summaryrefslogtreecommitdiff
path: root/include/net/xdp.h
blob: a5bc214a49d93feef96cbe5f8dc594f75283a3f6 (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
/* SPDX-License-Identifier: GPL-2.0-only */
/* include/net/xdp.h
 *
 * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
 */
#ifndef __LINUX_NET_XDP_H__
#define __LINUX_NET_XDP_H__

#include <linux/skbuff.h> /* skb_shared_info */

/**
 * DOC: XDP RX-queue information
 *
 * The XDP RX-queue info (xdp_rxq_info) is associated with the driver
 * level RX-ring queues.  It is information that is specific to how
 * the driver have configured a given RX-ring queue.
 *
 * Each xdp_buff frame received in the driver carry a (pointer)
 * reference to this xdp_rxq_info structure.  This provides the XDP
 * data-path read-access to RX-info for both kernel and bpf-side
 * (limited subset).
 *
 * For now, direct access is only safe while running in NAPI/softirq
 * context.  Contents is read-mostly and must not be updated during
 * driver NAPI/softirq poll.
 *
 * The driver usage API is a register and unregister API.
 *
 * The struct is not directly tied to the XDP prog.  A new XDP prog
 * can be attached as long as it doesn't change the underlying
 * RX-ring.  If the RX-ring does change significantly, the NIC driver
 * naturally need to stop the RX-ring before purging and reallocating
 * memory.  In that process the driver MUST call unregistor (which
 * also apply for driver shutdown and unload).  The register API is
 * also mandatory during RX-ring setup.
 */

enum xdp_mem_type {
	MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */
	MEM_TYPE_PAGE_ORDER0,     /* Orig XDP full page model */
	MEM_TYPE_PAGE_POOL,
	MEM_TYPE_XSK_BUFF_POOL,
	MEM_TYPE_MAX,
};

/* XDP flags for ndo_xdp_xmit */
#define XDP_XMIT_FLUSH		(1U << 0)	/* doorbell signal consumer */
#define XDP_XMIT_FLAGS_MASK	XDP_XMIT_FLUSH

struct xdp_mem_info {
	u32 type; /* enum xdp_mem_type, but known size type */
	u32 id;
};

struct page_pool;

struct xdp_rxq_info {
	struct net_device *dev;
	u32 queue_index;
	u32 reg_state;
	struct xdp_mem_info mem;
	unsigned int napi_id;
} ____cacheline_aligned; /* perf critical, avoid false-sharing */

struct xdp_txq_info {
	struct net_device *dev;
};

struct xdp_buff {
	void *data;
	void *data_end;
	void *data_meta;
	void *data_hard_start;
	struct xdp_rxq_info *rxq;
	struct xdp_txq_info *txq;
	u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
};

static __always_inline void
xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq)
{
	xdp->frame_sz = frame_sz;
	xdp->rxq = rxq;
}

static __always_inline void
xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start,
		 int headroom, int data_len, const bool meta_valid)
{
	unsigned char *data = hard_start + headroom;

	xdp->data_hard_start = hard_start;
	xdp->data = data;
	xdp->data_end = data + data_len;
	xdp->data_meta = meta_valid ? data : data + 1;
}

/* Reserve memory area at end-of data area.
 *
 * This macro reserves tailroom in the XDP buffer by limiting the
 * XDP/BPF data access to data_hard_end.  Notice same area (and size)
 * is used for XDP_PASS, when constructing the SKB via build_skb().
 */
#define xdp_data_hard_end(xdp)				\
	((xdp)->data_hard_start + (xdp)->frame_sz -	\
	 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))

static inline struct skb_shared_info *
xdp_get_shared_info_from_buff(struct xdp_buff *xdp)
{
	return (struct skb_shared_info *)xdp_data_hard_end(xdp);
}

struct xdp_frame {
	void *data;
	u16 len;
	u16 headroom;
	u32 metasize:8;
	u32 frame_sz:24;
	/* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time,
	 * while mem info is valid on remote CPU.
	 */
	struct xdp_mem_info mem;
	struct net_device *dev_rx; /* used by cpumap */
};

#define XDP_BULK_QUEUE_SIZE	16
struct xdp_frame_bulk {
	int count;
	void *xa;
	void *q[XDP_BULK_QUEUE_SIZE];
};

static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq)
{
	/* bq->count will be zero'ed when bq->xa gets updated */
	bq->xa = NULL;
}

static inline struct skb_shared_info *
xdp_get_shared_info_from_frame(struct xdp_frame *frame)
{
	void *data_hard_start = frame->data - frame->headroom - sizeof(*frame);

	return (struct skb_shared_info *)(data_hard_start + frame->frame_sz -
				SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
}

struct xdp_cpumap_stats {
	unsigned int redirect;
	unsigned int pass;
	unsigned int drop;
};

/* Clear kernel pointers in xdp_frame */
static inline void xdp_scrub_frame(struct xdp_frame *frame)
{
	frame->data = NULL;
	frame->dev_rx = NULL;
}

/* Avoids inlining WARN macro in fast-path */
void xdp_warn(const char *msg, const char *func, const int line);
#define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)

struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp);
struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
					   struct sk_buff *skb,
					   struct net_device *dev);
struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
					 struct net_device *dev);
int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp);

static inline
void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
{
	xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame);
	xdp->data = frame->data;
	xdp->data_end = frame->data + frame->len;
	xdp->data_meta = frame->data - frame->metasize;
	xdp->frame_sz = frame->frame_sz;
}

static inline
int xdp_update_frame_from_buff(struct xdp_buff *xdp,
			       struct xdp_frame *xdp_frame)
{
	int metasize, headroom;

	/* Assure headroom is available for storing info */
	headroom = xdp->data - xdp->data_hard_start;
	metasize = xdp->data - xdp->data_meta;
	metasize = metasize > 0 ? metasize : 0;
	if (unlikely((headroom - metasize) < sizeof(*xdp_frame)))
		return -ENOSPC;

	/* Catch if driver didn't reserve tailroom for skb_shared_info */
	if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) {
		XDP_WARN("Driver BUG: missing reserved tailroom");
		return -ENOSPC;
	}

	xdp_frame->data = xdp->data;
	xdp_frame->len  = xdp->data_end - xdp->data;
	xdp_frame->headroom = headroom - sizeof(*xdp_frame);
	xdp_frame->metasize = metasize;
	xdp_frame->frame_sz = xdp->frame_sz;

	return 0;
}

/* Convert xdp_buff to xdp_frame */
static inline
struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
{
	struct xdp_frame *xdp_frame;

	if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
		return xdp_convert_zc_to_xdp_frame(xdp);

	/* Store info in top of packet */
	xdp_frame = xdp->data_hard_start;
	if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0))
		return NULL;

	/* rxq only valid until napi_schedule ends, convert to xdp_mem_info */
	xdp_frame->mem = xdp->rxq->mem;

	return xdp_frame;
}

void xdp_return_frame(struct xdp_frame *xdpf);
void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
void xdp_return_buff(struct xdp_buff *xdp);
void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq);
void xdp_return_frame_bulk(struct xdp_frame *xdpf,
			   struct xdp_frame_bulk *bq);

/* When sending xdp_frame into the network stack, then there is no
 * return point callback, which is needed to release e.g. DMA-mapping
 * resources with page_pool.  Thus, have explicit function to release
 * frame resources.
 */
void __xdp_release_frame(void *data, struct xdp_mem_info *mem);
static inline void xdp_release_frame(struct xdp_frame *xdpf)
{
	struct xdp_mem_info *mem = &xdpf->mem;

	/* Curr only page_pool needs this */
	if (mem->type == MEM_TYPE_PAGE_POOL)
		__xdp_release_frame(xdpf->data, mem);
}

int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
		     struct net_device *dev, u32 queue_index, unsigned int napi_id);
void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq);
void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq);
bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq);
int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
			       enum xdp_mem_type type, void *allocator);
void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq);

/* Drivers not supporting XDP metadata can use this helper, which
 * rejects any room expansion for metadata as a result.
 */
static __always_inline void
xdp_set_data_meta_invalid(struct xdp_buff *xdp)
{
	xdp->data_meta = xdp->data + 1;
}

static __always_inline bool
xdp_data_meta_unsupported(const struct xdp_buff *xdp)
{
	return unlikely(xdp->data_meta > xdp->data);
}

struct xdp_attachment_info {
	struct bpf_prog *prog;
	u32 flags;
};

struct netdev_bpf;
void xdp_attachment_setup(struct xdp_attachment_info *info,
			  struct netdev_bpf *bpf);

#define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE

#endif /* __LINUX_NET_XDP_H__ */