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
|
/*
drbd_req.h
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2006-2008, LINBIT Information Technologies GmbH.
Copyright (C) 2006-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
Copyright (C) 2006-2008, Philipp Reisner <philipp.reisner@linbit.com>.
DRBD is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
DRBD is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with drbd; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _DRBD_REQ_H
#define _DRBD_REQ_H
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/drbd.h>
#include "drbd_int.h"
#include "drbd_wrappers.h"
/* The request callbacks will be called in irq context by the IDE drivers,
and in Softirqs/Tasklets/BH context by the SCSI drivers,
and by the receiver and worker in kernel-thread context.
Try to get the locking right :) */
/*
* Objects of type struct drbd_request do only exist on a R_PRIMARY node, and are
* associated with IO requests originating from the block layer above us.
*
* There are quite a few things that may happen to a drbd request
* during its lifetime.
*
* It will be created.
* It will be marked with the intention to be
* submitted to local disk and/or
* send via the network.
*
* It has to be placed on the transfer log and other housekeeping lists,
* In case we have a network connection.
*
* It may be identified as a concurrent (write) request
* and be handled accordingly.
*
* It may me handed over to the local disk subsystem.
* It may be completed by the local disk subsystem,
* either successfully or with io-error.
* In case it is a READ request, and it failed locally,
* it may be retried remotely.
*
* It may be queued for sending.
* It may be handed over to the network stack,
* which may fail.
* It may be acknowledged by the "peer" according to the wire_protocol in use.
* this may be a negative ack.
* It may receive a faked ack when the network connection is lost and the
* transfer log is cleaned up.
* Sending may be canceled due to network connection loss.
* When it finally has outlived its time,
* corresponding dirty bits in the resync-bitmap may be cleared or set,
* it will be destroyed,
* and completion will be signalled to the originator,
* with or without "success".
*/
enum drbd_req_event {
CREATED,
TO_BE_SENT,
TO_BE_SUBMITTED,
/* XXX yes, now I am inconsistent...
* these are not "events" but "actions"
* oh, well... */
QUEUE_FOR_NET_WRITE,
QUEUE_FOR_NET_READ,
QUEUE_FOR_SEND_OOS,
SEND_CANCELED,
SEND_FAILED,
HANDED_OVER_TO_NETWORK,
OOS_HANDED_TO_NETWORK,
CONNECTION_LOST_WHILE_PENDING,
READ_RETRY_REMOTE_CANCELED,
RECV_ACKED_BY_PEER,
WRITE_ACKED_BY_PEER,
WRITE_ACKED_BY_PEER_AND_SIS, /* and set_in_sync */
CONFLICT_DISCARDED_BY_PEER,
NEG_ACKED,
BARRIER_ACKED, /* in protocol A and B */
DATA_RECEIVED, /* (remote read) */
READ_COMPLETED_WITH_ERROR,
READ_AHEAD_COMPLETED_WITH_ERROR,
WRITE_COMPLETED_WITH_ERROR,
COMPLETED_OK,
RESEND,
FAIL_FROZEN_DISK_IO,
RESTART_FROZEN_DISK_IO,
NOTHING,
};
/* encoding of request states for now. we don't actually need that many bits.
* we don't need to do atomic bit operations either, since most of the time we
* need to look at the connection state and/or manipulate some lists at the
* same time, so we should hold the request lock anyways.
*/
enum drbd_req_state_bits {
/* 210
* 000: no local possible
* 001: to be submitted
* UNUSED, we could map: 011: submitted, completion still pending
* 110: completed ok
* 010: completed with error
*/
__RQ_LOCAL_PENDING,
__RQ_LOCAL_COMPLETED,
__RQ_LOCAL_OK,
/* 76543
* 00000: no network possible
* 00001: to be send
* 00011: to be send, on worker queue
* 00101: sent, expecting recv_ack (B) or write_ack (C)
* 11101: sent,
* recv_ack (B) or implicit "ack" (A),
* still waiting for the barrier ack.
* master_bio may already be completed and invalidated.
* 11100: write acked (C),
* data received (for remote read, any protocol)
* or finally the barrier ack has arrived (B,A)...
* request can be freed
* 01100: neg-acked (write, protocol C)
* or neg-d-acked (read, any protocol)
* or killed from the transfer log
* during cleanup after connection loss
* request can be freed
* 01000: canceled or send failed...
* request can be freed
*/
/* if "SENT" is not set, yet, this can still fail or be canceled.
* if "SENT" is set already, we still wait for an Ack packet.
* when cleared, the master_bio may be completed.
* in (B,A) the request object may still linger on the transaction log
* until the corresponding barrier ack comes in */
__RQ_NET_PENDING,
/* If it is QUEUED, and it is a WRITE, it is also registered in the
* transfer log. Currently we need this flag to avoid conflicts between
* worker canceling the request and tl_clear_barrier killing it from
* transfer log. We should restructure the code so this conflict does
* no longer occur. */
__RQ_NET_QUEUED,
/* well, actually only "handed over to the network stack".
*
* TODO can potentially be dropped because of the similar meaning
* of RQ_NET_SENT and ~RQ_NET_QUEUED.
* however it is not exactly the same. before we drop it
* we must ensure that we can tell a request with network part
* from a request without, regardless of what happens to it. */
__RQ_NET_SENT,
/* when set, the request may be freed (if RQ_NET_QUEUED is clear).
* basically this means the corresponding P_BARRIER_ACK was received */
__RQ_NET_DONE,
/* whether or not we know (C) or pretend (B,A) that the write
* was successfully written on the peer.
*/
__RQ_NET_OK,
/* peer called drbd_set_in_sync() for this write */
__RQ_NET_SIS,
/* keep this last, its for the RQ_NET_MASK */
__RQ_NET_MAX,
/* Set when this is a write, clear for a read */
__RQ_WRITE,
/* Should call drbd_al_complete_io() for this request... */
__RQ_IN_ACT_LOG,
};
#define RQ_LOCAL_PENDING (1UL << __RQ_LOCAL_PENDING)
#define RQ_LOCAL_COMPLETED (1UL << __RQ_LOCAL_COMPLETED)
#define RQ_LOCAL_OK (1UL << __RQ_LOCAL_OK)
#define RQ_LOCAL_MASK ((RQ_LOCAL_OK << 1)-1) /* 0x07 */
#define RQ_NET_PENDING (1UL << __RQ_NET_PENDING)
#define RQ_NET_QUEUED (1UL << __RQ_NET_QUEUED)
#define RQ_NET_SENT (1UL << __RQ_NET_SENT)
#define RQ_NET_DONE (1UL << __RQ_NET_DONE)
#define RQ_NET_OK (1UL << __RQ_NET_OK)
#define RQ_NET_SIS (1UL << __RQ_NET_SIS)
/* 0x1f8 */
#define RQ_NET_MASK (((1UL << __RQ_NET_MAX)-1) & ~RQ_LOCAL_MASK)
#define RQ_WRITE (1UL << __RQ_WRITE)
#define RQ_IN_ACT_LOG (1UL << __RQ_IN_ACT_LOG)
/* For waking up the frozen transfer log mod_req() has to return if the request
should be counted in the epoch object*/
#define MR_WRITE_SHIFT 0
#define MR_WRITE (1 << MR_WRITE_SHIFT)
#define MR_READ_SHIFT 1
#define MR_READ (1 << MR_READ_SHIFT)
static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src)
{
struct bio *bio;
bio = bio_clone(bio_src, GFP_NOIO); /* XXX cannot fail?? */
req->private_bio = bio;
bio->bi_private = req;
bio->bi_end_io = drbd_endio_pri;
bio->bi_next = NULL;
}
/* Short lived temporary struct on the stack.
* We could squirrel the error to be returned into
* bio->bi_size, or similar. But that would be too ugly. */
struct bio_and_error {
struct bio *bio;
int error;
};
extern void _req_may_be_done(struct drbd_request *req,
struct bio_and_error *m);
extern int __req_mod(struct drbd_request *req, enum drbd_req_event what,
struct bio_and_error *m);
extern void complete_master_bio(struct drbd_conf *mdev,
struct bio_and_error *m);
extern void request_timer_fn(unsigned long data);
extern void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what);
/* use this if you don't want to deal with calling complete_master_bio()
* outside the spinlock, e.g. when walking some list on cleanup. */
static inline int _req_mod(struct drbd_request *req, enum drbd_req_event what)
{
struct drbd_conf *mdev = req->w.mdev;
struct bio_and_error m;
int rv;
/* __req_mod possibly frees req, do not touch req after that! */
rv = __req_mod(req, what, &m);
if (m.bio)
complete_master_bio(mdev, &m);
return rv;
}
/* completion of master bio is outside of our spinlock.
* We still may or may not be inside some irqs disabled section
* of the lower level driver completion callback, so we need to
* spin_lock_irqsave here. */
static inline int req_mod(struct drbd_request *req,
enum drbd_req_event what)
{
unsigned long flags;
struct drbd_conf *mdev = req->w.mdev;
struct bio_and_error m;
int rv;
spin_lock_irqsave(&mdev->tconn->req_lock, flags);
rv = __req_mod(req, what, &m);
spin_unlock_irqrestore(&mdev->tconn->req_lock, flags);
if (m.bio)
complete_master_bio(mdev, &m);
return rv;
}
static inline bool drbd_should_do_remote(union drbd_state s)
{
return s.pdsk == D_UP_TO_DATE ||
(s.pdsk >= D_INCONSISTENT &&
s.conn >= C_WF_BITMAP_T &&
s.conn < C_AHEAD);
/* Before proto 96 that was >= CONNECTED instead of >= C_WF_BITMAP_T.
That is equivalent since before 96 IO was frozen in the C_WF_BITMAP*
states. */
}
static inline bool drbd_should_send_oos(union drbd_state s)
{
return s.conn == C_AHEAD || s.conn == C_WF_BITMAP_S;
/* pdsk = D_INCONSISTENT as a consequence. Protocol 96 check not necessary
since we enter state C_AHEAD only if proto >= 96 */
}
#endif
|