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
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
|
/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
/*
* Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved.
* Copyright (c) 2015 System Fabric Works, Inc. All rights reserved.
*/
#ifndef RXE_VERBS_H
#define RXE_VERBS_H
#include <linux/interrupt.h>
#include <linux/workqueue.h>
#include "rxe_pool.h"
#include "rxe_task.h"
#include "rxe_hw_counters.h"
static inline int pkey_match(u16 key1, u16 key2)
{
return (((key1 & 0x7fff) != 0) &&
((key1 & 0x7fff) == (key2 & 0x7fff)) &&
((key1 & 0x8000) || (key2 & 0x8000))) ? 1 : 0;
}
/* Return >0 if psn_a > psn_b
* 0 if psn_a == psn_b
* <0 if psn_a < psn_b
*/
static inline int psn_compare(u32 psn_a, u32 psn_b)
{
s32 diff;
diff = (psn_a - psn_b) << 8;
return diff;
}
struct rxe_ucontext {
struct ib_ucontext ibuc;
struct rxe_pool_elem elem;
};
struct rxe_pd {
struct ib_pd ibpd;
struct rxe_pool_elem elem;
};
struct rxe_ah {
struct ib_ah ibah;
struct rxe_pool_elem elem;
struct rxe_av av;
bool is_user;
int ah_num;
};
struct rxe_cqe {
union {
struct ib_wc ibwc;
struct ib_uverbs_wc uibwc;
};
};
struct rxe_cq {
struct ib_cq ibcq;
struct rxe_pool_elem elem;
struct rxe_queue *queue;
spinlock_t cq_lock;
u8 notify;
bool is_dying;
bool is_user;
struct tasklet_struct comp_task;
atomic_t num_wq;
};
enum wqe_state {
wqe_state_posted,
wqe_state_processing,
wqe_state_pending,
wqe_state_done,
wqe_state_error,
};
struct rxe_sq {
int max_wr;
int max_sge;
int max_inline;
spinlock_t sq_lock; /* guard queue */
struct rxe_queue *queue;
};
struct rxe_rq {
int max_wr;
int max_sge;
spinlock_t producer_lock; /* guard queue producer */
spinlock_t consumer_lock; /* guard queue consumer */
struct rxe_queue *queue;
};
struct rxe_srq {
struct ib_srq ibsrq;
struct rxe_pool_elem elem;
struct rxe_pd *pd;
struct rxe_rq rq;
u32 srq_num;
int limit;
int error;
};
enum rxe_qp_state {
QP_STATE_RESET,
QP_STATE_INIT,
QP_STATE_READY,
QP_STATE_DRAIN, /* req only */
QP_STATE_DRAINED, /* req only */
QP_STATE_ERROR
};
struct rxe_req_info {
enum rxe_qp_state state;
int wqe_index;
u32 psn;
int opcode;
atomic_t rd_atomic;
int wait_fence;
int need_rd_atomic;
int wait_psn;
int need_retry;
int wait_for_rnr_timer;
int noack_pkts;
struct rxe_task task;
};
struct rxe_comp_info {
enum rxe_qp_state state;
u32 psn;
int opcode;
int timeout;
int timeout_retry;
int started_retry;
u32 retry_cnt;
u32 rnr_retry;
struct rxe_task task;
};
enum rdatm_res_state {
rdatm_res_state_next,
rdatm_res_state_new,
rdatm_res_state_replay,
};
struct resp_res {
int type;
int replay;
u32 first_psn;
u32 last_psn;
u32 cur_psn;
enum rdatm_res_state state;
union {
struct {
u64 orig_val;
} atomic;
struct {
u64 va_org;
u32 rkey;
u32 length;
u64 va;
u32 resid;
} read;
};
};
struct rxe_resp_info {
enum rxe_qp_state state;
u32 msn;
u32 psn;
u32 ack_psn;
int opcode;
int drop_msg;
int goto_error;
int sent_psn_nak;
enum ib_wc_status status;
u8 aeth_syndrome;
/* Receive only */
struct rxe_recv_wqe *wqe;
/* RDMA read / atomic only */
u64 va;
u64 offset;
struct rxe_mr *mr;
u32 resid;
u32 rkey;
u32 length;
/* SRQ only */
struct {
struct rxe_recv_wqe wqe;
struct ib_sge sge[RXE_MAX_SGE];
} srq_wqe;
/* Responder resources. It's a circular list where the oldest
* resource is dropped first.
*/
struct resp_res *resources;
unsigned int res_head;
unsigned int res_tail;
struct resp_res *res;
struct rxe_task task;
};
struct rxe_qp {
struct ib_qp ibqp;
struct rxe_pool_elem elem;
struct ib_qp_attr attr;
unsigned int valid;
unsigned int mtu;
bool is_user;
struct rxe_pd *pd;
struct rxe_srq *srq;
struct rxe_cq *scq;
struct rxe_cq *rcq;
enum ib_sig_type sq_sig_type;
struct rxe_sq sq;
struct rxe_rq rq;
struct socket *sk;
u32 dst_cookie;
u16 src_port;
struct rxe_av pri_av;
struct rxe_av alt_av;
atomic_t mcg_num;
struct sk_buff_head req_pkts;
struct sk_buff_head resp_pkts;
struct rxe_req_info req;
struct rxe_comp_info comp;
struct rxe_resp_info resp;
atomic_t ssn;
atomic_t skb_out;
int need_req_skb;
/* Timer for retranmitting packet when ACKs have been lost. RC
* only. The requester sets it when it is not already
* started. The responder resets it whenever an ack is
* received.
*/
struct timer_list retrans_timer;
u64 qp_timeout_jiffies;
/* Timer for handling RNR NAKS. */
struct timer_list rnr_nak_timer;
spinlock_t state_lock; /* guard requester and completer */
struct execute_work cleanup_work;
};
enum rxe_mr_state {
RXE_MR_STATE_INVALID,
RXE_MR_STATE_FREE,
RXE_MR_STATE_VALID,
};
enum rxe_mr_copy_dir {
RXE_TO_MR_OBJ,
RXE_FROM_MR_OBJ,
};
enum rxe_mr_lookup_type {
RXE_LOOKUP_LOCAL,
RXE_LOOKUP_REMOTE,
};
#define RXE_BUF_PER_MAP (PAGE_SIZE / sizeof(struct rxe_phys_buf))
struct rxe_phys_buf {
u64 addr;
u64 size;
};
struct rxe_map {
struct rxe_phys_buf buf[RXE_BUF_PER_MAP];
};
static inline int rkey_is_mw(u32 rkey)
{
u32 index = rkey >> 8;
return (index >= RXE_MIN_MW_INDEX) && (index <= RXE_MAX_MW_INDEX);
}
struct rxe_mr {
struct rxe_pool_elem elem;
struct ib_mr ibmr;
struct ib_umem *umem;
u32 lkey;
u32 rkey;
enum rxe_mr_state state;
enum ib_mr_type type;
u64 va;
u64 iova;
size_t length;
u32 offset;
int access;
int page_shift;
int page_mask;
int map_shift;
int map_mask;
u32 num_buf;
u32 nbuf;
u32 max_buf;
u32 num_map;
atomic_t num_mw;
struct rxe_map **map;
};
enum rxe_mw_state {
RXE_MW_STATE_INVALID = RXE_MR_STATE_INVALID,
RXE_MW_STATE_FREE = RXE_MR_STATE_FREE,
RXE_MW_STATE_VALID = RXE_MR_STATE_VALID,
};
struct rxe_mw {
struct ib_mw ibmw;
struct rxe_pool_elem elem;
spinlock_t lock;
enum rxe_mw_state state;
struct rxe_qp *qp; /* Type 2 only */
struct rxe_mr *mr;
u32 rkey;
int access;
u64 addr;
u64 length;
};
struct rxe_mcg {
struct rb_node node;
struct kref ref_cnt;
struct rxe_dev *rxe;
struct list_head qp_list;
union ib_gid mgid;
atomic_t qp_num;
u32 qkey;
u16 pkey;
};
struct rxe_mca {
struct list_head qp_list;
struct rxe_qp *qp;
};
struct rxe_port {
struct ib_port_attr attr;
__be64 port_guid;
__be64 subnet_prefix;
spinlock_t port_lock; /* guard port */
unsigned int mtu_cap;
/* special QPs */
u32 qp_gsi_index;
};
struct rxe_dev {
struct ib_device ib_dev;
struct ib_device_attr attr;
int max_ucontext;
int max_inline_data;
struct mutex usdev_lock;
struct net_device *ndev;
struct rxe_pool uc_pool;
struct rxe_pool pd_pool;
struct rxe_pool ah_pool;
struct rxe_pool srq_pool;
struct rxe_pool qp_pool;
struct rxe_pool cq_pool;
struct rxe_pool mr_pool;
struct rxe_pool mw_pool;
/* multicast support */
spinlock_t mcg_lock;
struct rb_root mcg_tree;
atomic_t mcg_num;
atomic_t mcg_attach;
spinlock_t pending_lock; /* guard pending_mmaps */
struct list_head pending_mmaps;
spinlock_t mmap_offset_lock; /* guard mmap_offset */
u64 mmap_offset;
atomic64_t stats_counters[RXE_NUM_OF_COUNTERS];
struct rxe_port port;
struct crypto_shash *tfm;
};
static inline void rxe_counter_inc(struct rxe_dev *rxe, enum rxe_counters index)
{
atomic64_inc(&rxe->stats_counters[index]);
}
static inline struct rxe_dev *to_rdev(struct ib_device *dev)
{
return dev ? container_of(dev, struct rxe_dev, ib_dev) : NULL;
}
static inline struct rxe_ucontext *to_ruc(struct ib_ucontext *uc)
{
return uc ? container_of(uc, struct rxe_ucontext, ibuc) : NULL;
}
static inline struct rxe_pd *to_rpd(struct ib_pd *pd)
{
return pd ? container_of(pd, struct rxe_pd, ibpd) : NULL;
}
static inline struct rxe_ah *to_rah(struct ib_ah *ah)
{
return ah ? container_of(ah, struct rxe_ah, ibah) : NULL;
}
static inline struct rxe_srq *to_rsrq(struct ib_srq *srq)
{
return srq ? container_of(srq, struct rxe_srq, ibsrq) : NULL;
}
static inline struct rxe_qp *to_rqp(struct ib_qp *qp)
{
return qp ? container_of(qp, struct rxe_qp, ibqp) : NULL;
}
static inline struct rxe_cq *to_rcq(struct ib_cq *cq)
{
return cq ? container_of(cq, struct rxe_cq, ibcq) : NULL;
}
static inline struct rxe_mr *to_rmr(struct ib_mr *mr)
{
return mr ? container_of(mr, struct rxe_mr, ibmr) : NULL;
}
static inline struct rxe_mw *to_rmw(struct ib_mw *mw)
{
return mw ? container_of(mw, struct rxe_mw, ibmw) : NULL;
}
static inline struct rxe_pd *rxe_ah_pd(struct rxe_ah *ah)
{
return to_rpd(ah->ibah.pd);
}
static inline struct rxe_pd *mr_pd(struct rxe_mr *mr)
{
return to_rpd(mr->ibmr.pd);
}
static inline struct rxe_pd *rxe_mw_pd(struct rxe_mw *mw)
{
return to_rpd(mw->ibmw.pd);
}
int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name);
#endif /* RXE_VERBS_H */
|