summaryrefslogtreecommitdiffstats
path: root/drivers/net/vmxnet3/vmxnet3_xdp.c
blob: 80ddaff759d47a00d3749495928d515e8be9ecea (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Linux driver for VMware's vmxnet3 ethernet NIC.
 * Copyright (C) 2008-2023, VMware, Inc. All Rights Reserved.
 * Maintained by: pv-drivers@vmware.com
 *
 */

#include "vmxnet3_int.h"
#include "vmxnet3_xdp.h"

static void
vmxnet3_xdp_exchange_program(struct vmxnet3_adapter *adapter,
			     struct bpf_prog *prog)
{
	rcu_assign_pointer(adapter->xdp_bpf_prog, prog);
}

static inline struct vmxnet3_tx_queue *
vmxnet3_xdp_get_tq(struct vmxnet3_adapter *adapter)
{
	struct vmxnet3_tx_queue *tq;
	int tq_number;
	int cpu;

	tq_number = adapter->num_tx_queues;
	cpu = smp_processor_id();
	if (likely(cpu < tq_number))
		tq = &adapter->tx_queue[cpu];
	else
		tq = &adapter->tx_queue[reciprocal_scale(cpu, tq_number)];

	return tq;
}

static int
vmxnet3_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf,
		struct netlink_ext_ack *extack)
{
	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
	struct bpf_prog *new_bpf_prog = bpf->prog;
	struct bpf_prog *old_bpf_prog;
	bool need_update;
	bool running;
	int err;

	if (new_bpf_prog && netdev->mtu > VMXNET3_XDP_MAX_MTU) {
		NL_SET_ERR_MSG_FMT_MOD(extack, "MTU %u too large for XDP",
				       netdev->mtu);
		return -EOPNOTSUPP;
	}

	if (adapter->netdev->features & NETIF_F_LRO) {
		NL_SET_ERR_MSG_MOD(extack, "LRO is not supported with XDP");
		adapter->netdev->features &= ~NETIF_F_LRO;
	}

	old_bpf_prog = rcu_dereference(adapter->xdp_bpf_prog);
	if (!new_bpf_prog && !old_bpf_prog)
		return 0;

	running = netif_running(netdev);
	need_update = !!old_bpf_prog != !!new_bpf_prog;

	if (running && need_update)
		vmxnet3_quiesce_dev(adapter);

	vmxnet3_xdp_exchange_program(adapter, new_bpf_prog);
	if (old_bpf_prog)
		bpf_prog_put(old_bpf_prog);

	if (!running || !need_update)
		return 0;

	if (new_bpf_prog)
		xdp_features_set_redirect_target(netdev, false);
	else
		xdp_features_clear_redirect_target(netdev);

	vmxnet3_reset_dev(adapter);
	vmxnet3_rq_destroy_all(adapter);
	vmxnet3_adjust_rx_ring_size(adapter);
	err = vmxnet3_rq_create_all(adapter);
	if (err) {
		NL_SET_ERR_MSG_MOD(extack,
				   "failed to re-create rx queues for XDP.");
		return -EOPNOTSUPP;
	}
	err = vmxnet3_activate_dev(adapter);
	if (err) {
		NL_SET_ERR_MSG_MOD(extack,
				   "failed to activate device for XDP.");
		return -EOPNOTSUPP;
	}
	clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);

	return 0;
}

/* This is the main xdp call used by kernel to set/unset eBPF program. */
int
vmxnet3_xdp(struct net_device *netdev, struct netdev_bpf *bpf)
{
	switch (bpf->command) {
	case XDP_SETUP_PROG:
		return vmxnet3_xdp_set(netdev, bpf, bpf->extack);
	default:
		return -EINVAL;
	}

	return 0;
}

static int
vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
		       struct xdp_frame *xdpf,
		       struct vmxnet3_tx_queue *tq, bool dma_map)
{
	struct vmxnet3_tx_buf_info *tbi = NULL;
	union Vmxnet3_GenericDesc *gdesc;
	struct vmxnet3_tx_ctx ctx;
	int tx_num_deferred;
	struct page *page;
	u32 buf_size;
	u32 dw2;

	dw2 = (tq->tx_ring.gen ^ 0x1) << VMXNET3_TXD_GEN_SHIFT;
	dw2 |= xdpf->len;
	ctx.sop_txd = tq->tx_ring.base + tq->tx_ring.next2fill;
	gdesc = ctx.sop_txd;

	buf_size = xdpf->len;
	tbi = tq->buf_info + tq->tx_ring.next2fill;

	if (vmxnet3_cmd_ring_desc_avail(&tq->tx_ring) == 0) {
		tq->stats.tx_ring_full++;
		return -ENOSPC;
	}

	tbi->map_type = VMXNET3_MAP_XDP;
	if (dma_map) { /* ndo_xdp_xmit */
		tbi->dma_addr = dma_map_single(&adapter->pdev->dev,
					       xdpf->data, buf_size,
					       DMA_TO_DEVICE);
		if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
			return -EFAULT;
		tbi->map_type |= VMXNET3_MAP_SINGLE;
	} else { /* XDP buffer from page pool */
		page = virt_to_page(xdpf->data);
		tbi->dma_addr = page_pool_get_dma_addr(page) +
				VMXNET3_XDP_HEADROOM;
		dma_sync_single_for_device(&adapter->pdev->dev,
					   tbi->dma_addr, buf_size,
					   DMA_TO_DEVICE);
	}
	tbi->xdpf = xdpf;
	tbi->len = buf_size;

	gdesc = tq->tx_ring.base + tq->tx_ring.next2fill;
	WARN_ON_ONCE(gdesc->txd.gen == tq->tx_ring.gen);

	gdesc->txd.addr = cpu_to_le64(tbi->dma_addr);
	gdesc->dword[2] = cpu_to_le32(dw2);

	/* Setup the EOP desc */
	gdesc->dword[3] = cpu_to_le32(VMXNET3_TXD_CQ | VMXNET3_TXD_EOP);

	gdesc->txd.om = 0;
	gdesc->txd.msscof = 0;
	gdesc->txd.hlen = 0;
	gdesc->txd.ti = 0;

	tx_num_deferred = le32_to_cpu(tq->shared->txNumDeferred);
	le32_add_cpu(&tq->shared->txNumDeferred, 1);
	tx_num_deferred++;

	vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring);

	/* set the last buf_info for the pkt */
	tbi->sop_idx = ctx.sop_txd - tq->tx_ring.base;

	dma_wmb();
	gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^
						  VMXNET3_TXD_GEN);

	/* No need to handle the case when tx_num_deferred doesn't reach
	 * threshold. Backend driver at hypervisor side will poll and reset
	 * tq->shared->txNumDeferred to 0.
	 */
	if (tx_num_deferred >= le32_to_cpu(tq->shared->txThreshold)) {
		tq->shared->txNumDeferred = 0;
		VMXNET3_WRITE_BAR0_REG(adapter,
				       VMXNET3_REG_TXPROD + tq->qid * 8,
				       tq->tx_ring.next2fill);
	}

	return 0;
}

static int
vmxnet3_xdp_xmit_back(struct vmxnet3_adapter *adapter,
		      struct xdp_frame *xdpf)
{
	struct vmxnet3_tx_queue *tq;
	struct netdev_queue *nq;
	int err;

	tq = vmxnet3_xdp_get_tq(adapter);
	if (tq->stopped)
		return -ENETDOWN;

	nq = netdev_get_tx_queue(adapter->netdev, tq->qid);

	__netif_tx_lock(nq, smp_processor_id());
	err = vmxnet3_xdp_xmit_frame(adapter, xdpf, tq, false);
	__netif_tx_unlock(nq);

	return err;
}

/* ndo_xdp_xmit */
int
vmxnet3_xdp_xmit(struct net_device *dev,
		 int n, struct xdp_frame **frames, u32 flags)
{
	struct vmxnet3_adapter *adapter = netdev_priv(dev);
	struct vmxnet3_tx_queue *tq;
	int i;

	if (unlikely(test_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state)))
		return -ENETDOWN;
	if (unlikely(test_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state)))
		return -EINVAL;

	tq = vmxnet3_xdp_get_tq(adapter);
	if (tq->stopped)
		return -ENETDOWN;

	for (i = 0; i < n; i++) {
		if (vmxnet3_xdp_xmit_frame(adapter, frames[i], tq, true)) {
			tq->stats.xdp_xmit_err++;
			break;
		}
	}
	tq->stats.xdp_xmit += i;

	return i;
}

static int
vmxnet3_run_xdp(struct vmxnet3_rx_queue *rq, struct xdp_buff *xdp,
		struct bpf_prog *prog)
{
	struct xdp_frame *xdpf;
	struct page *page;
	int err;
	u32 act;

	rq->stats.xdp_packets++;
	act = bpf_prog_run_xdp(prog, xdp);
	page = virt_to_page(xdp->data_hard_start);

	switch (act) {
	case XDP_PASS:
		return act;
	case XDP_REDIRECT:
		err = xdp_do_redirect(rq->adapter->netdev, xdp, prog);
		if (!err) {
			rq->stats.xdp_redirects++;
		} else {
			rq->stats.xdp_drops++;
			page_pool_recycle_direct(rq->page_pool, page);
		}
		return act;
	case XDP_TX:
		xdpf = xdp_convert_buff_to_frame(xdp);
		if (unlikely(!xdpf ||
			     vmxnet3_xdp_xmit_back(rq->adapter, xdpf))) {
			rq->stats.xdp_drops++;
			page_pool_recycle_direct(rq->page_pool, page);
		} else {
			rq->stats.xdp_tx++;
		}
		return act;
	default:
		bpf_warn_invalid_xdp_action(rq->adapter->netdev, prog, act);
		fallthrough;
	case XDP_ABORTED:
		trace_xdp_exception(rq->adapter->netdev, prog, act);
		rq->stats.xdp_aborted++;
		break;
	case XDP_DROP:
		rq->stats.xdp_drops++;
		break;
	}

	page_pool_recycle_direct(rq->page_pool, page);

	return act;
}

static struct sk_buff *
vmxnet3_build_skb(struct vmxnet3_rx_queue *rq, struct page *page,
		  const struct xdp_buff *xdp)
{
	struct sk_buff *skb;

	skb = build_skb(page_address(page), PAGE_SIZE);
	if (unlikely(!skb)) {
		page_pool_recycle_direct(rq->page_pool, page);
		rq->stats.rx_buf_alloc_failure++;
		return NULL;
	}

	/* bpf prog might change len and data position. */
	skb_reserve(skb, xdp->data - xdp->data_hard_start);
	skb_put(skb, xdp->data_end - xdp->data);
	skb_mark_for_recycle(skb);

	return skb;
}

/* Handle packets from DataRing. */
int
vmxnet3_process_xdp_small(struct vmxnet3_adapter *adapter,
			  struct vmxnet3_rx_queue *rq,
			  void *data, int len,
			  struct sk_buff **skb_xdp_pass)
{
	struct bpf_prog *xdp_prog;
	struct xdp_buff xdp;
	struct page *page;
	int act;

	page = page_pool_alloc_pages(rq->page_pool, GFP_ATOMIC);
	if (unlikely(!page)) {
		rq->stats.rx_buf_alloc_failure++;
		return XDP_DROP;
	}

	xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq);
	xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset,
			 len, false);
	xdp_buff_clear_frags_flag(&xdp);

	/* Must copy the data because it's at dataring. */
	memcpy(xdp.data, data, len);

	xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog);
	if (!xdp_prog) {
		act = XDP_PASS;
		goto out_skb;
	}
	act = vmxnet3_run_xdp(rq, &xdp, xdp_prog);
	if (act != XDP_PASS)
		return act;

out_skb:
	*skb_xdp_pass = vmxnet3_build_skb(rq, page, &xdp);
	if (!*skb_xdp_pass)
		return XDP_DROP;

	/* No need to refill. */
	return likely(*skb_xdp_pass) ? act : XDP_DROP;
}

int
vmxnet3_process_xdp(struct vmxnet3_adapter *adapter,
		    struct vmxnet3_rx_queue *rq,
		    struct Vmxnet3_RxCompDesc *rcd,
		    struct vmxnet3_rx_buf_info *rbi,
		    struct Vmxnet3_RxDesc *rxd,
		    struct sk_buff **skb_xdp_pass)
{
	struct bpf_prog *xdp_prog;
	dma_addr_t new_dma_addr;
	struct xdp_buff xdp;
	struct page *page;
	void *new_data;
	int act;

	page = rbi->page;
	dma_sync_single_for_cpu(&adapter->pdev->dev,
				page_pool_get_dma_addr(page) +
				rq->page_pool->p.offset, rcd->len,
				page_pool_get_dma_dir(rq->page_pool));

	xdp_init_buff(&xdp, rbi->len, &rq->xdp_rxq);
	xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset,
			 rcd->len, false);
	xdp_buff_clear_frags_flag(&xdp);

	xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog);
	if (!xdp_prog) {
		act = XDP_PASS;
		goto out_skb;
	}
	act = vmxnet3_run_xdp(rq, &xdp, xdp_prog);

	if (act == XDP_PASS) {
out_skb:
		*skb_xdp_pass = vmxnet3_build_skb(rq, page, &xdp);
		if (!*skb_xdp_pass)
			act = XDP_DROP;
	}

	new_data = vmxnet3_pp_get_buff(rq->page_pool, &new_dma_addr,
				       GFP_ATOMIC);
	if (!new_data) {
		rq->stats.rx_buf_alloc_failure++;
		return XDP_DROP;
	}
	rbi->page = virt_to_page(new_data);
	rbi->dma_addr = new_dma_addr;
	rxd->addr = cpu_to_le64(rbi->dma_addr);
	rxd->len = rbi->len;

	return act;
}