summaryrefslogtreecommitdiff
path: root/drivers/net/mlx5/mlx5_rxtx_vec.c
blob: 9a3a5ae4375c6ea2dd44bbc883a88fdbb92f5577 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright 2017 6WIND S.A.
 * Copyright 2017 Mellanox Technologies, Ltd
 */

#include <assert.h>
#include <stdint.h>
#include <string.h>
#include <stdlib.h>

/* Verbs header. */
/* ISO C doesn't support unnamed structs/unions, disabling -pedantic. */
#ifdef PEDANTIC
#pragma GCC diagnostic ignored "-Wpedantic"
#endif
#include <infiniband/verbs.h>
#include <infiniband/mlx5dv.h>
#ifdef PEDANTIC
#pragma GCC diagnostic error "-Wpedantic"
#endif

#include <rte_mbuf.h>
#include <rte_mempool.h>
#include <rte_prefetch.h>

#include "mlx5.h"
#include "mlx5_utils.h"
#include "mlx5_rxtx.h"
#include "mlx5_rxtx_vec.h"
#include "mlx5_autoconf.h"
#include "mlx5_defs.h"
#include "mlx5_prm.h"

#if defined RTE_ARCH_X86_64
#include "mlx5_rxtx_vec_sse.h"
#elif defined RTE_ARCH_ARM64
#include "mlx5_rxtx_vec_neon.h"
#else
#error "This should not be compiled if SIMD instructions are not supported."
#endif

/**
 * Count the number of packets having same ol_flags and same metadata (if
 * PKT_TX_METADATA is set in ol_flags), and calculate cs_flags.
 *
 * @param pkts
 *   Pointer to array of packets.
 * @param pkts_n
 *   Number of packets.
 * @param cs_flags
 *   Pointer of flags to be returned.
 * @param metadata
 *   Pointer of metadata to be returned.
 * @param txq_offloads
 *   Offloads enabled on Tx queue
 *
 * @return
 *   Number of packets having same ol_flags and metadata, if relevant.
 */
static inline unsigned int
txq_calc_offload(struct rte_mbuf **pkts, uint16_t pkts_n, uint8_t *cs_flags,
		 rte_be32_t *metadata, const uint64_t txq_offloads)
{
	unsigned int pos;
	const uint64_t cksum_ol_mask =
		PKT_TX_IP_CKSUM | PKT_TX_TCP_CKSUM |
		PKT_TX_UDP_CKSUM | PKT_TX_TUNNEL_GRE |
		PKT_TX_TUNNEL_VXLAN | PKT_TX_OUTER_IP_CKSUM;
	rte_be32_t p0_metadata, pn_metadata;

	if (!pkts_n)
		return 0;
	p0_metadata = pkts[0]->ol_flags & PKT_TX_METADATA ?
			pkts[0]->tx_metadata : 0;
	/* Count the number of packets having same offload parameters. */
	for (pos = 1; pos < pkts_n; ++pos) {
		/* Check if packet has same checksum flags. */
		if ((txq_offloads & MLX5_VEC_TX_CKSUM_OFFLOAD_CAP) &&
		    ((pkts[pos]->ol_flags ^ pkts[0]->ol_flags) & cksum_ol_mask))
			break;
		/* Check if packet has same metadata. */
		if (txq_offloads & DEV_TX_OFFLOAD_MATCH_METADATA) {
			pn_metadata = pkts[pos]->ol_flags & PKT_TX_METADATA ?
					pkts[pos]->tx_metadata : 0;
			if (pn_metadata != p0_metadata)
				break;
		}
	}
	*cs_flags = txq_ol_cksum_to_cs(pkts[0]);
	*metadata = p0_metadata;
	return pos;
}

/**
 * DPDK callback for vectorized TX.
 *
 * @param dpdk_txq
 *   Generic pointer to TX queue structure.
 * @param[in] pkts
 *   Packets to transmit.
 * @param pkts_n
 *   Number of packets in array.
 *
 * @return
 *   Number of packets successfully transmitted (<= pkts_n).
 */
uint16_t
mlx5_tx_burst_raw_vec(void *dpdk_txq, struct rte_mbuf **pkts,
		      uint16_t pkts_n)
{
	struct mlx5_txq_data *txq = (struct mlx5_txq_data *)dpdk_txq;
	uint16_t nb_tx = 0;

	while (pkts_n > nb_tx) {
		uint16_t n;
		uint16_t ret;

		n = RTE_MIN((uint16_t)(pkts_n - nb_tx), MLX5_VPMD_TX_MAX_BURST);
		ret = txq_burst_v(txq, &pkts[nb_tx], n, 0, 0);
		nb_tx += ret;
		if (!ret)
			break;
	}
	return nb_tx;
}

/**
 * DPDK callback for vectorized TX with multi-seg packets and offload.
 *
 * @param dpdk_txq
 *   Generic pointer to TX queue structure.
 * @param[in] pkts
 *   Packets to transmit.
 * @param pkts_n
 *   Number of packets in array.
 *
 * @return
 *   Number of packets successfully transmitted (<= pkts_n).
 */
uint16_t
mlx5_tx_burst_vec(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
{
	struct mlx5_txq_data *txq = (struct mlx5_txq_data *)dpdk_txq;
	uint16_t nb_tx = 0;

	while (pkts_n > nb_tx) {
		uint8_t cs_flags = 0;
		uint16_t n;
		uint16_t ret;
		rte_be32_t metadata = 0;

		/* Transmit multi-seg packets in the head of pkts list. */
		if ((txq->offloads & DEV_TX_OFFLOAD_MULTI_SEGS) &&
		    NB_SEGS(pkts[nb_tx]) > 1)
			nb_tx += txq_scatter_v(txq,
					       &pkts[nb_tx],
					       pkts_n - nb_tx);
		n = RTE_MIN((uint16_t)(pkts_n - nb_tx), MLX5_VPMD_TX_MAX_BURST);
		if (txq->offloads & DEV_TX_OFFLOAD_MULTI_SEGS)
			n = txq_count_contig_single_seg(&pkts[nb_tx], n);
		if (txq->offloads & (MLX5_VEC_TX_CKSUM_OFFLOAD_CAP |
				     DEV_TX_OFFLOAD_MATCH_METADATA))
			n = txq_calc_offload(&pkts[nb_tx], n,
					     &cs_flags, &metadata,
					     txq->offloads);
		ret = txq_burst_v(txq, &pkts[nb_tx], n, cs_flags, metadata);
		nb_tx += ret;
		if (!ret)
			break;
	}
	return nb_tx;
}

/**
 * Skip error packets.
 *
 * @param rxq
 *   Pointer to RX queue structure.
 * @param[out] pkts
 *   Array to store received packets.
 * @param pkts_n
 *   Maximum number of packets in array.
 *
 * @return
 *   Number of packets successfully received (<= pkts_n).
 */
static uint16_t
rxq_handle_pending_error(struct mlx5_rxq_data *rxq, struct rte_mbuf **pkts,
			 uint16_t pkts_n)
{
	uint16_t n = 0;
	unsigned int i;
#ifdef MLX5_PMD_SOFT_COUNTERS
	uint32_t err_bytes = 0;
#endif

	for (i = 0; i < pkts_n; ++i) {
		struct rte_mbuf *pkt = pkts[i];

		if (pkt->packet_type == RTE_PTYPE_ALL_MASK) {
#ifdef MLX5_PMD_SOFT_COUNTERS
			err_bytes += PKT_LEN(pkt);
#endif
			rte_pktmbuf_free_seg(pkt);
		} else {
			pkts[n++] = pkt;
		}
	}
	rxq->stats.idropped += (pkts_n - n);
#ifdef MLX5_PMD_SOFT_COUNTERS
	/* Correct counters of errored completions. */
	rxq->stats.ipackets -= (pkts_n - n);
	rxq->stats.ibytes -= err_bytes;
#endif
	return n;
}

/**
 * DPDK callback for vectorized RX.
 *
 * @param dpdk_rxq
 *   Generic pointer to RX queue structure.
 * @param[out] pkts
 *   Array to store received packets.
 * @param pkts_n
 *   Maximum number of packets in array.
 *
 * @return
 *   Number of packets successfully received (<= pkts_n).
 */
uint16_t
mlx5_rx_burst_vec(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
{
	struct mlx5_rxq_data *rxq = dpdk_rxq;
	uint16_t nb_rx;
	uint64_t err = 0;

	nb_rx = rxq_burst_v(rxq, pkts, pkts_n, &err);
	if (unlikely(err))
		nb_rx = rxq_handle_pending_error(rxq, pkts, nb_rx);
	return nb_rx;
}

/**
 * Check Tx queue flags are set for raw vectorized Tx.
 *
 * @param dev
 *   Pointer to Ethernet device.
 *
 * @return
 *   1 if supported, negative errno value if not.
 */
int __attribute__((cold))
mlx5_check_raw_vec_tx_support(struct rte_eth_dev *dev)
{
	uint64_t offloads = dev->data->dev_conf.txmode.offloads;

	/* Doesn't support any offload. */
	if (offloads)
		return -ENOTSUP;
	return 1;
}

/**
 * Check a device can support vectorized TX.
 *
 * @param dev
 *   Pointer to Ethernet device.
 *
 * @return
 *   1 if supported, negative errno value if not.
 */
int __attribute__((cold))
mlx5_check_vec_tx_support(struct rte_eth_dev *dev)
{
	struct mlx5_priv *priv = dev->data->dev_private;
	uint64_t offloads = dev->data->dev_conf.txmode.offloads;

	if (!priv->config.tx_vec_en ||
	    priv->txqs_n > (unsigned int)priv->config.txqs_vec ||
	    priv->config.mps != MLX5_MPW_ENHANCED ||
	    offloads & ~MLX5_VEC_TX_OFFLOAD_CAP)
		return -ENOTSUP;
	return 1;
}

/**
 * Check a RX queue can support vectorized RX.
 *
 * @param rxq
 *   Pointer to RX queue.
 *
 * @return
 *   1 if supported, negative errno value if not.
 */
int __attribute__((cold))
mlx5_rxq_check_vec_support(struct mlx5_rxq_data *rxq)
{
	struct mlx5_rxq_ctrl *ctrl =
		container_of(rxq, struct mlx5_rxq_ctrl, rxq);

	if (mlx5_mprq_enabled(ETH_DEV(ctrl->priv)))
		return -ENOTSUP;
	if (!ctrl->priv->config.rx_vec_en || rxq->sges_n != 0)
		return -ENOTSUP;
	return 1;
}

/**
 * Check a device can support vectorized RX.
 *
 * @param dev
 *   Pointer to Ethernet device.
 *
 * @return
 *   1 if supported, negative errno value if not.
 */
int __attribute__((cold))
mlx5_check_vec_rx_support(struct rte_eth_dev *dev)
{
	struct mlx5_priv *priv = dev->data->dev_private;
	uint16_t i;

	if (!priv->config.rx_vec_en)
		return -ENOTSUP;
	if (mlx5_mprq_enabled(dev))
		return -ENOTSUP;
	/* All the configured queues should support. */
	for (i = 0; i < priv->rxqs_n; ++i) {
		struct mlx5_rxq_data *rxq = (*priv->rxqs)[i];

		if (!rxq)
			continue;
		if (mlx5_rxq_check_vec_support(rxq) < 0)
			break;
	}
	if (i != priv->rxqs_n)
		return -ENOTSUP;
	return 1;
}