summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
blob: b3fd8e5cd85b4f3b47b643d1895eac049f20c1b8 (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
// 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 "ixgbe.h"
#include "ixgbe_txrx_common.h"

struct xsk_buff_pool *ixgbe_xsk_pool(struct ixgbe_adapter *adapter,
				     struct ixgbe_ring *ring)
{
	bool xdp_on = READ_ONCE(adapter->xdp_prog);
	int qid = ring->ring_idx;

	if (!xdp_on || !test_bit(qid, adapter->af_xdp_zc_qps))
		return NULL;

	return xsk_get_pool_from_qid(adapter->netdev, qid);
}

static int ixgbe_xsk_pool_enable(struct ixgbe_adapter *adapter,
				 struct xsk_buff_pool *pool,
				 u16 qid)
{
	struct net_device *netdev = adapter->netdev;
	bool if_running;
	int err;

	if (qid >= adapter->num_rx_queues)
		return -EINVAL;

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

	err = xsk_pool_dma_map(pool, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR);
	if (err)
		return err;

	if_running = netif_running(adapter->netdev) &&
		     ixgbe_enabled_xdp_adapter(adapter);

	if (if_running)
		ixgbe_txrx_ring_disable(adapter, qid);

	set_bit(qid, adapter->af_xdp_zc_qps);

	if (if_running) {
		ixgbe_txrx_ring_enable(adapter, qid);

		/* Kick start the NAPI context so that receiving will start */
		err = ixgbe_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX);
		if (err) {
			clear_bit(qid, adapter->af_xdp_zc_qps);
			xsk_pool_dma_unmap(pool, IXGBE_RX_DMA_ATTR);
			return err;
		}
	}

	return 0;
}

static int ixgbe_xsk_pool_disable(struct ixgbe_adapter *adapter, u16 qid)
{
	struct xsk_buff_pool *pool;
	bool if_running;

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

	if_running = netif_running(adapter->netdev) &&
		     ixgbe_enabled_xdp_adapter(adapter);

	if (if_running)
		ixgbe_txrx_ring_disable(adapter, qid);

	clear_bit(qid, adapter->af_xdp_zc_qps);
	xsk_pool_dma_unmap(pool, IXGBE_RX_DMA_ATTR);

	if (if_running)
		ixgbe_txrx_ring_enable(adapter, qid);

	return 0;
}

int ixgbe_xsk_pool_setup(struct ixgbe_adapter *adapter,
			 struct xsk_buff_pool *pool,
			 u16 qid)
{
	return pool ? ixgbe_xsk_pool_enable(adapter, pool, qid) :
		ixgbe_xsk_pool_disable(adapter, qid);
}

static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
			    struct ixgbe_ring *rx_ring,
			    struct xdp_buff *xdp)
{
	int err, result = IXGBE_XDP_PASS;
	struct bpf_prog *xdp_prog;
	struct ixgbe_ring *ring;
	struct xdp_frame *xdpf;
	u32 act;

	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
	act = bpf_prog_run_xdp(xdp_prog, xdp);

	if (likely(act == XDP_REDIRECT)) {
		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
		if (err)
			goto out_failure;
		return IXGBE_XDP_REDIR;
	}

	switch (act) {
	case XDP_PASS:
		break;
	case XDP_TX:
		xdpf = xdp_convert_buff_to_frame(xdp);
		if (unlikely(!xdpf))
			goto out_failure;
		ring = ixgbe_determine_xdp_ring(adapter);
		if (static_branch_unlikely(&ixgbe_xdp_locking_key))
			spin_lock(&ring->tx_lock);
		result = ixgbe_xmit_xdp_ring(ring, xdpf);
		if (static_branch_unlikely(&ixgbe_xdp_locking_key))
			spin_unlock(&ring->tx_lock);
		if (result == IXGBE_XDP_CONSUMED)
			goto out_failure;
		break;
	default:
		bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
		fallthrough;
	case XDP_ABORTED:
out_failure:
		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
		fallthrough; /* handle aborts by dropping packet */
	case XDP_DROP:
		result = IXGBE_XDP_CONSUMED;
		break;
	}
	return result;
}

bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count)
{
	union ixgbe_adv_rx_desc *rx_desc;
	struct ixgbe_rx_buffer *bi;
	u16 i = rx_ring->next_to_use;
	dma_addr_t dma;
	bool ok = true;

	/* nothing to do */
	if (!count)
		return true;

	rx_desc = IXGBE_RX_DESC(rx_ring, i);
	bi = &rx_ring->rx_buffer_info[i];
	i -= rx_ring->count;

	do {
		bi->xdp = xsk_buff_alloc(rx_ring->xsk_pool);
		if (!bi->xdp) {
			ok = false;
			break;
		}

		dma = xsk_buff_xdp_get_dma(bi->xdp);

		/* Refresh the desc even if buffer_addrs didn't change
		 * because each write-back erases this info.
		 */
		rx_desc->read.pkt_addr = cpu_to_le64(dma);

		rx_desc++;
		bi++;
		i++;
		if (unlikely(!i)) {
			rx_desc = IXGBE_RX_DESC(rx_ring, 0);
			bi = rx_ring->rx_buffer_info;
			i -= rx_ring->count;
		}

		/* clear the length for the next_to_use descriptor */
		rx_desc->wb.upper.length = 0;

		count--;
	} while (count);

	i += rx_ring->count;

	if (rx_ring->next_to_use != i) {
		rx_ring->next_to_use = i;

		/* Force memory writes to complete before letting h/w
		 * know there are new descriptors to fetch.  (Only
		 * applicable for weak-ordered memory model archs,
		 * such as IA-64).
		 */
		wmb();
		writel(i, rx_ring->tail);
	}

	return ok;
}

static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring,
					      struct ixgbe_rx_buffer *bi)
{
	unsigned int metasize = bi->xdp->data - bi->xdp->data_meta;
	unsigned int datasize = bi->xdp->data_end - bi->xdp->data;
	struct sk_buff *skb;

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

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

	xsk_buff_free(bi->xdp);
	bi->xdp = NULL;
	return skb;
}

static void ixgbe_inc_ntc(struct ixgbe_ring *rx_ring)
{
	u32 ntc = rx_ring->next_to_clean + 1;

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

int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
			  struct ixgbe_ring *rx_ring,
			  const int budget)
{
	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
	struct ixgbe_adapter *adapter = q_vector->adapter;
	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
	unsigned int xdp_res, xdp_xmit = 0;
	bool failure = false;
	struct sk_buff *skb;

	while (likely(total_rx_packets < budget)) {
		union ixgbe_adv_rx_desc *rx_desc;
		struct ixgbe_rx_buffer *bi;
		unsigned int size;

		/* return some buffers to hardware, one at a time is too slow */
		if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
			failure = failure ||
				  !ixgbe_alloc_rx_buffers_zc(rx_ring,
							     cleaned_count);
			cleaned_count = 0;
		}

		rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean);
		size = le16_to_cpu(rx_desc->wb.upper.length);
		if (!size)
			break;

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

		bi = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];

		if (unlikely(!ixgbe_test_staterr(rx_desc,
						 IXGBE_RXD_STAT_EOP))) {
			struct ixgbe_rx_buffer *next_bi;

			xsk_buff_free(bi->xdp);
			bi->xdp = NULL;
			ixgbe_inc_ntc(rx_ring);
			next_bi =
			       &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
			next_bi->discard = true;
			continue;
		}

		if (unlikely(bi->discard)) {
			xsk_buff_free(bi->xdp);
			bi->xdp = NULL;
			bi->discard = false;
			ixgbe_inc_ntc(rx_ring);
			continue;
		}

		bi->xdp->data_end = bi->xdp->data + size;
		xsk_buff_dma_sync_for_cpu(bi->xdp, rx_ring->xsk_pool);
		xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp);

		if (xdp_res) {
			if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR))
				xdp_xmit |= xdp_res;
			else
				xsk_buff_free(bi->xdp);

			bi->xdp = NULL;
			total_rx_packets++;
			total_rx_bytes += size;

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

		/* XDP_PASS path */
		skb = ixgbe_construct_skb_zc(rx_ring, bi);
		if (!skb) {
			rx_ring->rx_stats.alloc_rx_buff_failed++;
			break;
		}

		cleaned_count++;
		ixgbe_inc_ntc(rx_ring);

		if (eth_skb_pad(skb))
			continue;

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

		ixgbe_process_skb_fields(rx_ring, rx_desc, skb);
		ixgbe_rx_skb(q_vector, skb);
	}

	if (xdp_xmit & IXGBE_XDP_REDIR)
		xdp_do_flush_map();

	if (xdp_xmit & IXGBE_XDP_TX) {
		struct ixgbe_ring *ring = ixgbe_determine_xdp_ring(adapter);

		ixgbe_xdp_ring_update_tail_locked(ring);
	}

	u64_stats_update_begin(&rx_ring->syncp);
	rx_ring->stats.packets += total_rx_packets;
	rx_ring->stats.bytes += total_rx_bytes;
	u64_stats_update_end(&rx_ring->syncp);
	q_vector->rx.total_packets += total_rx_packets;
	q_vector->rx.total_bytes += total_rx_bytes;

	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;
}

void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring)
{
	struct ixgbe_rx_buffer *bi;
	u16 i;

	for (i = 0; i < rx_ring->count; i++) {
		bi = &rx_ring->rx_buffer_info[i];

		if (!bi->xdp)
			continue;

		xsk_buff_free(bi->xdp);
		bi->xdp = NULL;
	}
}

static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
{
	struct xsk_buff_pool *pool = xdp_ring->xsk_pool;
	union ixgbe_adv_tx_desc *tx_desc = NULL;
	struct ixgbe_tx_buffer *tx_bi;
	bool work_done = true;
	struct xdp_desc desc;
	dma_addr_t dma;
	u32 cmd_type;

	while (budget-- > 0) {
		if (unlikely(!ixgbe_desc_unused(xdp_ring)) ||
		    !netif_carrier_ok(xdp_ring->netdev)) {
			work_done = false;
			break;
		}

		if (!xsk_tx_peek_desc(pool, &desc))
			break;

		dma = xsk_buff_raw_get_dma(pool, desc.addr);
		xsk_buff_raw_dma_sync_for_device(pool, dma, desc.len);

		tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use];
		tx_bi->bytecount = desc.len;
		tx_bi->xdpf = NULL;
		tx_bi->gso_segs = 1;

		tx_desc = IXGBE_TX_DESC(xdp_ring, xdp_ring->next_to_use);
		tx_desc->read.buffer_addr = cpu_to_le64(dma);

		/* put descriptor type bits */
		cmd_type = IXGBE_ADVTXD_DTYP_DATA |
			   IXGBE_ADVTXD_DCMD_DEXT |
			   IXGBE_ADVTXD_DCMD_IFCS;
		cmd_type |= desc.len | IXGBE_TXD_CMD;
		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
		tx_desc->read.olinfo_status =
			cpu_to_le32(desc.len << IXGBE_ADVTXD_PAYLEN_SHIFT);

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

	if (tx_desc) {
		ixgbe_xdp_ring_update_tail(xdp_ring);
		xsk_tx_release(pool);
	}

	return !!budget && work_done;
}

static void ixgbe_clean_xdp_tx_buffer(struct ixgbe_ring *tx_ring,
				      struct ixgbe_tx_buffer *tx_bi)
{
	xdp_return_frame(tx_bi->xdpf);
	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);
}

bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
			    struct ixgbe_ring *tx_ring, int napi_budget)
{
	u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
	unsigned int total_packets = 0, total_bytes = 0;
	struct xsk_buff_pool *pool = tx_ring->xsk_pool;
	union ixgbe_adv_tx_desc *tx_desc;
	struct ixgbe_tx_buffer *tx_bi;
	u32 xsk_frames = 0;

	tx_bi = &tx_ring->tx_buffer_info[ntc];
	tx_desc = IXGBE_TX_DESC(tx_ring, ntc);

	while (ntc != ntu) {
		if (!(tx_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
			break;

		total_bytes += tx_bi->bytecount;
		total_packets += tx_bi->gso_segs;

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

		tx_bi->xdpf = NULL;

		tx_bi++;
		tx_desc++;
		ntc++;
		if (unlikely(ntc == tx_ring->count)) {
			ntc = 0;
			tx_bi = tx_ring->tx_buffer_info;
			tx_desc = IXGBE_TX_DESC(tx_ring, 0);
		}

		/* issue prefetch for next Tx descriptor */
		prefetch(tx_desc);
	}

	tx_ring->next_to_clean = ntc;

	u64_stats_update_begin(&tx_ring->syncp);
	tx_ring->stats.bytes += total_bytes;
	tx_ring->stats.packets += total_packets;
	u64_stats_update_end(&tx_ring->syncp);
	q_vector->tx.total_bytes += total_bytes;
	q_vector->tx.total_packets += total_packets;

	if (xsk_frames)
		xsk_tx_completed(pool, xsk_frames);

	if (xsk_uses_need_wakeup(pool))
		xsk_set_tx_need_wakeup(pool);

	return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit);
}

int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
{
	struct ixgbe_adapter *adapter = netdev_priv(dev);
	struct ixgbe_ring *ring;

	if (test_bit(__IXGBE_DOWN, &adapter->state))
		return -ENETDOWN;

	if (!READ_ONCE(adapter->xdp_prog))
		return -ENXIO;

	if (qid >= adapter->num_xdp_queues)
		return -ENXIO;

	ring = adapter->xdp_ring[qid];

	if (test_bit(__IXGBE_TX_DISABLED, &ring->state))
		return -ENETDOWN;

	if (!ring->xsk_pool)
		return -ENXIO;

	if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) {
		u64 eics = BIT_ULL(ring->q_vector->v_idx);

		ixgbe_irq_rearm_queues(adapter, eics);
	}

	return 0;
}

void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring)
{
	u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
	struct xsk_buff_pool *pool = tx_ring->xsk_pool;
	struct ixgbe_tx_buffer *tx_bi;
	u32 xsk_frames = 0;

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

		if (tx_bi->xdpf)
			ixgbe_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(pool, xsk_frames);
}