@@ -684,8 +684,8 @@ struct idpf_tx_queue {
__cacheline_group_end_aligned(read_mostly);
__cacheline_group_begin_aligned(read_write);
- u16 next_to_use;
- u16 next_to_clean;
+ u32 next_to_use;
+ u32 next_to_clean;
union {
struct {
@@ -4,12 +4,9 @@
#ifndef _IDPF_XDP_H_
#define _IDPF_XDP_H_
-#include <linux/types.h>
+#include <net/libeth/xdp.h>
-struct bpf_prog;
-struct idpf_vport;
-struct net_device;
-struct netdev_bpf;
+#include "idpf_txrx.h"
int idpf_xdp_rxq_info_init_all(const struct idpf_vport *vport);
void idpf_xdp_rxq_info_deinit_all(const struct idpf_vport *vport);
@@ -19,6 +16,99 @@ void idpf_copy_xdp_prog_to_qs(const struct idpf_vport *vport,
int idpf_vport_xdpq_get(const struct idpf_vport *vport);
void idpf_vport_xdpq_put(const struct idpf_vport *vport);
+bool idpf_xdp_tx_flush_bulk(struct libeth_xdp_tx_bulk *bq, u32 flags);
+
+/**
+ * idpf_xdp_tx_xmit - produce a single HW Tx descriptor out of XDP desc
+ * @desc: XDP descriptor to pull the DMA address and length from
+ * @i: descriptor index on the queue to fill
+ * @sq: XDP queue to produce the HW Tx descriptor on
+ * @priv: &xsk_tx_metadata_ops on XSk xmit or %NULL
+ */
+static inline void idpf_xdp_tx_xmit(struct libeth_xdp_tx_desc desc, u32 i,
+ const struct libeth_xdpsq *sq, u64 priv)
+{
+ struct idpf_flex_tx_desc *tx_desc = sq->descs;
+ u32 cmd;
+
+ cmd = FIELD_PREP(IDPF_FLEX_TXD_QW1_DTYPE_M,
+ IDPF_TX_DESC_DTYPE_FLEX_L2TAG1_L2TAG2);
+ if (desc.flags & LIBETH_XDP_TX_LAST)
+ cmd |= FIELD_PREP(IDPF_FLEX_TXD_QW1_CMD_M,
+ IDPF_TX_DESC_CMD_EOP);
+ if (priv && (desc.flags & LIBETH_XDP_TX_CSUM))
+ cmd |= FIELD_PREP(IDPF_FLEX_TXD_QW1_CMD_M,
+ IDPF_TX_FLEX_DESC_CMD_CS_EN);
+
+ tx_desc = &tx_desc[i];
+ tx_desc->buf_addr = cpu_to_le64(desc.addr);
+#ifdef __LIBETH_WORD_ACCESS
+ *(u64 *)&tx_desc->qw1 = ((u64)desc.len << 48) | cmd;
+#else
+ tx_desc->qw1.buf_size = cpu_to_le16(desc.len);
+ tx_desc->qw1.cmd_dtype = cpu_to_le16(cmd);
+#endif
+}
+
+/**
+ * idpf_set_rs_bit - set RS bit on last produced descriptor
+ * @xdpq: XDP queue to produce the HW Tx descriptors on
+ */
+static inline void idpf_set_rs_bit(const struct idpf_tx_queue *xdpq)
+{
+ u32 ntu, cmd;
+
+ ntu = xdpq->next_to_use;
+ if (unlikely(!ntu))
+ ntu = xdpq->desc_count;
+
+ cmd = FIELD_PREP(IDPF_FLEX_TXD_QW1_CMD_M, IDPF_TX_DESC_CMD_RS);
+#ifdef __LIBETH_WORD_ACCESS
+ *(u64 *)&xdpq->flex_tx[ntu - 1].q.qw1 |= cmd;
+#else
+ xdpq->flex_tx[ntu - 1].q.qw1.cmd_dtype |= cpu_to_le16(cmd);
+#endif
+}
+
+/**
+ * idpf_xdpq_update_tail - update the XDP Tx queue tail register
+ * @xdpq: XDP Tx queue
+ */
+static inline void idpf_xdpq_update_tail(const struct idpf_tx_queue *xdpq)
+{
+ dma_wmb();
+ writel_relaxed(xdpq->next_to_use, xdpq->tail);
+}
+
+/**
+ * idpf_xdp_tx_finalize - Update RS bit and bump XDP Tx tail
+ * @_xdpq: XDP Tx queue
+ * @sent: whether any frames were sent
+ * @flush: whether to update RS bit and the tail register
+ *
+ * This function bumps XDP Tx tail and should be called when a batch of packets
+ * has been processed in the napi loop.
+ */
+static inline void idpf_xdp_tx_finalize(void *_xdpq, bool sent, bool flush)
+{
+ struct idpf_tx_queue *xdpq = _xdpq;
+
+ if ((!flush || unlikely(!sent)) &&
+ likely(xdpq->desc_count != xdpq->pending))
+ return;
+
+ libeth_xdpsq_lock(&xdpq->xdp_lock);
+
+ idpf_set_rs_bit(xdpq);
+ idpf_xdpq_update_tail(xdpq);
+
+ libeth_xdpsq_queue_timer(xdpq->timer);
+
+ libeth_xdpsq_unlock(&xdpq->xdp_lock);
+}
+
+void idpf_xdp_set_features(const struct idpf_vport *vport);
+
int idpf_xdp(struct net_device *dev, struct netdev_bpf *xdp);
#endif /* _IDPF_XDP_H_ */
@@ -814,6 +814,8 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
netdev->features |= dflt_features;
netdev->hw_features |= dflt_features | offloads;
netdev->hw_enc_features |= dflt_features | offloads;
+ idpf_xdp_set_features(vport);
+
idpf_set_ethtool_ops(netdev);
netif_set_affinity_auto(netdev);
SET_NETDEV_DEV(netdev, &adapter->pdev->dev);
@@ -1,8 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (C) 2023 Intel Corporation */
-#include <net/libeth/xdp.h>
-
#include "idpf.h"
#include "idpf_virtchnl.h"
#include "xdp.h"
@@ -3247,14 +3245,12 @@ static bool idpf_rx_process_skb_fields(struct sk_buff *skb,
return !__idpf_rx_process_skb_fields(rxq, skb, xdp->desc);
}
-static void
-idpf_xdp_run_pass(struct libeth_xdp_buff *xdp, struct napi_struct *napi,
- struct libeth_rq_napi_stats *ss,
- const struct virtchnl2_rx_flex_desc_adv_nic_3 *desc)
-{
- libeth_xdp_run_pass(xdp, NULL, napi, ss, desc, NULL,
- idpf_rx_process_skb_fields);
-}
+LIBETH_XDP_DEFINE_START();
+LIBETH_XDP_DEFINE_RUN(static idpf_xdp_run_pass, idpf_xdp_run_prog,
+ idpf_xdp_tx_flush_bulk, idpf_rx_process_skb_fields);
+LIBETH_XDP_DEFINE_FINALIZE(static idpf_xdp_finalize_rx, idpf_xdp_tx_flush_bulk,
+ idpf_xdp_tx_finalize);
+LIBETH_XDP_DEFINE_END();
/**
* idpf_rx_hsplit_wa - handle header buffer overflows and split errors
@@ -3338,9 +3334,12 @@ static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget)
{
struct idpf_buf_queue *rx_bufq = NULL;
struct libeth_rq_napi_stats rs = { };
+ struct libeth_xdp_tx_bulk bq;
LIBETH_XDP_ONSTACK_BUFF(xdp);
u16 ntc = rxq->next_to_clean;
+ libeth_xdp_tx_init_bulk(&bq, rxq->xdp_prog, rxq->xdp_rxq.dev,
+ rxq->xdpqs, rxq->num_xdp_txq);
libeth_xdp_init_buff(xdp, &rxq->xdp, &rxq->xdp_rxq);
/* Process Rx packets bounded by budget */
@@ -3435,11 +3434,13 @@ static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget)
if (!idpf_rx_splitq_is_eop(rx_desc) || unlikely(!xdp->data))
continue;
- idpf_xdp_run_pass(xdp, rxq->napi, &rs, rx_desc);
+ idpf_xdp_run_pass(xdp, &bq, rxq->napi, &rs, rx_desc);
}
rxq->next_to_clean = ntc;
+
libeth_xdp_save_buff(&rxq->xdp, xdp);
+ idpf_xdp_finalize_rx(&bq);
u64_stats_update_begin(&rxq->stats_sync);
u64_stats_add(&rxq->q_stats.packets, rs.packets);
@@ -1,8 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (C) 2024 Intel Corporation */
-#include <net/libeth/xdp.h>
-
#include "idpf.h"
#include "idpf_virtchnl.h"
#include "xdp.h"
@@ -143,6 +141,8 @@ void idpf_copy_xdp_prog_to_qs(const struct idpf_vport *vport,
idpf_rxq_for_each(vport, idpf_xdp_rxq_assign_prog, xdp_prog);
}
+static void idpf_xdp_tx_timer(struct work_struct *work);
+
int idpf_vport_xdpq_get(const struct idpf_vport *vport)
{
struct libeth_xdpsq_timer **timers __free(kvfree) = NULL;
@@ -183,6 +183,8 @@ int idpf_vport_xdpq_get(const struct idpf_vport *vport)
xdpq->timer = timers[i - sqs];
libeth_xdpsq_get(&xdpq->xdp_lock, dev, vport->xdpq_share);
+ libeth_xdpsq_init_timer(xdpq->timer, xdpq, &xdpq->xdp_lock,
+ idpf_xdp_tx_timer);
xdpq->pending = 0;
xdpq->xdp_tx = 0;
@@ -209,6 +211,7 @@ void idpf_vport_xdpq_put(const struct idpf_vport *vport)
if (!idpf_queue_has_clear(XDP, xdpq))
continue;
+ libeth_xdpsq_deinit_timer(xdpq->timer);
libeth_xdpsq_put(&xdpq->xdp_lock, dev);
kfree(xdpq->timer);
@@ -216,6 +219,154 @@ void idpf_vport_xdpq_put(const struct idpf_vport *vport)
}
}
+static int
+idpf_xdp_parse_compl_desc(const struct idpf_splitq_4b_tx_compl_desc *desc,
+ bool gen)
+{
+ u32 val;
+
+#ifdef __LIBETH_WORD_ACCESS
+ val = *(const u32 *)desc;
+#else
+ val = ((u32)le16_to_cpu(desc->q_head_compl_tag.q_head) << 16) |
+ le16_to_cpu(desc->qid_comptype_gen);
+#endif
+ if (!!(val & IDPF_TXD_COMPLQ_GEN_M) != gen)
+ return -ENODATA;
+
+ if (unlikely((val & GENMASK(IDPF_TXD_COMPLQ_GEN_S - 1, 0)) !=
+ FIELD_PREP(IDPF_TXD_COMPLQ_COMPL_TYPE_M,
+ IDPF_TXD_COMPLT_RS)))
+ return -EINVAL;
+
+ return upper_16_bits(val);
+}
+
+static u32 idpf_xdpsq_poll(struct idpf_tx_queue *xdpsq, u32 budget)
+{
+ struct idpf_compl_queue *cq = xdpsq->complq;
+ u32 tx_ntc = xdpsq->next_to_clean;
+ u32 tx_cnt = xdpsq->desc_count;
+ u32 ntc = cq->next_to_clean;
+ u32 cnt = cq->desc_count;
+ u32 done_frames;
+ bool gen;
+
+ gen = idpf_queue_has(GEN_CHK, cq);
+
+ for (done_frames = 0; done_frames < budget; ) {
+ int ret;
+
+ ret = idpf_xdp_parse_compl_desc(&cq->comp_4b[ntc], gen);
+ if (ret >= 0) {
+ done_frames = ret > tx_ntc ? ret - tx_ntc :
+ ret + tx_cnt - tx_ntc;
+ goto next;
+ }
+
+ switch (ret) {
+ case -ENODATA:
+ goto out;
+ case -EINVAL:
+ break;
+ }
+
+next:
+ if (unlikely(++ntc == cnt)) {
+ ntc = 0;
+ gen = !gen;
+ idpf_queue_change(GEN_CHK, cq);
+ }
+ }
+
+out:
+ cq->next_to_clean = ntc;
+
+ return done_frames;
+}
+
+/**
+ * idpf_clean_xdp_irq - Reclaim a batch of TX resources from completed XDP_TX
+ * @_xdpq: XDP Tx queue
+ * @budget: maximum number of descriptors to clean
+ *
+ * Returns number of cleaned descriptors.
+ */
+static u32 idpf_clean_xdp_irq(void *_xdpq, u32 budget)
+{
+ struct libeth_xdpsq_napi_stats ss = { };
+ struct idpf_tx_queue *xdpq = _xdpq;
+ u32 tx_ntc = xdpq->next_to_clean;
+ u32 tx_cnt = xdpq->desc_count;
+ struct xdp_frame_bulk bq;
+ struct libeth_cq_pp cp = {
+ .dev = xdpq->dev,
+ .bq = &bq,
+ .xss = &ss,
+ .napi = true,
+ };
+ u32 done_frames;
+
+ done_frames = idpf_xdpsq_poll(xdpq, budget);
+ if (unlikely(!done_frames))
+ return 0;
+
+ xdp_frame_bulk_init(&bq);
+
+ for (u32 i = 0; likely(i < done_frames); i++) {
+ libeth_xdp_complete_tx(&xdpq->tx_buf[tx_ntc], &cp);
+
+ if (unlikely(++tx_ntc == tx_cnt))
+ tx_ntc = 0;
+ }
+
+ xdp_flush_frame_bulk(&bq);
+
+ xdpq->next_to_clean = tx_ntc;
+ xdpq->pending -= done_frames;
+ xdpq->xdp_tx -= cp.xdp_tx;
+
+ return done_frames;
+}
+
+static u32 idpf_xdp_tx_prep(void *_xdpq, struct libeth_xdpsq *sq)
+{
+ struct idpf_tx_queue *xdpq = _xdpq;
+ u32 free;
+
+ libeth_xdpsq_lock(&xdpq->xdp_lock);
+
+ free = xdpq->desc_count - xdpq->pending;
+ if (free <= xdpq->thresh)
+ free += idpf_clean_xdp_irq(xdpq, xdpq->thresh);
+
+ *sq = (struct libeth_xdpsq){
+ .sqes = xdpq->tx_buf,
+ .descs = xdpq->desc_ring,
+ .count = xdpq->desc_count,
+ .lock = &xdpq->xdp_lock,
+ .ntu = &xdpq->next_to_use,
+ .pending = &xdpq->pending,
+ .xdp_tx = &xdpq->xdp_tx,
+ };
+
+ return free;
+}
+
+LIBETH_XDP_DEFINE_START();
+LIBETH_XDP_DEFINE_TIMER(static idpf_xdp_tx_timer, idpf_clean_xdp_irq);
+LIBETH_XDP_DEFINE_FLUSH_TX(idpf_xdp_tx_flush_bulk, idpf_xdp_tx_prep,
+ idpf_xdp_tx_xmit);
+LIBETH_XDP_DEFINE_END();
+
+void idpf_xdp_set_features(const struct idpf_vport *vport)
+{
+ if (!idpf_is_queue_model_split(vport->rxq_model))
+ return;
+
+ libeth_xdp_set_features_noredir(vport->netdev);
+}
+
/**
* idpf_xdp_setup_prog - handle XDP program install/remove requests
* @vport: vport to configure