summaryrefslogtreecommitdiffstats
path: root/net/xdp/xsk_buff_pool.c
blob: 9287eddec52c1e73a8b8fe45fdbf9edac74117b1 (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
// SPDX-License-Identifier: GPL-2.0

#include <net/xsk_buff_pool.h>
#include <net/xdp_sock.h>
#include <net/xdp_sock_drv.h>

#include "xsk_queue.h"
#include "xdp_umem.h"
#include "xsk.h"

void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
{
	unsigned long flags;

	if (!xs->tx)
		return;

	spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
	list_add_rcu(&xs->tx_list, &pool->xsk_tx_list);
	spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
}

void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
{
	unsigned long flags;

	if (!xs->tx)
		return;

	spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
	list_del_rcu(&xs->tx_list);
	spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
}

void xp_destroy(struct xsk_buff_pool *pool)
{
	if (!pool)
		return;

	kvfree(pool->heads);
	kvfree(pool);
}

struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
						struct xdp_umem *umem)
{
	struct xsk_buff_pool *pool;
	struct xdp_buff_xsk *xskb;
	u32 i;

	pool = kvzalloc(struct_size(pool, free_heads, umem->chunks),
			GFP_KERNEL);
	if (!pool)
		goto out;

	pool->heads = kvcalloc(umem->chunks, sizeof(*pool->heads), GFP_KERNEL);
	if (!pool->heads)
		goto out;

	pool->chunk_mask = ~((u64)umem->chunk_size - 1);
	pool->addrs_cnt = umem->size;
	pool->heads_cnt = umem->chunks;
	pool->free_heads_cnt = umem->chunks;
	pool->headroom = umem->headroom;
	pool->chunk_size = umem->chunk_size;
	pool->unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
	pool->frame_len = umem->chunk_size - umem->headroom -
		XDP_PACKET_HEADROOM;
	pool->umem = umem;
	pool->addrs = umem->addrs;
	INIT_LIST_HEAD(&pool->free_list);
	INIT_LIST_HEAD(&pool->xsk_tx_list);
	spin_lock_init(&pool->xsk_tx_list_lock);
	refcount_set(&pool->users, 1);

	pool->fq = xs->fq_tmp;
	pool->cq = xs->cq_tmp;
	xs->fq_tmp = NULL;
	xs->cq_tmp = NULL;

	for (i = 0; i < pool->free_heads_cnt; i++) {
		xskb = &pool->heads[i];
		xskb->pool = pool;
		xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;
		pool->free_heads[i] = xskb;
	}

	return pool;

out:
	xp_destroy(pool);
	return NULL;
}

void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
{
	u32 i;

	for (i = 0; i < pool->heads_cnt; i++)
		pool->heads[i].xdp.rxq = rxq;
}
EXPORT_SYMBOL(xp_set_rxq_info);

static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
{
	struct netdev_bpf bpf;
	int err;

	ASSERT_RTNL();

	if (pool->umem->zc) {
		bpf.command = XDP_SETUP_XSK_POOL;
		bpf.xsk.pool = NULL;
		bpf.xsk.queue_id = pool->queue_id;

		err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf);

		if (err)
			WARN(1, "Failed to disable zero-copy!\n");
	}
}

static int __xp_assign_dev(struct xsk_buff_pool *pool,
			   struct net_device *netdev, u16 queue_id, u16 flags)
{
	bool force_zc, force_copy;
	struct netdev_bpf bpf;
	int err = 0;

	ASSERT_RTNL();

	force_zc = flags & XDP_ZEROCOPY;
	force_copy = flags & XDP_COPY;

	if (force_zc && force_copy)
		return -EINVAL;

	if (xsk_get_pool_from_qid(netdev, queue_id))
		return -EBUSY;

	pool->netdev = netdev;
	pool->queue_id = queue_id;
	err = xsk_reg_pool_at_qid(netdev, pool, queue_id);
	if (err)
		return err;

	if (flags & XDP_USE_NEED_WAKEUP) {
		pool->uses_need_wakeup = true;
		/* Tx needs to be explicitly woken up the first time.
		 * Also for supporting drivers that do not implement this
		 * feature. They will always have to call sendto().
		 */
		pool->cached_need_wakeup = XDP_WAKEUP_TX;
	}

	dev_hold(netdev);

	if (force_copy)
		/* For copy-mode, we are done. */
		return 0;

	if (!netdev->netdev_ops->ndo_bpf ||
	    !netdev->netdev_ops->ndo_xsk_wakeup) {
		err = -EOPNOTSUPP;
		goto err_unreg_pool;
	}

	bpf.command = XDP_SETUP_XSK_POOL;
	bpf.xsk.pool = pool;
	bpf.xsk.queue_id = queue_id;

	err = netdev->netdev_ops->ndo_bpf(netdev, &bpf);
	if (err)
		goto err_unreg_pool;

	if (!pool->dma_pages) {
		WARN(1, "Driver did not DMA map zero-copy buffers");
		goto err_unreg_xsk;
	}
	pool->umem->zc = true;
	return 0;

err_unreg_xsk:
	xp_disable_drv_zc(pool);
err_unreg_pool:
	if (!force_zc)
		err = 0; /* fallback to copy mode */
	if (err) {
		xsk_clear_pool_at_qid(netdev, queue_id);
		dev_put(netdev);
	}
	return err;
}

int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
		  u16 queue_id, u16 flags)
{
	return __xp_assign_dev(pool, dev, queue_id, flags);
}

int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
			 struct net_device *dev, u16 queue_id)
{
	u16 flags;

	/* One fill and completion ring required for each queue id. */
	if (!pool->fq || !pool->cq)
		return -EINVAL;

	flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY;
	if (pool->uses_need_wakeup)
		flags |= XDP_USE_NEED_WAKEUP;

	return __xp_assign_dev(pool, dev, queue_id, flags);
}

void xp_clear_dev(struct xsk_buff_pool *pool)
{
	if (!pool->netdev)
		return;

	xp_disable_drv_zc(pool);
	xsk_clear_pool_at_qid(pool->netdev, pool->queue_id);
	dev_put(pool->netdev);
	pool->netdev = NULL;
}

static void xp_release_deferred(struct work_struct *work)
{
	struct xsk_buff_pool *pool = container_of(work, struct xsk_buff_pool,
						  work);

	rtnl_lock();
	xp_clear_dev(pool);
	rtnl_unlock();

	if (pool->fq) {
		xskq_destroy(pool->fq);
		pool->fq = NULL;
	}

	if (pool->cq) {
		xskq_destroy(pool->cq);
		pool->cq = NULL;
	}

	xdp_put_umem(pool->umem, false);
	xp_destroy(pool);
}

void xp_get_pool(struct xsk_buff_pool *pool)
{
	refcount_inc(&pool->users);
}

bool xp_put_pool(struct xsk_buff_pool *pool)
{
	if (!pool)
		return false;

	if (refcount_dec_and_test(&pool->users)) {
		INIT_WORK(&pool->work, xp_release_deferred);
		schedule_work(&pool->work);
		return true;
	}

	return false;
}

static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool)
{
	struct xsk_dma_map *dma_map;

	list_for_each_entry(dma_map, &pool->umem->xsk_dma_list, list) {
		if (dma_map->netdev == pool->netdev)
			return dma_map;
	}

	return NULL;
}

static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_device *netdev,
					     u32 nr_pages, struct xdp_umem *umem)
{
	struct xsk_dma_map *dma_map;

	dma_map = kzalloc(sizeof(*dma_map), GFP_KERNEL);
	if (!dma_map)
		return NULL;

	dma_map->dma_pages = kvcalloc(nr_pages, sizeof(*dma_map->dma_pages), GFP_KERNEL);
	if (!dma_map->dma_pages) {
		kfree(dma_map);
		return NULL;
	}

	dma_map->netdev = netdev;
	dma_map->dev = dev;
	dma_map->dma_need_sync = false;
	dma_map->dma_pages_cnt = nr_pages;
	refcount_set(&dma_map->users, 1);
	list_add(&dma_map->list, &umem->xsk_dma_list);
	return dma_map;
}

static void xp_destroy_dma_map(struct xsk_dma_map *dma_map)
{
	list_del(&dma_map->list);
	kvfree(dma_map->dma_pages);
	kfree(dma_map);
}

static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs)
{
	dma_addr_t *dma;
	u32 i;

	for (i = 0; i < dma_map->dma_pages_cnt; i++) {
		dma = &dma_map->dma_pages[i];
		if (*dma) {
			dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE,
					     DMA_BIDIRECTIONAL, attrs);
			*dma = 0;
		}
	}

	xp_destroy_dma_map(dma_map);
}

void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
{
	struct xsk_dma_map *dma_map;

	if (pool->dma_pages_cnt == 0)
		return;

	dma_map = xp_find_dma_map(pool);
	if (!dma_map) {
		WARN(1, "Could not find dma_map for device");
		return;
	}

	if (!refcount_dec_and_test(&dma_map->users))
		return;

	__xp_dma_unmap(dma_map, attrs);
	kvfree(pool->dma_pages);
	pool->dma_pages_cnt = 0;
	pool->dev = NULL;
}
EXPORT_SYMBOL(xp_dma_unmap);

static void xp_check_dma_contiguity(struct xsk_dma_map *dma_map)
{
	u32 i;

	for (i = 0; i < dma_map->dma_pages_cnt - 1; i++) {
		if (dma_map->dma_pages[i] + PAGE_SIZE == dma_map->dma_pages[i + 1])
			dma_map->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK;
		else
			dma_map->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK;
	}
}

static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_map)
{
	pool->dma_pages = kvcalloc(dma_map->dma_pages_cnt, sizeof(*pool->dma_pages), GFP_KERNEL);
	if (!pool->dma_pages)
		return -ENOMEM;

	pool->dev = dma_map->dev;
	pool->dma_pages_cnt = dma_map->dma_pages_cnt;
	pool->dma_need_sync = dma_map->dma_need_sync;
	memcpy(pool->dma_pages, dma_map->dma_pages,
	       pool->dma_pages_cnt * sizeof(*pool->dma_pages));

	return 0;
}

int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
	       unsigned long attrs, struct page **pages, u32 nr_pages)
{
	struct xsk_dma_map *dma_map;
	dma_addr_t dma;
	int err;
	u32 i;

	dma_map = xp_find_dma_map(pool);
	if (dma_map) {
		err = xp_init_dma_info(pool, dma_map);
		if (err)
			return err;

		refcount_inc(&dma_map->users);
		return 0;
	}

	dma_map = xp_create_dma_map(dev, pool->netdev, nr_pages, pool->umem);
	if (!dma_map)
		return -ENOMEM;

	for (i = 0; i < dma_map->dma_pages_cnt; i++) {
		dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE,
					 DMA_BIDIRECTIONAL, attrs);
		if (dma_mapping_error(dev, dma)) {
			__xp_dma_unmap(dma_map, attrs);
			return -ENOMEM;
		}
		if (dma_need_sync(dev, dma))
			dma_map->dma_need_sync = true;
		dma_map->dma_pages[i] = dma;
	}

	if (pool->unaligned)
		xp_check_dma_contiguity(dma_map);

	err = xp_init_dma_info(pool, dma_map);
	if (err) {
		__xp_dma_unmap(dma_map, attrs);
		return err;
	}

	return 0;
}
EXPORT_SYMBOL(xp_dma_map);

static bool xp_addr_crosses_non_contig_pg(struct xsk_buff_pool *pool,
					  u64 addr)
{
	return xp_desc_crosses_non_contig_pg(pool, addr, pool->chunk_size);
}

static bool xp_check_unaligned(struct xsk_buff_pool *pool, u64 *addr)
{
	*addr = xp_unaligned_extract_addr(*addr);
	if (*addr >= pool->addrs_cnt ||
	    *addr + pool->chunk_size > pool->addrs_cnt ||
	    xp_addr_crosses_non_contig_pg(pool, *addr))
		return false;
	return true;
}

static bool xp_check_aligned(struct xsk_buff_pool *pool, u64 *addr)
{
	*addr = xp_aligned_extract_addr(pool, *addr);
	return *addr < pool->addrs_cnt;
}

static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool)
{
	struct xdp_buff_xsk *xskb;
	u64 addr;
	bool ok;

	if (pool->free_heads_cnt == 0)
		return NULL;

	xskb = pool->free_heads[--pool->free_heads_cnt];

	for (;;) {
		if (!xskq_cons_peek_addr_unchecked(pool->fq, &addr)) {
			pool->fq->queue_empty_descs++;
			xp_release(xskb);
			return NULL;
		}

		ok = pool->unaligned ? xp_check_unaligned(pool, &addr) :
		     xp_check_aligned(pool, &addr);
		if (!ok) {
			pool->fq->invalid_descs++;
			xskq_cons_release(pool->fq);
			continue;
		}
		break;
	}
	xskq_cons_release(pool->fq);

	xskb->orig_addr = addr;
	xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom;
	if (pool->dma_pages_cnt) {
		xskb->frame_dma = (pool->dma_pages[addr >> PAGE_SHIFT] &
				   ~XSK_NEXT_PG_CONTIG_MASK) +
				  (addr & ~PAGE_MASK);
		xskb->dma = xskb->frame_dma + pool->headroom +
			    XDP_PACKET_HEADROOM;
	}
	return xskb;
}

struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool)
{
	struct xdp_buff_xsk *xskb;

	if (!pool->free_list_cnt) {
		xskb = __xp_alloc(pool);
		if (!xskb)
			return NULL;
	} else {
		pool->free_list_cnt--;
		xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk,
					free_list_node);
		list_del(&xskb->free_list_node);
	}

	xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM;
	xskb->xdp.data_meta = xskb->xdp.data;

	if (pool->dma_need_sync) {
		dma_sync_single_range_for_device(pool->dev, xskb->dma, 0,
						 pool->frame_len,
						 DMA_BIDIRECTIONAL);
	}
	return &xskb->xdp;
}
EXPORT_SYMBOL(xp_alloc);

bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count)
{
	if (pool->free_list_cnt >= count)
		return true;
	return xskq_cons_has_entries(pool->fq, count - pool->free_list_cnt);
}
EXPORT_SYMBOL(xp_can_alloc);

void xp_free(struct xdp_buff_xsk *xskb)
{
	xskb->pool->free_list_cnt++;
	list_add(&xskb->free_list_node, &xskb->pool->free_list);
}
EXPORT_SYMBOL(xp_free);

void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
{
	addr = pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr;
	return pool->addrs + addr;
}
EXPORT_SYMBOL(xp_raw_get_data);

dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr)
{
	addr = pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr;
	return (pool->dma_pages[addr >> PAGE_SHIFT] &
		~XSK_NEXT_PG_CONTIG_MASK) +
		(addr & ~PAGE_MASK);
}
EXPORT_SYMBOL(xp_raw_get_dma);

void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb)
{
	dma_sync_single_range_for_cpu(xskb->pool->dev, xskb->dma, 0,
				      xskb->pool->frame_len, DMA_BIDIRECTIONAL);
}
EXPORT_SYMBOL(xp_dma_sync_for_cpu_slow);

void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma,
				 size_t size)
{
	dma_sync_single_range_for_device(pool->dev, dma, 0,
					 size, DMA_BIDIRECTIONAL);
}
EXPORT_SYMBOL(xp_dma_sync_for_device_slow);