summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/i40e/i40e_xsk.c
blob: 567fd67e900efd0b2ef6b38ef7bc789be1dc247c (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
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2018 Intel Corporation. */

#include <linux/bpf_trace.h>
#include <net/xdp_sock_drv.h>
#include <net/xdp.h>

#include "i40e.h"
#include "i40e_txrx_common.h"
#include "i40e_xsk.h"

int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring)
{
	unsigned long sz = sizeof(*rx_ring->rx_bi_zc) * rx_ring->count;

	rx_ring->rx_bi_zc = kzalloc(sz, GFP_KERNEL);
	return rx_ring->rx_bi_zc ? 0 : -ENOMEM;
}

void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring)
{
	memset(rx_ring->rx_bi_zc, 0,
	       sizeof(*rx_ring->rx_bi_zc) * rx_ring->count);
}

static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
{
	return &rx_ring->rx_bi_zc[idx];
}

/**
 * i40e_xsk_pool_enable - Enable/associate an AF_XDP buffer pool to a
 * certain ring/qid
 * @vsi: Current VSI
 * @pool: buffer pool
 * @qid: Rx ring to associate buffer pool with
 *
 * Returns 0 on success, <0 on failure
 **/
static int i40e_xsk_pool_enable(struct i40e_vsi *vsi,
				struct xsk_buff_pool *pool,
				u16 qid)
{
	struct net_device *netdev = vsi->netdev;
	bool if_running;
	int err;

	if (vsi->type != I40E_VSI_MAIN)
		return -EINVAL;

	if (qid >= vsi->num_queue_pairs)
		return -EINVAL;

	if (qid >= netdev->real_num_rx_queues ||
	    qid >= netdev->real_num_tx_queues)
		return -EINVAL;

	err = xsk_pool_dma_map(pool, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR);
	if (err)
		return err;

	set_bit(qid, vsi->af_xdp_zc_qps);

	if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);

	if (if_running) {
		err = i40e_queue_pair_disable(vsi, qid);
		if (err)
			return err;

		err = i40e_queue_pair_enable(vsi, qid);
		if (err)
			return err;

		/* Kick start the NAPI context so that receiving will start */
		err = i40e_xsk_wakeup(vsi->netdev, qid, XDP_WAKEUP_RX);
		if (err)
			return err;
	}

	return 0;
}

/**
 * i40e_xsk_pool_disable - Disassociate an AF_XDP buffer pool from a
 * certain ring/qid
 * @vsi: Current VSI
 * @qid: Rx ring to associate buffer pool with
 *
 * Returns 0 on success, <0 on failure
 **/
static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid)
{
	struct net_device *netdev = vsi->netdev;
	struct xsk_buff_pool *pool;
	bool if_running;
	int err;

	pool = xsk_get_pool_from_qid(netdev, qid);
	if (!pool)
		return -EINVAL;

	if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);

	if (if_running) {
		err = i40e_queue_pair_disable(vsi, qid);
		if (err)
			return err;
	}

	clear_bit(qid, vsi->af_xdp_zc_qps);
	xsk_pool_dma_unmap(pool, I40E_RX_DMA_ATTR);

	if (if_running) {
		err = i40e_queue_pair_enable(vsi, qid);
		if (err)
			return err;
	}

	return 0;
}

/**
 * i40e_xsk_pool_setup - Enable/disassociate an AF_XDP buffer pool to/from
 * a ring/qid
 * @vsi: Current VSI
 * @pool: Buffer pool to enable/associate to a ring, or NULL to disable
 * @qid: Rx ring to (dis)associate buffer pool (from)to
 *
 * This function enables or disables a buffer pool to a certain ring.
 *
 * Returns 0 on success, <0 on failure
 **/
int i40e_xsk_pool_setup(struct i40e_vsi *vsi, struct xsk_buff_pool *pool,
			u16 qid)
{
	return pool ? i40e_xsk_pool_enable(vsi, pool, qid) :
		i40e_xsk_pool_disable(vsi, qid);
}

/**
 * i40e_run_xdp_zc - Executes an XDP program on an xdp_buff
 * @rx_ring: Rx ring
 * @xdp: xdp_buff used as input to the XDP program
 *
 * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR}
 **/
static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
{
	int err, result = I40E_XDP_PASS;
	struct i40e_ring *xdp_ring;
	struct bpf_prog *xdp_prog;
	u32 act;

	rcu_read_lock();
	/* NB! xdp_prog will always be !NULL, due to the fact that
	 * this path is enabled by setting an XDP program.
	 */
	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
	act = bpf_prog_run_xdp(xdp_prog, xdp);

	switch (act) {
	case XDP_PASS:
		break;
	case XDP_TX:
		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
		result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
		break;
	case XDP_REDIRECT:
		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
		break;
	default:
		bpf_warn_invalid_xdp_action(act);
		fallthrough;
	case XDP_ABORTED:
		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
		fallthrough; /* handle aborts by dropping packet */
	case XDP_DROP:
		result = I40E_XDP_CONSUMED;
		break;
	}
	rcu_read_unlock();
	return result;
}

bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
{
	u16 ntu = rx_ring->next_to_use;
	union i40e_rx_desc *rx_desc;
	struct xdp_buff **bi, *xdp;
	dma_addr_t dma;
	bool ok = true;

	rx_desc = I40E_RX_DESC(rx_ring, ntu);
	bi = i40e_rx_bi(rx_ring, ntu);
	do {
		xdp = xsk_buff_alloc(rx_ring->xsk_pool);
		if (!xdp) {
			ok = false;
			goto no_buffers;
		}
		*bi = xdp;
		dma = xsk_buff_xdp_get_dma(xdp);
		rx_desc->read.pkt_addr = cpu_to_le64(dma);
		rx_desc->read.hdr_addr = 0;

		rx_desc++;
		bi++;
		ntu++;

		if (unlikely(ntu == rx_ring->count)) {
			rx_desc = I40E_RX_DESC(rx_ring, 0);
			bi = i40e_rx_bi(rx_ring, 0);
			ntu = 0;
		}

		count--;
	} while (count);

no_buffers:
	if (rx_ring->next_to_use != ntu)
		i40e_release_rx_desc(rx_ring, ntu);

	return ok;
}

/**
 * i40e_construct_skb_zc - Create skbuff from zero-copy Rx buffer
 * @rx_ring: Rx ring
 * @xdp: xdp_buff
 *
 * This functions allocates a new skb from a zero-copy Rx buffer.
 *
 * Returns the skb, or NULL on failure.
 **/
static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
					     struct xdp_buff *xdp)
{
	unsigned int metasize = xdp->data - xdp->data_meta;
	unsigned int datasize = xdp->data_end - xdp->data;
	struct sk_buff *skb;

	/* allocate a skb to store the frags */
	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
			       xdp->data_end - xdp->data_hard_start,
			       GFP_ATOMIC | __GFP_NOWARN);
	if (unlikely(!skb))
		return NULL;

	skb_reserve(skb, xdp->data - xdp->data_hard_start);
	memcpy(__skb_put(skb, datasize), xdp->data, datasize);
	if (metasize)
		skb_metadata_set(skb, metasize);

	xsk_buff_free(xdp);
	return skb;
}

/**
 * i40e_inc_ntc: Advance the next_to_clean index
 * @rx_ring: Rx ring
 **/
static void i40e_inc_ntc(struct i40e_ring *rx_ring)
{
	u32 ntc = rx_ring->next_to_clean + 1;

	ntc = (ntc < rx_ring->count) ? ntc : 0;
	rx_ring->next_to_clean = ntc;
}

/**
 * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring
 * @rx_ring: Rx ring
 * @budget: NAPI budget
 *
 * Returns amount of work completed
 **/
int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
{
	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
	unsigned int xdp_res, xdp_xmit = 0;
	bool failure = false;
	struct sk_buff *skb;

	while (likely(total_rx_packets < (unsigned int)budget)) {
		union i40e_rx_desc *rx_desc;
		struct xdp_buff **bi;
		unsigned int size;
		u64 qword;

		rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean);
		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);

		/* This memory barrier is needed to keep us from reading
		 * any other fields out of the rx_desc until we have
		 * verified the descriptor has been written back.
		 */
		dma_rmb();

		if (i40e_rx_is_programming_status(qword)) {
			i40e_clean_programming_status(rx_ring,
						      rx_desc->raw.qword[0],
						      qword);
			bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
			xsk_buff_free(*bi);
			*bi = NULL;
			cleaned_count++;
			i40e_inc_ntc(rx_ring);
			continue;
		}

		bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
		       I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
		if (!size)
			break;

		bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
		(*bi)->data_end = (*bi)->data + size;
		xsk_buff_dma_sync_for_cpu(*bi, rx_ring->xsk_pool);

		xdp_res = i40e_run_xdp_zc(rx_ring, *bi);
		if (xdp_res) {
			if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR))
				xdp_xmit |= xdp_res;
			else
				xsk_buff_free(*bi);

			*bi = NULL;
			total_rx_bytes += size;
			total_rx_packets++;

			cleaned_count++;
			i40e_inc_ntc(rx_ring);
			continue;
		}

		/* XDP_PASS path */

		/* NB! We are not checking for errors using
		 * i40e_test_staterr with
		 * BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that
		 * SBP is *not* set in PRT_SBPVSI (default not set).
		 */
		skb = i40e_construct_skb_zc(rx_ring, *bi);
		*bi = NULL;
		if (!skb) {
			rx_ring->rx_stats.alloc_buff_failed++;
			break;
		}

		cleaned_count++;
		i40e_inc_ntc(rx_ring);

		if (eth_skb_pad(skb))
			continue;

		total_rx_bytes += skb->len;
		total_rx_packets++;

		i40e_process_skb_fields(rx_ring, rx_desc, skb);
		napi_gro_receive(&rx_ring->q_vector->napi, skb);
	}

	if (cleaned_count >= I40E_RX_BUFFER_WRITE)
		failure = !i40e_alloc_rx_buffers_zc(rx_ring, cleaned_count);

	i40e_finalize_xdp_rx(rx_ring, xdp_xmit);
	i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);

	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {
		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
			xsk_set_rx_need_wakeup(rx_ring->xsk_pool);
		else
			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool);

		return (int)total_rx_packets;
	}
	return failure ? budget : (int)total_rx_packets;
}

/**
 * i40e_xmit_zc - Performs zero-copy Tx AF_XDP
 * @xdp_ring: XDP Tx ring
 * @budget: NAPI budget
 *
 * Returns true if the work is finished.
 **/
static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
{
	unsigned int sent_frames = 0, total_bytes = 0;
	struct i40e_tx_desc *tx_desc = NULL;
	struct i40e_tx_buffer *tx_bi;
	struct xdp_desc desc;
	dma_addr_t dma;

	while (budget-- > 0) {
		if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc))
			break;

		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr);
		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma,
						 desc.len);

		tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
		tx_bi->bytecount = desc.len;

		tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use);
		tx_desc->buffer_addr = cpu_to_le64(dma);
		tx_desc->cmd_type_offset_bsz =
			build_ctob(I40E_TX_DESC_CMD_ICRC
				   | I40E_TX_DESC_CMD_EOP,
				   0, desc.len, 0);

		sent_frames++;
		total_bytes += tx_bi->bytecount;

		xdp_ring->next_to_use++;
		if (xdp_ring->next_to_use == xdp_ring->count)
			xdp_ring->next_to_use = 0;
	}

	if (tx_desc) {
		/* Request an interrupt for the last frame and bump tail ptr. */
		tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS <<
						 I40E_TXD_QW1_CMD_SHIFT);
		i40e_xdp_ring_update_tail(xdp_ring);

		xsk_tx_release(xdp_ring->xsk_pool);
		i40e_update_tx_stats(xdp_ring, sent_frames, total_bytes);
	}

	return !!budget;
}

/**
 * i40e_clean_xdp_tx_buffer - Frees and unmaps an XDP Tx entry
 * @tx_ring: XDP Tx ring
 * @tx_bi: Tx buffer info to clean
 **/
static void i40e_clean_xdp_tx_buffer(struct i40e_ring *tx_ring,
				     struct i40e_tx_buffer *tx_bi)
{
	xdp_return_frame(tx_bi->xdpf);
	tx_ring->xdp_tx_active--;
	dma_unmap_single(tx_ring->dev,
			 dma_unmap_addr(tx_bi, dma),
			 dma_unmap_len(tx_bi, len), DMA_TO_DEVICE);
	dma_unmap_len_set(tx_bi, len, 0);
}

/**
 * i40e_clean_xdp_tx_irq - Completes AF_XDP entries, and cleans XDP entries
 * @vsi: Current VSI
 * @tx_ring: XDP Tx ring
 *
 * Returns true if cleanup/tranmission is done.
 **/
bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring)
{
	struct xsk_buff_pool *bp = tx_ring->xsk_pool;
	u32 i, completed_frames, xsk_frames = 0;
	u32 head_idx = i40e_get_head(tx_ring);
	struct i40e_tx_buffer *tx_bi;
	unsigned int ntc;

	if (head_idx < tx_ring->next_to_clean)
		head_idx += tx_ring->count;
	completed_frames = head_idx - tx_ring->next_to_clean;

	if (completed_frames == 0)
		goto out_xmit;

	if (likely(!tx_ring->xdp_tx_active)) {
		xsk_frames = completed_frames;
		goto skip;
	}

	ntc = tx_ring->next_to_clean;

	for (i = 0; i < completed_frames; i++) {
		tx_bi = &tx_ring->tx_bi[ntc];

		if (tx_bi->xdpf) {
			i40e_clean_xdp_tx_buffer(tx_ring, tx_bi);
			tx_bi->xdpf = NULL;
		} else {
			xsk_frames++;
		}

		if (++ntc >= tx_ring->count)
			ntc = 0;
	}

skip:
	tx_ring->next_to_clean += completed_frames;
	if (unlikely(tx_ring->next_to_clean >= tx_ring->count))
		tx_ring->next_to_clean -= tx_ring->count;

	if (xsk_frames)
		xsk_tx_completed(bp, xsk_frames);

	i40e_arm_wb(tx_ring, vsi, completed_frames);

out_xmit:
	if (xsk_uses_need_wakeup(tx_ring->xsk_pool))
		xsk_set_tx_need_wakeup(tx_ring->xsk_pool);

	return i40e_xmit_zc(tx_ring, I40E_DESC_UNUSED(tx_ring));
}

/**
 * i40e_xsk_wakeup - Implements the ndo_xsk_wakeup
 * @dev: the netdevice
 * @queue_id: queue id to wake up
 * @flags: ignored in our case since we have Rx and Tx in the same NAPI.
 *
 * Returns <0 for errors, 0 otherwise.
 **/
int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
{
	struct i40e_netdev_priv *np = netdev_priv(dev);
	struct i40e_vsi *vsi = np->vsi;
	struct i40e_pf *pf = vsi->back;
	struct i40e_ring *ring;

	if (test_bit(__I40E_CONFIG_BUSY, pf->state))
		return -EAGAIN;

	if (test_bit(__I40E_VSI_DOWN, vsi->state))
		return -ENETDOWN;

	if (!i40e_enabled_xdp_vsi(vsi))
		return -ENXIO;

	if (queue_id >= vsi->num_queue_pairs)
		return -ENXIO;

	if (!vsi->xdp_rings[queue_id]->xsk_pool)
		return -ENXIO;

	ring = vsi->xdp_rings[queue_id];

	/* The idea here is that if NAPI is running, mark a miss, so
	 * it will run again. If not, trigger an interrupt and
	 * schedule the NAPI from interrupt context. If NAPI would be
	 * scheduled here, the interrupt affinity would not be
	 * honored.
	 */
	if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi))
		i40e_force_wb(vsi, ring->q_vector);

	return 0;
}

void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
{
	u16 i;

	for (i = 0; i < rx_ring->count; i++) {
		struct xdp_buff *rx_bi = *i40e_rx_bi(rx_ring, i);

		if (!rx_bi)
			continue;

		xsk_buff_free(rx_bi);
		rx_bi = NULL;
	}
}

/**
 * i40e_xsk_clean_xdp_ring - Clean the XDP Tx ring on shutdown
 * @tx_ring: XDP Tx ring
 **/
void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring)
{
	u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
	struct xsk_buff_pool *bp = tx_ring->xsk_pool;
	struct i40e_tx_buffer *tx_bi;
	u32 xsk_frames = 0;

	while (ntc != ntu) {
		tx_bi = &tx_ring->tx_bi[ntc];

		if (tx_bi->xdpf)
			i40e_clean_xdp_tx_buffer(tx_ring, tx_bi);
		else
			xsk_frames++;

		tx_bi->xdpf = NULL;

		ntc++;
		if (ntc >= tx_ring->count)
			ntc = 0;
	}

	if (xsk_frames)
		xsk_tx_completed(bp, xsk_frames);
}

/**
 * i40e_xsk_any_rx_ring_enabled - Checks if Rx rings have an AF_XDP
 * buffer pool attached
 * @vsi: vsi
 *
 * Returns true if any of the Rx rings has an AF_XDP buffer pool attached
 **/
bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi)
{
	struct net_device *netdev = vsi->netdev;
	int i;

	for (i = 0; i < vsi->num_queue_pairs; i++) {
		if (xsk_get_pool_from_qid(netdev, i))
			return true;
	}

	return false;
}