summaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/google/gve/gve_rx.c
blob: edec61dfc8687fff6f4867e4463753d28aab202e (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
// SPDX-License-Identifier: (GPL-2.0 OR MIT)
/* Google virtual Ethernet (gve) driver
 *
 * Copyright (C) 2015-2019 Google, Inc.
 */

#include "gve.h"
#include "gve_adminq.h"
#include <linux/etherdevice.h>

static void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx)
{
	struct gve_notify_block *block =
			&priv->ntfy_blocks[gve_rx_idx_to_ntfy(priv, queue_idx)];

	block->rx = NULL;
}

static void gve_rx_free_ring(struct gve_priv *priv, int idx)
{
	struct gve_rx_ring *rx = &priv->rx[idx];
	struct device *dev = &priv->pdev->dev;
	size_t bytes;
	u32 slots;

	gve_rx_remove_from_block(priv, idx);

	bytes = sizeof(struct gve_rx_desc) * priv->rx_desc_cnt;
	dma_free_coherent(dev, bytes, rx->desc.desc_ring, rx->desc.bus);
	rx->desc.desc_ring = NULL;

	dma_free_coherent(dev, sizeof(*rx->q_resources),
			  rx->q_resources, rx->q_resources_bus);
	rx->q_resources = NULL;

	gve_unassign_qpl(priv, rx->data.qpl->id);
	rx->data.qpl = NULL;
	kvfree(rx->data.page_info);

	slots = rx->mask + 1;
	bytes = sizeof(*rx->data.data_ring) * slots;
	dma_free_coherent(dev, bytes, rx->data.data_ring,
			  rx->data.data_bus);
	rx->data.data_ring = NULL;
	netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx);
}

static void gve_setup_rx_buffer(struct gve_rx_slot_page_info *page_info,
				struct gve_rx_data_slot *slot,
				dma_addr_t addr, struct page *page)
{
	page_info->page = page;
	page_info->page_offset = 0;
	page_info->page_address = page_address(page);
	slot->qpl_offset = cpu_to_be64(addr);
}

static int gve_prefill_rx_pages(struct gve_rx_ring *rx)
{
	struct gve_priv *priv = rx->gve;
	u32 slots;
	int i;

	/* Allocate one page per Rx queue slot. Each page is split into two
	 * packet buffers, when possible we "page flip" between the two.
	 */
	slots = rx->mask + 1;

	rx->data.page_info = kvzalloc(slots *
				      sizeof(*rx->data.page_info), GFP_KERNEL);
	if (!rx->data.page_info)
		return -ENOMEM;

	rx->data.qpl = gve_assign_rx_qpl(priv);

	for (i = 0; i < slots; i++) {
		struct page *page = rx->data.qpl->pages[i];
		dma_addr_t addr = i * PAGE_SIZE;

		gve_setup_rx_buffer(&rx->data.page_info[i],
				    &rx->data.data_ring[i], addr, page);
	}

	return slots;
}

static void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx)
{
	u32 ntfy_idx = gve_rx_idx_to_ntfy(priv, queue_idx);
	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
	struct gve_rx_ring *rx = &priv->rx[queue_idx];

	block->rx = rx;
	rx->ntfy_id = ntfy_idx;
}

static int gve_rx_alloc_ring(struct gve_priv *priv, int idx)
{
	struct gve_rx_ring *rx = &priv->rx[idx];
	struct device *hdev = &priv->pdev->dev;
	u32 slots, npages;
	int filled_pages;
	size_t bytes;
	int err;

	netif_dbg(priv, drv, priv->dev, "allocating rx ring\n");
	/* Make sure everything is zeroed to start with */
	memset(rx, 0, sizeof(*rx));

	rx->gve = priv;
	rx->q_num = idx;

	slots = priv->rx_pages_per_qpl;
	rx->mask = slots - 1;

	/* alloc rx data ring */
	bytes = sizeof(*rx->data.data_ring) * slots;
	rx->data.data_ring = dma_alloc_coherent(hdev, bytes,
						&rx->data.data_bus,
						GFP_KERNEL);
	if (!rx->data.data_ring)
		return -ENOMEM;
	filled_pages = gve_prefill_rx_pages(rx);
	if (filled_pages < 0) {
		err = -ENOMEM;
		goto abort_with_slots;
	}
	rx->fill_cnt = filled_pages;
	/* Ensure data ring slots (packet buffers) are visible. */
	dma_wmb();

	/* Alloc gve_queue_resources */
	rx->q_resources =
		dma_alloc_coherent(hdev,
				   sizeof(*rx->q_resources),
				   &rx->q_resources_bus,
				   GFP_KERNEL);
	if (!rx->q_resources) {
		err = -ENOMEM;
		goto abort_filled;
	}
	netif_dbg(priv, drv, priv->dev, "rx[%d]->data.data_bus=%lx\n", idx,
		  (unsigned long)rx->data.data_bus);

	/* alloc rx desc ring */
	bytes = sizeof(struct gve_rx_desc) * priv->rx_desc_cnt;
	npages = bytes / PAGE_SIZE;
	if (npages * PAGE_SIZE != bytes) {
		err = -EIO;
		goto abort_with_q_resources;
	}

	rx->desc.desc_ring = dma_alloc_coherent(hdev, bytes, &rx->desc.bus,
						GFP_KERNEL);
	if (!rx->desc.desc_ring) {
		err = -ENOMEM;
		goto abort_with_q_resources;
	}
	rx->mask = slots - 1;
	rx->cnt = 0;
	rx->desc.seqno = 1;
	gve_rx_add_to_block(priv, idx);

	return 0;

abort_with_q_resources:
	dma_free_coherent(hdev, sizeof(*rx->q_resources),
			  rx->q_resources, rx->q_resources_bus);
	rx->q_resources = NULL;
abort_filled:
	kvfree(rx->data.page_info);
abort_with_slots:
	bytes = sizeof(*rx->data.data_ring) * slots;
	dma_free_coherent(hdev, bytes, rx->data.data_ring, rx->data.data_bus);
	rx->data.data_ring = NULL;

	return err;
}

int gve_rx_alloc_rings(struct gve_priv *priv)
{
	int err = 0;
	int i;

	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
		err = gve_rx_alloc_ring(priv, i);
		if (err) {
			netif_err(priv, drv, priv->dev,
				  "Failed to alloc rx ring=%d: err=%d\n",
				  i, err);
			break;
		}
	}
	/* Unallocate if there was an error */
	if (err) {
		int j;

		for (j = 0; j < i; j++)
			gve_rx_free_ring(priv, j);
	}
	return err;
}

void gve_rx_free_rings(struct gve_priv *priv)
{
	int i;

	for (i = 0; i < priv->rx_cfg.num_queues; i++)
		gve_rx_free_ring(priv, i);
}

void gve_rx_write_doorbell(struct gve_priv *priv, struct gve_rx_ring *rx)
{
	u32 db_idx = be32_to_cpu(rx->q_resources->db_index);

	iowrite32be(rx->fill_cnt, &priv->db_bar2[db_idx]);
}

static enum pkt_hash_types gve_rss_type(__be16 pkt_flags)
{
	if (likely(pkt_flags & (GVE_RXF_TCP | GVE_RXF_UDP)))
		return PKT_HASH_TYPE_L4;
	if (pkt_flags & (GVE_RXF_IPV4 | GVE_RXF_IPV6))
		return PKT_HASH_TYPE_L3;
	return PKT_HASH_TYPE_L2;
}

static struct sk_buff *gve_rx_copy(struct net_device *dev,
				   struct napi_struct *napi,
				   struct gve_rx_slot_page_info *page_info,
				   u16 len)
{
	struct sk_buff *skb = napi_alloc_skb(napi, len);
	void *va = page_info->page_address + GVE_RX_PAD +
		   page_info->page_offset;

	if (unlikely(!skb))
		return NULL;

	__skb_put(skb, len);

	skb_copy_to_linear_data(skb, va, len);

	skb->protocol = eth_type_trans(skb, dev);
	return skb;
}

static struct sk_buff *gve_rx_add_frags(struct net_device *dev,
					struct napi_struct *napi,
					struct gve_rx_slot_page_info *page_info,
					u16 len)
{
	struct sk_buff *skb = napi_get_frags(napi);

	if (unlikely(!skb))
		return NULL;

	skb_add_rx_frag(skb, 0, page_info->page,
			page_info->page_offset +
			GVE_RX_PAD, len, PAGE_SIZE / 2);

	return skb;
}

static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info,
			     struct gve_rx_data_slot *data_ring)
{
	u64 addr = be64_to_cpu(data_ring->qpl_offset);

	page_info->page_offset ^= PAGE_SIZE / 2;
	addr ^= PAGE_SIZE / 2;
	data_ring->qpl_offset = cpu_to_be64(addr);
}

static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc,
		   netdev_features_t feat, u32 idx)
{
	struct gve_rx_slot_page_info *page_info;
	struct gve_priv *priv = rx->gve;
	struct napi_struct *napi = &priv->ntfy_blocks[rx->ntfy_id].napi;
	struct net_device *dev = priv->dev;
	struct sk_buff *skb;
	int pagecount;
	u16 len;

	/* drop this packet */
	if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR))
		return true;

	len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD;
	page_info = &rx->data.page_info[idx];
	dma_sync_single_for_cpu(&priv->pdev->dev, rx->data.qpl->page_buses[idx],
				PAGE_SIZE, DMA_FROM_DEVICE);

	/* gvnic can only receive into registered segments. If the buffer
	 * can't be recycled, our only choice is to copy the data out of
	 * it so that we can return it to the device.
	 */

	if (PAGE_SIZE == 4096) {
		if (len <= priv->rx_copybreak) {
			/* Just copy small packets */
			skb = gve_rx_copy(dev, napi, page_info, len);
			goto have_skb;
		}
		if (unlikely(!gve_can_recycle_pages(dev))) {
			skb = gve_rx_copy(dev, napi, page_info, len);
			goto have_skb;
		}
		pagecount = page_count(page_info->page);
		if (pagecount == 1) {
			/* No part of this page is used by any SKBs; we attach
			 * the page fragment to a new SKB and pass it up the
			 * stack.
			 */
			skb = gve_rx_add_frags(dev, napi, page_info, len);
			if (!skb)
				return true;
			/* Make sure the kernel stack can't release the page */
			get_page(page_info->page);
			/* "flip" to other packet buffer on this page */
			gve_rx_flip_buff(page_info, &rx->data.data_ring[idx]);
		} else if (pagecount >= 2) {
			/* We have previously passed the other half of this
			 * page up the stack, but it has not yet been freed.
			 */
			skb = gve_rx_copy(dev, napi, page_info, len);
		} else {
			WARN(pagecount < 1, "Pagecount should never be < 1");
			return false;
		}
	} else {
		skb = gve_rx_copy(dev, napi, page_info, len);
	}

have_skb:
	/* We didn't manage to allocate an skb but we haven't had any
	 * reset worthy failures.
	 */
	if (!skb)
		return true;

	if (likely(feat & NETIF_F_RXCSUM)) {
		/* NIC passes up the partial sum */
		if (rx_desc->csum)
			skb->ip_summed = CHECKSUM_COMPLETE;
		else
			skb->ip_summed = CHECKSUM_NONE;
		skb->csum = csum_unfold(rx_desc->csum);
	}

	/* parse flags & pass relevant info up */
	if (likely(feat & NETIF_F_RXHASH) &&
	    gve_needs_rss(rx_desc->flags_seq))
		skb_set_hash(skb, be32_to_cpu(rx_desc->rss_hash),
			     gve_rss_type(rx_desc->flags_seq));

	if (skb_is_nonlinear(skb))
		napi_gro_frags(napi);
	else
		napi_gro_receive(napi, skb);
	return true;
}

static bool gve_rx_work_pending(struct gve_rx_ring *rx)
{
	struct gve_rx_desc *desc;
	__be16 flags_seq;
	u32 next_idx;

	next_idx = rx->cnt & rx->mask;
	desc = rx->desc.desc_ring + next_idx;

	flags_seq = desc->flags_seq;
	/* Make sure we have synchronized the seq no with the device */
	smp_rmb();

	return (GVE_SEQNO(flags_seq) == rx->desc.seqno);
}

bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget,
		       netdev_features_t feat)
{
	struct gve_priv *priv = rx->gve;
	struct gve_rx_desc *desc;
	u32 cnt = rx->cnt;
	u32 idx = cnt & rx->mask;
	u32 work_done = 0;
	u64 bytes = 0;

	desc = rx->desc.desc_ring + idx;
	while ((GVE_SEQNO(desc->flags_seq) == rx->desc.seqno) &&
	       work_done < budget) {
		netif_info(priv, rx_status, priv->dev,
			   "[%d] idx=%d desc=%p desc->flags_seq=0x%x\n",
			   rx->q_num, idx, desc, desc->flags_seq);
		netif_info(priv, rx_status, priv->dev,
			   "[%d] seqno=%d rx->desc.seqno=%d\n",
			   rx->q_num, GVE_SEQNO(desc->flags_seq),
			   rx->desc.seqno);
		bytes += be16_to_cpu(desc->len) - GVE_RX_PAD;
		if (!gve_rx(rx, desc, feat, idx))
			gve_schedule_reset(priv);
		cnt++;
		idx = cnt & rx->mask;
		desc = rx->desc.desc_ring + idx;
		rx->desc.seqno = gve_next_seqno(rx->desc.seqno);
		work_done++;
	}

	if (!work_done)
		return false;

	u64_stats_update_begin(&rx->statss);
	rx->rpackets += work_done;
	rx->rbytes += bytes;
	u64_stats_update_end(&rx->statss);
	rx->cnt = cnt;
	rx->fill_cnt += work_done;

	/* restock desc ring slots */
	dma_wmb();	/* Ensure descs are visible before ringing doorbell */
	gve_rx_write_doorbell(priv, rx);
	return gve_rx_work_pending(rx);
}

bool gve_rx_poll(struct gve_notify_block *block, int budget)
{
	struct gve_rx_ring *rx = block->rx;
	netdev_features_t feat;
	bool repoll = false;

	feat = block->napi.dev->features;

	/* If budget is 0, do all the work */
	if (budget == 0)
		budget = INT_MAX;

	if (budget > 0)
		repoll |= gve_clean_rx_done(rx, budget, feat);
	else
		repoll |= gve_rx_work_pending(rx);
	return repoll;
}