summaryrefslogtreecommitdiff
path: root/drivers/net/xen-netback/common.h
blob: 0333ab0fd9267f2910398bfc3270f615e76cc686 (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
/*
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License version 2
 * as published by the Free Software Foundation; or, when distributed
 * separately from the Linux kernel or incorporated into other
 * software packages, subject to the following license:
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this source file (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use, copy, modify,
 * merge, publish, distribute, sublicense, and/or sell copies of the Software,
 * and to permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 */

#ifndef __XEN_NETBACK__COMMON_H__
#define __XEN_NETBACK__COMMON_H__

#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__

#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/ip.h>
#include <linux/in.h>
#include <linux/io.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/wait.h>
#include <linux/sched.h>

#include <xen/interface/io/netif.h>
#include <xen/interface/grant_table.h>
#include <xen/grant_table.h>
#include <xen/xenbus.h>
#include <xen/page.h>
#include <linux/debugfs.h>

typedef unsigned int pending_ring_idx_t;
#define INVALID_PENDING_RING_IDX (~0U)

struct pending_tx_info {
	struct xen_netif_tx_request req; /* tx request */
	/* Callback data for released SKBs. The callback is always
	 * xenvif_zerocopy_callback, desc contains the pending_idx, which is
	 * also an index in pending_tx_info array. It is initialized in
	 * xenvif_alloc and it never changes.
	 * skb_shinfo(skb)->destructor_arg points to the first mapped slot's
	 * callback_struct in this array of struct pending_tx_info's, then ctx
	 * to the next, or NULL if there is no more slot for this skb.
	 * ubuf_to_vif is a helper which finds the struct xenvif from a pointer
	 * to this field.
	 */
	struct ubuf_info callback_struct;
};

#define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, XEN_PAGE_SIZE)
#define XEN_NETIF_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, XEN_PAGE_SIZE)

struct xenvif_rx_meta {
	int id;
	int size;
	int gso_type;
	int gso_size;
};

#define GSO_BIT(type) \
	(1 << XEN_NETIF_GSO_TYPE_ ## type)

/* Discriminate from any valid pending_idx value. */
#define INVALID_PENDING_IDX 0xFFFF

#define MAX_BUFFER_OFFSET XEN_PAGE_SIZE

#define MAX_PENDING_REQS XEN_NETIF_TX_RING_SIZE

/* The maximum number of frags is derived from the size of a grant (same
 * as a Xen page size for now).
 */
#define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1)

/* It's possible for an skb to have a maximal number of frags
 * but still be less than MAX_BUFFER_OFFSET in size. Thus the
 * worst-case number of copy operations is MAX_XEN_SKB_FRAGS per
 * ring slot.
 */
#define MAX_GRANT_COPY_OPS (MAX_XEN_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE)

#define NETBACK_INVALID_HANDLE -1

/* To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating
 * the maximum slots a valid packet can use. Now this value is defined
 * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by
 * all backend.
 */
#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN

/* Queue name is interface name with "-qNNN" appended */
#define QUEUE_NAME_SIZE (IFNAMSIZ + 5)

/* IRQ name is queue name with "-tx" or "-rx" appended */
#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)

struct xenvif;

struct xenvif_stats {
	/* Stats fields to be updated per-queue.
	 * A subset of struct net_device_stats that contains only the
	 * fields that are updated in netback.c for each queue.
	 */
	unsigned int rx_bytes;
	unsigned int rx_packets;
	unsigned int tx_bytes;
	unsigned int tx_packets;

	/* Additional stats used by xenvif */
	unsigned long rx_gso_checksum_fixup;
	unsigned long tx_zerocopy_sent;
	unsigned long tx_zerocopy_success;
	unsigned long tx_zerocopy_fail;
	unsigned long tx_frag_overflow;
};

struct xenvif_queue { /* Per-queue data for xenvif */
	unsigned int id; /* Queue ID, 0-based */
	char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */
	struct xenvif *vif; /* Parent VIF */

	/* Use NAPI for guest TX */
	struct napi_struct napi;
	/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
	unsigned int tx_irq;
	/* Only used when feature-split-event-channels = 1 */
	char tx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-tx */
	struct xen_netif_tx_back_ring tx;
	struct sk_buff_head tx_queue;
	struct page *mmap_pages[MAX_PENDING_REQS];
	pending_ring_idx_t pending_prod;
	pending_ring_idx_t pending_cons;
	u16 pending_ring[MAX_PENDING_REQS];
	struct pending_tx_info pending_tx_info[MAX_PENDING_REQS];
	grant_handle_t grant_tx_handle[MAX_PENDING_REQS];

	struct gnttab_copy tx_copy_ops[MAX_PENDING_REQS];
	struct gnttab_map_grant_ref tx_map_ops[MAX_PENDING_REQS];
	struct gnttab_unmap_grant_ref tx_unmap_ops[MAX_PENDING_REQS];
	/* passed to gnttab_[un]map_refs with pages under (un)mapping */
	struct page *pages_to_map[MAX_PENDING_REQS];
	struct page *pages_to_unmap[MAX_PENDING_REQS];

	/* This prevents zerocopy callbacks  to race over dealloc_ring */
	spinlock_t callback_lock;
	/* This prevents dealloc thread and NAPI instance to race over response
	 * creation and pending_ring in xenvif_idx_release. In xenvif_tx_err
	 * it only protect response creation
	 */
	spinlock_t response_lock;
	pending_ring_idx_t dealloc_prod;
	pending_ring_idx_t dealloc_cons;
	u16 dealloc_ring[MAX_PENDING_REQS];
	struct task_struct *dealloc_task;
	wait_queue_head_t dealloc_wq;
	atomic_t inflight_packets;

	/* Use kthread for guest RX */
	struct task_struct *task;
	wait_queue_head_t wq;
	/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
	unsigned int rx_irq;
	/* Only used when feature-split-event-channels = 1 */
	char rx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-rx */
	struct xen_netif_rx_back_ring rx;
	struct sk_buff_head rx_queue;

	unsigned int rx_queue_max;
	unsigned int rx_queue_len;
	unsigned long last_rx_time;
	bool stalled;

	struct gnttab_copy grant_copy_op[MAX_GRANT_COPY_OPS];

	/* We create one meta structure per ring request we consume, so
	 * the maximum number is the same as the ring size.
	 */
	struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE];

	/* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */
	unsigned long   credit_bytes;
	unsigned long   credit_usec;
	unsigned long   remaining_credit;
	struct timer_list credit_timeout;
	u64 credit_window_start;

	/* Statistics */
	struct xenvif_stats stats;
};

enum state_bit_shift {
	/* This bit marks that the vif is connected */
	VIF_STATUS_CONNECTED,
};

struct xenvif_mcast_addr {
	struct list_head entry;
	struct rcu_head rcu;
	u8 addr[6];
};

#define XEN_NETBK_MCAST_MAX 64

struct xenvif {
	/* Unique identifier for this interface. */
	domid_t          domid;
	unsigned int     handle;

	u8               fe_dev_addr[6];
	struct list_head fe_mcast_addr;
	unsigned int     fe_mcast_count;

	/* Frontend feature information. */
	int gso_mask;
	int gso_prefix_mask;

	u8 can_sg:1;
	u8 ip_csum:1;
	u8 ipv6_csum:1;
	u8 multicast_control:1;

	/* Is this interface disabled? True when backend discovers
	 * frontend is rogue.
	 */
	bool disabled;
	unsigned long status;
	unsigned long drain_timeout;
	unsigned long stall_timeout;

	/* Queues */
	struct xenvif_queue *queues;
	unsigned int num_queues; /* active queues, resource allocated */
	unsigned int stalled_queues;

	struct xenbus_watch credit_watch;

	spinlock_t lock;

#ifdef CONFIG_DEBUG_FS
	struct dentry *xenvif_dbg_root;
#endif

	/* Miscellaneous private stuff. */
	struct net_device *dev;
};

struct xenvif_rx_cb {
	unsigned long expires;
	int meta_slots_used;
};

#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb)

static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif)
{
	return to_xenbus_device(vif->dev->dev.parent);
}

void xenvif_tx_credit_callback(unsigned long data);

struct xenvif *xenvif_alloc(struct device *parent,
			    domid_t domid,
			    unsigned int handle);

int xenvif_init_queue(struct xenvif_queue *queue);
void xenvif_deinit_queue(struct xenvif_queue *queue);

int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref,
		   unsigned long rx_ring_ref, unsigned int tx_evtchn,
		   unsigned int rx_evtchn);
void xenvif_disconnect(struct xenvif *vif);
void xenvif_free(struct xenvif *vif);

int xenvif_xenbus_init(void);
void xenvif_xenbus_fini(void);

int xenvif_schedulable(struct xenvif *vif);

int xenvif_queue_stopped(struct xenvif_queue *queue);
void xenvif_wake_queue(struct xenvif_queue *queue);

/* (Un)Map communication rings. */
void xenvif_unmap_frontend_rings(struct xenvif_queue *queue);
int xenvif_map_frontend_rings(struct xenvif_queue *queue,
			      grant_ref_t tx_ring_ref,
			      grant_ref_t rx_ring_ref);

/* Check for SKBs from frontend and schedule backend processing */
void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue);

/* Prevent the device from generating any further traffic. */
void xenvif_carrier_off(struct xenvif *vif);

int xenvif_tx_action(struct xenvif_queue *queue, int budget);

int xenvif_kthread_guest_rx(void *data);
void xenvif_kick_thread(struct xenvif_queue *queue);

int xenvif_dealloc_kthread(void *data);

void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb);

void xenvif_carrier_on(struct xenvif *vif);

/* Callback from stack when TX packet can be released */
void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success);

/* Unmap a pending page and release it back to the guest */
void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx);

static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue)
{
	return MAX_PENDING_REQS -
		queue->pending_prod + queue->pending_cons;
}

irqreturn_t xenvif_interrupt(int irq, void *dev_id);

extern bool separate_tx_rx_irq;

extern unsigned int rx_drain_timeout_msecs;
extern unsigned int rx_stall_timeout_msecs;
extern unsigned int xenvif_max_queues;

#ifdef CONFIG_DEBUG_FS
extern struct dentry *xen_netback_dbg_root;
#endif

void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue,
				 struct sk_buff *skb);
void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue);

/* Multicast control */
bool xenvif_mcast_match(struct xenvif *vif, const u8 *addr);
void xenvif_mcast_addr_list_free(struct xenvif *vif);

#endif /* __XEN_NETBACK__COMMON_H__ */