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
|
/*
* Functions to sequence FLUSH and FUA writes.
*
* Copyright (C) 2011 Max Planck Institute for Gravitational Physics
* Copyright (C) 2011 Tejun Heo <tj@kernel.org>
*
* This file is released under the GPLv2.
*
* REQ_{FLUSH|FUA} requests are decomposed to sequences consisted of three
* optional steps - PREFLUSH, DATA and POSTFLUSH - according to the request
* properties and hardware capability.
*
* If a request doesn't have data, only REQ_FLUSH makes sense, which
* indicates a simple flush request. If there is data, REQ_FLUSH indicates
* that the device cache should be flushed before the data is executed, and
* REQ_FUA means that the data must be on non-volatile media on request
* completion.
*
* If the device doesn't have writeback cache, FLUSH and FUA don't make any
* difference. The requests are either completed immediately if there's no
* data or executed as normal requests otherwise.
*
* If the device has writeback cache and supports FUA, REQ_FLUSH is
* translated to PREFLUSH but REQ_FUA is passed down directly with DATA.
*
* If the device has writeback cache and doesn't support FUA, REQ_FLUSH is
* translated to PREFLUSH and REQ_FUA to POSTFLUSH.
*
* The actual execution of flush is double buffered. Whenever a request
* needs to execute PRE or POSTFLUSH, it queues at
* q->flush_queue[q->flush_pending_idx]. Once certain criteria are met, a
* flush is issued and the pending_idx is toggled. When the flush
* completes, all the requests which were pending are proceeded to the next
* step. This allows arbitrary merging of different types of FLUSH/FUA
* requests.
*
* Currently, the following conditions are used to determine when to issue
* flush.
*
* C1. At any given time, only one flush shall be in progress. This makes
* double buffering sufficient.
*
* C2. Flush is deferred if any request is executing DATA of its sequence.
* This avoids issuing separate POSTFLUSHes for requests which shared
* PREFLUSH.
*
* C3. The second condition is ignored if there is a request which has
* waited longer than FLUSH_PENDING_TIMEOUT. This is to avoid
* starvation in the unlikely case where there are continuous stream of
* FUA (without FLUSH) requests.
*
* For devices which support FUA, it isn't clear whether C2 (and thus C3)
* is beneficial.
*
* Note that a sequenced FLUSH/FUA request with DATA is completed twice.
* Once while executing DATA and again after the whole sequence is
* complete. The first completion updates the contained bio but doesn't
* finish it so that the bio submitter is notified only after the whole
* sequence is complete. This is implemented by testing REQ_FLUSH_SEQ in
* req_bio_endio().
*
* The above peculiarity requires that each FLUSH/FUA request has only one
* bio attached to it, which is guaranteed as they aren't allowed to be
* merged in the usual way.
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/gfp.h>
#include "blk.h"
/* FLUSH/FUA sequences */
enum {
REQ_FSEQ_PREFLUSH = (1 << 0), /* pre-flushing in progress */
REQ_FSEQ_DATA = (1 << 1), /* data write in progress */
REQ_FSEQ_POSTFLUSH = (1 << 2), /* post-flushing in progress */
REQ_FSEQ_DONE = (1 << 3),
REQ_FSEQ_ACTIONS = REQ_FSEQ_PREFLUSH | REQ_FSEQ_DATA |
REQ_FSEQ_POSTFLUSH,
/*
* If flush has been pending longer than the following timeout,
* it's issued even if flush_data requests are still in flight.
*/
FLUSH_PENDING_TIMEOUT = 5 * HZ,
};
static bool blk_kick_flush(struct request_queue *q);
static unsigned int blk_flush_policy(unsigned int fflags, struct request *rq)
{
unsigned int policy = 0;
if (fflags & REQ_FLUSH) {
if (rq->cmd_flags & REQ_FLUSH)
policy |= REQ_FSEQ_PREFLUSH;
if (blk_rq_sectors(rq))
policy |= REQ_FSEQ_DATA;
if (!(fflags & REQ_FUA) && (rq->cmd_flags & REQ_FUA))
policy |= REQ_FSEQ_POSTFLUSH;
}
return policy;
}
static unsigned int blk_flush_cur_seq(struct request *rq)
{
return 1 << ffz(rq->flush.seq);
}
static void blk_flush_restore_request(struct request *rq)
{
/*
* After flush data completion, @rq->bio is %NULL but we need to
* complete the bio again. @rq->biotail is guaranteed to equal the
* original @rq->bio. Restore it.
*/
rq->bio = rq->biotail;
/* make @rq a normal request */
rq->cmd_flags &= ~REQ_FLUSH_SEQ;
rq->end_io = NULL;
}
/**
* blk_flush_complete_seq - complete flush sequence
* @rq: FLUSH/FUA request being sequenced
* @seq: sequences to complete (mask of %REQ_FSEQ_*, can be zero)
* @error: whether an error occurred
*
* @rq just completed @seq part of its flush sequence, record the
* completion and trigger the next step.
*
* CONTEXT:
* spin_lock_irq(q->queue_lock)
*
* RETURNS:
* %true if requests were added to the dispatch queue, %false otherwise.
*/
static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
int error)
{
struct request_queue *q = rq->q;
struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
bool queued = false;
BUG_ON(rq->flush.seq & seq);
rq->flush.seq |= seq;
if (likely(!error))
seq = blk_flush_cur_seq(rq);
else
seq = REQ_FSEQ_DONE;
switch (seq) {
case REQ_FSEQ_PREFLUSH:
case REQ_FSEQ_POSTFLUSH:
/* queue for flush */
if (list_empty(pending))
q->flush_pending_since = jiffies;
list_move_tail(&rq->flush.list, pending);
break;
case REQ_FSEQ_DATA:
list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
list_add(&rq->queuelist, &q->queue_head);
queued = true;
break;
case REQ_FSEQ_DONE:
/*
* @rq was previously adjusted by blk_flush_issue() for
* flush sequencing and may already have gone through the
* flush data request completion path. Restore @rq for
* normal completion and end it.
*/
BUG_ON(!list_empty(&rq->queuelist));
list_del_init(&rq->flush.list);
blk_flush_restore_request(rq);
__blk_end_request_all(rq, error);
break;
default:
BUG();
}
return blk_kick_flush(q) | queued;
}
static void flush_end_io(struct request *flush_rq, int error)
{
struct request_queue *q = flush_rq->q;
struct list_head *running = &q->flush_queue[q->flush_running_idx];
bool was_empty = elv_queue_empty(q);
bool queued = false;
struct request *rq, *n;
BUG_ON(q->flush_pending_idx == q->flush_running_idx);
/* account completion of the flush request */
q->flush_running_idx ^= 1;
elv_completed_request(q, flush_rq);
/* and push the waiting requests to the next stage */
list_for_each_entry_safe(rq, n, running, flush.list) {
unsigned int seq = blk_flush_cur_seq(rq);
BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH);
queued |= blk_flush_complete_seq(rq, seq, error);
}
/* after populating an empty queue, kick it to avoid stall */
if (queued && was_empty)
__blk_run_queue(q);
}
/**
* blk_kick_flush - consider issuing flush request
* @q: request_queue being kicked
*
* Flush related states of @q have changed, consider issuing flush request.
* Please read the comment at the top of this file for more info.
*
* CONTEXT:
* spin_lock_irq(q->queue_lock)
*
* RETURNS:
* %true if flush was issued, %false otherwise.
*/
static bool blk_kick_flush(struct request_queue *q)
{
struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
struct request *first_rq =
list_first_entry(pending, struct request, flush.list);
/* C1 described at the top of this file */
if (q->flush_pending_idx != q->flush_running_idx || list_empty(pending))
return false;
/* C2 and C3 */
if (!list_empty(&q->flush_data_in_flight) &&
time_before(jiffies,
q->flush_pending_since + FLUSH_PENDING_TIMEOUT))
return false;
/*
* Issue flush and toggle pending_idx. This makes pending_idx
* different from running_idx, which means flush is in flight.
*/
blk_rq_init(q, &q->flush_rq);
q->flush_rq.cmd_type = REQ_TYPE_FS;
q->flush_rq.cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
q->flush_rq.rq_disk = first_rq->rq_disk;
q->flush_rq.end_io = flush_end_io;
q->flush_pending_idx ^= 1;
elv_insert(q, &q->flush_rq, ELEVATOR_INSERT_FRONT);
return true;
}
static void flush_data_end_io(struct request *rq, int error)
{
struct request_queue *q = rq->q;
bool was_empty = elv_queue_empty(q);
/* after populating an empty queue, kick it to avoid stall */
if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error) && was_empty)
__blk_run_queue(q);
}
/**
* blk_insert_flush - insert a new FLUSH/FUA request
* @rq: request to insert
*
* To be called from elv_insert() for %ELEVATOR_INSERT_FLUSH insertions.
* @rq is being submitted. Analyze what needs to be done and put it on the
* right queue.
*
* CONTEXT:
* spin_lock_irq(q->queue_lock)
*/
void blk_insert_flush(struct request *rq)
{
struct request_queue *q = rq->q;
unsigned int fflags = q->flush_flags; /* may change, cache */
unsigned int policy = blk_flush_policy(fflags, rq);
BUG_ON(rq->end_io);
BUG_ON(!rq->bio || rq->bio != rq->biotail);
/*
* @policy now records what operations need to be done. Adjust
* REQ_FLUSH and FUA for the driver.
*/
rq->cmd_flags &= ~REQ_FLUSH;
if (!(fflags & REQ_FUA))
rq->cmd_flags &= ~REQ_FUA;
/*
* If there's data but flush is not necessary, the request can be
* processed directly without going through flush machinery. Queue
* for normal execution.
*/
if ((policy & REQ_FSEQ_DATA) &&
!(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
list_add(&rq->queuelist, &q->queue_head);
return;
}
/*
* @rq should go through flush machinery. Mark it part of flush
* sequence and submit for further processing.
*/
memset(&rq->flush, 0, sizeof(rq->flush));
|