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
|
/*
* Some low level IO code, and hacks for various block layer limitations
*
* Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
* Copyright 2012 Google, Inc.
*/
#include "bcache.h"
#include "bset.h"
#include "debug.h"
static void bch_bi_idx_hack_endio(struct bio *bio, int error)
{
struct bio *p = bio->bi_private;
bio_endio(p, error);
bio_put(bio);
}
static void bch_generic_make_request_hack(struct bio *bio)
{
if (bio->bi_idx) {
struct bio *clone = bio_alloc(GFP_NOIO, bio_segments(bio));
memcpy(clone->bi_io_vec,
bio_iovec(bio),
bio_segments(bio) * sizeof(struct bio_vec));
clone->bi_sector = bio->bi_sector;
clone->bi_bdev = bio->bi_bdev;
clone->bi_rw = bio->bi_rw;
clone->bi_vcnt = bio_segments(bio);
clone->bi_size = bio->bi_size;
clone->bi_private = bio;
clone->bi_end_io = bch_bi_idx_hack_endio;
bio = clone;
}
/*
* Hack, since drivers that clone bios clone up to bi_max_vecs, but our
* bios might have had more than that (before we split them per device
* limitations).
*
* To be taken out once immutable bvec stuff is in.
*/
bio->bi_max_vecs = bio->bi_vcnt;
generic_make_request(bio);
}
/**
* bch_bio_split - split a bio
* @bio: bio to split
* @sectors: number of sectors to split from the front of @bio
* @gfp: gfp mask
* @bs: bio set to allocate from
*
* Allocates and returns a new bio which represents @sectors from the start of
* @bio, and updates @bio to represent the remaining sectors.
*
* If bio_sectors(@bio) was less than or equal to @sectors, returns @bio
* unchanged.
*
* The newly allocated bio will point to @bio's bi_io_vec, if the split was on a
* bvec boundry; it is the caller's responsibility to ensure that @bio is not
* freed before the split.
*
* If bch_bio_split() is running under generic_make_request(), it's not safe to
* allocate more than one bio from the same bio set. Therefore, if it is running
* under generic_make_request() it masks out __GFP_WAIT when doing the
* allocation. The caller must check for failure if there's any possibility of
* it being called from under generic_make_request(); it is then the caller's
* responsibility to retry from a safe context (by e.g. punting to workqueue).
*/
struct bio *bch_bio_split(struct bio *bio, int sectors,
gfp_t gfp, struct bio_set *bs)
{
unsigned idx = bio->bi_idx, vcnt = 0, nbytes = sectors << 9;
struct bio_vec *bv;
struct bio *ret = NULL;
BUG_ON(sectors <= 0);
/*
* If we're being called from underneath generic_make_request() and we
* already allocated any bios from this bio set, we risk deadlock if we
* use the mempool. So instead, we possibly fail and let the caller punt
* to workqueue or somesuch and retry in a safe context.
*/
if (current->bio_list)
gfp &= ~__GFP_WAIT;
if (sectors >= bio_sectors(bio))
return bio;
if (bio->bi_rw & REQ_DISCARD) {
ret = bio_alloc_bioset(gfp, 1, bs);
idx = 0;
goto out;
}
bio_for_each_segment(bv, bio, idx) {
vcnt = idx - bio->bi_idx;
if (!nbytes) {
ret = bio_alloc_bioset(gfp, vcnt, bs);
if (!ret)
return NULL;
memcpy(ret->bi_io_vec, bio_iovec(bio),
sizeof(struct bio_vec) * vcnt);
break;
} else if (nbytes < bv->bv_len) {
ret = bio_alloc_bioset(gfp, ++vcnt, bs);
if (!ret)
return NULL;
memcpy(ret->bi_io_vec, bio_iovec(bio),
sizeof(struct bio_vec) * vcnt);
ret->bi_io_vec[vcnt - 1].bv_len = nbytes;
bv->bv_offset += nbytes;
bv->bv_len -= nbytes;
break;
}
nbytes -= bv->bv_len;
}
out:
ret->bi_bdev = bio->bi_bdev;
ret->bi_sector = bio->bi_sector;
ret->bi_size = sectors << 9;
ret->bi_rw = bio->bi_rw;
ret->bi_vcnt = vcnt;
ret->bi_max_vecs = vcnt;
bio->bi_sector += sectors;
bio->bi_size -= sectors << 9;
bio->bi_idx = idx;
if (bio_integrity(bio)) {
if (bio_integrity_clone(ret, bio, gfp)) {
bio_put(ret);
return NULL;
}
bio_integrity_trim(ret, 0, bio_sectors(ret));
bio_integrity_trim(bio, bio_sectors(ret), bio_sectors(bio));
}
return ret;
}
static unsigned bch_bio_max_sectors(struct bio *bio)
{
unsigned ret = bio_sectors(bio);
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
unsigned max_segments = min_t(unsigned, BIO_MAX_PAGES,
queue_max_segments(q));
struct bio_vec *bv, *end = bio_iovec(bio) +
min_t(int, bio_segments(bio), max_segments);
if (bio->bi_rw & REQ_DISCARD)
return min(ret, q->limits.max_discard_sectors);
if (bio_segments(bio) > max_segments ||
q->merge_bvec_fn) {
ret = 0;
for (bv = bio_iovec(bio); bv < end; bv++) {
struct bvec_merge_data bvm = {
.bi_bdev = bio->bi_bdev,
.bi_sector = bio->bi_sector,
.bi_size = ret << 9,
.bi_rw = bio->bi_rw,
};
if (q->merge_bvec_fn &&
q->merge_bvec_fn(q, &bvm, bv) < (int) bv->bv_len)
break;
ret += bv->bv_len >> 9;
}
}
ret = min(ret, queue_max_sectors(q));
WARN_ON(!ret);
ret = max_t(int, ret, bio_iovec(bio)->bv_len >> 9);
return ret;
}
static void bch_bio_submit_split_done(struct closure *cl)
{
struct bio_split_hook *s = container_of(cl, struct bio_split_hook, cl);
s->bio->bi_end_io = s->bi_end_io;
s->bio->bi_private = s->bi_private;
bio_endio(s->bio, 0);
closure_debug_destroy(&s->cl);
mempool_free(s, s->p->bio_split_hook);
}
static void bch_bio_submit_split_endio(struct bio *bio, int error)
{
struct closure *cl = bio->bi_private;
struct bio_split_hook *s = container_of(cl, struct bio_split_hook, cl);
if (error)
clear_bit(BIO_UPTODATE, &s->bio->bi_flags);
bio_put(bio);
closure_put(cl);
}
static void __bch_bio_submit_split(struct closure *cl)
{
struct bio_split_hook *s = container_of(cl, struct bio_split_hook, cl);
struct bio *bio = s->bio, *n;
do {
n = bch_bio_split(bio, bch_bio_max_sectors(bio),
GFP_NOIO, s->p->bio_split);
if (!n)
continue_at(cl, __bch_bio_submit_split, system_wq);
n->bi_end_io = bch_bio_submit_split_endio;
n->bi_private = cl;
closure_get(cl);
bch_generic_make_request_hack(n);
} while (n != bio);
continue_at(cl, bch_bio_submit_split_done, NULL);
}
void bch_generic_make_request(struct bio *bio, struct bio_split_pool *p)
{
struct bio_split_hook *s;
if (!bio_has_data(bio) && !(bio->bi_rw & REQ_DISCARD))
goto submit;
if (bio_sectors(bio) <= bch_bio_max_sectors(bio))
goto submit;
s = mempool_alloc(p->bio_split_hook, GFP_NOIO);
s->bio = bio;
s->p = p;
s->bi_end_io
|