summaryrefslogtreecommitdiffstats
path: root/include/net/xdp_sock.h
blob: e3780e4b74e1037d0047a1f3ac0ca449eb448eff (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
/* SPDX-License-Identifier: GPL-2.0 */
/* AF_XDP internal functions
 * Copyright(c) 2018 Intel Corporation.
 */

#ifndef _LINUX_XDP_SOCK_H
#define _LINUX_XDP_SOCK_H

#include <linux/workqueue.h>
#include <linux/if_xdp.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <net/sock.h>

struct net_device;
struct xsk_queue;

/* Masks for xdp_umem_page flags.
 * The low 12-bits of the addr will be 0 since this is the page address, so we
 * can use them for flags.
 */
#define XSK_NEXT_PG_CONTIG_SHIFT 0
#define XSK_NEXT_PG_CONTIG_MASK (1ULL << XSK_NEXT_PG_CONTIG_SHIFT)

struct xdp_umem_page {
	void *addr;
	dma_addr_t dma;
};

struct xdp_umem_fq_reuse {
	u32 nentries;
	u32 length;
	u64 handles[];
};

/* Flags for the umem flags field.
 *
 * The NEED_WAKEUP flag is 1 due to the reuse of the flags field for public
 * flags. See inlude/uapi/include/linux/if_xdp.h.
 */
#define XDP_UMEM_USES_NEED_WAKEUP (1 << 1)

struct xdp_umem {
	struct xsk_queue *fq;
	struct xsk_queue *cq;
	struct xdp_umem_page *pages;
	u64 chunk_mask;
	u64 size;
	u32 headroom;
	u32 chunk_size_nohr;
	struct user_struct *user;
	unsigned long address;
	refcount_t users;
	struct work_struct work;
	struct page **pgs;
	u32 npgs;
	u16 queue_id;
	u8 need_wakeup;
	u8 flags;
	int id;
	struct net_device *dev;
	struct xdp_umem_fq_reuse *fq_reuse;
	bool zc;
	spinlock_t xsk_list_lock;
	struct list_head xsk_list;
};

/* Nodes are linked in the struct xdp_sock map_list field, and used to
 * track which maps a certain socket reside in.
 */

struct xsk_map {
	struct bpf_map map;
	struct list_head __percpu *flush_list;
	spinlock_t lock; /* Synchronize map updates */
	struct xdp_sock *xsk_map[];
};

struct xsk_map_node {
	struct list_head node;
	struct xsk_map *map;
	struct xdp_sock **map_entry;
};

struct xdp_sock {
	/* struct sock must be the first member of struct xdp_sock */
	struct sock sk;
	struct xsk_queue *rx;
	struct net_device *dev;
	struct xdp_umem *umem;
	struct list_head flush_node;
	u16 queue_id;
	bool zc;
	enum {
		XSK_READY = 0,
		XSK_BOUND,
		XSK_UNBOUND,
	} state;
	/* Protects multiple processes in the control path */
	struct mutex mutex;
	struct xsk_queue *tx ____cacheline_aligned_in_smp;
	struct list_head list;
	/* Mutual exclusion of NAPI TX thread and sendmsg error paths
	 * in the SKB destructor callback.
	 */
	spinlock_t tx_completion_lock;
	/* Protects generic receive. */
	spinlock_t rx_lock;
	u64 rx_dropped;
	struct list_head map_list;
	/* Protects map_list */
	spinlock_t map_list_lock;
};

struct xdp_buff;
#ifdef CONFIG_XDP_SOCKETS
int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
/* Used from netdev driver */
bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt);
u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr);
void xsk_umem_discard_addr(struct xdp_umem *umem);
void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc);
void xsk_umem_consume_tx_done(struct xdp_umem *umem);
struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries);
struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem,
					  struct xdp_umem_fq_reuse *newq);
void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq);
struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id);
void xsk_set_rx_need_wakeup(struct xdp_umem *umem);
void xsk_set_tx_need_wakeup(struct xdp_umem *umem);
void xsk_clear_rx_need_wakeup(struct xdp_umem *umem);
void xsk_clear_tx_need_wakeup(struct xdp_umem *umem);
bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem);

void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
			     struct xdp_sock **map_entry);
int xsk_map_inc(struct xsk_map *map);
void xsk_map_put(struct xsk_map *map);
int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
		       struct xdp_sock *xs);
void __xsk_map_flush(struct bpf_map *map);

static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
						     u32 key)
{
	struct xsk_map *m = container_of(map, struct xsk_map, map);
	struct xdp_sock *xs;

	if (key >= map->max_entries)
		return NULL;

	xs = READ_ONCE(m->xsk_map[key]);
	return xs;
}

static inline u64 xsk_umem_extract_addr(u64 addr)
{
	return addr & XSK_UNALIGNED_BUF_ADDR_MASK;
}

static inline u64 xsk_umem_extract_offset(u64 addr)
{
	return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
}

static inline u64 xsk_umem_add_offset_to_addr(u64 addr)
{
	return xsk_umem_extract_addr(addr) + xsk_umem_extract_offset(addr);
}

static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
{
	unsigned long page_addr;

	addr = xsk_umem_add_offset_to_addr(addr);
	page_addr = (unsigned long)umem->pages[addr >> PAGE_SHIFT].addr;

	return (char *)(page_addr & PAGE_MASK) + (addr & ~PAGE_MASK);
}

static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
{
	addr = xsk_umem_add_offset_to_addr(addr);

	return umem->pages[addr >> PAGE_SHIFT].dma + (addr & ~PAGE_MASK);
}

/* Reuse-queue aware version of FILL queue helpers */
static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
{
	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;

	if (rq->length >= cnt)
		return true;

	return xsk_umem_has_addrs(umem, cnt - rq->length);
}

static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
{
	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;

	if (!rq->length)
		return xsk_umem_peek_addr(umem, addr);

	*addr = rq->handles[rq->length - 1];
	return addr;
}

static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem)
{
	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;

	if (!rq->length)
		xsk_umem_discard_addr(umem);
	else
		rq->length--;
}

static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
{
	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;

	rq->handles[rq->length++] = addr;
}

/* Handle the offset appropriately depending on aligned or unaligned mode.
 * For unaligned mode, we store the offset in the upper 16-bits of the address.
 * For aligned mode, we simply add the offset to the address.
 */
static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 address,
					 u64 offset)
{
	if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG)
		return address + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
	else
		return address + offset;
}
#else
static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
	return -ENOTSUPP;
}

static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
{
	return false;
}

static inline bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt)
{
	return false;
}

static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
{
	return NULL;
}

static inline void xsk_umem_discard_addr(struct xdp_umem *umem)
{
}

static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
{
}

static inline bool xsk_umem_consume_tx(struct xdp_umem *umem,
				       struct xdp_desc *desc)
{
	return false;
}

static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem)
{
}

static inline struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries)
{
	return NULL;
}

static inline struct xdp_umem_fq_reuse *xsk_reuseq_swap(
	struct xdp_umem *umem,
	struct xdp_umem_fq_reuse *newq)
{
	return NULL;
}
static inline void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq)
{
}

static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
						     u16 queue_id)
{
	return NULL;
}

static inline u64 xsk_umem_extract_addr(u64 addr)
{
	return 0;
}

static inline u64 xsk_umem_extract_offset(u64 addr)
{
	return 0;
}

static inline u64 xsk_umem_add_offset_to_addr(u64 addr)
{
	return 0;
}

static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
{
	return NULL;
}

static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
{
	return 0;
}

static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
{
	return false;
}

static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
{
	return NULL;
}

static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem)
{
}

static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
{
}

static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
{
}

static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
{
}

static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
{
}

static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
{
}

static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
{
	return false;
}

static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle,
					 u64 offset)
{
	return 0;
}

static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
				     struct xdp_sock *xs)
{
	return -EOPNOTSUPP;
}

static inline void __xsk_map_flush(struct bpf_map *map)
{
}

static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
						     u32 key)
{
	return NULL;
}
#endif /* CONFIG_XDP_SOCKETS */

#endif /* _LINUX_XDP_SOCK_H */