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
|
/*
* block_copy API
*
* Copyright (C) 2013 Proxmox Server Solutions
* Copyright (c) 2019 Virtuozzo International GmbH.
*
* Authors:
* Dietmar Maurer (dietmar@proxmox.com)
* Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "trace.h"
#include "qapi/error.h"
#include "block/block-copy.h"
#include "sysemu/block-backend.h"
#include "qemu/units.h"
#define BLOCK_COPY_MAX_COPY_RANGE (16 * MiB)
#define BLOCK_COPY_MAX_BUFFER (1 * MiB)
#define BLOCK_COPY_MAX_MEM (128 * MiB)
static BlockCopyInFlightReq *find_conflicting_inflight_req(BlockCopyState *s,
int64_t offset,
int64_t bytes)
{
BlockCopyInFlightReq *req;
QLIST_FOREACH(req, &s->inflight_reqs, list) {
if (offset + bytes > req->offset && offset < req->offset + req->bytes) {
return req;
}
}
return NULL;
}
static void coroutine_fn block_copy_wait_inflight_reqs(BlockCopyState *s,
int64_t offset,
int64_t bytes)
{
BlockCopyInFlightReq *req;
while ((req = find_conflicting_inflight_req(s, offset, bytes))) {
qemu_co_queue_wait(&req->wait_queue, NULL);
}
}
static void block_copy_inflight_req_begin(BlockCopyState *s,
BlockCopyInFlightReq *req,
int64_t offset, int64_t bytes)
{
req->offset = offset;
req->bytes = bytes;
qemu_co_queue_init(&req->wait_queue);
QLIST_INSERT_HEAD(&s->inflight_reqs, req, list);
}
static void coroutine_fn block_copy_inflight_req_end(BlockCopyInFlightReq *req)
{
QLIST_REMOVE(req, list);
qemu_co_queue_restart_all(&req->wait_queue);
}
void block_copy_state_free(BlockCopyState *s)
{
if (!s) {
return;
}
bdrv_release_dirty_bitmap(s->copy_bitmap);
shres_destroy(s->mem);
g_free(s);
}
static uint32_t block_copy_max_transfer(BdrvChild *source, BdrvChild *target)
{
return MIN_NON_ZERO(INT_MAX,
MIN_NON_ZERO(source->bs->bl.max_transfer,
target->bs->bl.max_transfer));
}
BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
int64_t cluster_size,
BdrvRequestFlags write_flags, Error **errp)
{
BlockCopyState *s;
BdrvDirtyBitmap *copy_bitmap;
copy_bitmap = bdrv_create_dirty_bitmap(source->bs, cluster_size, NULL,
errp);
if (!copy_bitmap) {
return NULL;
}
bdrv_disable_dirty_bitmap(copy_bitmap);
s = g_new(BlockCopyState, 1);
*s = (BlockCopyState) {
.source = source,
.target = target,
.copy_bitmap = copy_bitmap,
.cluster_size = cluster_size,
.len = bdrv_dirty_bitmap_size(copy_bitmap),
.write_flags = write_flags,
.mem = shres_create(BLOCK_COPY_MAX_MEM),
};
if (block_copy_max_transfer(source, target) < cluster_size) {
/*
* copy_range does not respect max_transfer. We don't want to bother
* with requests smaller than block-copy cluster size, so fallback to
* buffered copying (read and write respect max_transfer on their
* behalf).
*/
s->use_copy_range = false;
s->copy_size = cluster_size;
} else if (write_flags & BDRV_REQ_WRITE_COMPRESSED) {
/* Compression supports only cluster-size writes and no copy-range. */
s->use_copy_range = false;
s->copy_size = cluster_size;
} else {
/*
* We enable copy-range, but keep small copy_size, until first
* successful copy_range (look at block_copy_do_copy).
*/
s->use_copy_range = true;
s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER);
}
QLIST_INIT(&s->inflight_reqs);
return s;
}
void block_copy_set_progress_callback(
BlockCopyState *s,
ProgressBytesCallbackFunc progress_bytes_callback,
void *progress_opaque)
{
s->progress_bytes_callback = progress_bytes_callback;
s->progress_opaque = progress_opaque;
}
void block_copy_set_progress_meter(BlockCopyState *s, ProgressMeter *pm)
{
s->progress = pm;
}
/*
* block_copy_do_copy
*
* Do copy of cluster-aligned chunk. Requested region is allowed to exceed
* s->len only to cover last cluster when s->len is not aligned to clusters.
*
* No sync here: nor bitmap neighter intersecting requests handling, only copy.
*
* Returns 0 on success.
*/
static int coroutine_fn block_copy_do_copy(BlockCopyState *s,
int64_t offset, int64_t bytes,
bool zeroes, bool *error_is_read)
{
int ret;
int64_t nbytes = MIN(offset + bytes, s->len) - offset;
void *bounce_buffer = NULL;
assert(offset >= 0 && bytes > 0 && INT64_MAX - offset >= bytes);
assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
assert(QEMU_IS_ALIGNED(bytes, s->cluster_size));
assert(offset < s->len);
assert(offset + bytes <= s->len ||
offset + bytes == QEMU_ALIGN_UP(s->len, s->cluster_size));
assert(nbytes < INT_MAX);
if (zeroes) {
ret = bdrv_co_pwrite_zeroes(s->target, offset, nbytes, s->write_flags &
~BDRV_REQ_WRITE_COMPRESSED);
if (ret < 0) {
trace_block_copy_write_zeroes_fail(s, offset, ret);
if (error_is_read) {
*error_is_read = false;
}
}
return ret;
}
if (s->use_copy_range) {
ret = bdrv_co_copy_range(s->source, offset, s->target, offset, nbytes,
0, s->write_flags);
if (ret < 0) {
trace_block_copy_copy_range_fail(s, offset, ret);
s->use_copy_range = false;
s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER);
/* Fallback to read+write with allocated buffer */
} else {
if (s->use_copy_range) {
/*
* Successful copy-range. Now increase copy_size. copy_range
* does not respect max_transfer (it's a TODO), so we factor
* that in here.
*
* Note: we double-check s->use_copy_range for the case when
* parallel block-copy request unsets it during previous
* bdrv_co_copy_range call.
*/
s->copy_size =
MIN(MAX(s->cluster_size, BLOCK_COPY_MAX_COPY_RANGE),
QEMU_ALIGN_DOWN(block_copy_max_transfer(s->source,
s->target),
s->cluster_size));
}
goto out;
}
}
/*
* In case of failed copy_range request above, we may proceed with buffered
* request larger than BLOCK_COPY_MAX_BUFFER. Still, further requests will
* be properly limited, so don't care too much. Moreover the most likely
* case (copy_range is unsupported for the configuration, so the very first
* copy_range request fails) is handled by setting large copy_size only
* after first successful copy_range.
*/
bounce_buffer = qemu_blockalign(s->source->bs, nbytes);
ret = bdrv_co_pread(s->source, offset, nbytes, bounce_buffer, 0);
if (ret < 0) {
trace_block_copy_read_fail(s, offset, ret);
if (error_is_read) {
*error_is_read = true;
}
goto out;
}
ret = bdrv_co_pwrite(s->target, offset, nbytes, bounce_buffer,
s->write_flags);
if (ret < 0) {
trace_block_copy_write_fail(s, offset, ret);
if (error_is_read) {
*error_is_read = false;
}
goto out;
}
out:
qemu_vfree(bounce_buffer);
return ret;
}
static int block_copy_block_status(BlockCopyState *s, int64_t offset,
int64_t bytes, int64_t *pnum)
{
int64_t num;
BlockDriverState *base;
int ret;
if (s->skip_unallocated && s->source->bs->backing) {
base = s->source->bs->backing->bs;
} else {
base = NULL;
}
ret = bdrv_block_status_above(s->source->bs, base, offset, bytes, &num,
NULL, NULL);
if (ret < 0 || num < s->cluster_size) {
/*
* On error or if failed to obtain large enough chunk just fallback to
* copy one cluster.
*/
num = s->cluster_size;
ret = BDRV_BLOCK_ALLOCATED | BDRV_BLOCK_DATA;
} else if (offset + num == s->len) {
num = QEMU_ALIGN_UP(num, s->cluster_size);
} else {
num = QEMU_ALIGN_DOWN(num, s->cluster_size);
}
*pnum = num;
return ret;
}
/*
* Check if the cluster starting at offset is allocated or not.
* return via pnum the number of contiguous clusters sharing this allocation.
*/
static int block_copy_is_cluster_allocated(BlockCopyState *s, int64_t offset,
int64_t *pnum)
{
BlockDriverState *bs = s->source->bs;
int64_t count, total_count = 0;
int64_t bytes = s->len - offset;
int ret;
assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
while (true) {
ret = bdrv_is_allocated(bs, offset, bytes, &count);
if (ret < 0) {
return ret;
}
total_count += count;
if (ret || count == 0) {
/*
* ret: partial segment(s) are considered allocated.
* otherwise: unallocated tail is treated as an entire segment.
*/
*pnum = DIV_ROUND_UP(total_count, s->cluster_size);
return ret;
}
/* Unallocated segment(s) with uncertain following segment(s) */
if (total_count >= s->cluster_size) {
*pnum = total_count / s->cluster_size;
return 0;
}
offset += count;
bytes -= count;
}
}
/*
* Reset bits in copy_bitmap starting at offset if they represent unallocated
* data in the image. May reset subsequent contiguous bits.
* @return 0 when the cluster at @offset was unallocated,
* 1 otherwise, and -ret on error.
*/
int64_t block_copy_reset_unallocated(BlockCopyState *s,
int64_t offset, int64_t *count)
{
int ret;
int64_t clusters, bytes;
ret = block_copy_is_cluster_allocated(s, offset, &clusters);
if (ret < 0) {
return ret;
}
bytes = clusters * s->cluster_size;
if (!ret) {
bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes);
progress_set_remaining(s->progress,
bdrv_get_dirty_count(s->copy_bitmap) +
s->in_flight_bytes);
}
*count = bytes;
return ret;
}
int coroutine_fn block_copy(BlockCopyState *s,
int64_t offset, int64_t bytes,
bool *error_is_read)
{
int ret = 0;
BlockCopyInFlightReq req;
/*
* block_copy() user is responsible for keeping source and target in same
* aio context
*/
assert(bdrv_get_aio_context(s->source->bs) ==
bdrv_get_aio_context(s->target->bs));
assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
assert(QEMU_IS_ALIGNED(bytes, s->cluster_size));
block_copy_wait_inflight_reqs(s, offset, bytes);
block_copy_inflight_req_begin(s, &req, offset, bytes);
while (bytes) {
int64_t next_zero, cur_bytes, status_bytes;
if (!bdrv_dirty_bitmap_get(s->copy_bitmap, offset)) {
trace_block_copy_skip(s, offset);
offset += s->cluster_size;
bytes -= s->cluster_size;
continue; /* already copied */
}
cur_bytes = MIN(bytes, s->copy_size);
next_zero = bdrv_dirty_bitmap_next_zero(s->copy_bitmap, offset,
cur_bytes);
if (next_zero >= 0) {
assert(next_zero > offset); /* offset is dirty */
assert(next_zero < offset + cur_bytes); /* no need to do MIN() */
cur_bytes = next_zero - offset;
}
ret = block_copy_block_status(s, offset, cur_bytes, &status_bytes);
if (s->skip_unallocated && !(ret & BDRV_BLOCK_ALLOCATED)) {
bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, status_bytes);
progress_set_remaining(s->progress,
bdrv_get_dirty_count(s->copy_bitmap) +
s->in_flight_bytes);
trace_block_copy_skip_range(s, offset, status_bytes);
offset += status_bytes;
bytes -= status_bytes;
continue;
}
cur_bytes = MIN(cur_bytes, status_bytes);
trace_block_copy_process(s, offset);
bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, cur_bytes);
s->in_flight_bytes += cur_bytes;
co_get_from_shres(s->mem, cur_bytes);
ret = block_copy_do_copy(s, offset, cur_bytes, ret & BDRV_BLOCK_ZERO,
error_is_read);
co_put_to_shres(s->mem, cur_bytes);
s->in_flight_bytes -= cur_bytes;
if (ret < 0) {
bdrv_set_dirty_bitmap(s->copy_bitmap, offset, cur_bytes);
break;
}
progress_work_done(s->progress, cur_bytes);
s->progress_bytes_callback(cur_bytes, s->progress_opaque);
offset += cur_bytes;
bytes -= cur_bytes;
}
block_copy_inflight_req_end(&req);
return ret;
}
|