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
|
/*
* Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the BSD-type
* license below:
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials provided
* with the distribution.
*
* Neither the name of the Network Appliance, Inc. nor the names of
* its contributors may be used to endorse or promote products
* derived from this software without specific prior written
* permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef _LINUX_SUNRPC_XPRT_RDMA_H
#define _LINUX_SUNRPC_XPRT_RDMA_H
#include <linux/wait.h> /* wait_queue_head_t, etc */
#include <linux/spinlock.h> /* spinlock_t, etc */
#include <linux/atomic.h> /* atomic_t, etc */
#include <linux/workqueue.h> /* struct work_struct */
#include <rdma/rdma_cm.h> /* RDMA connection api */
#include <rdma/ib_verbs.h> /* RDMA verbs api */
#include <linux/sunrpc/clnt.h> /* rpc_xprt */
#include <linux/sunrpc/rpc_rdma.h> /* RPC/RDMA protocol */
#include <linux/sunrpc/xprtrdma.h> /* xprt parameters */
#include <linux/sunrpc/svc.h> /* RPCSVC_MAXPAYLOAD */
#define RDMA_RESOLVE_TIMEOUT (5000) /* 5 seconds */
#define RDMA_CONNECT_RETRY_MAX (2) /* retries if no listener backlog */
/*
* Interface Adapter -- one per transport instance
*/
struct rpcrdma_ia {
const struct rpcrdma_memreg_ops *ri_ops;
rwlock_t ri_qplock;
struct rdma_cm_id *ri_id;
struct ib_pd *ri_pd;
struct ib_mr *ri_bind_mem;
u32 ri_dma_lkey;
int ri_have_dma_lkey;
struct completion ri_done;
int ri_async_rc;
enum rpcrdma_memreg ri_memreg_strategy;
unsigned int ri_max_frmr_depth;
struct ib_device_attr ri_devattr;
struct ib_qp_attr ri_qp_attr;
struct ib_qp_init_attr ri_qp_init_attr;
};
/*
* RDMA Endpoint -- one per transport instance
*/
#define RPCRDMA_WC_BUDGET (128)
#define RPCRDMA_POLLSIZE (16)
struct rpcrdma_ep {
atomic_t rep_cqcount;
int rep_cqinit;
int rep_connected;
struct ib_qp_init_attr rep_attr;
wait_queue_head_t rep_connect_wait;
struct rpcrdma_regbuf *rep_padbuf;
struct rdma_conn_param rep_remote_cma;
struct sockaddr_storage rep_remote_addr;
struct delayed_work rep_connect_worker;
struct ib_wc rep_send_wcs[RPCRDMA_POLLSIZE];
struct ib_wc rep_recv_wcs[RPCRDMA_POLLSIZE];
};
/*
* Force a signaled SEND Work Request every so often,
* in case the provider needs to do some housekeeping.
*/
#define RPCRDMA_MAX_UNSIGNALED_SENDS (32)
#define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit)
#define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount)
/* Registered buffer -- registered kmalloc'd memory for RDMA SEND/RECV
*
* The below structure appears at the front of a large region of kmalloc'd
* memory, which always starts on a good alignment boundary.
*/
struct rpcrdma_regbuf {
size_t rg_size;
struct rpcrdma_req *rg_owner;
struct ib_mr *rg_mr;
struct ib_sge rg_iov;
__be32 rg_base[0] __attribute__ ((aligned(256)));
};
static inline u64
rdmab_addr(struct rpcrdma_regbuf *rb)
{
return rb->rg_iov.addr;
}
static inline u32
rdmab_length(struct rpcrdma_regbuf *rb)
{
return rb->rg_iov.length;
}
static inline u32
rdmab_lkey(struct rpcrdma_regbuf *rb)
{
return rb->rg_iov.lkey;
}
static inline struct rpcrdma_msg *
rdmab_to_msg(struct rpcrdma_regbuf *rb)
{
return (struct rpcrdma_msg *)rb->rg_base;
}
/*
* struct rpcrdma_rep -- this structure encapsulates state required to recv
* and complete a reply, asychronously. It needs several pieces of
* state:
* o recv buffer (posted to provider)
* o ib_sge (also donated to provider)
* o status of reply (length, success or not)
* o bookkeeping state to get run by tasklet (list, etc)
*
* These are allocated during initialization, per-transport instance;
* however, the tasklet execution list itself is global, as it should
* always be pretty short.
*
* N of these are associated with a transport instance, and stored in
* struct rpcrdma_buffer. N is the max number of outstanding requests.
*/
/* temporary static scatter/gather max */
#define RPCRDMA_MAX_DATA_SEGS (64) /* max scatter/gather */
#define RPCRDMA_MAX_SEGS (RPCRDMA_MAX_DATA_SEGS + 2) /* head+tail = 2 */
struct rpcrdma_buffer;
struct rpcrdma_rep {
unsigned int rr_len;
struct rpcrdma_buffer *rr_buffer;
struct rpc_xprt *rr_xprt;
void (*rr_func)(struct rpcrdma_rep *);
struct list_head rr_list;
struct rpcrdma_regbuf *rr_rdmabuf;
};
/*
* struct rpcrdma_mw - external memory region metadata
*
* An external memory region is any buffer or page that is registered
* on the fly (ie, not pre-registered).
*
* Each rpcrdma_buffer has a list of free MWs anchored in rb_mws. During
* call_allocate, rpcrdma_buffer_get() assigns one to each segment in
* an rpcrdma_req. Then rpcrdma_register_external() grabs these to keep
* track of registration metadata while each RPC is pending.
* rpcrdma_deregister_external() uses this metadata to unmap and
* release these resources when an RPC is complete.
*/
enum rpcrdma_frmr_state {
FRMR_IS_INVALID, /* ready to be used */
FRMR_IS_VALID, /* in use */
FRMR_IS_STALE, /* failed completion */
};
struct rpcrdma_frmr {
struct ib_fast_reg_page_list *fr_pgl;
struct ib_mr *fr_mr;
enum rpcrdma_frmr_state fr_state;
};
struct rpcrdma_mw {
union {
struct ib_fmr *fmr;
struct rpcrdma_frmr frmr;
} r;
struct list_head mw_list;
struct list_head mw_all;
};
/*
* struct rpcrdma_req -- structure central to the request/reply sequence.
*
* N of these are associated with a transport instance, and stored in
* struct rpcrdma_buffer. N is the max number of outstanding requests.
*
* It includes pre-registered buffer memory for send AND recv.
* The recv buffer, however, is not owned by this structure, and
* is "donated" to the hardware when a recv is posted. When a
* reply is handled, the recv buffer used is given back to the
* struct rpcrdma_req associated with the request.
*
* In addition to the basic memory, this structure includes an array
* of iovs for send operations. The reason is that the iovs passed to
* ib_post_{send,recv} must not be modified until the work request
* completes.
*
* NOTES:
* o RPCRDMA_MAX_SEGS is the max number of addressible chunk elements we
* marshal. The number needed varies depending on the iov lists that
* are passed to us, the memory registration mode we are in, and if
* physical addressing is used, the layout.
*/
struct rpcrdma_mr_seg { /* chunk descriptors */
struct rpcrdma_mw *rl_mw; /* registered MR */
u64 mr_base; /* registration result */
u32 mr_rkey; /* registration result */
u32 mr_len; /* length of chunk or segment */
int mr_nsegs; /* number of segments in chunk or 0 */
enum dma_data_direction mr_dir; /* segment mapping direction */
dma_addr_t mr_dma; /* segment mapping address */
size_t mr_dmalen; /* segment mapping length */
struct page *mr_page; /* owning page, if any */
char *mr_offset; /* kva if no page, else offset */
};
struct rpcrdma_req {
unsigned int rl_niovs; /* 0, 2 or 4 */
unsigned int rl_nchunks; /* non-zero if chunks */
unsigned int rl_connect_cookie; /* retry detection */
struct rpcrdma_buffer *rl_buffer; /* home base for this structure */
struct rpcrdma_rep *rl_reply;/* holder for reply buffer */
struct ib_sge rl_send_iov[4]; /* for active requests */
struct rpcrdma_regbuf *rl_rdmabuf;
struct rpcrdma_regbuf *rl_sendbuf;
struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS];
};
static inline struct rpcrdma_req *
rpcr_to_rdmar(struct rpc_rqst *rqst)
{
void *buffer = rqst->rq_buffer;
struct rpcrdma_regbuf *rb;
rb = container_of(buffer, struct rpcrdma_regbuf, rg_base);
return rb->rg_owner;
}
/*
* struct rpcrdma_buffer -- holds list/queue of pre-registered memory for
* inline requests/replies, and client/server credits.
*
* One of these is associated with a transport instance
*/
struct rpcrdma_buffer {
spinlock_t rb_lock; /* protects indexes */
u32 rb_max_requests;/* client max requests */
struct list_head rb_mws; /* optional memory windows/fmrs/frmrs */
struct list_head rb_all;
int rb_send_index;
struct rpcrdma_req **rb_send_bufs;
int rb_recv_index;
struct rpcrdma_rep **rb_recv_bufs;
char *rb_pool;
};
#define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia)
/*
* Internal structure for transport instance creation. This
* exists primarily for modularity.
*
* This data should be set with mount options
*/
struct rpcrdma_create_data_internal {
struct sockaddr_storage addr; /* RDMA server address */
unsigned int max_requests; /* max requests (slots) in flight */
unsigned int rsize; /* mount rsize - max read hdr+data */
unsigned int wsize; /* mount wsize - max write hdr+data */
unsigned int inline_rsize; /* max non-rdma read data payload */
unsigned int inline_wsize; /* max non-rdma write data payload */
unsigned int padding; /* non-rdma write header padding */
};
#define RPCRDMA_INLINE_READ_THRESHOLD(rq) \
(rpcx_to_rdmad(rq->rq_xprt).inline_rsize)
#define RPCRDMA_INLINE_WRITE_THRESHOLD(rq)\
(rpcx_to_rdmad(rq->rq_xprt).inline_wsize)
#define RPCRDMA_INLINE_PAD_VALUE(rq)\
rpcx_to_rdmad(rq->rq_xprt).padding
/*
* Statistics for RPCRDMA
*/
struct rpcrdma_stats {
unsigned long read_chunk_count;
unsigned long write_chunk_count;
unsigned long reply_chunk_count;
unsigned long long total_rdma_request;
unsigned long long total_rdma_reply;
unsigned long long pullup_copy_count;
unsigned long long fixup_copy_count;
unsigned long hardway_register_count;
unsigned long failed_marshal_count;
unsigned long bad_reply_count;
};
/*
* Per-registration mode operations
*/
struct rpcrdma_memreg_ops {
const char *ro_displayname;
};
extern const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops;
extern const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops;
extern const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops;
/*
* RPCRDMA transport -- encapsulates the structures above for
* integration with RPC.
*
* The contained structures are embedded, not pointers,
* for convenience. This structure need not be visible externally.
*
* It is allocated and initialized during mount, and released
* during unmount.
*/
struct rpcrdma_xprt {
struct rpc_xprt rx_xprt;
struct rpcrdma_ia rx_ia;
struct rpcrdma_ep rx_ep;
struct rpcrdma_buffer rx_buf;
struct rpcrdma_create_data_internal rx_data;
struct delayed_work rx_connect_worker;
struct rpcrdma_stats rx_stats;
};
#define rpcx_to_rdmax(x) container_of(x, struct rpcrdma_xprt, rx_xprt)
#define rpcx_to_rdmad(x) (rpcx_to_rdmax(x)->rx_data)
/* Setting this to 0 ensures interoperability with early servers.
* Setting this to 1 enhances certain unaligned read/write performance.
* Default is 0, see sysctl entry and rpc_rdma.c rpcrdma_convert_iovs() */
extern int xprt_rdma_pad_optimize;
/*
* Interface Adapter calls - xprtrdma/verbs.c
*/
int rpcrdma_ia_open(struct rpcrdma_xprt *, struct sockaddr *, int);
void rpcrdma_ia_close(struct rpcrdma_ia *);
/*
* Endpoint calls - xprtrdma/verbs.c
*/
int rpcrdma_ep_create(struct rpcrdma_ep *, struct rpcrdma_ia *,
struct rpcrdma_create_data_internal *);
void rpcrdma_ep_destroy(struct rpcrdma_ep *, struct rpcrdma_ia *);
int rpcrdma_ep_connect(struct rpcrdma_ep *, struct rpcrdma_ia *);
void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *);
int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *,
struct rpcrdma_req *);
int rpcrdma_ep_post_recv(struct rpcrdma_ia *, struct rpcrdma_ep *,
struct rpcrdma_rep *);
/*
* Buffer calls - xprtrdma/verbs.c
*/
int rpcrdma_buffer_create(struct rpcrdma_xprt *);
void rpcrdma_buffer_destroy(struct rpcrdma_buffer *);
struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *);
void rpcrdma_buffer_put(struct rpcrdma_req *);
void rpcrdma_recv_buffer_get(struct rpcrdma_req *);
void rpcrdma_recv_buffer_put(struct rpcrdma_rep *);
int rpcrdma_register_external(struct rpcrdma_mr_seg *,
int, int, struct rpcrdma_xprt *);
int rpcrdma_deregister_external(struct rpcrdma_mr_seg *,
struct rpcrdma_xprt *);
struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(struct rpcrdma_ia *,
size_t, gfp_t);
void rpcrdma_free_regbuf(struct rpcrdma_ia *,
struct rpcrdma_regbuf *);
/*
* RPC/RDMA connection management calls - xprtrdma/rpc_rdma.c
*/
void rpcrdma_connect_worker(struct work_struct *);
void rpcrdma_conn_func(struct rpcrdma_ep *);
void rpcrdma_reply_handler(struct rpcrdma_rep *);
/*
* RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c
*/
int rpcrdma_marshal_req(struct rpc_rqst *);
size_t rpcrdma_max_payload(struct rpcrdma_xprt *);
/* Temporary NFS request map cache. Created in svc_rdma.c */
extern struct kmem_cache *svc_rdma_map_cachep;
/* WR context cache. Created in svc_rdma.c */
extern struct kmem_cache *svc_rdma_ctxt_cachep;
/* Workqueue created in svc_rdma.c */
extern struct workqueue_struct *svc_rdma_wq;
#if RPCSVC_MAXPAYLOAD < (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT)
#define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD
#else
#define RPCSVC_MAXPAYLOAD_RDMA (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT)
#endif
#endif /* _LINUX_SUNRPC_XPRT_RDMA_H */
|