
@@ -225,6 +260,10 @@ static struct sk_buff *ionic_rx_frags(struct ionic_queue *q,
 			buf_info->page = NULL;
 		}
 
+		/* only needed on the first buffer */
+		if (headroom)
+			headroom = 0;
+
 		buf_info++;
 
 		i--;
@@ -235,19 +274,19 @@ static struct sk_buff *ionic_rx_frags(struct ionic_queue *q,
 
 static struct sk_buff *ionic_rx_copybreak(struct ionic_queue *q,
 					  struct ionic_desc_info *desc_info,
-					  struct ionic_rxq_comp *comp)
+					  unsigned int headroom,
+					  unsigned int len,
+					  bool synced)
 {
 	struct net_device *netdev = q->lif->netdev;
 	struct ionic_buf_info *buf_info;
 	struct ionic_rx_stats *stats;
 	struct device *dev = q->dev;
 	struct sk_buff *skb;
-	u16 len;
 
 	stats = q_to_rx_stats(q);
 
 	buf_info = &desc_info->bufs[0];
-	len = le16_to_cpu(comp->len);
 
 	skb = napi_alloc_skb(&q_to_qcq(q)->napi, len);
 	if (unlikely(!skb)) {
@@ -262,11 +301,12 @@ static struct sk_buff *ionic_rx_copybreak(struct ionic_queue *q,
 		return NULL;
 	}
 
-	dma_sync_single_for_cpu(dev, buf_info->dma_addr + buf_info->page_offset,
-				len, DMA_FROM_DEVICE);
-	skb_copy_to_linear_data(skb, page_address(buf_info->page) + buf_info->page_offset, len);
-	dma_sync_single_for_device(dev, buf_info->dma_addr + buf_info->page_offset,
-				   len, DMA_FROM_DEVICE);
+	if (!synced)
+		dma_sync_single_range_for_cpu(dev, ionic_rx_buf_pa(buf_info),
+					      headroom, len, DMA_FROM_DEVICE);
+	skb_copy_to_linear_data(skb, ionic_rx_buf_va(buf_info) + headroom, len);
+	dma_sync_single_range_for_device(dev, ionic_rx_buf_pa(buf_info),
+					 headroom, len, DMA_FROM_DEVICE);
 
 	skb_put(skb, len);
 	skb->protocol = eth_type_trans(skb, q->lif->netdev);
@@ -274,6 +314,315 @@ static struct sk_buff *ionic_rx_copybreak(struct ionic_queue *q,
 	return skb;
 }
 
+static void ionic_xdp_tx_desc_clean(struct ionic_queue *q,
+				    struct ionic_desc_info *desc_info)
+{
+	unsigned int nbufs = desc_info->nbufs;
+	struct ionic_buf_info *buf_info;
+	struct device *dev = q->dev;
+	int i;
+
+	if (!nbufs)
+		return;
+
+	buf_info = desc_info->bufs;
+	dma_unmap_single(dev, buf_info->dma_addr,
+			 buf_info->len, DMA_TO_DEVICE);
+	if (desc_info->act == XDP_TX)
+		__free_pages(buf_info->page, 0);
+	buf_info->page = NULL;
+
+	buf_info++;
+	for (i = 1; i < nbufs + 1 && buf_info->page; i++, buf_info++) {
+		dma_unmap_page(dev, buf_info->dma_addr,
+			       buf_info->len, DMA_TO_DEVICE);
+		if (desc_info->act == XDP_TX)
+			__free_pages(buf_info->page, 0);
+		buf_info->page = NULL;
+	}
+
+	if (desc_info->act == XDP_REDIRECT)
+		xdp_return_frame(desc_info->xdpf);
+
+	desc_info->nbufs = 0;
+	desc_info->xdpf = NULL;
+	desc_info->act = 0;
+}
+
+static int ionic_xdp_post_frame(struct net_device *netdev,
+				struct ionic_queue *q, struct xdp_frame *frame,
+				enum xdp_action act, struct page *page, int off,
+				bool ring_doorbell)
+{
+	struct ionic_desc_info *desc_info;
+	struct ionic_buf_info *buf_info;
+	struct ionic_tx_stats *stats;
+	struct ionic_txq_desc *desc;
+	size_t len = frame->len;
+	dma_addr_t dma_addr;
+	u64 cmd;
+
+	desc_info = &q->info[q->head_idx];
+	desc = desc_info->txq_desc;
+	buf_info = desc_info->bufs;
+	stats = q_to_tx_stats(q);
+
+	dma_addr = ionic_tx_map_single(q, frame->data, len);
+	if (dma_mapping_error(q->dev, dma_addr)) {
+		stats->dma_map_err++;
+		return -EIO;
+	}
+	buf_info->dma_addr = dma_addr;
+	buf_info->len = len;
+	buf_info->page = page;
+	buf_info->page_offset = off;
+
+	desc_info->nbufs = 1;
+	desc_info->xdpf = frame;
+	desc_info->act = act;
+
+	if (xdp_frame_has_frags(frame)) {
+		struct ionic_txq_sg_elem *elem;
+		struct skb_shared_info *sinfo;
+		struct ionic_buf_info *bi;
+		skb_frag_t *frag;
+		int i;
+
+		bi = &buf_info[1];
+		sinfo = xdp_get_shared_info_from_frame(frame);
+		frag = sinfo->frags;
+		elem = desc_info->txq_sg_desc->elems;
+		for (i = 0; i < sinfo->nr_frags; i++, frag++, bi++) {
+			dma_addr = ionic_tx_map_frag(q, frag, 0, skb_frag_size(frag));
+			if (dma_mapping_error(q->dev, dma_addr)) {
+				stats->dma_map_err++;
+				ionic_tx_desc_unmap_bufs(q, desc_info);
+				return -EIO;
+			}
+			bi->dma_addr = dma_addr;
+			bi->len = skb_frag_size(frag);
+			bi->page = skb_frag_page(frag);
+
+			elem->addr = cpu_to_le64(bi->dma_addr);
+			elem->len = cpu_to_le16(bi->len);
+			elem++;
+
+			desc_info->nbufs++;
+		}
+	}
+
+	cmd = encode_txq_desc_cmd(IONIC_TXQ_DESC_OPCODE_CSUM_NONE,
+				  0, (desc_info->nbufs - 1), buf_info->dma_addr);
+	desc->cmd = cpu_to_le64(cmd);
+	desc->len = cpu_to_le16(len);
+	desc->csum_start = 0;
+	desc->csum_offset = 0;
+
+	stats->xdp_frames++;
+	stats->pkts++;
+	stats->bytes += len;
+
+	ionic_txq_post(q, ring_doorbell, ionic_tx_clean, NULL);
+
+	return 0;
+}
+
+int ionic_xdp_xmit(struct net_device *netdev, int n,
+		   struct xdp_frame **xdp_frames, u32 flags)
+{
+	struct ionic_lif *lif = netdev_priv(netdev);
+	struct ionic_queue *txq;
+	struct netdev_queue *nq;
+	int nxmit;
+	int space;
+	int cpu;
+	int qi;
+
+	if (unlikely(!test_bit(IONIC_LIF_F_UP, lif->state)))
+		return -ENETDOWN;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	/* AdminQ is assumed on cpu 0, while we attempt to affinitize the
+	 * TxRx queue pairs 0..n-1 on cpus 1..n.  We try to keep with that
+	 * affinitization here, but of course irqbalance and friends might
+	 * have juggled things anyway, so we have to check for the 0 case.
+	 */
+	cpu = smp_processor_id();
+	qi = cpu ? (cpu - 1) % lif->nxqs : cpu;
+
+	txq = &lif->txqcqs[qi]->q;
+	nq = netdev_get_tx_queue(netdev, txq->index);
+	__netif_tx_lock(nq, cpu);
+	txq_trans_cond_update(nq);
+
+	if (netif_tx_queue_stopped(nq) ||
+	    unlikely(ionic_maybe_stop_tx(txq, 1))) {
+		__netif_tx_unlock(nq);
+		return -EIO;
+	}
+
+	space = min_t(int, n, ionic_q_space_avail(txq));
+	for (nxmit = 0; nxmit < space ; nxmit++) {
+		if (ionic_xdp_post_frame(netdev, txq, xdp_frames[nxmit],
+					 XDP_REDIRECT,
+					 virt_to_page(xdp_frames[nxmit]->data),
+					 0, false)) {
+			nxmit--;
+			break;
+		}
+	}
+
+	if (flags & XDP_XMIT_FLUSH)
+		ionic_dbell_ring(lif->kern_dbpage, txq->hw_type,
+				 txq->dbval | txq->head_idx);
+
+	ionic_maybe_stop_tx(txq, 4);
+	__netif_tx_unlock(nq);
+
+	return nxmit;
+}
+
+static bool ionic_run_xdp(struct ionic_rx_stats *stats,
+			  struct net_device *netdev,
+			  struct bpf_prog *xdp_prog,
+			  struct ionic_queue *rxq,
+			  struct ionic_buf_info *buf_info,
+			  int len)
+{
+	u32 xdp_action = XDP_ABORTED;
+	struct xdp_buff xdp_buf;
+	struct ionic_queue *txq;
+	struct netdev_queue *nq;
+	struct xdp_frame *xdpf;
+	int remain_len;
+	int frag_len;
+	int err = 0;
+
+	xdp_init_buff(&xdp_buf, IONIC_PAGE_SIZE, rxq->xdp_rxq_info);
+	frag_len = min_t(u16, len, IONIC_XDP_MAX_LINEAR_MTU + VLAN_ETH_HLEN);
+	xdp_prepare_buff(&xdp_buf, ionic_rx_buf_va(buf_info),
+			 XDP_PACKET_HEADROOM, frag_len, false);
+
+	dma_sync_single_range_for_cpu(rxq->dev, ionic_rx_buf_pa(buf_info),
+				      XDP_PACKET_HEADROOM, len,
+				      DMA_FROM_DEVICE);
+
+	prefetchw(&xdp_buf.data_hard_start);
+
+	/*  We limit MTU size to one buffer if !xdp_has_frags, so
+	 *  if the recv len is bigger than one buffer
+	 *     then we know we have frag info to gather
+	 */
+	remain_len = len - frag_len;
+	if (remain_len) {
+		struct skb_shared_info *sinfo;
+		struct ionic_buf_info *bi;
+		skb_frag_t *frag;
+
+		bi = buf_info;
+		sinfo = xdp_get_shared_info_from_buff(&xdp_buf);
+		sinfo->nr_frags = 0;
+		sinfo->xdp_frags_size = 0;
+		xdp_buff_set_frags_flag(&xdp_buf);
+
+		do {
+			if (unlikely(sinfo->nr_frags >= MAX_SKB_FRAGS)) {
+				err = -ENOSPC;
+				goto out_xdp_abort;
+			}
+
+			frag = &sinfo->frags[sinfo->nr_frags];
+			sinfo->nr_frags++;
+			bi++;
+			frag_len = min_t(u16, remain_len, ionic_rx_buf_size(bi));
+			dma_sync_single_range_for_cpu(rxq->dev, ionic_rx_buf_pa(bi),
+						      0, frag_len, DMA_FROM_DEVICE);
+			skb_frag_fill_page_desc(frag, bi->page, 0, frag_len);
+			sinfo->xdp_frags_size += frag_len;
+			remain_len -= frag_len;
+
+			if (page_is_pfmemalloc(bi->page))
+				xdp_buff_set_frag_pfmemalloc(&xdp_buf);
+		} while (remain_len > 0);
+	}
+
+	xdp_action = bpf_prog_run_xdp(xdp_prog, &xdp_buf);
+
+	switch (xdp_action) {
+	case XDP_PASS:
+		stats->xdp_pass++;
+		return false;  /* false = we didn't consume the packet */
+
+	case XDP_DROP:
+		ionic_rx_page_free(rxq, buf_info);
+		stats->xdp_drop++;
+		break;
+
+	case XDP_TX:
+		xdpf = xdp_convert_buff_to_frame(&xdp_buf);
+		if (!xdpf)
+			goto out_xdp_abort;
+
+		txq = rxq->partner;
+		nq = netdev_get_tx_queue(netdev, txq->index);
+		__netif_tx_lock(nq, smp_processor_id());
+		txq_trans_cond_update(nq);
+
+		if (netif_tx_queue_stopped(nq) ||
+		    unlikely(ionic_maybe_stop_tx(txq, 1))) {
+			__netif_tx_unlock(nq);
+			goto out_xdp_abort;
+		}
+
+		dma_unmap_page(rxq->dev, buf_info->dma_addr,
+			       IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
+
+		err = ionic_xdp_post_frame(netdev, txq, xdpf, XDP_TX,
+					   buf_info->page,
+					   buf_info->page_offset,
+					   true);
+		__netif_tx_unlock(nq);
+		if (err) {
+			netdev_dbg(netdev, "tx ionic_xdp_post_frame err %d\n", err);
+			goto out_xdp_abort;
+		}
+		stats->xdp_tx++;
+
+		/* the Tx completion will free the buffers */
+		break;
+
+	case XDP_REDIRECT:
+		/* unmap the pages before handing them to a different device */
+		dma_unmap_page(rxq->dev, buf_info->dma_addr,
+			       IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
+
+		err = xdp_do_redirect(netdev, &xdp_buf, xdp_prog);
+		if (err) {
+			netdev_dbg(netdev, "xdp_do_redirect err %d\n", err);
+			goto out_xdp_abort;
+		}
+		buf_info->page = NULL;
+		rxq->xdp_flush = true;
+		stats->xdp_redirect++;
+		break;
+
+	case XDP_ABORTED:
+	default:
+		goto out_xdp_abort;
+	}
+
+	return true;
+
+out_xdp_abort:
+	trace_xdp_exception(netdev, xdp_prog, xdp_action);
+	ionic_rx_page_free(rxq, buf_info);
+	stats->xdp_aborted++;
+
+	return true;
+}
+
 static void ionic_rx_clean(struct ionic_queue *q,
 			   struct ionic_desc_info *desc_info,
 			   struct ionic_cq_info *cq_info,
@@ -283,7 +632,10 @@ static void ionic_rx_clean(struct ionic_queue *q,
 	struct ionic_qcq *qcq = q_to_qcq(q);
 	struct ionic_rx_stats *stats;
 	struct ionic_rxq_comp *comp;
+	struct bpf_prog *xdp_prog;
+	unsigned int headroom;
 	struct sk_buff *skb;
+	u16 len;
 
 	comp = cq_info->cq_desc + qcq->cq.desc_size - sizeof(*comp);
 
@@ -294,13 +646,21 @@ static void ionic_rx_clean(struct ionic_queue *q,
 		return;
 	}
 
+	len = le16_to_cpu(comp->len);
 	stats->pkts++;
-	stats->bytes += le16_to_cpu(comp->len);
+	stats->bytes += len;
+
+	xdp_prog = READ_ONCE(q->lif->xdp_prog);
+	if (xdp_prog &&
+	    ionic_run_xdp(stats, netdev, xdp_prog, q, desc_info->bufs, len))
+		return;
 
-	if (le16_to_cpu(comp->len) <= q->lif->rx_copybreak)
-		skb = ionic_rx_copybreak(q, desc_info, comp);
+	headroom = q->xdp_rxq_info ? XDP_PACKET_HEADROOM : 0;
+	if (len <= q->lif->rx_copybreak)
+		skb = ionic_rx_copybreak(q, desc_info, headroom, len, !!xdp_prog);
 	else
-		skb = ionic_rx_frags(q, desc_info, comp);
+		skb = ionic_rx_frags(q, desc_info, headroom, len,
+				     comp->num_sg_elems, !!xdp_prog);
 
 	if (unlikely(!skb)) {
 		stats->dropped++;
@@ -367,7 +727,7 @@ static void ionic_rx_clean(struct ionic_queue *q,
 		}
 	}
 
-	if (le16_to_cpu(comp->len) <= q->lif->rx_copybreak)
+	if (len <= q->lif->rx_copybreak)
 		napi_gro_receive(&qcq->napi, skb);
 	else
 		napi_gro_frags(&qcq->napi);
@@ -424,8 +784,9 @@ void ionic_rx_fill(struct ionic_queue *q)
 	unsigned int frag_len;
 	unsigned int nfrags;
 	unsigned int n_fill;
-	unsigned int i, j;
 	unsigned int len;
+	unsigned int i;
+	unsigned int j;
 
 	n_fill = ionic_q_space_avail(q);
 
@@ -434,9 +795,12 @@ void ionic_rx_fill(struct ionic_queue *q)
 	if (n_fill < fill_threshold)
 		return;
 
-	len = netdev->mtu + ETH_HLEN + VLAN_HLEN;
+	len = netdev->mtu + VLAN_ETH_HLEN;
 
 	for (i = n_fill; i; i--) {
+		unsigned int headroom;
+		unsigned int buf_len;
+
 		nfrags = 0;
 		remain_len = len;
 		desc_info = &q->info[q->head_idx];
@@ -451,10 +815,18 @@ void ionic_rx_fill(struct ionic_queue *q)
 			}
 		}
 
-		/* fill main descriptor - buf[0] */
-		desc->addr = cpu_to_le64(buf_info->dma_addr + buf_info->page_offset);
-		frag_len = min_t(u16, len, min_t(u32, IONIC_MAX_BUF_LEN,
-						 IONIC_PAGE_SIZE - buf_info->page_offset));
+		/* fill main descriptor - buf[0]
+		 * XDP uses space in the first buffer, so account for
+		 * head room, tail room, and ip header in the first frag size.
+		 */
+		headroom = q->xdp_rxq_info ? XDP_PACKET_HEADROOM : 0;
+		if (q->xdp_rxq_info)
+			buf_len = IONIC_XDP_MAX_LINEAR_MTU + VLAN_ETH_HLEN;
+		else
+			buf_len = ionic_rx_buf_size(buf_info);
+		frag_len = min_t(u16, len, buf_len);
+
+		desc->addr = cpu_to_le64(ionic_rx_buf_pa(buf_info) + headroom);
 		desc->len = cpu_to_le16(frag_len);
 		remain_len -= frag_len;
 		buf_info++;
@@ -472,10 +844,8 @@ void ionic_rx_fill(struct ionic_queue *q)
 				}
 			}
 
-			sg_elem->addr = cpu_to_le64(buf_info->dma_addr + buf_info->page_offset);
-			frag_len = min_t(u16, remain_len, min_t(u32, IONIC_MAX_BUF_LEN,
-								IONIC_PAGE_SIZE -
-								buf_info->page_offset));
+			sg_elem->addr = cpu_to_le64(ionic_rx_buf_pa(buf_info));
+			frag_len = min_t(u16, remain_len, ionic_rx_buf_size(buf_info));
 			sg_elem->len = cpu_to_le16(frag_len);
 			remain_len -= frag_len;
 			buf_info++;
@@ -601,6 +971,14 @@ int ionic_tx_napi(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
+static void ionic_xdp_do_flush(struct ionic_cq *cq)
+{
+	if (cq->bound_q->xdp_flush) {
+		xdp_do_flush();
+		cq->bound_q->xdp_flush = false;
+	}
+}
+
 int ionic_rx_napi(struct napi_struct *napi, int budget)
 {
 	struct ionic_qcq *qcq = napi_to_qcq(napi);
@@ -621,6 +999,7 @@ int ionic_rx_napi(struct napi_struct *napi, int budget)
 
 	ionic_rx_fill(cq->bound_q);
 
+	ionic_xdp_do_flush(cq);
 	if (work_done < budget && napi_complete_done(napi, work_done)) {
 		ionic_dim_update(qcq, IONIC_LIF_F_RX_DIM_INTR);
 		flags |= IONIC_INTR_CRED_UNMASK;
@@ -670,6 +1049,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget)
 
 	ionic_rx_fill(rxcq->bound_q);
 
+	ionic_xdp_do_flush(rxcq);
 	if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) {
 		ionic_dim_update(rxqcq, 0);
 		flags |= IONIC_INTR_CRED_UNMASK;
@@ -805,6 +1185,16 @@ static void ionic_tx_clean(struct ionic_queue *q,
 	struct sk_buff *skb = cb_arg;
 	u16 qi;
 
+	if (desc_info->xdpf) {
+		ionic_xdp_tx_desc_clean(q->partner, desc_info);
+		stats->clean++;
+
+		if (unlikely(__netif_subqueue_stopped(q->lif->netdev, q->index)))
+			netif_wake_subqueue(q->lif->netdev, q->index);
+
+		return;
+	}
+
 	ionic_tx_desc_unmap_bufs(q, desc_info);
 
 	if (!skb)

drivers/net/ethernet/pensando/ionic/ionic_txrx.h

@@ -17,4 +17,5 @@ netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev);
 bool ionic_rx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info);
 bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info);
 
+int ionic_xdp_xmit(struct net_device *netdev, int n, struct xdp_frame **xdp, u32 flags);
 #endif /* _IONIC_TXRX_H_ */