Line | Count | Source |
1 | | /* |
2 | | * Block layer I/O functions |
3 | | * |
4 | | * Copyright (c) 2003 Fabrice Bellard |
5 | | * |
6 | | * Permission is hereby granted, free of charge, to any person obtaining a copy |
7 | | * of this software and associated documentation files (the "Software"), to deal |
8 | | * in the Software without restriction, including without limitation the rights |
9 | | * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
10 | | * copies of the Software, and to permit persons to whom the Software is |
11 | | * furnished to do so, subject to the following conditions: |
12 | | * |
13 | | * The above copyright notice and this permission notice shall be included in |
14 | | * all copies or substantial portions of the Software. |
15 | | * |
16 | | * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
17 | | * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
18 | | * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL |
19 | | * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
20 | | * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
21 | | * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN |
22 | | * THE SOFTWARE. |
23 | | */ |
24 | | |
25 | | #include "qemu/osdep.h" |
26 | | #include "trace.h" |
27 | | #include "system/block-backend.h" |
28 | | #include "qemu/aio-wait.h" |
29 | | #include "block/blockjob.h" |
30 | | #include "block/blockjob_int.h" |
31 | | #include "block/block_int.h" |
32 | | #include "block/coroutines.h" |
33 | | #include "block/dirty-bitmap.h" |
34 | | #include "block/write-threshold.h" |
35 | | #include "qemu/cutils.h" |
36 | | #include "qemu/memalign.h" |
37 | | #include "qapi/error.h" |
38 | | #include "qemu/error-report.h" |
39 | | #include "qemu/main-loop.h" |
40 | | #include "system/replay.h" |
41 | | #include "qemu/units.h" |
42 | | #include "qemu/atomic.h" |
43 | | |
44 | | /* Maximum bounce buffer for copy-on-read and write zeroes, in bytes */ |
45 | | #define MAX_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS) |
46 | | |
47 | | /* Maximum read size for checking if data reads as zero, in bytes */ |
48 | 0 | #define MAX_ZERO_CHECK_BUFFER (128 * KiB) |
49 | | |
50 | | static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, |
51 | | int64_t offset, int64_t bytes, BdrvRequestFlags flags); |
52 | | |
53 | | static void coroutine_fn |
54 | | bdrv_wait_serialising_requests_locked(BdrvTrackedRequest *self); |
55 | | |
56 | | static void GRAPH_RDLOCK |
57 | | bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore) |
58 | 288k | { |
59 | 288k | BdrvChild *c, *next; |
60 | 288k | IO_OR_GS_CODE(); |
61 | 288k | assert_bdrv_graph_readable(); |
62 | | |
63 | 288k | QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) { |
64 | 288k | if (c == ignore) { |
65 | 0 | continue; |
66 | 0 | } |
67 | 288k | bdrv_parent_drained_begin_single(c); |
68 | 288k | } |
69 | 288k | } |
70 | | |
71 | | void bdrv_parent_drained_end_single(BdrvChild *c) |
72 | 288k | { |
73 | 288k | GLOBAL_STATE_CODE(); |
74 | | |
75 | 288k | assert(c->quiesced_parent); |
76 | 288k | c->quiesced_parent = false; |
77 | | |
78 | 288k | if (c->klass->drained_end) { |
79 | 288k | c->klass->drained_end(c); |
80 | 288k | } |
81 | 288k | } |
82 | | |
83 | | static void GRAPH_RDLOCK |
84 | | bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore) |
85 | 288k | { |
86 | 288k | BdrvChild *c; |
87 | 288k | IO_OR_GS_CODE(); |
88 | 288k | assert_bdrv_graph_readable(); |
89 | | |
90 | 288k | QLIST_FOREACH(c, &bs->parents, next_parent) { |
91 | 288k | if (c == ignore) { |
92 | 0 | continue; |
93 | 0 | } |
94 | 288k | bdrv_parent_drained_end_single(c); |
95 | 288k | } |
96 | 288k | } |
97 | | |
98 | | bool bdrv_parent_drained_poll_single(BdrvChild *c) |
99 | 203k | { |
100 | 203k | IO_OR_GS_CODE(); |
101 | | |
102 | 203k | if (c->klass->drained_poll) { |
103 | 203k | return c->klass->drained_poll(c); |
104 | 203k | } |
105 | 0 | return false; |
106 | 203k | } |
107 | | |
108 | | static bool GRAPH_RDLOCK |
109 | | bdrv_parent_drained_poll(BlockDriverState *bs, BdrvChild *ignore, |
110 | | bool ignore_bds_parents) |
111 | 289k | { |
112 | 289k | BdrvChild *c, *next; |
113 | 289k | bool busy = false; |
114 | 289k | IO_OR_GS_CODE(); |
115 | 289k | assert_bdrv_graph_readable(); |
116 | | |
117 | 289k | QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) { |
118 | 289k | if (c == ignore || (ignore_bds_parents && c->klass->parent_is_bds)) { |
119 | 85.7k | continue; |
120 | 85.7k | } |
121 | 203k | busy |= bdrv_parent_drained_poll_single(c); |
122 | 203k | } |
123 | | |
124 | 289k | return busy; |
125 | 289k | } |
126 | | |
127 | | void bdrv_parent_drained_begin_single(BdrvChild *c) |
128 | 288k | { |
129 | 288k | GLOBAL_STATE_CODE(); |
130 | | |
131 | 288k | assert(!c->quiesced_parent); |
132 | 288k | c->quiesced_parent = true; |
133 | | |
134 | 288k | if (c->klass->drained_begin) { |
135 | | /* called with rdlock taken, but it doesn't really need it. */ |
136 | 288k | c->klass->drained_begin(c); |
137 | 288k | } |
138 | 288k | } |
139 | | |
140 | | static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src) |
141 | 15 | { |
142 | 15 | dst->pdiscard_alignment = MAX(dst->pdiscard_alignment, |
143 | 15 | src->pdiscard_alignment); |
144 | 15 | dst->opt_transfer = MAX(dst->opt_transfer, src->opt_transfer); |
145 | 15 | dst->max_transfer = MIN_NON_ZERO(dst->max_transfer, src->max_transfer); |
146 | 15 | dst->max_hw_transfer = MIN_NON_ZERO(dst->max_hw_transfer, |
147 | 15 | src->max_hw_transfer); |
148 | 15 | dst->opt_mem_alignment = MAX(dst->opt_mem_alignment, |
149 | 15 | src->opt_mem_alignment); |
150 | 15 | dst->min_mem_alignment = MAX(dst->min_mem_alignment, |
151 | 15 | src->min_mem_alignment); |
152 | 15 | dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov); |
153 | 15 | dst->max_hw_iov = MIN_NON_ZERO(dst->max_hw_iov, src->max_hw_iov); |
154 | 15 | } |
155 | | |
156 | | typedef struct BdrvRefreshLimitsState { |
157 | | BlockDriverState *bs; |
158 | | BlockLimits old_bl; |
159 | | } BdrvRefreshLimitsState; |
160 | | |
161 | | static void bdrv_refresh_limits_abort(void *opaque) |
162 | 0 | { |
163 | 0 | BdrvRefreshLimitsState *s = opaque; |
164 | |
|
165 | 0 | s->bs->bl = s->old_bl; |
166 | 0 | } |
167 | | |
168 | | static TransactionActionDrv bdrv_refresh_limits_drv = { |
169 | | .abort = bdrv_refresh_limits_abort, |
170 | | .clean = g_free, |
171 | | }; |
172 | | |
173 | | /* @tran is allowed to be NULL, in this case no rollback is possible. */ |
174 | | void bdrv_refresh_limits(BlockDriverState *bs, Transaction *tran, Error **errp) |
175 | 31 | { |
176 | 31 | ERRP_GUARD(); |
177 | 31 | BlockDriver *drv = bs->drv; |
178 | 31 | BdrvChild *c; |
179 | 31 | bool have_limits; |
180 | | |
181 | 31 | GLOBAL_STATE_CODE(); |
182 | | |
183 | 31 | if (tran) { |
184 | 0 | BdrvRefreshLimitsState *s = g_new(BdrvRefreshLimitsState, 1); |
185 | 0 | *s = (BdrvRefreshLimitsState) { |
186 | 0 | .bs = bs, |
187 | 0 | .old_bl = bs->bl, |
188 | 0 | }; |
189 | 0 | tran_add(tran, &bdrv_refresh_limits_drv, s); |
190 | 0 | } |
191 | | |
192 | 31 | memset(&bs->bl, 0, sizeof(bs->bl)); |
193 | | |
194 | 31 | if (!drv) { |
195 | 0 | return; |
196 | 0 | } |
197 | | |
198 | | /* Default alignment based on whether driver has byte interface */ |
199 | 31 | bs->bl.request_alignment = (drv->bdrv_co_preadv || |
200 | 0 | drv->bdrv_aio_preadv || |
201 | 31 | drv->bdrv_co_preadv_part) ? 1 : 512; |
202 | | |
203 | | /* Take some limits from the children as a default */ |
204 | 31 | have_limits = false; |
205 | 31 | QLIST_FOREACH(c, &bs->children, next) { |
206 | 15 | if (c->role & (BDRV_CHILD_DATA | BDRV_CHILD_FILTERED | BDRV_CHILD_COW)) |
207 | 15 | { |
208 | 15 | bdrv_merge_limits(&bs->bl, &c->bs->bl); |
209 | 15 | have_limits = true; |
210 | 15 | } |
211 | | |
212 | 15 | if (c->role & BDRV_CHILD_FILTERED) { |
213 | 15 | bs->bl.has_variable_length |= c->bs->bl.has_variable_length; |
214 | 15 | } |
215 | 15 | } |
216 | | |
217 | 31 | if (!have_limits) { |
218 | 16 | bs->bl.min_mem_alignment = 512; |
219 | 16 | bs->bl.opt_mem_alignment = qemu_real_host_page_size(); |
220 | | |
221 | | /* Safe default since most protocols use readv()/writev()/etc */ |
222 | 16 | bs->bl.max_iov = IOV_MAX; |
223 | 16 | } |
224 | | |
225 | | /* Then let the driver override it */ |
226 | 31 | if (drv->bdrv_refresh_limits) { |
227 | 15 | drv->bdrv_refresh_limits(bs, errp); |
228 | 15 | if (*errp) { |
229 | 0 | return; |
230 | 0 | } |
231 | 15 | } |
232 | | |
233 | 31 | if (bs->bl.zone_size) { |
234 | 0 | assert(is_power_of_2(bs->bl.zone_size)); |
235 | 0 | bs->bl.zone_size_bits = ctz64(bs->bl.zone_size); |
236 | 0 | } |
237 | | |
238 | 31 | if (bs->bl.request_alignment > BDRV_MAX_ALIGNMENT) { |
239 | 0 | error_setg(errp, "Driver requires too large request alignment"); |
240 | 0 | } |
241 | 31 | } |
242 | | |
243 | | /** |
244 | | * The copy-on-read flag is actually a reference count so multiple users may |
245 | | * use the feature without worrying about clobbering its previous state. |
246 | | * Copy-on-read stays enabled until all users have called to disable it. |
247 | | */ |
248 | | void bdrv_enable_copy_on_read(BlockDriverState *bs) |
249 | 0 | { |
250 | 0 | IO_CODE(); |
251 | 0 | qatomic_inc(&bs->copy_on_read); |
252 | 0 | } |
253 | | |
254 | | void bdrv_disable_copy_on_read(BlockDriverState *bs) |
255 | 0 | { |
256 | 0 | int old = qatomic_fetch_dec(&bs->copy_on_read); |
257 | 0 | IO_CODE(); |
258 | 0 | assert(old >= 1); |
259 | 0 | } |
260 | | |
261 | | typedef struct { |
262 | | Coroutine *co; |
263 | | BlockDriverState *bs; |
264 | | bool done; |
265 | | bool begin; |
266 | | bool poll; |
267 | | BdrvChild *parent; |
268 | | } BdrvCoDrainData; |
269 | | |
270 | | /* Returns true if BDRV_POLL_WHILE() should go into a blocking aio_poll() */ |
271 | | bool bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent, |
272 | | bool ignore_bds_parents) |
273 | 289k | { |
274 | 289k | GLOBAL_STATE_CODE(); |
275 | | |
276 | 289k | if (bdrv_parent_drained_poll(bs, ignore_parent, ignore_bds_parents)) { |
277 | 908 | return true; |
278 | 908 | } |
279 | | |
280 | 288k | if (qatomic_read(&bs->in_flight)) { |
281 | 0 | return true; |
282 | 0 | } |
283 | | |
284 | 288k | return false; |
285 | 288k | } |
286 | | |
287 | | static bool bdrv_drain_poll_top_level(BlockDriverState *bs, |
288 | | BdrvChild *ignore_parent) |
289 | 118k | { |
290 | 118k | GLOBAL_STATE_CODE(); |
291 | 118k | GRAPH_RDLOCK_GUARD_MAINLOOP(); |
292 | | |
293 | 118k | return bdrv_drain_poll(bs, ignore_parent, false); |
294 | 118k | } |
295 | | |
296 | | static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent, |
297 | | bool poll); |
298 | | static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent); |
299 | | |
300 | | static void bdrv_co_drain_bh_cb(void *opaque) |
301 | 0 | { |
302 | 0 | BdrvCoDrainData *data = opaque; |
303 | 0 | Coroutine *co = data->co; |
304 | 0 | BlockDriverState *bs = data->bs; |
305 | |
|
306 | 0 | if (bs) { |
307 | 0 | bdrv_dec_in_flight(bs); |
308 | 0 | if (data->begin) { |
309 | 0 | bdrv_do_drained_begin(bs, data->parent, data->poll); |
310 | 0 | } else { |
311 | 0 | assert(!data->poll); |
312 | 0 | bdrv_do_drained_end(bs, data->parent); |
313 | 0 | } |
314 | 0 | } else { |
315 | 0 | assert(data->begin); |
316 | 0 | bdrv_drain_all_begin(); |
317 | 0 | } |
318 | |
|
319 | 0 | data->done = true; |
320 | 0 | aio_co_wake(co); |
321 | 0 | } |
322 | | |
323 | | static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, |
324 | | bool begin, |
325 | | BdrvChild *parent, |
326 | | bool poll) |
327 | 0 | { |
328 | 0 | BdrvCoDrainData data; |
329 | 0 | Coroutine *self = qemu_coroutine_self(); |
330 | | |
331 | | /* Calling bdrv_drain() from a BH ensures the current coroutine yields and |
332 | | * other coroutines run if they were queued by aio_co_enter(). */ |
333 | |
|
334 | 0 | assert(qemu_in_coroutine()); |
335 | 0 | data = (BdrvCoDrainData) { |
336 | 0 | .co = self, |
337 | 0 | .bs = bs, |
338 | 0 | .done = false, |
339 | 0 | .begin = begin, |
340 | 0 | .parent = parent, |
341 | 0 | .poll = poll, |
342 | 0 | }; |
343 | |
|
344 | 0 | if (bs) { |
345 | 0 | bdrv_inc_in_flight(bs); |
346 | 0 | } |
347 | |
|
348 | 0 | replay_bh_schedule_oneshot_event(qemu_get_aio_context(), |
349 | 0 | bdrv_co_drain_bh_cb, &data); |
350 | |
|
351 | 0 | qemu_coroutine_yield(); |
352 | | /* If we are resumed from some other event (such as an aio completion or a |
353 | | * timer callback), it is a bug in the caller that should be fixed. */ |
354 | 0 | assert(data.done); |
355 | 0 | } |
356 | | |
357 | | static void coroutine_mixed_fn |
358 | | bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent, |
359 | | bool poll) |
360 | 374k | { |
361 | 374k | IO_OR_GS_CODE(); |
362 | | |
363 | 374k | if (qemu_in_coroutine()) { |
364 | 0 | bdrv_co_yield_to_drain(bs, true, parent, poll); |
365 | 0 | return; |
366 | 0 | } |
367 | | |
368 | 374k | GLOBAL_STATE_CODE(); |
369 | | |
370 | | /* Stop things in parent-to-child order */ |
371 | 374k | if (bs->quiesce_counter++ == 0) { |
372 | 288k | GRAPH_RDLOCK_GUARD_MAINLOOP(); |
373 | 288k | bdrv_parent_drained_begin(bs, parent); |
374 | 288k | if (bs->drv && bs->drv->bdrv_drain_begin) { |
375 | 0 | bs->drv->bdrv_drain_begin(bs); |
376 | 0 | } |
377 | 288k | } |
378 | | |
379 | | /* |
380 | | * Wait for drained requests to finish. |
381 | | * |
382 | | * Calling BDRV_POLL_WHILE() only once for the top-level node is okay: The |
383 | | * call is needed so things in this AioContext can make progress even |
384 | | * though we don't return to the main AioContext loop - this automatically |
385 | | * includes other nodes in the same AioContext and therefore all child |
386 | | * nodes. |
387 | | */ |
388 | 374k | if (poll) { |
389 | 117k | BDRV_POLL_WHILE(bs, bdrv_drain_poll_top_level(bs, parent)); |
390 | 117k | } |
391 | 374k | } |
392 | | |
393 | | void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent) |
394 | 85.5k | { |
395 | 85.5k | bdrv_do_drained_begin(bs, parent, false); |
396 | 85.5k | } |
397 | | |
398 | | void coroutine_mixed_fn |
399 | | bdrv_drained_begin(BlockDriverState *bs) |
400 | 117k | { |
401 | 117k | IO_OR_GS_CODE(); |
402 | 117k | bdrv_do_drained_begin(bs, NULL, true); |
403 | 117k | } |
404 | | |
405 | | /** |
406 | | * This function does not poll, nor must any of its recursively called |
407 | | * functions. |
408 | | */ |
409 | | static void coroutine_mixed_fn |
410 | | bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent) |
411 | 374k | { |
412 | 374k | IO_OR_GS_CODE(); |
413 | | |
414 | 374k | if (qemu_in_coroutine()) { |
415 | 0 | bdrv_co_yield_to_drain(bs, false, parent, false); |
416 | 0 | return; |
417 | 0 | } |
418 | | |
419 | | /* At this point, we should be always running in the main loop. */ |
420 | 374k | GLOBAL_STATE_CODE(); |
421 | 374k | assert(bs->quiesce_counter > 0); |
422 | | |
423 | | /* Re-enable things in child-to-parent order */ |
424 | 374k | if (--bs->quiesce_counter == 0) { |
425 | 288k | GRAPH_RDLOCK_GUARD_MAINLOOP(); |
426 | 288k | if (bs->drv && bs->drv->bdrv_drain_end) { |
427 | 0 | bs->drv->bdrv_drain_end(bs); |
428 | 0 | } |
429 | 288k | bdrv_parent_drained_end(bs, parent); |
430 | 288k | } |
431 | 374k | } |
432 | | |
433 | | void bdrv_drained_end(BlockDriverState *bs) |
434 | 203k | { |
435 | 203k | IO_OR_GS_CODE(); |
436 | 203k | bdrv_do_drained_end(bs, NULL); |
437 | 203k | } |
438 | | |
439 | | void bdrv_drain(BlockDriverState *bs) |
440 | 0 | { |
441 | 0 | IO_OR_GS_CODE(); |
442 | 0 | bdrv_drained_begin(bs); |
443 | 0 | bdrv_drained_end(bs); |
444 | 0 | } |
445 | | |
446 | | static void bdrv_drain_assert_idle(BlockDriverState *bs) |
447 | 256k | { |
448 | 256k | BdrvChild *child, *next; |
449 | 256k | GLOBAL_STATE_CODE(); |
450 | 256k | GRAPH_RDLOCK_GUARD_MAINLOOP(); |
451 | | |
452 | 256k | assert(qatomic_read(&bs->in_flight) == 0); |
453 | 256k | QLIST_FOREACH_SAFE(child, &bs->children, next, next) { |
454 | 85.4k | bdrv_drain_assert_idle(child->bs); |
455 | 85.4k | } |
456 | 256k | } |
457 | | |
458 | | unsigned int bdrv_drain_all_count = 0; |
459 | | |
460 | | static bool bdrv_drain_all_poll(void) |
461 | 85.7k | { |
462 | 85.7k | BlockDriverState *bs = NULL; |
463 | 85.7k | bool result = false; |
464 | | |
465 | 85.7k | GLOBAL_STATE_CODE(); |
466 | 85.7k | GRAPH_RDLOCK_GUARD_MAINLOOP(); |
467 | | |
468 | | /* |
469 | | * bdrv_drain_poll() can't make changes to the graph and we hold the BQL, |
470 | | * so iterating bdrv_next_all_states() is safe. |
471 | | */ |
472 | 257k | while ((bs = bdrv_next_all_states(bs))) { |
473 | 171k | result |= bdrv_drain_poll(bs, NULL, true); |
474 | 171k | } |
475 | | |
476 | 85.7k | return result; |
477 | 85.7k | } |
478 | | |
479 | | /* |
480 | | * Wait for pending requests to complete across all BlockDriverStates |
481 | | * |
482 | | * This function does not flush data to disk, use bdrv_flush_all() for that |
483 | | * after calling this function. |
484 | | * |
485 | | * This pauses all block jobs and disables external clients. It must |
486 | | * be paired with bdrv_drain_all_end(). |
487 | | * |
488 | | * NOTE: no new block jobs or BlockDriverStates can be created between |
489 | | * the bdrv_drain_all_begin() and bdrv_drain_all_end() calls. |
490 | | */ |
491 | | void bdrv_drain_all_begin_nopoll(void) |
492 | 85.5k | { |
493 | 85.5k | BlockDriverState *bs = NULL; |
494 | 85.5k | GLOBAL_STATE_CODE(); |
495 | | |
496 | | /* |
497 | | * bdrv queue is managed by record/replay, |
498 | | * waiting for finishing the I/O requests may |
499 | | * be infinite |
500 | | */ |
501 | 85.5k | if (replay_events_enabled()) { |
502 | 0 | return; |
503 | 0 | } |
504 | | |
505 | | /* AIO_WAIT_WHILE() with a NULL context can only be called from the main |
506 | | * loop AioContext, so make sure we're in the main context. */ |
507 | 85.5k | assert(qemu_get_current_aio_context() == qemu_get_aio_context()); |
508 | 85.5k | assert(bdrv_drain_all_count < INT_MAX); |
509 | 85.5k | bdrv_drain_all_count++; |
510 | | |
511 | | /* Quiesce all nodes, without polling in-flight requests yet. The graph |
512 | | * cannot change during this loop. */ |
513 | 256k | while ((bs = bdrv_next_all_states(bs))) { |
514 | 170k | bdrv_do_drained_begin(bs, NULL, false); |
515 | 170k | } |
516 | 85.5k | } |
517 | | |
518 | | void coroutine_mixed_fn bdrv_drain_all_begin(void) |
519 | 85.5k | { |
520 | 85.5k | BlockDriverState *bs = NULL; |
521 | | |
522 | 85.5k | if (qemu_in_coroutine()) { |
523 | 0 | bdrv_co_yield_to_drain(NULL, true, NULL, true); |
524 | 0 | return; |
525 | 0 | } |
526 | | |
527 | | /* |
528 | | * bdrv queue is managed by record/replay, |
529 | | * waiting for finishing the I/O requests may |
530 | | * be infinite |
531 | | */ |
532 | 85.5k | if (replay_events_enabled()) { |
533 | 0 | return; |
534 | 0 | } |
535 | | |
536 | 85.5k | bdrv_drain_all_begin_nopoll(); |
537 | | |
538 | | /* Now poll the in-flight requests */ |
539 | 85.5k | AIO_WAIT_WHILE_UNLOCKED(NULL, bdrv_drain_all_poll()); |
540 | | |
541 | 256k | while ((bs = bdrv_next_all_states(bs))) { |
542 | 170k | bdrv_drain_assert_idle(bs); |
543 | 170k | } |
544 | 85.5k | } |
545 | | |
546 | | void bdrv_drain_all_end_quiesce(BlockDriverState *bs) |
547 | 0 | { |
548 | 0 | GLOBAL_STATE_CODE(); |
549 | |
|
550 | 0 | g_assert(bs->quiesce_counter > 0); |
551 | 0 | g_assert(!bs->refcnt); |
552 | | |
553 | 0 | while (bs->quiesce_counter) { |
554 | 0 | bdrv_do_drained_end(bs, NULL); |
555 | 0 | } |
556 | 0 | } |
557 | | |
558 | | void bdrv_drain_all_end(void) |
559 | 85.5k | { |
560 | 85.5k | BlockDriverState *bs = NULL; |
561 | 85.5k | GLOBAL_STATE_CODE(); |
562 | | |
563 | | /* |
564 | | * bdrv queue is managed by record/replay, |
565 | | * waiting for finishing the I/O requests may |
566 | | * be endless |
567 | | */ |
568 | 85.5k | if (replay_events_enabled()) { |
569 | 0 | return; |
570 | 0 | } |
571 | | |
572 | 256k | while ((bs = bdrv_next_all_states(bs))) { |
573 | 170k | bdrv_do_drained_end(bs, NULL); |
574 | 170k | } |
575 | | |
576 | 85.5k | assert(qemu_get_current_aio_context() == qemu_get_aio_context()); |
577 | 85.5k | assert(bdrv_drain_all_count > 0); |
578 | 85.5k | bdrv_drain_all_count--; |
579 | 85.5k | } |
580 | | |
581 | | void bdrv_drain_all(void) |
582 | 0 | { |
583 | 0 | GLOBAL_STATE_CODE(); |
584 | 0 | bdrv_drain_all_begin(); |
585 | 0 | bdrv_drain_all_end(); |
586 | 0 | } |
587 | | |
588 | | /** |
589 | | * Remove an active request from the tracked requests list |
590 | | * |
591 | | * This function should be called when a tracked request is completing. |
592 | | */ |
593 | | static void coroutine_fn tracked_request_end(BdrvTrackedRequest *req) |
594 | 40.2M | { |
595 | 40.2M | if (req->serialising) { |
596 | 0 | qatomic_dec(&req->bs->serialising_in_flight); |
597 | 0 | } |
598 | | |
599 | 40.2M | qemu_mutex_lock(&req->bs->reqs_lock); |
600 | 40.2M | QLIST_REMOVE(req, list); |
601 | 40.2M | qemu_mutex_unlock(&req->bs->reqs_lock); |
602 | | |
603 | | /* |
604 | | * At this point qemu_co_queue_wait(&req->wait_queue, ...) won't be called |
605 | | * anymore because the request has been removed from the list, so it's safe |
606 | | * to restart the queue outside reqs_lock to minimize the critical section. |
607 | | */ |
608 | 40.2M | qemu_co_queue_restart_all(&req->wait_queue); |
609 | 40.2M | } |
610 | | |
611 | | /** |
612 | | * Add an active request to the tracked requests list |
613 | | */ |
614 | | static void coroutine_fn tracked_request_begin(BdrvTrackedRequest *req, |
615 | | BlockDriverState *bs, |
616 | | int64_t offset, |
617 | | int64_t bytes, |
618 | | enum BdrvTrackedRequestType type) |
619 | 40.2M | { |
620 | 40.2M | bdrv_check_request(offset, bytes, &error_abort); |
621 | | |
622 | 40.2M | *req = (BdrvTrackedRequest){ |
623 | 40.2M | .bs = bs, |
624 | 40.2M | .offset = offset, |
625 | 40.2M | .bytes = bytes, |
626 | 40.2M | .type = type, |
627 | 40.2M | .co = qemu_coroutine_self(), |
628 | 40.2M | .serialising = false, |
629 | 40.2M | .active_owner = false, |
630 | 40.2M | .overlap_offset = offset, |
631 | 40.2M | .overlap_bytes = bytes, |
632 | 40.2M | }; |
633 | | |
634 | 40.2M | qemu_co_queue_init(&req->wait_queue); |
635 | | |
636 | 40.2M | qemu_mutex_lock(&bs->reqs_lock); |
637 | 40.2M | QLIST_INSERT_HEAD(&bs->tracked_requests, req, list); |
638 | | |
639 | | /* |
640 | | * Set .waiting_for while we're holding the lock, otherwise we'd open a race |
641 | | * window where another request in the middle of its RMW cycle starts |
642 | | * waiting for us, leading to potential data corruption if this request |
643 | | * overwrites a block the RMW request has already read. |
644 | | */ |
645 | 40.2M | bdrv_wait_serialising_requests_locked(req); |
646 | | |
647 | 40.2M | qemu_mutex_unlock(&bs->reqs_lock); |
648 | 40.2M | } |
649 | | |
650 | | static bool tracked_request_overlaps(BdrvTrackedRequest *req, |
651 | | int64_t offset, int64_t bytes) |
652 | 0 | { |
653 | 0 | bdrv_check_request(offset, bytes, &error_abort); |
654 | | |
655 | | /* aaaa bbbb */ |
656 | 0 | if (offset >= req->overlap_offset + req->overlap_bytes) { |
657 | 0 | return false; |
658 | 0 | } |
659 | | /* bbbb aaaa */ |
660 | 0 | if (req->overlap_offset >= offset + bytes) { |
661 | 0 | return false; |
662 | 0 | } |
663 | 0 | return true; |
664 | 0 | } |
665 | | |
666 | | /* Called with self->bs->reqs_lock held */ |
667 | | static coroutine_fn BdrvTrackedRequest * |
668 | | bdrv_find_conflicting_request(BdrvTrackedRequest *self) |
669 | 40.2M | { |
670 | 40.2M | BdrvTrackedRequest *req; |
671 | | |
672 | 40.2M | QLIST_FOREACH(req, &self->bs->tracked_requests, list) { |
673 | 40.2M | if (req == self || (!req->serialising && !self->serialising)) { |
674 | 40.2M | continue; |
675 | 40.2M | } |
676 | 0 | if (tracked_request_overlaps(req, self->overlap_offset, |
677 | 0 | self->overlap_bytes)) |
678 | 0 | { |
679 | | /* |
680 | | * Hitting this means there was a reentrant request, for |
681 | | * example, a block driver issuing nested requests. This must |
682 | | * never happen since it means deadlock. |
683 | | */ |
684 | 0 | assert(qemu_coroutine_self() != req->co); |
685 | | |
686 | | /* |
687 | | * If the request is already (indirectly) waiting for us, or |
688 | | * will wait for us as soon as it wakes up, then just go on |
689 | | * (instead of producing a deadlock in the former case). |
690 | | */ |
691 | 0 | if (!req->waiting_for) { |
692 | 0 | return req; |
693 | 0 | } |
694 | 0 | } |
695 | 0 | } |
696 | | |
697 | 40.2M | return NULL; |
698 | 40.2M | } |
699 | | |
700 | | /* Called with self->bs->reqs_lock held */ |
701 | | static void coroutine_fn |
702 | | bdrv_wait_serialising_requests_locked(BdrvTrackedRequest *self) |
703 | 40.2M | { |
704 | 40.2M | BdrvTrackedRequest *req; |
705 | | |
706 | 40.2M | while ((req = bdrv_find_conflicting_request(self))) { |
707 | | /* |
708 | | * If this request is the active owner of the data blocks it accesses, |
709 | | * no other conflicting request may exist; other requests have to wait |
710 | | * for this one, not the other way around. If this condition is |
711 | | * violated, RMW operations may be interrupted in the middle, operate on |
712 | | * stale data and introduce data corruption. |
713 | | */ |
714 | 0 | assert(!self->active_owner); |
715 | |
|
716 | 0 | self->waiting_for = req; |
717 | 0 | qemu_co_queue_wait(&req->wait_queue, &self->bs->reqs_lock); |
718 | 0 | self->waiting_for = NULL; |
719 | 0 | } |
720 | 40.2M | } |
721 | | |
722 | | /* Called with req->bs->reqs_lock held */ |
723 | | static void tracked_request_set_serialising(BdrvTrackedRequest *req, |
724 | | uint64_t align) |
725 | 0 | { |
726 | 0 | int64_t overlap_offset = req->offset & ~(align - 1); |
727 | 0 | int64_t overlap_bytes = |
728 | 0 | ROUND_UP(req->offset + req->bytes, align) - overlap_offset; |
729 | |
|
730 | 0 | bdrv_check_request(req->offset, req->bytes, &error_abort); |
731 | |
|
732 | 0 | if (!req->serialising) { |
733 | 0 | qatomic_inc(&req->bs->serialising_in_flight); |
734 | 0 | req->serialising = true; |
735 | 0 | } |
736 | |
|
737 | 0 | req->overlap_offset = MIN(req->overlap_offset, overlap_offset); |
738 | 0 | req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes); |
739 | 0 | } |
740 | | |
741 | | /** |
742 | | * Return the tracked request on @bs for the current coroutine, or |
743 | | * NULL if there is none. |
744 | | */ |
745 | | BdrvTrackedRequest *coroutine_fn bdrv_co_get_self_request(BlockDriverState *bs) |
746 | 0 | { |
747 | 0 | BdrvTrackedRequest *req; |
748 | 0 | Coroutine *self = qemu_coroutine_self(); |
749 | 0 | IO_CODE(); |
750 | |
|
751 | 0 | QEMU_LOCK_GUARD(&bs->reqs_lock); |
752 | 0 | QLIST_FOREACH(req, &bs->tracked_requests, list) { |
753 | 0 | if (req->co == self) { |
754 | 0 | return req; |
755 | 0 | } |
756 | 0 | } |
757 | | |
758 | 0 | return NULL; |
759 | 0 | } |
760 | | |
761 | | /** |
762 | | * Round a region to subcluster (if supported) or cluster boundaries |
763 | | */ |
764 | | void coroutine_fn GRAPH_RDLOCK |
765 | | bdrv_round_to_subclusters(BlockDriverState *bs, int64_t offset, int64_t bytes, |
766 | | int64_t *align_offset, int64_t *align_bytes) |
767 | 0 | { |
768 | 0 | BlockDriverInfo bdi; |
769 | 0 | IO_CODE(); |
770 | 0 | if (bdrv_co_get_info(bs, &bdi) < 0 || bdi.subcluster_size == 0) { |
771 | 0 | *align_offset = offset; |
772 | 0 | *align_bytes = bytes; |
773 | 0 | } else { |
774 | 0 | int64_t c = bdi.subcluster_size; |
775 | 0 | *align_offset = QEMU_ALIGN_DOWN(offset, c); |
776 | 0 | *align_bytes = QEMU_ALIGN_UP(offset - *align_offset + bytes, c); |
777 | 0 | } |
778 | 0 | } |
779 | | |
780 | | static int coroutine_fn GRAPH_RDLOCK bdrv_get_cluster_size(BlockDriverState *bs) |
781 | 0 | { |
782 | 0 | BlockDriverInfo bdi; |
783 | 0 | int ret; |
784 | |
|
785 | 0 | ret = bdrv_co_get_info(bs, &bdi); |
786 | 0 | if (ret < 0 || bdi.cluster_size == 0) { |
787 | 0 | return bs->bl.request_alignment; |
788 | 0 | } else { |
789 | 0 | return bdi.cluster_size; |
790 | 0 | } |
791 | 0 | } |
792 | | |
793 | | void bdrv_inc_in_flight(BlockDriverState *bs) |
794 | 60.4M | { |
795 | 60.4M | IO_CODE(); |
796 | 60.4M | qatomic_inc(&bs->in_flight); |
797 | 60.4M | } |
798 | | |
799 | | void bdrv_wakeup(BlockDriverState *bs) |
800 | 60.4M | { |
801 | 60.4M | IO_CODE(); |
802 | 60.4M | aio_wait_kick(); |
803 | 60.4M | } |
804 | | |
805 | | void bdrv_dec_in_flight(BlockDriverState *bs) |
806 | 60.4M | { |
807 | 60.4M | IO_CODE(); |
808 | 60.4M | qatomic_dec(&bs->in_flight); |
809 | 60.4M | bdrv_wakeup(bs); |
810 | 60.4M | } |
811 | | |
812 | | void coroutine_fn bdrv_make_request_serialising(BdrvTrackedRequest *req, |
813 | | uint64_t align) |
814 | 0 | { |
815 | 0 | IO_CODE(); |
816 | |
|
817 | 0 | qemu_mutex_lock(&req->bs->reqs_lock); |
818 | |
|
819 | 0 | tracked_request_set_serialising(req, align); |
820 | 0 | bdrv_wait_serialising_requests_locked(req); |
821 | 0 | req->active_owner = true; |
822 | |
|
823 | 0 | qemu_mutex_unlock(&req->bs->reqs_lock); |
824 | 0 | } |
825 | | |
826 | | int bdrv_check_qiov_request(int64_t offset, int64_t bytes, |
827 | | QEMUIOVector *qiov, size_t qiov_offset, |
828 | | Error **errp) |
829 | 245M | { |
830 | | /* |
831 | | * Check generic offset/bytes correctness |
832 | | */ |
833 | | |
834 | 245M | if (offset < 0) { |
835 | 0 | error_setg(errp, "offset is negative: %" PRIi64, offset); |
836 | 0 | return -EIO; |
837 | 0 | } |
838 | | |
839 | 245M | if (bytes < 0) { |
840 | 0 | error_setg(errp, "bytes is negative: %" PRIi64, bytes); |
841 | 0 | return -EIO; |
842 | 0 | } |
843 | | |
844 | 245M | if (bytes > BDRV_MAX_LENGTH) { |
845 | 0 | error_setg(errp, "bytes(%" PRIi64 ") exceeds maximum(%" PRIi64 ")", |
846 | 0 | bytes, BDRV_MAX_LENGTH); |
847 | 0 | return -EIO; |
848 | 0 | } |
849 | | |
850 | 245M | if (offset > BDRV_MAX_LENGTH) { |
851 | 0 | error_setg(errp, "offset(%" PRIi64 ") exceeds maximum(%" PRIi64 ")", |
852 | 0 | offset, BDRV_MAX_LENGTH); |
853 | 0 | return -EIO; |
854 | 0 | } |
855 | | |
856 | 245M | if (offset > BDRV_MAX_LENGTH - bytes) { |
857 | 0 | error_setg(errp, "sum of offset(%" PRIi64 ") and bytes(%" PRIi64 ") " |
858 | 0 | "exceeds maximum(%" PRIi64 ")", offset, bytes, |
859 | 0 | BDRV_MAX_LENGTH); |
860 | 0 | return -EIO; |
861 | 0 | } |
862 | | |
863 | 245M | if (!qiov) { |
864 | 83.9M | return 0; |
865 | 83.9M | } |
866 | | |
867 | | /* |
868 | | * Check qiov and qiov_offset |
869 | | */ |
870 | | |
871 | 161M | if (qiov_offset > qiov->size) { |
872 | 0 | error_setg(errp, "qiov_offset(%zu) overflow io vector size(%zu)", |
873 | 0 | qiov_offset, qiov->size); |
874 | 0 | return -EIO; |
875 | 0 | } |
876 | | |
877 | 161M | if (bytes > qiov->size - qiov_offset) { |
878 | 0 | error_setg(errp, "bytes(%" PRIi64 ") + qiov_offset(%zu) overflow io " |
879 | 0 | "vector size(%zu)", bytes, qiov_offset, qiov->size); |
880 | 0 | return -EIO; |
881 | 0 | } |
882 | | |
883 | 161M | return 0; |
884 | 161M | } |
885 | | |
886 | | int bdrv_check_request(int64_t offset, int64_t bytes, Error **errp) |
887 | 83.9M | { |
888 | 83.9M | return bdrv_check_qiov_request(offset, bytes, NULL, 0, errp); |
889 | 83.9M | } |
890 | | |
891 | | static int bdrv_check_request32(int64_t offset, int64_t bytes, |
892 | | QEMUIOVector *qiov, size_t qiov_offset) |
893 | 80.5M | { |
894 | 80.5M | int ret = bdrv_check_qiov_request(offset, bytes, qiov, qiov_offset, NULL); |
895 | 80.5M | if (ret < 0) { |
896 | 0 | return ret; |
897 | 0 | } |
898 | | |
899 | 80.5M | if (bytes > BDRV_REQUEST_MAX_BYTES) { |
900 | 0 | return -EIO; |
901 | 0 | } |
902 | | |
903 | 80.5M | return 0; |
904 | 80.5M | } |
905 | | |
906 | | /* |
907 | | * Completely zero out a block device with the help of bdrv_pwrite_zeroes. |
908 | | * The operation is sped up by checking the block status and only writing |
909 | | * zeroes to the device if they currently do not return zeroes. Optional |
910 | | * flags are passed through to bdrv_pwrite_zeroes (e.g. BDRV_REQ_MAY_UNMAP, |
911 | | * BDRV_REQ_FUA). |
912 | | * |
913 | | * Returns < 0 on error, 0 on success. For error codes see bdrv_pwrite(). |
914 | | */ |
915 | | int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) |
916 | 0 | { |
917 | 0 | int ret; |
918 | 0 | int64_t target_size, bytes, offset = 0; |
919 | 0 | BlockDriverState *bs = child->bs; |
920 | 0 | IO_CODE(); |
921 | |
|
922 | 0 | target_size = bdrv_getlength(bs); |
923 | 0 | if (target_size < 0) { |
924 | 0 | return target_size; |
925 | 0 | } |
926 | | |
927 | 0 | for (;;) { |
928 | 0 | bytes = MIN(target_size - offset, BDRV_REQUEST_MAX_BYTES); |
929 | 0 | if (bytes <= 0) { |
930 | 0 | return 0; |
931 | 0 | } |
932 | 0 | ret = bdrv_block_status(bs, offset, bytes, &bytes, NULL, NULL); |
933 | 0 | if (ret < 0) { |
934 | 0 | return ret; |
935 | 0 | } |
936 | 0 | if (ret & BDRV_BLOCK_ZERO) { |
937 | 0 | offset += bytes; |
938 | 0 | continue; |
939 | 0 | } |
940 | 0 | ret = bdrv_pwrite_zeroes(child, offset, bytes, flags); |
941 | 0 | if (ret < 0) { |
942 | 0 | return ret; |
943 | 0 | } |
944 | 0 | offset += bytes; |
945 | 0 | } |
946 | 0 | } |
947 | | |
948 | | /* |
949 | | * Writes to the file and ensures that no writes are reordered across this |
950 | | * request (acts as a barrier) |
951 | | * |
952 | | * Returns 0 on success, -errno in error cases. |
953 | | */ |
954 | | int coroutine_fn bdrv_co_pwrite_sync(BdrvChild *child, int64_t offset, |
955 | | int64_t bytes, const void *buf, |
956 | | BdrvRequestFlags flags) |
957 | 0 | { |
958 | 0 | int ret; |
959 | 0 | IO_CODE(); |
960 | 0 | assert_bdrv_graph_readable(); |
961 | |
|
962 | 0 | ret = bdrv_co_pwrite(child, offset, bytes, buf, flags); |
963 | 0 | if (ret < 0) { |
964 | 0 | return ret; |
965 | 0 | } |
966 | | |
967 | 0 | ret = bdrv_co_flush(child->bs); |
968 | 0 | if (ret < 0) { |
969 | 0 | return ret; |
970 | 0 | } |
971 | | |
972 | 0 | return 0; |
973 | 0 | } |
974 | | |
975 | | typedef struct CoroutineIOCompletion { |
976 | | Coroutine *coroutine; |
977 | | int ret; |
978 | | } CoroutineIOCompletion; |
979 | | |
980 | | static void bdrv_co_io_em_complete(void *opaque, int ret) |
981 | 0 | { |
982 | 0 | CoroutineIOCompletion *co = opaque; |
983 | |
|
984 | 0 | co->ret = ret; |
985 | 0 | aio_co_wake(co->coroutine); |
986 | 0 | } |
987 | | |
988 | | static int coroutine_fn GRAPH_RDLOCK |
989 | | bdrv_driver_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes, |
990 | | QEMUIOVector *qiov, size_t qiov_offset, int flags) |
991 | 38.6M | { |
992 | 38.6M | BlockDriver *drv = bs->drv; |
993 | 38.6M | int64_t sector_num; |
994 | 38.6M | unsigned int nb_sectors; |
995 | 38.6M | QEMUIOVector local_qiov; |
996 | 38.6M | int ret; |
997 | 38.6M | assert_bdrv_graph_readable(); |
998 | | |
999 | 38.6M | bdrv_check_qiov_request(offset, bytes, qiov, qiov_offset, &error_abort); |
1000 | 38.6M | assert(!(flags & ~bs->supported_read_flags)); |
1001 | | |
1002 | 38.6M | if (!drv) { |
1003 | 0 | return -ENOMEDIUM; |
1004 | 0 | } |
1005 | | |
1006 | 38.6M | if (drv->bdrv_co_preadv_part) { |
1007 | 0 | return drv->bdrv_co_preadv_part(bs, offset, bytes, qiov, qiov_offset, |
1008 | 0 | flags); |
1009 | 0 | } |
1010 | | |
1011 | 38.6M | if (qiov_offset > 0 || bytes != qiov->size) { |
1012 | 0 | qemu_iovec_init_slice(&local_qiov, qiov, qiov_offset, bytes); |
1013 | 0 | qiov = &local_qiov; |
1014 | 0 | } |
1015 | | |
1016 | 38.6M | if (drv->bdrv_co_preadv) { |
1017 | 38.6M | ret = drv->bdrv_co_preadv(bs, offset, bytes, qiov, flags); |
1018 | 38.6M | goto out; |
1019 | 38.6M | } |
1020 | | |
1021 | 0 | if (drv->bdrv_aio_preadv) { |
1022 | 0 | BlockAIOCB *acb; |
1023 | 0 | CoroutineIOCompletion co = { |
1024 | 0 | .coroutine = qemu_coroutine_self(), |
1025 | 0 | }; |
1026 | |
|
1027 | 0 | acb = drv->bdrv_aio_preadv(bs, offset, bytes, qiov, flags, |
1028 | 0 | bdrv_co_io_em_complete, &co); |
1029 | 0 | if (acb == NULL) { |
1030 | 0 | ret = -EIO; |
1031 | 0 | goto out; |
1032 | 0 | } else { |
1033 | 0 | qemu_coroutine_yield(); |
1034 | 0 | ret = co.ret; |
1035 | 0 | goto out; |
1036 | 0 | } |
1037 | 0 | } |
1038 | | |
1039 | 0 | sector_num = offset >> BDRV_SECTOR_BITS; |
1040 | 0 | nb_sectors = bytes >> BDRV_SECTOR_BITS; |
1041 | |
|
1042 | 0 | assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)); |
1043 | 0 | assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE)); |
1044 | 0 | assert(bytes <= BDRV_REQUEST_MAX_BYTES); |
1045 | 0 | assert(drv->bdrv_co_readv); |
1046 | |
|
1047 | 0 | ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov); |
1048 | |
|
1049 | 38.6M | out: |
1050 | 38.6M | if (qiov == &local_qiov) { |
1051 | 0 | qemu_iovec_destroy(&local_qiov); |
1052 | 0 | } |
1053 | | |
1054 | 38.6M | return ret; |
1055 | 0 | } |
1056 | | |
1057 | | static int coroutine_fn GRAPH_RDLOCK |
1058 | | bdrv_driver_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes, |
1059 | | QEMUIOVector *qiov, size_t qiov_offset, |
1060 | | BdrvRequestFlags flags) |
1061 | 1.62M | { |
1062 | 1.62M | BlockDriver *drv = bs->drv; |
1063 | 1.62M | bool emulate_fua = false; |
1064 | 1.62M | int64_t sector_num; |
1065 | 1.62M | unsigned int nb_sectors; |
1066 | 1.62M | QEMUIOVector local_qiov; |
1067 | 1.62M | int ret; |
1068 | 1.62M | assert_bdrv_graph_readable(); |
1069 | | |
1070 | 1.62M | bdrv_check_qiov_request(offset, bytes, qiov, qiov_offset, &error_abort); |
1071 | | |
1072 | 1.62M | if (!drv) { |
1073 | 0 | return -ENOMEDIUM; |
1074 | 0 | } |
1075 | | |
1076 | 1.62M | if (bs->open_flags & BDRV_O_NO_FLUSH) { |
1077 | 0 | flags &= ~BDRV_REQ_FUA; |
1078 | 0 | } |
1079 | | |
1080 | 1.62M | if ((flags & BDRV_REQ_FUA) && |
1081 | 157k | (~bs->supported_write_flags & BDRV_REQ_FUA)) { |
1082 | 0 | flags &= ~BDRV_REQ_FUA; |
1083 | 0 | emulate_fua = true; |
1084 | 0 | } |
1085 | | |
1086 | 1.62M | flags &= bs->supported_write_flags; |
1087 | | |
1088 | 1.62M | if (drv->bdrv_co_pwritev_part) { |
1089 | 0 | ret = drv->bdrv_co_pwritev_part(bs, offset, bytes, qiov, qiov_offset, |
1090 | 0 | flags); |
1091 | 0 | goto emulate_flags; |
1092 | 0 | } |
1093 | | |
1094 | 1.62M | if (qiov_offset > 0 || bytes != qiov->size) { |
1095 | 0 | qemu_iovec_init_slice(&local_qiov, qiov, qiov_offset, bytes); |
1096 | 0 | qiov = &local_qiov; |
1097 | 0 | } |
1098 | | |
1099 | 1.62M | if (drv->bdrv_co_pwritev) { |
1100 | 1.62M | ret = drv->bdrv_co_pwritev(bs, offset, bytes, qiov, flags); |
1101 | 1.62M | goto emulate_flags; |
1102 | 1.62M | } |
1103 | | |
1104 | 0 | if (drv->bdrv_aio_pwritev) { |
1105 | 0 | BlockAIOCB *acb; |
1106 | 0 | CoroutineIOCompletion co = { |
1107 | 0 | .coroutine = qemu_coroutine_self(), |
1108 | 0 | }; |
1109 | |
|
1110 | 0 | acb = drv->bdrv_aio_pwritev(bs, offset, bytes, qiov, flags, |
1111 | 0 | bdrv_co_io_em_complete, &co); |
1112 | 0 | if (acb == NULL) { |
1113 | 0 | ret = -EIO; |
1114 | 0 | } else { |
1115 | 0 | qemu_coroutine_yield(); |
1116 | 0 | ret = co.ret; |
1117 | 0 | } |
1118 | 0 | goto emulate_flags; |
1119 | 0 | } |
1120 | | |
1121 | 0 | sector_num = offset >> BDRV_SECTOR_BITS; |
1122 | 0 | nb_sectors = bytes >> BDRV_SECTOR_BITS; |
1123 | |
|
1124 | 0 | assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)); |
1125 | 0 | assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE)); |
1126 | 0 | assert(bytes <= BDRV_REQUEST_MAX_BYTES); |
1127 | |
|
1128 | 0 | assert(drv->bdrv_co_writev); |
1129 | 0 | ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov, flags); |
1130 | |
|
1131 | 1.62M | emulate_flags: |
1132 | 1.62M | if (ret == 0 && emulate_fua) { |
1133 | 0 | ret = bdrv_co_flush(bs); |
1134 | 0 | } |
1135 | | |
1136 | 1.62M | if (qiov == &local_qiov) { |
1137 | 0 | qemu_iovec_destroy(&local_qiov); |
1138 | 0 | } |
1139 | | |
1140 | 1.62M | return ret; |
1141 | 0 | } |
1142 | | |
1143 | | static int coroutine_fn GRAPH_RDLOCK |
1144 | | bdrv_driver_pwritev_compressed(BlockDriverState *bs, int64_t offset, |
1145 | | int64_t bytes, QEMUIOVector *qiov, |
1146 | | size_t qiov_offset) |
1147 | 0 | { |
1148 | 0 | BlockDriver *drv = bs->drv; |
1149 | 0 | QEMUIOVector local_qiov; |
1150 | 0 | int ret; |
1151 | 0 | assert_bdrv_graph_readable(); |
1152 | |
|
1153 | 0 | bdrv_check_qiov_request(offset, bytes, qiov, qiov_offset, &error_abort); |
1154 | |
|
1155 | 0 | if (!drv) { |
1156 | 0 | return -ENOMEDIUM; |
1157 | 0 | } |
1158 | | |
1159 | 0 | if (!block_driver_can_compress(drv)) { |
1160 | 0 | return -ENOTSUP; |
1161 | 0 | } |
1162 | | |
1163 | 0 | if (drv->bdrv_co_pwritev_compressed_part) { |
1164 | 0 | return drv->bdrv_co_pwritev_compressed_part(bs, offset, bytes, |
1165 | 0 | qiov, qiov_offset); |
1166 | 0 | } |
1167 | | |
1168 | 0 | if (qiov_offset == 0) { |
1169 | 0 | return drv->bdrv_co_pwritev_compressed(bs, offset, bytes, qiov); |
1170 | 0 | } |
1171 | | |
1172 | 0 | qemu_iovec_init_slice(&local_qiov, qiov, qiov_offset, bytes); |
1173 | 0 | ret = drv->bdrv_co_pwritev_compressed(bs, offset, bytes, &local_qiov); |
1174 | 0 | qemu_iovec_destroy(&local_qiov); |
1175 | |
|
1176 | 0 | return ret; |
1177 | 0 | } |
1178 | | |
1179 | | static int coroutine_fn GRAPH_RDLOCK |
1180 | | bdrv_co_do_copy_on_readv(BdrvChild *child, int64_t offset, int64_t bytes, |
1181 | | QEMUIOVector *qiov, size_t qiov_offset, int flags) |
1182 | 0 | { |
1183 | 0 | BlockDriverState *bs = child->bs; |
1184 | | |
1185 | | /* Perform I/O through a temporary buffer so that users who scribble over |
1186 | | * their read buffer while the operation is in progress do not end up |
1187 | | * modifying the image file. This is critical for zero-copy guest I/O |
1188 | | * where anything might happen inside guest memory. |
1189 | | */ |
1190 | 0 | void *bounce_buffer = NULL; |
1191 | |
|
1192 | 0 | BlockDriver *drv = bs->drv; |
1193 | 0 | int64_t align_offset; |
1194 | 0 | int64_t align_bytes; |
1195 | 0 | int64_t skip_bytes; |
1196 | 0 | int ret; |
1197 | 0 | int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer, |
1198 | 0 | BDRV_REQUEST_MAX_BYTES); |
1199 | 0 | int64_t progress = 0; |
1200 | 0 | bool skip_write; |
1201 | |
|
1202 | 0 | bdrv_check_qiov_request(offset, bytes, qiov, qiov_offset, &error_abort); |
1203 | |
|
1204 | 0 | if (!drv) { |
1205 | 0 | return -ENOMEDIUM; |
1206 | 0 | } |
1207 | | |
1208 | | /* |
1209 | | * Do not write anything when the BDS is inactive. That is not |
1210 | | * allowed, and it would not help. |
1211 | | */ |
1212 | 0 | skip_write = (bs->open_flags & BDRV_O_INACTIVE); |
1213 | | |
1214 | | /* FIXME We cannot require callers to have write permissions when all they |
1215 | | * are doing is a read request. If we did things right, write permissions |
1216 | | * would be obtained anyway, but internally by the copy-on-read code. As |
1217 | | * long as it is implemented here rather than in a separate filter driver, |
1218 | | * the copy-on-read code doesn't have its own BdrvChild, however, for which |
1219 | | * it could request permissions. Therefore we have to bypass the permission |
1220 | | * system for the moment. */ |
1221 | | // assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE)); |
1222 | | |
1223 | | /* Cover entire cluster so no additional backing file I/O is required when |
1224 | | * allocating cluster in the image file. Note that this value may exceed |
1225 | | * BDRV_REQUEST_MAX_BYTES (even when the original read did not), which |
1226 | | * is one reason we loop rather than doing it all at once. |
1227 | | */ |
1228 | 0 | bdrv_round_to_subclusters(bs, offset, bytes, &align_offset, &align_bytes); |
1229 | 0 | skip_bytes = offset - align_offset; |
1230 | |
|
1231 | 0 | trace_bdrv_co_do_copy_on_readv(bs, offset, bytes, |
1232 | 0 | align_offset, align_bytes); |
1233 | |
|
1234 | 0 | while (align_bytes) { |
1235 | 0 | int64_t pnum; |
1236 | |
|
1237 | 0 | if (skip_write) { |
1238 | 0 | ret = 1; /* "already allocated", so nothing will be copied */ |
1239 | 0 | pnum = MIN(align_bytes, max_transfer); |
1240 | 0 | } else { |
1241 | 0 | ret = bdrv_co_is_allocated(bs, align_offset, |
1242 | 0 | MIN(align_bytes, max_transfer), &pnum); |
1243 | 0 | if (ret < 0) { |
1244 | | /* |
1245 | | * Safe to treat errors in querying allocation as if |
1246 | | * unallocated; we'll probably fail again soon on the |
1247 | | * read, but at least that will set a decent errno. |
1248 | | */ |
1249 | 0 | pnum = MIN(align_bytes, max_transfer); |
1250 | 0 | } |
1251 | | |
1252 | | /* Stop at EOF if the image ends in the middle of the cluster */ |
1253 | 0 | if (ret == 0 && pnum == 0) { |
1254 | 0 | assert(progress >= bytes); |
1255 | 0 | break; |
1256 | 0 | } |
1257 | | |
1258 | 0 | assert(skip_bytes < pnum); |
1259 | 0 | } |
1260 | | |
1261 | 0 | if (ret <= 0) { |
1262 | 0 | QEMUIOVector local_qiov; |
1263 | | |
1264 | | /* Must copy-on-read; use the bounce buffer */ |
1265 | 0 | pnum = MIN(pnum, MAX_BOUNCE_BUFFER); |
1266 | 0 | if (!bounce_buffer) { |
1267 | 0 | int64_t max_we_need = MAX(pnum, align_bytes - pnum); |
1268 | 0 | int64_t max_allowed = MIN(max_transfer, MAX_BOUNCE_BUFFER); |
1269 | 0 | int64_t bounce_buffer_len = MIN(max_we_need, max_allowed); |
1270 | |
|
1271 | 0 | bounce_buffer = qemu_try_blockalign(bs, bounce_buffer_len); |
1272 | 0 | if (!bounce_buffer) { |
1273 | 0 | ret = -ENOMEM; |
1274 | 0 | goto err; |
1275 | 0 | } |
1276 | 0 | } |
1277 | 0 | qemu_iovec_init_buf(&local_qiov, bounce_buffer, pnum); |
1278 | |
|
1279 | 0 | ret = bdrv_driver_preadv(bs, align_offset, pnum, |
1280 | 0 | &local_qiov, 0, 0); |
1281 | 0 | if (ret < 0) { |
1282 | 0 | goto err; |
1283 | 0 | } |
1284 | | |
1285 | 0 | bdrv_co_debug_event(bs, BLKDBG_COR_WRITE); |
1286 | 0 | if (drv->bdrv_co_pwrite_zeroes && |
1287 | 0 | buffer_is_zero(bounce_buffer, pnum)) { |
1288 | | /* FIXME: Should we (perhaps conditionally) be setting |
1289 | | * BDRV_REQ_MAY_UNMAP, if it will allow for a sparser copy |
1290 | | * that still correctly reads as zero? */ |
1291 | 0 | ret = bdrv_co_do_pwrite_zeroes(bs, align_offset, pnum, |
1292 | 0 | BDRV_REQ_WRITE_UNCHANGED); |
1293 | 0 | } else { |
1294 | | /* This does not change the data on the disk, it is not |
1295 | | * necessary to flush even in cache=writethrough mode. |
1296 | | */ |
1297 | 0 | ret = bdrv_driver_pwritev(bs, align_offset, pnum, |
1298 | 0 | &local_qiov, 0, |
1299 | 0 | BDRV_REQ_WRITE_UNCHANGED); |
1300 | 0 | } |
1301 | |
|
1302 | 0 | if (ret < 0) { |
1303 | | /* It might be okay to ignore write errors for guest |
1304 | | * requests. If this is a deliberate copy-on-read |
1305 | | * then we don't want to ignore the error. Simply |
1306 | | * report it in all cases. |
1307 | | */ |
1308 | 0 | goto err; |
1309 | 0 | } |
1310 | | |
1311 | 0 | if (!(flags & BDRV_REQ_PREFETCH)) { |
1312 | 0 | qemu_iovec_from_buf(qiov, qiov_offset + progress, |
1313 | 0 | bounce_buffer + skip_bytes, |
1314 | 0 | MIN(pnum - skip_bytes, bytes - progress)); |
1315 | 0 | } |
1316 | 0 | } else if (!(flags & BDRV_REQ_PREFETCH)) { |
1317 | | /* Read directly into the destination */ |
1318 | 0 | ret = bdrv_driver_preadv(bs, offset + progress, |
1319 | 0 | MIN(pnum - skip_bytes, bytes - progress), |
1320 | 0 | qiov, qiov_offset + progress, 0); |
1321 | 0 | if (ret < 0) { |
1322 | 0 | goto err; |
1323 | 0 | } |
1324 | 0 | } |
1325 | | |
1326 | 0 | align_offset += pnum; |
1327 | 0 | align_bytes -= pnum; |
1328 | 0 | progress += pnum - skip_bytes; |
1329 | 0 | skip_bytes = 0; |
1330 | 0 | } |
1331 | 0 | ret = 0; |
1332 | |
|
1333 | 0 | err: |
1334 | 0 | qemu_vfree(bounce_buffer); |
1335 | 0 | return ret; |
1336 | 0 | } |
1337 | | |
1338 | | /* |
1339 | | * Forwards an already correctly aligned request to the BlockDriver. This |
1340 | | * handles copy on read, zeroing after EOF, and fragmentation of large |
1341 | | * reads; any other features must be implemented by the caller. |
1342 | | */ |
1343 | | static int coroutine_fn GRAPH_RDLOCK |
1344 | | bdrv_aligned_preadv(BdrvChild *child, BdrvTrackedRequest *req, |
1345 | | int64_t offset, int64_t bytes, int64_t align, |
1346 | | QEMUIOVector *qiov, size_t qiov_offset, int flags) |
1347 | 38.6M | { |
1348 | 38.6M | BlockDriverState *bs = child->bs; |
1349 | 38.6M | int64_t total_bytes, max_bytes; |
1350 | 38.6M | int ret = 0; |
1351 | 38.6M | int64_t bytes_remaining = bytes; |
1352 | 38.6M | int max_transfer; |
1353 | | |
1354 | 38.6M | bdrv_check_qiov_request(offset, bytes, qiov, qiov_offset, &error_abort); |
1355 | 38.6M | assert(is_power_of_2(align)); |
1356 | 38.6M | assert((offset & (align - 1)) == 0); |
1357 | 38.6M | assert((bytes & (align - 1)) == 0); |
1358 | 38.6M | assert((bs->open_flags & BDRV_O_NO_IO) == 0); |
1359 | 38.6M | max_transfer = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_transfer, INT_MAX), |
1360 | 38.6M | align); |
1361 | | |
1362 | | /* |
1363 | | * TODO: We would need a per-BDS .supported_read_flags and |
1364 | | * potential fallback support, if we ever implement any read flags |
1365 | | * to pass through to drivers. For now, there aren't any |
1366 | | * passthrough flags except the BDRV_REQ_REGISTERED_BUF optimization hint. |
1367 | | */ |
1368 | 38.6M | assert(!(flags & ~(BDRV_REQ_COPY_ON_READ | BDRV_REQ_PREFETCH | |
1369 | 38.6M | BDRV_REQ_REGISTERED_BUF))); |
1370 | | |
1371 | | /* Handle Copy on Read and associated serialisation */ |
1372 | 38.6M | if (flags & BDRV_REQ_COPY_ON_READ) { |
1373 | | /* If we touch the same cluster it counts as an overlap. This |
1374 | | * guarantees that allocating writes will be serialized and not race |
1375 | | * with each other for the same cluster. For example, in copy-on-read |
1376 | | * it ensures that the CoR read and write operations are atomic and |
1377 | | * guest writes cannot interleave between them. */ |
1378 | 0 | bdrv_make_request_serialising(req, bdrv_get_cluster_size(bs)); |
1379 | 0 | } |
1380 | | |
1381 | 38.6M | if (flags & BDRV_REQ_COPY_ON_READ) { |
1382 | 0 | int64_t pnum; |
1383 | | |
1384 | | /* The flag BDRV_REQ_COPY_ON_READ has reached its addressee */ |
1385 | 0 | flags &= ~BDRV_REQ_COPY_ON_READ; |
1386 | |
|
1387 | 0 | ret = bdrv_co_is_allocated(bs, offset, bytes, &pnum); |
1388 | 0 | if (ret < 0) { |
1389 | 0 | goto out; |
1390 | 0 | } |
1391 | | |
1392 | 0 | if (!ret || pnum != bytes) { |
1393 | 0 | ret = bdrv_co_do_copy_on_readv(child, offset, bytes, |
1394 | 0 | qiov, qiov_offset, flags); |
1395 | 0 | goto out; |
1396 | 0 | } else if (flags & BDRV_REQ_PREFETCH) { |
1397 | 0 | goto out; |
1398 | 0 | } |
1399 | 0 | } |
1400 | | |
1401 | | /* Forward the request to the BlockDriver, possibly fragmenting it */ |
1402 | 38.6M | total_bytes = bdrv_co_getlength(bs); |
1403 | 38.6M | if (total_bytes < 0) { |
1404 | 0 | ret = total_bytes; |
1405 | 0 | goto out; |
1406 | 0 | } |
1407 | | |
1408 | 38.6M | assert(!(flags & ~(bs->supported_read_flags | BDRV_REQ_REGISTERED_BUF))); |
1409 | | |
1410 | 38.6M | max_bytes = ROUND_UP(MAX(0, total_bytes - offset), align); |
1411 | 38.6M | if (bytes <= max_bytes && bytes <= max_transfer) { |
1412 | 38.6M | ret = bdrv_driver_preadv(bs, offset, bytes, qiov, qiov_offset, flags); |
1413 | 38.6M | goto out; |
1414 | 38.6M | } |
1415 | | |
1416 | 0 | while (bytes_remaining) { |
1417 | 0 | int64_t num; |
1418 | |
|
1419 | 0 | if (max_bytes) { |
1420 | 0 | num = MIN(bytes_remaining, MIN(max_bytes, max_transfer)); |
1421 | 0 | assert(num); |
1422 | |
|
1423 | 0 | ret = bdrv_driver_preadv(bs, offset + bytes - bytes_remaining, |
1424 | 0 | num, qiov, |
1425 | 0 | qiov_offset + bytes - bytes_remaining, |
1426 | 0 | flags); |
1427 | 0 | max_bytes -= num; |
1428 | 0 | } else { |
1429 | 0 | num = bytes_remaining; |
1430 | 0 | ret = qemu_iovec_memset(qiov, qiov_offset + bytes - bytes_remaining, |
1431 | 0 | 0, bytes_remaining); |
1432 | 0 | } |
1433 | 0 | if (ret < 0) { |
1434 | 0 | goto out; |
1435 | 0 | } |
1436 | 0 | bytes_remaining -= num; |
1437 | 0 | } |
1438 | | |
1439 | 38.6M | out: |
1440 | 38.6M | return ret < 0 ? ret : 0; |
1441 | 0 | } |
1442 | | |
1443 | | /* |
1444 | | * Request padding |
1445 | | * |
1446 | | * |<---- align ----->| |<----- align ---->| |
1447 | | * |<- head ->|<------------- bytes ------------->|<-- tail -->| |
1448 | | * | | | | | | |
1449 | | * -*----------$-------*-------- ... --------*-----$------------*--- |
1450 | | * | | | | | | |
1451 | | * | offset | | end | |
1452 | | * ALIGN_DOWN(offset) ALIGN_UP(offset) ALIGN_DOWN(end) ALIGN_UP(end) |
1453 | | * [buf ... ) [tail_buf ) |
1454 | | * |
1455 | | * @buf is an aligned allocation needed to store @head and @tail paddings. @head |
1456 | | * is placed at the beginning of @buf and @tail at the @end. |
1457 | | * |
1458 | | * @tail_buf is a pointer to sub-buffer, corresponding to align-sized chunk |
1459 | | * around tail, if tail exists. |
1460 | | * |
1461 | | * @merge_reads is true for small requests, |
1462 | | * if @buf_len == @head + bytes + @tail. In this case it is possible that both |
1463 | | * head and tail exist but @buf_len == align and @tail_buf == @buf. |
1464 | | * |
1465 | | * @write is true for write requests, false for read requests. |
1466 | | * |
1467 | | * If padding makes the vector too long (exceeding IOV_MAX), then we need to |
1468 | | * merge existing vector elements into a single one. @collapse_bounce_buf acts |
1469 | | * as the bounce buffer in such cases. @pre_collapse_qiov has the pre-collapse |
1470 | | * I/O vector elements so for read requests, the data can be copied back after |
1471 | | * the read is done. |
1472 | | */ |
1473 | | typedef struct BdrvRequestPadding { |
1474 | | uint8_t *buf; |
1475 | | size_t buf_len; |
1476 | | uint8_t *tail_buf; |
1477 | | size_t head; |
1478 | | size_t tail; |
1479 | | bool merge_reads; |
1480 | | bool write; |
1481 | | QEMUIOVector local_qiov; |
1482 | | |
1483 | | uint8_t *collapse_bounce_buf; |
1484 | | size_t collapse_len; |
1485 | | QEMUIOVector pre_collapse_qiov; |
1486 | | } BdrvRequestPadding; |
1487 | | |
1488 | | static bool bdrv_init_padding(BlockDriverState *bs, |
1489 | | int64_t offset, int64_t bytes, |
1490 | | bool write, |
1491 | | BdrvRequestPadding *pad) |
1492 | 40.2M | { |
1493 | 40.2M | int64_t align = bs->bl.request_alignment; |
1494 | 40.2M | int64_t sum; |
1495 | | |
1496 | 40.2M | bdrv_check_request(offset, bytes, &error_abort); |
1497 | 40.2M | assert(align <= INT_MAX); /* documented in block/block_int.h */ |
1498 | 40.2M | assert(align <= SIZE_MAX / 2); /* so we can allocate the buffer */ |
1499 | | |
1500 | 40.2M | memset(pad, 0, sizeof(*pad)); |
1501 | | |
1502 | 40.2M | pad->head = offset & (align - 1); |
1503 | 40.2M | pad->tail = ((offset + bytes) & (align - 1)); |
1504 | 40.2M | if (pad->tail) { |
1505 | 0 | pad->tail = align - pad->tail; |
1506 | 0 | } |
1507 | | |
1508 | 40.2M | if (!pad->head && !pad->tail) { |
1509 | 40.2M | return false; |
1510 | 40.2M | } |
1511 | | |
1512 | 40.2M | assert(bytes); /* Nothing good in aligning zero-length requests */ |
1513 | |
|
1514 | 0 | sum = pad->head + bytes + pad->tail; |
1515 | 0 | pad->buf_len = (sum > align && pad->head && pad->tail) ? 2 * align : align; |
1516 | 0 | pad->buf = qemu_blockalign(bs, pad->buf_len); |
1517 | 0 | pad->merge_reads = sum == pad->buf_len; |
1518 | 0 | if (pad->tail) { |
1519 | 0 | pad->tail_buf = pad->buf + pad->buf_len - align; |
1520 | 0 | } |
1521 | |
|
1522 | 0 | pad->write = write; |
1523 | |
|
1524 | 0 | return true; |
1525 | 0 | } |
1526 | | |
1527 | | static int coroutine_fn GRAPH_RDLOCK |
1528 | | bdrv_padding_rmw_read(BdrvChild *child, BdrvTrackedRequest *req, |
1529 | | BdrvRequestPadding *pad, bool zero_middle) |
1530 | 0 | { |
1531 | 0 | QEMUIOVector local_qiov; |
1532 | 0 | BlockDriverState *bs = child->bs; |
1533 | 0 | uint64_t align = bs->bl.request_alignment; |
1534 | 0 | int ret; |
1535 | |
|
1536 | 0 | assert(req->serialising && pad->buf); |
1537 | |
|
1538 | 0 | if (pad->head || pad->merge_reads) { |
1539 | 0 | int64_t bytes = pad->merge_reads ? pad->buf_len : align; |
1540 | |
|
1541 | 0 | qemu_iovec_init_buf(&local_qiov, pad->buf, bytes); |
1542 | |
|
1543 | 0 | if (pad->head) { |
1544 | 0 | bdrv_co_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD); |
1545 | 0 | } |
1546 | 0 | if (pad->merge_reads && pad->tail) { |
1547 | 0 | bdrv_co_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL); |
1548 | 0 | } |
1549 | 0 | ret = bdrv_aligned_preadv(child, req, req->overlap_offset, bytes, |
1550 | 0 | align, &local_qiov, 0, 0); |
1551 | 0 | if (ret < 0) { |
1552 | 0 | return ret; |
1553 | 0 | } |
1554 | 0 | if (pad->head) { |
1555 | 0 | bdrv_co_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_HEAD); |
1556 | 0 | } |
1557 | 0 | if (pad->merge_reads && pad->tail) { |
1558 | 0 | bdrv_co_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_TAIL); |
1559 | 0 | } |
1560 | |
|
1561 | 0 | if (pad->merge_reads) { |
1562 | 0 | goto zero_mem; |
1563 | 0 | } |
1564 | 0 | } |
1565 | | |
1566 | 0 | if (pad->tail) { |
1567 | 0 | qemu_iovec_init_buf(&local_qiov, pad->tail_buf, align); |
1568 | |
|
1569 | 0 | bdrv_co_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL); |
1570 | 0 | ret = bdrv_aligned_preadv( |
1571 | 0 | child, req, |
1572 | 0 | req->overlap_offset + req->overlap_bytes - align, |
1573 | 0 | align, align, &local_qiov, 0, 0); |
1574 | 0 | if (ret < 0) { |
1575 | 0 | return ret; |
1576 | 0 | } |
1577 | 0 | bdrv_co_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_TAIL); |
1578 | 0 | } |
1579 | | |
1580 | 0 | zero_mem: |
1581 | 0 | if (zero_middle) { |
1582 | 0 | memset(pad->buf + pad->head, 0, pad->buf_len - pad->head - pad->tail); |
1583 | 0 | } |
1584 | |
|
1585 | 0 | return 0; |
1586 | 0 | } |
1587 | | |
1588 | | /** |
1589 | | * Free *pad's associated buffers, and perform any necessary finalization steps. |
1590 | | */ |
1591 | | static void bdrv_padding_finalize(BdrvRequestPadding *pad) |
1592 | 40.2M | { |
1593 | 40.2M | if (pad->collapse_bounce_buf) { |
1594 | 0 | if (!pad->write) { |
1595 | | /* |
1596 | | * If padding required elements in the vector to be collapsed into a |
1597 | | * bounce buffer, copy the bounce buffer content back |
1598 | | */ |
1599 | 0 | qemu_iovec_from_buf(&pad->pre_collapse_qiov, 0, |
1600 | 0 | pad->collapse_bounce_buf, pad->collapse_len); |
1601 | 0 | } |
1602 | 0 | qemu_vfree(pad->collapse_bounce_buf); |
1603 | 0 | qemu_iovec_destroy(&pad->pre_collapse_qiov); |
1604 | 0 | } |
1605 | 40.2M | if (pad->buf) { |
1606 | 0 | qemu_vfree(pad->buf); |
1607 | 0 | qemu_iovec_destroy(&pad->local_qiov); |
1608 | 0 | } |
1609 | 40.2M | memset(pad, 0, sizeof(*pad)); |
1610 | 40.2M | } |
1611 | | |
1612 | | /* |
1613 | | * Create pad->local_qiov by wrapping @iov in the padding head and tail, while |
1614 | | * ensuring that the resulting vector will not exceed IOV_MAX elements. |
1615 | | * |
1616 | | * To ensure this, when necessary, the first two or three elements of @iov are |
1617 | | * merged into pad->collapse_bounce_buf and replaced by a reference to that |
1618 | | * bounce buffer in pad->local_qiov. |
1619 | | * |
1620 | | * After performing a read request, the data from the bounce buffer must be |
1621 | | * copied back into pad->pre_collapse_qiov (e.g. by bdrv_padding_finalize()). |
1622 | | */ |
1623 | | static int bdrv_create_padded_qiov(BlockDriverState *bs, |
1624 | | BdrvRequestPadding *pad, |
1625 | | struct iovec *iov, int niov, |
1626 | | size_t iov_offset, size_t bytes) |
1627 | 0 | { |
1628 | 0 | int padded_niov, surplus_count, collapse_count; |
1629 | | |
1630 | | /* Assert this invariant */ |
1631 | 0 | assert(niov <= IOV_MAX); |
1632 | | |
1633 | | /* |
1634 | | * Cannot pad if resulting length would exceed SIZE_MAX. Returning an error |
1635 | | * to the guest is not ideal, but there is little else we can do. At least |
1636 | | * this will practically never happen on 64-bit systems. |
1637 | | */ |
1638 | 0 | if (SIZE_MAX - pad->head < bytes || |
1639 | 0 | SIZE_MAX - pad->head - bytes < pad->tail) |
1640 | 0 | { |
1641 | 0 | return -EINVAL; |
1642 | 0 | } |
1643 | | |
1644 | | /* Length of the resulting IOV if we just concatenated everything */ |
1645 | 0 | padded_niov = !!pad->head + niov + !!pad->tail; |
1646 | |
|
1647 | 0 | qemu_iovec_init(&pad->local_qiov, MIN(padded_niov, IOV_MAX)); |
1648 | |
|
1649 | 0 | if (pad->head) { |
1650 | 0 | qemu_iovec_add(&pad->local_qiov, pad->buf, pad->head); |
1651 | 0 | } |
1652 | | |
1653 | | /* |
1654 | | * If padded_niov > IOV_MAX, we cannot just concatenate everything. |
1655 | | * Instead, merge the first two or three elements of @iov to reduce the |
1656 | | * number of vector elements as necessary. |
1657 | | */ |
1658 | 0 | if (padded_niov > IOV_MAX) { |
1659 | | /* |
1660 | | * Only head and tail can have lead to the number of entries exceeding |
1661 | | * IOV_MAX, so we can exceed it by the head and tail at most. We need |
1662 | | * to reduce the number of elements by `surplus_count`, so we merge that |
1663 | | * many elements plus one into one element. |
1664 | | */ |
1665 | 0 | surplus_count = padded_niov - IOV_MAX; |
1666 | 0 | assert(surplus_count <= !!pad->head + !!pad->tail); |
1667 | 0 | collapse_count = surplus_count + 1; |
1668 | | |
1669 | | /* |
1670 | | * Move the elements to collapse into `pad->pre_collapse_qiov`, then |
1671 | | * advance `iov` (and associated variables) by those elements. |
1672 | | */ |
1673 | 0 | qemu_iovec_init(&pad->pre_collapse_qiov, collapse_count); |
1674 | 0 | qemu_iovec_concat_iov(&pad->pre_collapse_qiov, iov, |
1675 | 0 | collapse_count, iov_offset, SIZE_MAX); |
1676 | 0 | iov += collapse_count; |
1677 | 0 | iov_offset = 0; |
1678 | 0 | niov -= collapse_count; |
1679 | 0 | bytes -= pad->pre_collapse_qiov.size; |
1680 | | |
1681 | | /* |
1682 | | * Construct the bounce buffer to match the length of the to-collapse |
1683 | | * vector elements, and for write requests, initialize it with the data |
1684 | | * from those elements. Then add it to `pad->local_qiov`. |
1685 | | */ |
1686 | 0 | pad->collapse_len = pad->pre_collapse_qiov.size; |
1687 | 0 | pad->collapse_bounce_buf = qemu_blockalign(bs, pad->collapse_len); |
1688 | 0 | if (pad->write) { |
1689 | 0 | qemu_iovec_to_buf(&pad->pre_collapse_qiov, 0, |
1690 | 0 | pad->collapse_bounce_buf, pad->collapse_len); |
1691 | 0 | } |
1692 | 0 | qemu_iovec_add(&pad->local_qiov, |
1693 | 0 | pad->collapse_bounce_buf, pad->collapse_len); |
1694 | 0 | } |
1695 | |
|
1696 | 0 | qemu_iovec_concat_iov(&pad->local_qiov, iov, niov, iov_offset, bytes); |
1697 | |
|
1698 | 0 | if (pad->tail) { |
1699 | 0 | qemu_iovec_add(&pad->local_qiov, |
1700 | 0 | pad->buf + pad->buf_len - pad->tail, pad->tail); |
1701 | 0 | } |
1702 | |
|
1703 | 0 | assert(pad->local_qiov.niov == MIN(padded_niov, IOV_MAX)); |
1704 | 0 | return 0; |
1705 | 0 | } |
1706 | | |
1707 | | /* |
1708 | | * bdrv_pad_request |
1709 | | * |
1710 | | * Exchange request parameters with padded request if needed. Don't include RMW |
1711 | | * read of padding, bdrv_padding_rmw_read() should be called separately if |
1712 | | * needed. |
1713 | | * |
1714 | | * @write is true for write requests, false for read requests. |
1715 | | * |
1716 | | * Request parameters (@qiov, &qiov_offset, &offset, &bytes) are in-out: |
1717 | | * - on function start they represent original request |
1718 | | * - on failure or when padding is not needed they are unchanged |
1719 | | * - on success when padding is needed they represent padded request |
1720 | | */ |
1721 | | static int bdrv_pad_request(BlockDriverState *bs, |
1722 | | QEMUIOVector **qiov, size_t *qiov_offset, |
1723 | | int64_t *offset, int64_t *bytes, |
1724 | | bool write, |
1725 | | BdrvRequestPadding *pad, bool *padded, |
1726 | | BdrvRequestFlags *flags) |
1727 | 40.2M | { |
1728 | 40.2M | int ret; |
1729 | 40.2M | struct iovec *sliced_iov; |
1730 | 40.2M | int sliced_niov; |
1731 | 40.2M | size_t sliced_head, sliced_tail; |
1732 | | |
1733 | | /* Should have been checked by the caller already */ |
1734 | 40.2M | ret = bdrv_check_request32(*offset, *bytes, *qiov, *qiov_offset); |
1735 | 40.2M | if (ret < 0) { |
1736 | 0 | return ret; |
1737 | 0 | } |
1738 | | |
1739 | 40.2M | if (!bdrv_init_padding(bs, *offset, *bytes, write, pad)) { |
1740 | 40.2M | if (padded) { |
1741 | 1.61M | *padded = false; |
1742 | 1.61M | } |
1743 | 40.2M | return 0; |
1744 | 40.2M | } |
1745 | | |
1746 | | /* |
1747 | | * For prefetching in stream_populate(), no qiov is passed along, because |
1748 | | * only copy-on-read matters. |
1749 | | */ |
1750 | 0 | if (*qiov) { |
1751 | 0 | sliced_iov = qemu_iovec_slice(*qiov, *qiov_offset, *bytes, |
1752 | 0 | &sliced_head, &sliced_tail, |
1753 | 0 | &sliced_niov); |
1754 | | |
1755 | | /* Guaranteed by bdrv_check_request32() */ |
1756 | 0 | assert(*bytes <= SIZE_MAX); |
1757 | 0 | ret = bdrv_create_padded_qiov(bs, pad, sliced_iov, sliced_niov, |
1758 | 0 | sliced_head, *bytes); |
1759 | 0 | if (ret < 0) { |
1760 | 0 | bdrv_padding_finalize(pad); |
1761 | 0 | return ret; |
1762 | 0 | } |
1763 | 0 | *qiov = &pad->local_qiov; |
1764 | 0 | *qiov_offset = 0; |
1765 | 0 | } |
1766 | | |
1767 | 0 | *bytes += pad->head + pad->tail; |
1768 | 0 | *offset -= pad->head; |
1769 | 0 | if (padded) { |
1770 | 0 | *padded = true; |
1771 | 0 | } |
1772 | 0 | if (flags) { |
1773 | | /* Can't use optimization hint with bounce buffer */ |
1774 | 0 | *flags &= ~BDRV_REQ_REGISTERED_BUF; |
1775 | 0 | } |
1776 | |
|
1777 | 0 | return 0; |
1778 | 0 | } |
1779 | | |
1780 | | int coroutine_fn bdrv_co_preadv(BdrvChild *child, |
1781 | | int64_t offset, int64_t bytes, QEMUIOVector *qiov, |
1782 | | BdrvRequestFlags flags) |
1783 | 19.3M | { |
1784 | 19.3M | IO_CODE(); |
1785 | 19.3M | return bdrv_co_preadv_part(child, offset, bytes, qiov, 0, flags); |
1786 | 19.3M | } |
1787 | | |
1788 | | int coroutine_fn bdrv_co_preadv_part(BdrvChild *child, |
1789 | | int64_t offset, int64_t bytes, |
1790 | | QEMUIOVector *qiov, size_t qiov_offset, |
1791 | | BdrvRequestFlags flags) |
1792 | 38.6M | { |
1793 | 38.6M | BlockDriverState *bs = child->bs; |
1794 | 38.6M | BdrvTrackedRequest req; |
1795 | 38.6M | BdrvRequestPadding pad; |
1796 | 38.6M | int ret; |
1797 | 38.6M | IO_CODE(); |
1798 | | |
1799 | 38.6M | trace_bdrv_co_preadv_part(bs, offset, bytes, flags); |
1800 | | |
1801 | 38.6M | if (!bdrv_co_is_inserted(bs)) { |
1802 | 0 | return -ENOMEDIUM; |
1803 | 0 | } |
1804 | | |
1805 | 38.6M | ret = bdrv_check_request32(offset, bytes, qiov, qiov_offset); |
1806 | 38.6M | if (ret < 0) { |
1807 | 0 | return ret; |
1808 | 0 | } |
1809 | | |
1810 | 38.6M | if (bytes == 0 && !QEMU_IS_ALIGNED(offset, bs->bl.request_alignment)) { |
1811 | | /* |
1812 | | * Aligning zero request is nonsense. Even if driver has special meaning |
1813 | | * of zero-length (like qcow2_co_pwritev_compressed_part), we can't pass |
1814 | | * it to driver due to request_alignment. |
1815 | | * |
1816 | | * Still, no reason to return an error if someone do unaligned |
1817 | | * zero-length read occasionally. |
1818 | | */ |
1819 | 0 | return 0; |
1820 | 0 | } |
1821 | | |
1822 | 38.6M | bdrv_inc_in_flight(bs); |
1823 | | |
1824 | | /* Don't do copy-on-read if we read data before write operation */ |
1825 | 38.6M | if (qatomic_read(&bs->copy_on_read)) { |
1826 | 0 | flags |= BDRV_REQ_COPY_ON_READ; |
1827 | 0 | } |
1828 | | |
1829 | 38.6M | ret = bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, false, |
1830 | 38.6M | &pad, NULL, &flags); |
1831 | 38.6M | if (ret < 0) { |
1832 | 0 | goto fail; |
1833 | 0 | } |
1834 | | |
1835 | 38.6M | tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_READ); |
1836 | 38.6M | ret = bdrv_aligned_preadv(child, &req, offset, bytes, |
1837 | 38.6M | bs->bl.request_alignment, |
1838 | 38.6M | qiov, qiov_offset, flags); |
1839 | 38.6M | tracked_request_end(&req); |
1840 | 38.6M | bdrv_padding_finalize(&pad); |
1841 | | |
1842 | 38.6M | fail: |
1843 | 38.6M | bdrv_dec_in_flight(bs); |
1844 | | |
1845 | 38.6M | return ret; |
1846 | 38.6M | } |
1847 | | |
1848 | | static int coroutine_fn GRAPH_RDLOCK |
1849 | | bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int64_t bytes, |
1850 | | BdrvRequestFlags flags) |
1851 | 932 | { |
1852 | 932 | BlockDriver *drv = bs->drv; |
1853 | 932 | QEMUIOVector qiov; |
1854 | 932 | void *buf = NULL; |
1855 | 932 | int ret = 0; |
1856 | 932 | bool need_flush = false; |
1857 | 932 | int head = 0; |
1858 | 932 | int tail = 0; |
1859 | | |
1860 | 932 | int64_t max_write_zeroes = MIN_NON_ZERO(bs->bl.max_pwrite_zeroes, |
1861 | 932 | INT64_MAX); |
1862 | 932 | int alignment = MAX(bs->bl.pwrite_zeroes_alignment, |
1863 | 932 | bs->bl.request_alignment); |
1864 | 932 | int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer, MAX_BOUNCE_BUFFER); |
1865 | | |
1866 | 932 | assert_bdrv_graph_readable(); |
1867 | 932 | bdrv_check_request(offset, bytes, &error_abort); |
1868 | | |
1869 | 932 | if (!drv) { |
1870 | 0 | return -ENOMEDIUM; |
1871 | 0 | } |
1872 | | |
1873 | 932 | if ((flags & ~bs->supported_zero_flags) & BDRV_REQ_NO_FALLBACK) { |
1874 | 0 | return -ENOTSUP; |
1875 | 0 | } |
1876 | | |
1877 | | /* By definition there is no user buffer so this flag doesn't make sense */ |
1878 | 932 | if (flags & BDRV_REQ_REGISTERED_BUF) { |
1879 | 0 | return -EINVAL; |
1880 | 0 | } |
1881 | | |
1882 | | /* If opened with discard=off we should never unmap. */ |
1883 | 932 | if (!(bs->open_flags & BDRV_O_UNMAP)) { |
1884 | 466 | flags &= ~BDRV_REQ_MAY_UNMAP; |
1885 | 466 | } |
1886 | | |
1887 | | /* Invalidate the cached block-status data range if this write overlaps */ |
1888 | 932 | bdrv_bsc_invalidate_range(bs, offset, bytes); |
1889 | | |
1890 | 932 | assert(alignment % bs->bl.request_alignment == 0); |
1891 | 932 | head = offset % alignment; |
1892 | 932 | tail = (offset + bytes) % alignment; |
1893 | 932 | max_write_zeroes = QEMU_ALIGN_DOWN(max_write_zeroes, alignment); |
1894 | 932 | assert(max_write_zeroes >= bs->bl.request_alignment); |
1895 | | |
1896 | 6.53k | while (bytes > 0 && !ret) { |
1897 | 5.59k | int64_t num = bytes; |
1898 | | |
1899 | | /* Align request. Block drivers can expect the "bulk" of the request |
1900 | | * to be aligned, and that unaligned requests do not cross cluster |
1901 | | * boundaries. |
1902 | | */ |
1903 | 5.59k | if (head) { |
1904 | | /* Make a small request up to the first aligned sector. For |
1905 | | * convenience, limit this request to max_transfer even if |
1906 | | * we don't need to fall back to writes. */ |
1907 | 0 | num = MIN(MIN(bytes, max_transfer), alignment - head); |
1908 | 0 | head = (head + num) % alignment; |
1909 | 0 | assert(num < max_write_zeroes); |
1910 | 5.59k | } else if (tail && num > alignment) { |
1911 | | /* Shorten the request to the last aligned sector. */ |
1912 | 0 | num -= tail; |
1913 | 0 | } |
1914 | | |
1915 | | /* limit request size */ |
1916 | 5.59k | if (num > max_write_zeroes) { |
1917 | 0 | num = max_write_zeroes; |
1918 | 0 | } |
1919 | | |
1920 | 5.59k | ret = -ENOTSUP; |
1921 | | /* First try the efficient write zeroes operation */ |
1922 | 5.59k | if (drv->bdrv_co_pwrite_zeroes) { |
1923 | 466 | ret = drv->bdrv_co_pwrite_zeroes(bs, offset, num, |
1924 | 466 | flags & bs->supported_zero_flags); |
1925 | 466 | if (ret != -ENOTSUP && (flags & BDRV_REQ_FUA) && |
1926 | 88 | !(bs->supported_zero_flags & BDRV_REQ_FUA)) { |
1927 | 88 | need_flush = true; |
1928 | 88 | } |
1929 | 5.13k | } else { |
1930 | 5.13k | assert(!bs->supported_zero_flags); |
1931 | 5.13k | } |
1932 | | |
1933 | | /* |
1934 | | * TODO The ret == -EINVAL && num < alignment case is a workaround for |
1935 | | * when request_alignment is 1 on files with cache=writeback. The Linux |
1936 | | * ioctl(BLKZEROOUT) requires block alignment and will fail with |
1937 | | * EINVAL. The block layer should align the request to |
1938 | | * write_zeroes_alignment instead of trying the syscall, failing, and |
1939 | | * falling back to a bounce buffer. Doing that is not easy so for now |
1940 | | * we use a bounce buffer: |
1941 | | * https://lore.kernel.org/qemu-devel/20260109120837.2772961-1-f.ebner@proxmox.com/ |
1942 | | */ |
1943 | 5.59k | if ((ret == -ENOTSUP || (ret == -EINVAL && num < alignment)) && |
1944 | 5.13k | !(flags & BDRV_REQ_NO_FALLBACK)) { |
1945 | | /* Fall back to bounce buffer if write zeroes is unsupported */ |
1946 | 5.13k | BdrvRequestFlags write_flags = flags & ~BDRV_REQ_ZERO_WRITE; |
1947 | | |
1948 | 5.13k | if ((flags & BDRV_REQ_FUA) && |
1949 | 0 | !(bs->supported_write_flags & BDRV_REQ_FUA)) { |
1950 | | /* No need for bdrv_driver_pwrite() to do a fallback |
1951 | | * flush on each chunk; use just one at the end */ |
1952 | 0 | write_flags &= ~BDRV_REQ_FUA; |
1953 | 0 | need_flush = true; |
1954 | 0 | } |
1955 | 5.13k | num = MIN(num, max_transfer); |
1956 | 5.13k | if (buf == NULL) { |
1957 | 466 | buf = qemu_try_blockalign0(bs, num); |
1958 | 466 | if (buf == NULL) { |
1959 | 0 | ret = -ENOMEM; |
1960 | 0 | goto fail; |
1961 | 0 | } |
1962 | 466 | } |
1963 | 5.13k | qemu_iovec_init_buf(&qiov, buf, num); |
1964 | | |
1965 | 5.13k | ret = bdrv_driver_pwritev(bs, offset, num, &qiov, 0, write_flags); |
1966 | | |
1967 | | /* Keep bounce buffer around if it is big enough for all |
1968 | | * all future requests. |
1969 | | */ |
1970 | 5.13k | if (num < max_transfer) { |
1971 | 211 | qemu_vfree(buf); |
1972 | 211 | buf = NULL; |
1973 | 211 | } |
1974 | 5.13k | } |
1975 | | |
1976 | 5.59k | offset += num; |
1977 | 5.59k | bytes -= num; |
1978 | 5.59k | } |
1979 | | |
1980 | 932 | fail: |
1981 | 932 | if (ret == 0 && need_flush) { |
1982 | 88 | ret = bdrv_co_flush(bs); |
1983 | 88 | } |
1984 | 932 | qemu_vfree(buf); |
1985 | 932 | return ret; |
1986 | 932 | } |
1987 | | |
1988 | | static inline int coroutine_fn GRAPH_RDLOCK |
1989 | | bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, int64_t bytes, |
1990 | | BdrvTrackedRequest *req, int flags) |
1991 | 1.61M | { |
1992 | 1.61M | BlockDriverState *bs = child->bs; |
1993 | | |
1994 | 1.61M | bdrv_check_request(offset, bytes, &error_abort); |
1995 | | |
1996 | 1.61M | if (bdrv_is_read_only(bs)) { |
1997 | 0 | return -EPERM; |
1998 | 0 | } |
1999 | | |
2000 | 1.61M | assert(!(bs->open_flags & BDRV_O_INACTIVE)); |
2001 | 1.61M | assert((bs->open_flags & BDRV_O_NO_IO) == 0); |
2002 | 1.61M | assert(!(flags & ~BDRV_REQ_MASK)); |
2003 | 1.61M | assert(!((flags & BDRV_REQ_NO_WAIT) && !(flags & BDRV_REQ_SERIALISING))); |
2004 | | |
2005 | 1.61M | if (flags & BDRV_REQ_SERIALISING) { |
2006 | 0 | QEMU_LOCK_GUARD(&bs->reqs_lock); |
2007 | |
|
2008 | 0 | tracked_request_set_serialising(req, bdrv_get_cluster_size(bs)); |
2009 | |
|
2010 | 0 | if ((flags & BDRV_REQ_NO_WAIT) && bdrv_find_conflicting_request(req)) { |
2011 | 0 | return -EBUSY; |
2012 | 0 | } |
2013 | | |
2014 | 0 | bdrv_wait_serialising_requests_locked(req); |
2015 | 0 | } |
2016 | | |
2017 | 1.61M | assert(req->overlap_offset <= offset); |
2018 | 1.61M | assert(offset + bytes <= req->overlap_offset + req->overlap_bytes); |
2019 | 1.61M | assert(offset + bytes <= bs->total_sectors * BDRV_SECTOR_SIZE || |
2020 | 1.61M | child->perm & BLK_PERM_RESIZE); |
2021 | | |
2022 | 1.61M | switch (req->type) { |
2023 | 1.61M | case BDRV_TRACKED_WRITE: |
2024 | 1.61M | case BDRV_TRACKED_DISCARD: |
2025 | 1.61M | if (flags & BDRV_REQ_WRITE_UNCHANGED) { |
2026 | 0 | assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE)); |
2027 | 1.61M | } else { |
2028 | 1.61M | assert(child->perm & BLK_PERM_WRITE); |
2029 | 1.61M | } |
2030 | 1.61M | bdrv_write_threshold_check_write(bs, offset, bytes); |
2031 | 1.61M | return 0; |
2032 | 0 | case BDRV_TRACKED_TRUNCATE: |
2033 | 0 | assert(child->perm & BLK_PERM_RESIZE); |
2034 | 0 | return 0; |
2035 | 0 | default: |
2036 | 0 | abort(); |
2037 | 1.61M | } |
2038 | 1.61M | } |
2039 | | |
2040 | | static inline void coroutine_fn GRAPH_RDLOCK |
2041 | | bdrv_co_write_req_finish(BdrvChild *child, int64_t offset, int64_t bytes, |
2042 | | BdrvTrackedRequest *req, int ret) |
2043 | 1.61M | { |
2044 | 1.61M | int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE); |
2045 | 1.61M | BlockDriverState *bs = child->bs; |
2046 | | |
2047 | 1.61M | bdrv_check_request(offset, bytes, &error_abort); |
2048 | | |
2049 | 1.61M | qatomic_inc(&bs->write_gen); |
2050 | | |
2051 | | /* |
2052 | | * Discard cannot extend the image, but in error handling cases, such as |
2053 | | * when reverting a qcow2 cluster allocation, the discarded range can pass |
2054 | | * the end of image file, so we cannot assert about BDRV_TRACKED_DISCARD |
2055 | | * here. Instead, just skip it, since semantically a discard request |
2056 | | * beyond EOF cannot expand the image anyway. |
2057 | | */ |
2058 | 1.61M | if (ret == 0 && |
2059 | 1.61M | (req->type == BDRV_TRACKED_TRUNCATE || |
2060 | 1.61M | end_sector > bs->total_sectors) && |
2061 | 0 | req->type != BDRV_TRACKED_DISCARD) { |
2062 | 0 | bs->total_sectors = end_sector; |
2063 | 0 | bdrv_co_parent_cb_resize(bs); |
2064 | 0 | bdrv_dirty_bitmap_truncate(bs, end_sector << BDRV_SECTOR_BITS); |
2065 | 0 | } |
2066 | 1.61M | if (req->bytes) { |
2067 | 1.61M | switch (req->type) { |
2068 | 1.61M | case BDRV_TRACKED_WRITE: |
2069 | 1.61M | { |
2070 | 1.61M | uint64_t new = offset + bytes; |
2071 | 1.61M | uint64_t old = qatomic_read(&bs->wr_highest_offset); |
2072 | | |
2073 | 1.61M | while (old < new) { |
2074 | 1.65k | old = qatomic_cmpxchg(&bs->wr_highest_offset, old, new); |
2075 | 1.65k | } |
2076 | 1.61M | } |
2077 | | /* fall through, to set dirty bits */ |
2078 | 1.61M | case BDRV_TRACKED_DISCARD: |
2079 | 1.61M | bdrv_set_dirty(bs, offset, bytes); |
2080 | 1.61M | break; |
2081 | 0 | default: |
2082 | 0 | break; |
2083 | 1.61M | } |
2084 | 1.61M | } |
2085 | 1.61M | } |
2086 | | |
2087 | | /* |
2088 | | * Forwards an already correctly aligned write request to the BlockDriver, |
2089 | | * after possibly fragmenting it. |
2090 | | */ |
2091 | | static int coroutine_fn GRAPH_RDLOCK |
2092 | | bdrv_aligned_pwritev(BdrvChild *child, BdrvTrackedRequest *req, |
2093 | | int64_t offset, int64_t bytes, int64_t align, |
2094 | | QEMUIOVector *qiov, size_t qiov_offset, |
2095 | | BdrvRequestFlags flags) |
2096 | 1.61M | { |
2097 | 1.61M | BlockDriverState *bs = child->bs; |
2098 | 1.61M | BlockDriver *drv = bs->drv; |
2099 | 1.61M | int ret; |
2100 | | |
2101 | 1.61M | int64_t bytes_remaining = bytes; |
2102 | 1.61M | int max_transfer; |
2103 | | |
2104 | 1.61M | bdrv_check_qiov_request(offset, bytes, qiov, qiov_offset, &error_abort); |
2105 | | |
2106 | 1.61M | if (!drv) { |
2107 | 0 | return -ENOMEDIUM; |
2108 | 0 | } |
2109 | | |
2110 | 1.61M | if (bdrv_has_readonly_bitmaps(bs)) { |
2111 | 0 | return -EPERM; |
2112 | 0 | } |
2113 | | |
2114 | 1.61M | assert(is_power_of_2(align)); |
2115 | 1.61M | assert((offset & (align - 1)) == 0); |
2116 | 1.61M | assert((bytes & (align - 1)) == 0); |
2117 | 1.61M | max_transfer = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_transfer, INT_MAX), |
2118 | 1.61M | align); |
2119 | | |
2120 | 1.61M | ret = bdrv_co_write_req_prepare(child, offset, bytes, req, flags); |
2121 | | |
2122 | 1.61M | if (!ret && bs->detect_zeroes != BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF && |
2123 | 0 | !(flags & BDRV_REQ_ZERO_WRITE) && drv->bdrv_co_pwrite_zeroes && |
2124 | 0 | qemu_iovec_is_zero(qiov, qiov_offset, bytes)) { |
2125 | 0 | flags |= BDRV_REQ_ZERO_WRITE; |
2126 | 0 | if (bs->detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP) { |
2127 | 0 | flags |= BDRV_REQ_MAY_UNMAP; |
2128 | 0 | } |
2129 | | |
2130 | | /* Can't use optimization hint with bufferless zero write */ |
2131 | 0 | flags &= ~BDRV_REQ_REGISTERED_BUF; |
2132 | 0 | } |
2133 | | |
2134 | 1.61M | if (ret < 0) { |
2135 | | /* Do nothing, write notifier decided to fail this request */ |
2136 | 1.61M | } else if (flags & BDRV_REQ_ZERO_WRITE) { |
2137 | 932 | bdrv_co_debug_event(bs, BLKDBG_PWRITEV_ZERO); |
2138 | 932 | ret = bdrv_co_do_pwrite_zeroes(bs, offset, bytes, flags); |
2139 | 1.61M | } else if (flags & BDRV_REQ_WRITE_COMPRESSED) { |
2140 | 0 | ret = bdrv_driver_pwritev_compressed(bs, offset, bytes, |
2141 | 0 | qiov, qiov_offset); |
2142 | 1.61M | } else if (bytes <= max_transfer) { |
2143 | 1.61M | bdrv_co_debug_event(bs, BLKDBG_PWRITEV); |
2144 | 1.61M | ret = bdrv_driver_pwritev(bs, offset, bytes, qiov, qiov_offset, flags); |
2145 | 1.61M | } else { |
2146 | 0 | bdrv_co_debug_event(bs, BLKDBG_PWRITEV); |
2147 | 0 | while (bytes_remaining) { |
2148 | 0 | int num = MIN(bytes_remaining, max_transfer); |
2149 | 0 | int local_flags = flags; |
2150 | |
|
2151 | 0 | assert(num); |
2152 | 0 | if (num < bytes_remaining && (flags & BDRV_REQ_FUA) && |
2153 | 0 | !(bs->supported_write_flags & BDRV_REQ_FUA)) { |
2154 | | /* If FUA is going to be emulated by flush, we only |
2155 | | * need to flush on the last iteration */ |
2156 | 0 | local_flags &= ~BDRV_REQ_FUA; |
2157 | 0 | } |
2158 | |
|
2159 | 0 | ret = bdrv_driver_pwritev(bs, offset + bytes - bytes_remaining, |
2160 | 0 | num, qiov, |
2161 | 0 | qiov_offset + bytes - bytes_remaining, |
2162 | 0 | local_flags); |
2163 | 0 | if (ret < 0) { |
2164 | 0 | break; |
2165 | 0 | } |
2166 | 0 | bytes_remaining -= num; |
2167 | 0 | } |
2168 | 0 | } |
2169 | 1.61M | bdrv_co_debug_event(bs, BLKDBG_PWRITEV_DONE); |
2170 | | |
2171 | 1.61M | if (ret >= 0) { |
2172 | 1.61M | ret = 0; |
2173 | 1.61M | } |
2174 | 1.61M | bdrv_co_write_req_finish(child, offset, bytes, req, ret); |
2175 | | |
2176 | 1.61M | return ret; |
2177 | 1.61M | } |
2178 | | |
2179 | | static int coroutine_fn GRAPH_RDLOCK |
2180 | | bdrv_co_do_zero_pwritev(BdrvChild *child, int64_t offset, int64_t bytes, |
2181 | | BdrvRequestFlags flags, BdrvTrackedRequest *req) |
2182 | 932 | { |
2183 | 932 | BlockDriverState *bs = child->bs; |
2184 | 932 | QEMUIOVector local_qiov; |
2185 | 932 | uint64_t align = bs->bl.request_alignment; |
2186 | 932 | int ret = 0; |
2187 | 932 | bool padding; |
2188 | 932 | BdrvRequestPadding pad; |
2189 | | |
2190 | | /* This flag doesn't make sense for padding or zero writes */ |
2191 | 932 | flags &= ~BDRV_REQ_REGISTERED_BUF; |
2192 | | |
2193 | 932 | padding = bdrv_init_padding(bs, offset, bytes, true, &pad); |
2194 | 932 | if (padding) { |
2195 | 0 | assert(!(flags & BDRV_REQ_NO_WAIT)); |
2196 | 0 | bdrv_make_request_serialising(req, align); |
2197 | |
|
2198 | 0 | bdrv_padding_rmw_read(child, req, &pad, true); |
2199 | |
|
2200 | 0 | if (pad.head || pad.merge_reads) { |
2201 | 0 | int64_t aligned_offset = offset & ~(align - 1); |
2202 | 0 | int64_t write_bytes = pad.merge_reads ? pad.buf_len : align; |
2203 | |
|
2204 | 0 | qemu_iovec_init_buf(&local_qiov, pad.buf, write_bytes); |
2205 | 0 | ret = bdrv_aligned_pwritev(child, req, aligned_offset, write_bytes, |
2206 | 0 | align, &local_qiov, 0, |
2207 | 0 | flags & ~BDRV_REQ_ZERO_WRITE); |
2208 | 0 | if (ret < 0 || pad.merge_reads) { |
2209 | | /* Error or all work is done */ |
2210 | 0 | goto out; |
2211 | 0 | } |
2212 | 0 | offset += write_bytes - pad.head; |
2213 | 0 | bytes -= write_bytes - pad.head; |
2214 | 0 | } |
2215 | 0 | } |
2216 | | |
2217 | 932 | assert(!bytes || (offset & (align - 1)) == 0); |
2218 | 932 | if (bytes >= align) { |
2219 | | /* Write the aligned part in the middle. */ |
2220 | 932 | int64_t aligned_bytes = bytes & ~(align - 1); |
2221 | 932 | ret = bdrv_aligned_pwritev(child, req, offset, aligned_bytes, align, |
2222 | 932 | NULL, 0, flags); |
2223 | 932 | if (ret < 0) { |
2224 | 0 | goto out; |
2225 | 0 | } |
2226 | 932 | bytes -= aligned_bytes; |
2227 | 932 | offset += aligned_bytes; |
2228 | 932 | } |
2229 | | |
2230 | 932 | assert(!bytes || (offset & (align - 1)) == 0); |
2231 | 932 | if (bytes) { |
2232 | 0 | assert(align == pad.tail + bytes); |
2233 | |
|
2234 | 0 | qemu_iovec_init_buf(&local_qiov, pad.tail_buf, align); |
2235 | 0 | ret = bdrv_aligned_pwritev(child, req, offset, align, align, |
2236 | 0 | &local_qiov, 0, |
2237 | 0 | flags & ~BDRV_REQ_ZERO_WRITE); |
2238 | 0 | } |
2239 | | |
2240 | 932 | out: |
2241 | 932 | bdrv_padding_finalize(&pad); |
2242 | | |
2243 | 932 | return ret; |
2244 | 932 | } |
2245 | | |
2246 | | /* |
2247 | | * Handle a write request in coroutine context |
2248 | | */ |
2249 | | int coroutine_fn bdrv_co_pwritev(BdrvChild *child, |
2250 | | int64_t offset, int64_t bytes, QEMUIOVector *qiov, |
2251 | | BdrvRequestFlags flags) |
2252 | 808k | { |
2253 | 808k | IO_CODE(); |
2254 | 808k | return bdrv_co_pwritev_part(child, offset, bytes, qiov, 0, flags); |
2255 | 808k | } |
2256 | | |
2257 | | int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child, |
2258 | | int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset, |
2259 | | BdrvRequestFlags flags) |
2260 | 1.61M | { |
2261 | 1.61M | BlockDriverState *bs = child->bs; |
2262 | 1.61M | BdrvTrackedRequest req; |
2263 | 1.61M | uint64_t align = bs->bl.request_alignment; |
2264 | 1.61M | BdrvRequestPadding pad; |
2265 | 1.61M | int ret; |
2266 | 1.61M | bool padded = false; |
2267 | 1.61M | IO_CODE(); |
2268 | | |
2269 | 1.61M | trace_bdrv_co_pwritev_part(child->bs, offset, bytes, flags); |
2270 | | |
2271 | 1.61M | if (!bdrv_co_is_inserted(bs)) { |
2272 | 0 | return -ENOMEDIUM; |
2273 | 0 | } |
2274 | | |
2275 | 1.61M | if (flags & BDRV_REQ_ZERO_WRITE) { |
2276 | 932 | ret = bdrv_check_qiov_request(offset, bytes, qiov, qiov_offset, NULL); |
2277 | 1.61M | } else { |
2278 | 1.61M | ret = bdrv_check_request32(offset, bytes, qiov, qiov_offset); |
2279 | 1.61M | } |
2280 | 1.61M | if (ret < 0) { |
2281 | 0 | return ret; |
2282 | 0 | } |
2283 | | |
2284 | | /* If the request is misaligned then we can't make it efficient */ |
2285 | 1.61M | if ((flags & BDRV_REQ_NO_FALLBACK) && |
2286 | 0 | !QEMU_IS_ALIGNED(offset | bytes, align)) |
2287 | 0 | { |
2288 | 0 | return -ENOTSUP; |
2289 | 0 | } |
2290 | | |
2291 | 1.61M | if (bytes == 0 && !QEMU_IS_ALIGNED(offset, bs->bl.request_alignment)) { |
2292 | | /* |
2293 | | * Aligning zero request is nonsense. Even if driver has special meaning |
2294 | | * of zero-length (like qcow2_co_pwritev_compressed_part), we can't pass |
2295 | | * it to driver due to request_alignment. |
2296 | | * |
2297 | | * Still, no reason to return an error if someone do unaligned |
2298 | | * zero-length write occasionally. |
2299 | | */ |
2300 | 0 | return 0; |
2301 | 0 | } |
2302 | | |
2303 | 1.61M | if (!(flags & BDRV_REQ_ZERO_WRITE)) { |
2304 | | /* |
2305 | | * Pad request for following read-modify-write cycle. |
2306 | | * bdrv_co_do_zero_pwritev() does aligning by itself, so, we do |
2307 | | * alignment only if there is no ZERO flag. |
2308 | | */ |
2309 | 1.61M | ret = bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, true, |
2310 | 1.61M | &pad, &padded, &flags); |
2311 | 1.61M | if (ret < 0) { |
2312 | 0 | return ret; |
2313 | 0 | } |
2314 | 1.61M | } |
2315 | | |
2316 | 1.61M | bdrv_inc_in_flight(bs); |
2317 | 1.61M | tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_WRITE); |
2318 | | |
2319 | 1.61M | if (flags & BDRV_REQ_ZERO_WRITE) { |
2320 | 932 | assert(!padded); |
2321 | 932 | ret = bdrv_co_do_zero_pwritev(child, offset, bytes, flags, &req); |
2322 | 932 | goto out; |
2323 | 932 | } |
2324 | | |
2325 | 1.61M | if (padded) { |
2326 | | /* |
2327 | | * Request was unaligned to request_alignment and therefore |
2328 | | * padded. We are going to do read-modify-write, and must |
2329 | | * serialize the request to prevent interactions of the |
2330 | | * widened region with other transactions. |
2331 | | */ |
2332 | 0 | assert(!(flags & BDRV_REQ_NO_WAIT)); |
2333 | 0 | bdrv_make_request_serialising(&req, align); |
2334 | 0 | bdrv_padding_rmw_read(child, &req, &pad, false); |
2335 | 0 | } |
2336 | | |
2337 | 1.61M | ret = bdrv_aligned_pwritev(child, &req, offset, bytes, align, |
2338 | 1.61M | qiov, qiov_offset, flags); |
2339 | | |
2340 | 1.61M | bdrv_padding_finalize(&pad); |
2341 | | |
2342 | 1.61M | out: |
2343 | 1.61M | tracked_request_end(&req); |
2344 | 1.61M | bdrv_dec_in_flight(bs); |
2345 | | |
2346 | 1.61M | return ret; |
2347 | 1.61M | } |
2348 | | |
2349 | | int coroutine_fn bdrv_co_pwrite_zeroes(BdrvChild *child, int64_t offset, |
2350 | | int64_t bytes, BdrvRequestFlags flags) |
2351 | 466 | { |
2352 | 466 | IO_CODE(); |
2353 | 466 | trace_bdrv_co_pwrite_zeroes(child->bs, offset, bytes, flags); |
2354 | 466 | assert_bdrv_graph_readable(); |
2355 | | |
2356 | 466 | return bdrv_co_pwritev(child, offset, bytes, NULL, |
2357 | 466 | BDRV_REQ_ZERO_WRITE | flags); |
2358 | 466 | } |
2359 | | |
2360 | | /* |
2361 | | * Flush ALL BDSes regardless of if they are reachable via a BlkBackend or not. |
2362 | | */ |
2363 | | int bdrv_flush_all(void) |
2364 | 0 | { |
2365 | 0 | BdrvNextIterator it; |
2366 | 0 | BlockDriverState *bs = NULL; |
2367 | 0 | int result = 0; |
2368 | |
|
2369 | 0 | GLOBAL_STATE_CODE(); |
2370 | 0 | GRAPH_RDLOCK_GUARD_MAINLOOP(); |
2371 | | |
2372 | | /* |
2373 | | * bdrv queue is managed by record/replay, |
2374 | | * creating new flush request for stopping |
2375 | | * the VM may break the determinism |
2376 | | */ |
2377 | 0 | if (replay_events_enabled()) { |
2378 | 0 | return result; |
2379 | 0 | } |
2380 | | |
2381 | 0 | for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { |
2382 | 0 | int ret = bdrv_flush(bs); |
2383 | 0 | if (ret < 0 && !result) { |
2384 | 0 | result = ret; |
2385 | 0 | } |
2386 | 0 | } |
2387 | |
|
2388 | 0 | return result; |
2389 | 0 | } |
2390 | | |
2391 | | /* |
2392 | | * Returns the allocation status of the specified sectors. |
2393 | | * Drivers not implementing the functionality are assumed to not support |
2394 | | * backing files, hence all their sectors are reported as allocated. |
2395 | | * |
2396 | | * 'mode' serves as a hint as to which results are favored; see the |
2397 | | * BDRV_WANT_* macros for details. |
2398 | | * |
2399 | | * If 'offset' is beyond the end of the disk image the return value is |
2400 | | * BDRV_BLOCK_EOF and 'pnum' is set to 0. |
2401 | | * |
2402 | | * 'bytes' is the max value 'pnum' should be set to. If bytes goes |
2403 | | * beyond the end of the disk image it will be clamped; if 'pnum' is set to |
2404 | | * the end of the image, then the returned value will include BDRV_BLOCK_EOF. |
2405 | | * |
2406 | | * 'pnum' is set to the number of bytes (including and immediately |
2407 | | * following the specified offset) that are easily known to be in the |
2408 | | * same allocated/unallocated state. Note that a second call starting |
2409 | | * at the original offset plus returned pnum may have the same status. |
2410 | | * The returned value is non-zero on success except at end-of-file. |
2411 | | * |
2412 | | * Returns negative errno on failure. Otherwise, if the |
2413 | | * BDRV_BLOCK_OFFSET_VALID bit is set, 'map' and 'file' (if non-NULL) are |
2414 | | * set to the host mapping and BDS corresponding to the guest offset. |
2415 | | */ |
2416 | | static int coroutine_fn GRAPH_RDLOCK |
2417 | | bdrv_co_do_block_status(BlockDriverState *bs, unsigned int mode, |
2418 | | int64_t offset, int64_t bytes, |
2419 | | int64_t *pnum, int64_t *map, BlockDriverState **file) |
2420 | 0 | { |
2421 | 0 | int64_t total_size; |
2422 | 0 | int64_t n; /* bytes */ |
2423 | 0 | int ret; |
2424 | 0 | int64_t local_map = 0; |
2425 | 0 | BlockDriverState *local_file = NULL; |
2426 | 0 | int64_t aligned_offset, aligned_bytes; |
2427 | 0 | uint32_t align; |
2428 | 0 | bool has_filtered_child; |
2429 | |
|
2430 | 0 | assert(pnum); |
2431 | 0 | assert_bdrv_graph_readable(); |
2432 | 0 | *pnum = 0; |
2433 | 0 | total_size = bdrv_co_getlength(bs); |
2434 | 0 | if (total_size < 0) { |
2435 | 0 | ret = total_size; |
2436 | 0 | goto early_out; |
2437 | 0 | } |
2438 | | |
2439 | 0 | if (offset >= total_size) { |
2440 | 0 | ret = BDRV_BLOCK_EOF; |
2441 | 0 | goto early_out; |
2442 | 0 | } |
2443 | 0 | if (!bytes) { |
2444 | 0 | ret = 0; |
2445 | 0 | goto early_out; |
2446 | 0 | } |
2447 | | |
2448 | 0 | n = total_size - offset; |
2449 | 0 | if (n < bytes) { |
2450 | 0 | bytes = n; |
2451 | 0 | } |
2452 | | |
2453 | | /* Must be non-NULL or bdrv_co_getlength() would have failed */ |
2454 | 0 | assert(bs->drv); |
2455 | 0 | has_filtered_child = bdrv_filter_child(bs); |
2456 | 0 | if (!bs->drv->bdrv_co_block_status && !has_filtered_child) { |
2457 | 0 | *pnum = bytes; |
2458 | 0 | ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED; |
2459 | 0 | if (offset + bytes == total_size) { |
2460 | 0 | ret |= BDRV_BLOCK_EOF; |
2461 | 0 | } |
2462 | 0 | if (bs->drv->protocol_name) { |
2463 | 0 | ret |= BDRV_BLOCK_OFFSET_VALID; |
2464 | 0 | local_map = offset; |
2465 | 0 | local_file = bs; |
2466 | 0 | } |
2467 | 0 | goto early_out; |
2468 | 0 | } |
2469 | | |
2470 | 0 | bdrv_inc_in_flight(bs); |
2471 | | |
2472 | | /* Round out to request_alignment boundaries */ |
2473 | 0 | align = bs->bl.request_alignment; |
2474 | 0 | aligned_offset = QEMU_ALIGN_DOWN(offset, align); |
2475 | 0 | aligned_bytes = ROUND_UP(offset + bytes, align) - aligned_offset; |
2476 | |
|
2477 | 0 | if (bs->drv->bdrv_co_block_status) { |
2478 | | /* |
2479 | | * Use the block-status cache only for protocol nodes: Format |
2480 | | * drivers are generally quick to inquire the status, but protocol |
2481 | | * drivers often need to get information from outside of qemu, so |
2482 | | * we do not have control over the actual implementation. There |
2483 | | * have been cases where inquiring the status took an unreasonably |
2484 | | * long time, and we can do nothing in qemu to fix it. |
2485 | | * This is especially problematic for images with large data areas, |
2486 | | * because finding the few holes in them and giving them special |
2487 | | * treatment does not gain much performance. Therefore, we try to |
2488 | | * cache the last-identified data region. |
2489 | | * |
2490 | | * Second, limiting ourselves to protocol nodes allows us to assume |
2491 | | * the block status for data regions to be DATA | OFFSET_VALID, and |
2492 | | * that the host offset is the same as the guest offset. |
2493 | | * |
2494 | | * Note that it is possible that external writers zero parts of |
2495 | | * the cached regions without the cache being invalidated, and so |
2496 | | * we may report zeroes as data. This is not catastrophic, |
2497 | | * however, because reporting zeroes as data is fine. |
2498 | | */ |
2499 | 0 | if (QLIST_EMPTY(&bs->children) && |
2500 | 0 | bdrv_bsc_is_data(bs, aligned_offset, pnum)) |
2501 | 0 | { |
2502 | 0 | ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID; |
2503 | 0 | local_file = bs; |
2504 | 0 | local_map = aligned_offset; |
2505 | 0 | } else { |
2506 | 0 | ret = bs->drv->bdrv_co_block_status(bs, mode, aligned_offset, |
2507 | 0 | aligned_bytes, pnum, &local_map, |
2508 | 0 | &local_file); |
2509 | | |
2510 | | /* |
2511 | | * Note that checking QLIST_EMPTY(&bs->children) is also done when |
2512 | | * the cache is queried above. Technically, we do not need to check |
2513 | | * it here; the worst that can happen is that we fill the cache for |
2514 | | * non-protocol nodes, and then it is never used. However, filling |
2515 | | * the cache requires an RCU update, so double check here to avoid |
2516 | | * such an update if possible. |
2517 | | * |
2518 | | * Check mode, because we only want to update the cache when we |
2519 | | * have accurate information about what is zero and what is data. |
2520 | | */ |
2521 | 0 | if (mode == BDRV_WANT_PRECISE && |
2522 | 0 | ret == (BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID) && |
2523 | 0 | QLIST_EMPTY(&bs->children)) |
2524 | 0 | { |
2525 | | /* |
2526 | | * When a protocol driver reports BLOCK_OFFSET_VALID, the |
2527 | | * returned local_map value must be the same as the offset we |
2528 | | * have passed (aligned_offset), and local_bs must be the node |
2529 | | * itself. |
2530 | | * Assert this, because we follow this rule when reading from |
2531 | | * the cache (see the `local_file = bs` and |
2532 | | * `local_map = aligned_offset` assignments above), and the |
2533 | | * result the cache delivers must be the same as the driver |
2534 | | * would deliver. |
2535 | | */ |
2536 | 0 | assert(local_file == bs); |
2537 | 0 | assert(local_map == aligned_offset); |
2538 | 0 | bdrv_bsc_fill(bs, aligned_offset, *pnum); |
2539 | 0 | } |
2540 | 0 | } |
2541 | 0 | } else { |
2542 | | /* Default code for filters */ |
2543 | |
|
2544 | 0 | local_file = bdrv_filter_bs(bs); |
2545 | 0 | assert(local_file); |
2546 | |
|
2547 | 0 | *pnum = aligned_bytes; |
2548 | 0 | local_map = aligned_offset; |
2549 | 0 | ret = BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID; |
2550 | 0 | } |
2551 | 0 | if (ret < 0) { |
2552 | 0 | *pnum = 0; |
2553 | 0 | goto out; |
2554 | 0 | } |
2555 | | |
2556 | | /* |
2557 | | * The driver's result must be a non-zero multiple of request_alignment. |
2558 | | * Clamp pnum and adjust map to original request. |
2559 | | */ |
2560 | 0 | assert(*pnum && QEMU_IS_ALIGNED(*pnum, align) && |
2561 | 0 | align > offset - aligned_offset); |
2562 | 0 | if (ret & BDRV_BLOCK_RECURSE) { |
2563 | 0 | assert(ret & BDRV_BLOCK_DATA); |
2564 | 0 | assert(ret & BDRV_BLOCK_OFFSET_VALID); |
2565 | 0 | assert(!(ret & BDRV_BLOCK_ZERO)); |
2566 | 0 | } |
2567 | |
|
2568 | 0 | *pnum -= offset - aligned_offset; |
2569 | 0 | if (*pnum > bytes) { |
2570 | 0 | *pnum = bytes; |
2571 | 0 | } |
2572 | 0 | if (ret & BDRV_BLOCK_OFFSET_VALID) { |
2573 | 0 | local_map += offset - aligned_offset; |
2574 | 0 | } |
2575 | |
|
2576 | 0 | if (ret & BDRV_BLOCK_RAW) { |
2577 | 0 | assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file); |
2578 | 0 | ret = bdrv_co_do_block_status(local_file, mode, local_map, |
2579 | 0 | *pnum, pnum, &local_map, &local_file); |
2580 | 0 | goto out; |
2581 | 0 | } |
2582 | | |
2583 | 0 | if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) { |
2584 | 0 | ret |= BDRV_BLOCK_ALLOCATED; |
2585 | 0 | } else if (bs->drv->supports_backing) { |
2586 | 0 | BlockDriverState *cow_bs = bdrv_cow_bs(bs); |
2587 | |
|
2588 | 0 | if (!cow_bs) { |
2589 | 0 | ret |= BDRV_BLOCK_ZERO; |
2590 | 0 | } else if (mode == BDRV_WANT_PRECISE) { |
2591 | 0 | int64_t size2 = bdrv_co_getlength(cow_bs); |
2592 | |
|
2593 | 0 | if (size2 >= 0 && offset >= size2) { |
2594 | 0 | ret |= BDRV_BLOCK_ZERO; |
2595 | 0 | } |
2596 | 0 | } |
2597 | 0 | } |
2598 | |
|
2599 | 0 | if (mode == BDRV_WANT_PRECISE && ret & BDRV_BLOCK_RECURSE && |
2600 | 0 | local_file && local_file != bs && |
2601 | 0 | (ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) && |
2602 | 0 | (ret & BDRV_BLOCK_OFFSET_VALID)) { |
2603 | 0 | int64_t file_pnum; |
2604 | 0 | int ret2; |
2605 | |
|
2606 | 0 | ret2 = bdrv_co_do_block_status(local_file, mode, local_map, |
2607 | 0 | *pnum, &file_pnum, NULL, NULL); |
2608 | 0 | if (ret2 >= 0) { |
2609 | | /* Ignore errors. This is just providing extra information, it |
2610 | | * is useful but not necessary. |
2611 | | */ |
2612 | 0 | if (ret2 & BDRV_BLOCK_EOF && |
2613 | 0 | (!file_pnum || ret2 & BDRV_BLOCK_ZERO)) { |
2614 | | /* |
2615 | | * It is valid for the format block driver to read |
2616 | | * beyond the end of the underlying file's current |
2617 | | * size; such areas read as zero. |
2618 | | */ |
2619 | 0 | ret |= BDRV_BLOCK_ZERO; |
2620 | 0 | } else { |
2621 | | /* Limit request to the range reported by the protocol driver */ |
2622 | 0 | *pnum = file_pnum; |
2623 | 0 | ret |= (ret2 & BDRV_BLOCK_ZERO); |
2624 | 0 | } |
2625 | 0 | } |
2626 | | |
2627 | | /* |
2628 | | * Now that the recursive search was done, clear the flag. Otherwise, |
2629 | | * with more complicated block graphs like snapshot-access -> |
2630 | | * copy-before-write -> qcow2, where the return value will be propagated |
2631 | | * further up to a parent bdrv_co_do_block_status() call, both the |
2632 | | * BDRV_BLOCK_RECURSE and BDRV_BLOCK_ZERO flags would be set, which is |
2633 | | * not allowed. |
2634 | | */ |
2635 | 0 | ret &= ~BDRV_BLOCK_RECURSE; |
2636 | 0 | } |
2637 | |
|
2638 | 0 | out: |
2639 | 0 | bdrv_dec_in_flight(bs); |
2640 | 0 | if (ret >= 0 && offset + *pnum == total_size) { |
2641 | 0 | ret |= BDRV_BLOCK_EOF; |
2642 | 0 | } |
2643 | 0 | early_out: |
2644 | 0 | if (file) { |
2645 | 0 | *file = local_file; |
2646 | 0 | } |
2647 | 0 | if (map) { |
2648 | 0 | *map = local_map; |
2649 | 0 | } |
2650 | 0 | return ret; |
2651 | 0 | } |
2652 | | |
2653 | | int coroutine_fn |
2654 | | bdrv_co_common_block_status_above(BlockDriverState *bs, |
2655 | | BlockDriverState *base, |
2656 | | bool include_base, |
2657 | | unsigned int mode, |
2658 | | int64_t offset, |
2659 | | int64_t bytes, |
2660 | | int64_t *pnum, |
2661 | | int64_t *map, |
2662 | | BlockDriverState **file, |
2663 | | int *depth) |
2664 | 0 | { |
2665 | 0 | int ret; |
2666 | 0 | BlockDriverState *p; |
2667 | 0 | int64_t eof = 0; |
2668 | 0 | int dummy; |
2669 | 0 | IO_CODE(); |
2670 | |
|
2671 | 0 | assert(!include_base || base); /* Can't include NULL base */ |
2672 | 0 | assert_bdrv_graph_readable(); |
2673 | |
|
2674 | 0 | if (!depth) { |
2675 | 0 | depth = &dummy; |
2676 | 0 | } |
2677 | 0 | *depth = 0; |
2678 | |
|
2679 | 0 | if (!include_base && bs == base) { |
2680 | 0 | *pnum = bytes; |
2681 | 0 | return 0; |
2682 | 0 | } |
2683 | | |
2684 | 0 | ret = bdrv_co_do_block_status(bs, mode, offset, bytes, pnum, |
2685 | 0 | map, file); |
2686 | 0 | ++*depth; |
2687 | 0 | if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { |
2688 | 0 | return ret; |
2689 | 0 | } |
2690 | | |
2691 | 0 | if (ret & BDRV_BLOCK_EOF) { |
2692 | 0 | eof = offset + *pnum; |
2693 | 0 | } |
2694 | |
|
2695 | 0 | assert(*pnum <= bytes); |
2696 | 0 | bytes = *pnum; |
2697 | |
|
2698 | 0 | for (p = bdrv_filter_or_cow_bs(bs); include_base || p != base; |
2699 | 0 | p = bdrv_filter_or_cow_bs(p)) |
2700 | 0 | { |
2701 | 0 | ret = bdrv_co_do_block_status(p, mode, offset, bytes, pnum, |
2702 | 0 | map, file); |
2703 | 0 | ++*depth; |
2704 | 0 | if (ret < 0) { |
2705 | 0 | return ret; |
2706 | 0 | } |
2707 | 0 | if (*pnum == 0) { |
2708 | | /* |
2709 | | * The top layer deferred to this layer, and because this layer is |
2710 | | * short, any zeroes that we synthesize beyond EOF behave as if they |
2711 | | * were allocated at this layer. |
2712 | | * |
2713 | | * We don't include BDRV_BLOCK_EOF into ret, as upper layer may be |
2714 | | * larger. We'll add BDRV_BLOCK_EOF if needed at function end, see |
2715 | | * below. |
2716 | | */ |
2717 | 0 | assert(ret & BDRV_BLOCK_EOF); |
2718 | 0 | *pnum = bytes; |
2719 | 0 | if (file) { |
2720 | 0 | *file = p; |
2721 | 0 | } |
2722 | 0 | ret = BDRV_BLOCK_ZERO | BDRV_BLOCK_ALLOCATED; |
2723 | 0 | break; |
2724 | 0 | } |
2725 | 0 | if (ret & BDRV_BLOCK_ALLOCATED) { |
2726 | | /* |
2727 | | * We've found the node and the status, we must break. |
2728 | | * |
2729 | | * Drop BDRV_BLOCK_EOF, as it's not for upper layer, which may be |
2730 | | * larger. We'll add BDRV_BLOCK_EOF if needed at function end, see |
2731 | | * below. |
2732 | | */ |
2733 | 0 | ret &= ~BDRV_BLOCK_EOF; |
2734 | 0 | break; |
2735 | 0 | } |
2736 | | |
2737 | 0 | if (p == base) { |
2738 | 0 | assert(include_base); |
2739 | 0 | break; |
2740 | 0 | } |
2741 | | |
2742 | | /* |
2743 | | * OK, [offset, offset + *pnum) region is unallocated on this layer, |
2744 | | * let's continue the diving. |
2745 | | */ |
2746 | 0 | assert(*pnum <= bytes); |
2747 | 0 | bytes = *pnum; |
2748 | 0 | } |
2749 | | |
2750 | 0 | if (offset + *pnum == eof) { |
2751 | 0 | ret |= BDRV_BLOCK_EOF; |
2752 | 0 | } |
2753 | |
|
2754 | 0 | return ret; |
2755 | 0 | } |
2756 | | |
2757 | | int coroutine_fn bdrv_co_block_status_above(BlockDriverState *bs, |
2758 | | BlockDriverState *base, |
2759 | | int64_t offset, int64_t bytes, |
2760 | | int64_t *pnum, int64_t *map, |
2761 | | BlockDriverState **file) |
2762 | 0 | { |
2763 | 0 | IO_CODE(); |
2764 | 0 | return bdrv_co_common_block_status_above(bs, base, false, |
2765 | 0 | BDRV_WANT_PRECISE, offset, |
2766 | 0 | bytes, pnum, map, file, NULL); |
2767 | 0 | } |
2768 | | |
2769 | | int coroutine_fn bdrv_co_block_status(BlockDriverState *bs, int64_t offset, |
2770 | | int64_t bytes, int64_t *pnum, |
2771 | | int64_t *map, BlockDriverState **file) |
2772 | 0 | { |
2773 | 0 | IO_CODE(); |
2774 | 0 | return bdrv_co_block_status_above(bs, bdrv_filter_or_cow_bs(bs), |
2775 | 0 | offset, bytes, pnum, map, file); |
2776 | 0 | } |
2777 | | |
2778 | | /* |
2779 | | * Check @bs (and its backing chain) to see if the range defined |
2780 | | * by @offset and @bytes is known to read as zeroes. |
2781 | | * Return 1 if that is the case, 0 otherwise and -errno on error. |
2782 | | * This test is meant to be fast rather than accurate so returning 0 |
2783 | | * does not guarantee non-zero data; but a return of 1 is reliable. |
2784 | | */ |
2785 | | int coroutine_fn bdrv_co_is_zero_fast(BlockDriverState *bs, int64_t offset, |
2786 | | int64_t bytes) |
2787 | 0 | { |
2788 | 0 | int ret; |
2789 | 0 | int64_t pnum; |
2790 | 0 | IO_CODE(); |
2791 | |
|
2792 | 0 | while (bytes) { |
2793 | 0 | ret = bdrv_co_common_block_status_above(bs, NULL, false, |
2794 | 0 | BDRV_WANT_ZERO, offset, bytes, |
2795 | 0 | &pnum, NULL, NULL, NULL); |
2796 | |
|
2797 | 0 | if (ret < 0) { |
2798 | 0 | return ret; |
2799 | 0 | } |
2800 | 0 | if (!(ret & BDRV_BLOCK_ZERO)) { |
2801 | 0 | return 0; |
2802 | 0 | } |
2803 | 0 | offset += pnum; |
2804 | 0 | bytes -= pnum; |
2805 | 0 | } |
2806 | | |
2807 | 0 | return 1; |
2808 | 0 | } |
2809 | | |
2810 | | /* |
2811 | | * Check @bs (and its backing chain) to see if the entire image is known |
2812 | | * to read as zeroes. |
2813 | | * Return 1 if that is the case, 0 otherwise and -errno on error. |
2814 | | * This test is meant to be fast rather than accurate so returning 0 |
2815 | | * does not guarantee non-zero data; however, a return of 1 is reliable, |
2816 | | * and this function can report 1 in more cases than bdrv_co_is_zero_fast. |
2817 | | */ |
2818 | | int coroutine_fn bdrv_co_is_all_zeroes(BlockDriverState *bs) |
2819 | 0 | { |
2820 | 0 | int ret; |
2821 | 0 | int64_t pnum, bytes; |
2822 | 0 | char *buf; |
2823 | 0 | QEMUIOVector local_qiov; |
2824 | 0 | IO_CODE(); |
2825 | |
|
2826 | 0 | bytes = bdrv_co_getlength(bs); |
2827 | 0 | if (bytes < 0) { |
2828 | 0 | return bytes; |
2829 | 0 | } |
2830 | | |
2831 | | /* First probe - see if the entire image reads as zero */ |
2832 | 0 | ret = bdrv_co_common_block_status_above(bs, NULL, false, BDRV_WANT_ZERO, |
2833 | 0 | 0, bytes, &pnum, NULL, NULL, |
2834 | 0 | NULL); |
2835 | 0 | if (ret < 0) { |
2836 | 0 | return ret; |
2837 | 0 | } |
2838 | 0 | if (ret & BDRV_BLOCK_ZERO) { |
2839 | 0 | return bdrv_co_is_zero_fast(bs, pnum, bytes - pnum); |
2840 | 0 | } |
2841 | | |
2842 | | /* |
2843 | | * Because of the way 'blockdev-create' works, raw files tend to |
2844 | | * be created with a non-sparse region at the front to make |
2845 | | * alignment probing easier. If the block starts with only a |
2846 | | * small allocated region, it is still worth the effort to see if |
2847 | | * the rest of the image is still sparse, coupled with manually |
2848 | | * reading the first region to see if it reads zero after all. |
2849 | | */ |
2850 | 0 | if (pnum > MAX_ZERO_CHECK_BUFFER) { |
2851 | 0 | return 0; |
2852 | 0 | } |
2853 | 0 | ret = bdrv_co_is_zero_fast(bs, pnum, bytes - pnum); |
2854 | 0 | if (ret <= 0) { |
2855 | 0 | return ret; |
2856 | 0 | } |
2857 | | /* Only the head of the image is unknown, and it's small. Read it. */ |
2858 | 0 | buf = qemu_blockalign(bs, pnum); |
2859 | 0 | qemu_iovec_init_buf(&local_qiov, buf, pnum); |
2860 | 0 | ret = bdrv_driver_preadv(bs, 0, pnum, &local_qiov, 0, 0); |
2861 | 0 | if (ret >= 0) { |
2862 | 0 | ret = buffer_is_zero(buf, pnum); |
2863 | 0 | } |
2864 | 0 | qemu_vfree(buf); |
2865 | 0 | return ret; |
2866 | 0 | } |
2867 | | |
2868 | | int coroutine_fn bdrv_co_is_allocated(BlockDriverState *bs, int64_t offset, |
2869 | | int64_t bytes, int64_t *pnum) |
2870 | 0 | { |
2871 | 0 | int ret; |
2872 | 0 | int64_t dummy; |
2873 | 0 | IO_CODE(); |
2874 | |
|
2875 | 0 | ret = bdrv_co_common_block_status_above(bs, bs, true, BDRV_WANT_ALLOCATED, |
2876 | 0 | offset, bytes, pnum ? pnum : &dummy, |
2877 | 0 | NULL, NULL, NULL); |
2878 | 0 | if (ret < 0) { |
2879 | 0 | return ret; |
2880 | 0 | } |
2881 | 0 | return !!(ret & BDRV_BLOCK_ALLOCATED); |
2882 | 0 | } |
2883 | | |
2884 | | /* |
2885 | | * Given an image chain: ... -> [BASE] -> [INTER1] -> [INTER2] -> [TOP] |
2886 | | * |
2887 | | * Return a positive depth if (a prefix of) the given range is allocated |
2888 | | * in any image between BASE and TOP (BASE is only included if include_base |
2889 | | * is set). Depth 1 is TOP, 2 is the first backing layer, and so forth. |
2890 | | * BASE can be NULL to check if the given offset is allocated in any |
2891 | | * image of the chain. Return 0 otherwise, or negative errno on |
2892 | | * failure. |
2893 | | * |
2894 | | * 'pnum' is set to the number of bytes (including and immediately |
2895 | | * following the specified offset) that are known to be in the same |
2896 | | * allocated/unallocated state. Note that a subsequent call starting |
2897 | | * at 'offset + *pnum' may return the same allocation status (in other |
2898 | | * words, the result is not necessarily the maximum possible range); |
2899 | | * but 'pnum' will only be 0 when end of file is reached. |
2900 | | */ |
2901 | | int coroutine_fn bdrv_co_is_allocated_above(BlockDriverState *bs, |
2902 | | BlockDriverState *base, |
2903 | | bool include_base, int64_t offset, |
2904 | | int64_t bytes, int64_t *pnum) |
2905 | 0 | { |
2906 | 0 | int depth; |
2907 | 0 | int ret; |
2908 | 0 | IO_CODE(); |
2909 | |
|
2910 | 0 | ret = bdrv_co_common_block_status_above(bs, base, include_base, |
2911 | 0 | BDRV_WANT_ALLOCATED, |
2912 | 0 | offset, bytes, pnum, NULL, NULL, |
2913 | 0 | &depth); |
2914 | 0 | if (ret < 0) { |
2915 | 0 | return ret; |
2916 | 0 | } |
2917 | | |
2918 | 0 | if (ret & BDRV_BLOCK_ALLOCATED) { |
2919 | 0 | return depth; |
2920 | 0 | } |
2921 | 0 | return 0; |
2922 | 0 | } |
2923 | | |
2924 | | int coroutine_fn |
2925 | | bdrv_co_readv_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos) |
2926 | 0 | { |
2927 | 0 | BlockDriver *drv = bs->drv; |
2928 | 0 | BlockDriverState *child_bs = bdrv_primary_bs(bs); |
2929 | 0 | int ret; |
2930 | 0 | IO_CODE(); |
2931 | 0 | assert_bdrv_graph_readable(); |
2932 | |
|
2933 | 0 | ret = bdrv_check_qiov_request(pos, qiov->size, qiov, 0, NULL); |
2934 | 0 | if (ret < 0) { |
2935 | 0 | return ret; |
2936 | 0 | } |
2937 | | |
2938 | 0 | if (!drv) { |
2939 | 0 | return -ENOMEDIUM; |
2940 | 0 | } |
2941 | | |
2942 | 0 | bdrv_inc_in_flight(bs); |
2943 | |
|
2944 | 0 | if (drv->bdrv_co_load_vmstate) { |
2945 | 0 | ret = drv->bdrv_co_load_vmstate(bs, qiov, pos); |
2946 | 0 | } else if (child_bs) { |
2947 | 0 | ret = bdrv_co_readv_vmstate(child_bs, qiov, pos); |
2948 | 0 | } else { |
2949 | 0 | ret = -ENOTSUP; |
2950 | 0 | } |
2951 | |
|
2952 | 0 | bdrv_dec_in_flight(bs); |
2953 | |
|
2954 | 0 | return ret; |
2955 | 0 | } |
2956 | | |
2957 | | int coroutine_fn |
2958 | | bdrv_co_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos) |
2959 | 0 | { |
2960 | 0 | BlockDriver *drv = bs->drv; |
2961 | 0 | BlockDriverState *child_bs = bdrv_primary_bs(bs); |
2962 | 0 | int ret; |
2963 | 0 | IO_CODE(); |
2964 | 0 | assert_bdrv_graph_readable(); |
2965 | |
|
2966 | 0 | ret = bdrv_check_qiov_request(pos, qiov->size, qiov, 0, NULL); |
2967 | 0 | if (ret < 0) { |
2968 | 0 | return ret; |
2969 | 0 | } |
2970 | | |
2971 | 0 | if (!drv) { |
2972 | 0 | return -ENOMEDIUM; |
2973 | 0 | } |
2974 | | |
2975 | 0 | bdrv_inc_in_flight(bs); |
2976 | |
|
2977 | 0 | if (drv->bdrv_co_save_vmstate) { |
2978 | 0 | ret = drv->bdrv_co_save_vmstate(bs, qiov, pos); |
2979 | 0 | } else if (child_bs) { |
2980 | 0 | ret = bdrv_co_writev_vmstate(child_bs, qiov, pos); |
2981 | 0 | } else { |
2982 | 0 | ret = -ENOTSUP; |
2983 | 0 | } |
2984 | |
|
2985 | 0 | bdrv_dec_in_flight(bs); |
2986 | |
|
2987 | 0 | return ret; |
2988 | 0 | } |
2989 | | |
2990 | | int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf, |
2991 | | int64_t pos, int size) |
2992 | 0 | { |
2993 | 0 | QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, size); |
2994 | 0 | int ret = bdrv_writev_vmstate(bs, &qiov, pos); |
2995 | 0 | IO_CODE(); |
2996 | |
|
2997 | 0 | return ret < 0 ? ret : size; |
2998 | 0 | } |
2999 | | |
3000 | | int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf, |
3001 | | int64_t pos, int size) |
3002 | 0 | { |
3003 | 0 | QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, size); |
3004 | 0 | int ret = bdrv_readv_vmstate(bs, &qiov, pos); |
3005 | 0 | IO_CODE(); |
3006 | |
|
3007 | 0 | return ret < 0 ? ret : size; |
3008 | 0 | } |
3009 | | |
3010 | | /**************************************************************/ |
3011 | | /* async I/Os */ |
3012 | | |
3013 | | /** |
3014 | | * Synchronously cancels an acb. Must be called with the BQL held and the acb |
3015 | | * must be processed with the BQL held too (IOThreads are not allowed). |
3016 | | * |
3017 | | * Use bdrv_aio_cancel_async() instead when possible. |
3018 | | */ |
3019 | | void bdrv_aio_cancel(BlockAIOCB *acb) |
3020 | 317 | { |
3021 | 317 | GLOBAL_STATE_CODE(); |
3022 | 317 | qemu_aio_ref(acb); |
3023 | 317 | bdrv_aio_cancel_async(acb); |
3024 | 317 | AIO_WAIT_WHILE_UNLOCKED(NULL, acb->refcnt > 1); |
3025 | 317 | qemu_aio_unref(acb); |
3026 | 317 | } |
3027 | | |
3028 | | /* Async version of aio cancel. The caller is not blocked if the acb implements |
3029 | | * cancel_async, otherwise we do nothing and let the request normally complete. |
3030 | | * In either case the completion callback must be called. */ |
3031 | | void bdrv_aio_cancel_async(BlockAIOCB *acb) |
3032 | 1.80k | { |
3033 | 1.80k | IO_CODE(); |
3034 | 1.80k | if (acb->aiocb_info->cancel_async) { |
3035 | 0 | acb->aiocb_info->cancel_async(acb); |
3036 | 0 | } |
3037 | 1.80k | } |
3038 | | |
3039 | | /**************************************************************/ |
3040 | | /* Coroutine block device emulation */ |
3041 | | |
3042 | | int coroutine_fn bdrv_co_flush(BlockDriverState *bs) |
3043 | 7.32k | { |
3044 | 7.32k | BdrvChild *primary_child = bdrv_primary_child(bs); |
3045 | 7.32k | BdrvChild *child; |
3046 | 7.32k | int current_gen; |
3047 | 7.32k | int ret = 0; |
3048 | 7.32k | IO_CODE(); |
3049 | | |
3050 | 7.32k | assert_bdrv_graph_readable(); |
3051 | 7.32k | bdrv_inc_in_flight(bs); |
3052 | | |
3053 | 7.32k | if (!bdrv_co_is_inserted(bs) || bdrv_is_read_only(bs) || |
3054 | 7.32k | bdrv_is_sg(bs)) { |
3055 | 0 | goto early_exit; |
3056 | 0 | } |
3057 | | |
3058 | 14.6k | qemu_mutex_lock(&bs->reqs_lock); |
3059 | 14.6k | current_gen = qatomic_read(&bs->write_gen); |
3060 | | |
3061 | | /* Wait until any previous flushes are completed */ |
3062 | 7.32k | while (bs->active_flush_req) { |
3063 | 0 | qemu_co_queue_wait(&bs->flush_queue, &bs->reqs_lock); |
3064 | 0 | } |
3065 | | |
3066 | | /* Flushes reach this point in nondecreasing current_gen order. */ |
3067 | 7.32k | bs->active_flush_req = true; |
3068 | 7.32k | qemu_mutex_unlock(&bs->reqs_lock); |
3069 | | |
3070 | | /* Write back all layers by calling one driver function */ |
3071 | 7.32k | if (bs->drv->bdrv_co_flush) { |
3072 | 0 | ret = bs->drv->bdrv_co_flush(bs); |
3073 | 0 | goto out; |
3074 | 0 | } |
3075 | | |
3076 | | /* Write back cached data to the OS even with cache=unsafe */ |
3077 | 7.32k | BLKDBG_CO_EVENT(primary_child, BLKDBG_FLUSH_TO_OS); |
3078 | 7.32k | if (bs->drv->bdrv_co_flush_to_os) { |
3079 | 0 | ret = bs->drv->bdrv_co_flush_to_os(bs); |
3080 | 0 | if (ret < 0) { |
3081 | 0 | goto out; |
3082 | 0 | } |
3083 | 0 | } |
3084 | | |
3085 | | /* But don't actually force it to the disk with cache=unsafe */ |
3086 | 7.32k | if (bs->open_flags & BDRV_O_NO_FLUSH) { |
3087 | 0 | goto flush_children; |
3088 | 0 | } |
3089 | | |
3090 | | /* Check if we really need to flush anything */ |
3091 | 7.32k | if (bs->flushed_gen == current_gen) { |
3092 | 5.57k | goto flush_children; |
3093 | 5.57k | } |
3094 | | |
3095 | 1.75k | BLKDBG_CO_EVENT(primary_child, BLKDBG_FLUSH_TO_DISK); |
3096 | 1.75k | if (!bs->drv) { |
3097 | | /* bs->drv->bdrv_co_flush() might have ejected the BDS |
3098 | | * (even in case of apparent success) */ |
3099 | 0 | ret = -ENOMEDIUM; |
3100 | 0 | goto out; |
3101 | 0 | } |
3102 | 1.75k | if (bs->drv->bdrv_co_flush_to_disk) { |
3103 | 877 | ret = bs->drv->bdrv_co_flush_to_disk(bs); |
3104 | 877 | } else if (bs->drv->bdrv_aio_flush) { |
3105 | 0 | BlockAIOCB *acb; |
3106 | 0 | CoroutineIOCompletion co = { |
3107 | 0 | .coroutine = qemu_coroutine_self(), |
3108 | 0 | }; |
3109 | |
|
3110 | 0 | acb = bs->drv->bdrv_aio_flush(bs, bdrv_co_io_em_complete, &co); |
3111 | 0 | if (acb == NULL) { |
3112 | 0 | ret = -EIO; |
3113 | 0 | } else { |
3114 | 0 | qemu_coroutine_yield(); |
3115 | 0 | ret = co.ret; |
3116 | 0 | } |
3117 | 877 | } else { |
3118 | | /* |
3119 | | * Some block drivers always operate in either writethrough or unsafe |
3120 | | * mode and don't support bdrv_flush therefore. Usually qemu doesn't |
3121 | | * know how the server works (because the behaviour is hardcoded or |
3122 | | * depends on server-side configuration), so we can't ensure that |
3123 | | * everything is safe on disk. Returning an error doesn't work because |
3124 | | * that would break guests even if the server operates in writethrough |
3125 | | * mode. |
3126 | | * |
3127 | | * Let's hope the user knows what he's doing. |
3128 | | */ |
3129 | 877 | ret = 0; |
3130 | 877 | } |
3131 | | |
3132 | 1.75k | if (ret < 0) { |
3133 | 0 | goto out; |
3134 | 0 | } |
3135 | | |
3136 | | /* Now flush the underlying protocol. It will also have BDRV_O_NO_FLUSH |
3137 | | * in the case of cache=unsafe, so there are no useless flushes. |
3138 | | */ |
3139 | 7.32k | flush_children: |
3140 | 7.32k | ret = 0; |
3141 | 7.32k | QLIST_FOREACH(child, &bs->children, next) { |
3142 | 3.66k | if (child->perm & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) { |
3143 | 3.66k | int this_child_ret = bdrv_co_flush(child->bs); |
3144 | 3.66k | if (!ret) { |
3145 | 3.66k | ret = this_child_ret; |
3146 | 3.66k | } |
3147 | 3.66k | } |
3148 | 3.66k | } |
3149 | | |
3150 | 7.32k | out: |
3151 | | /* Notify any pending flushes that we have completed */ |
3152 | 7.32k | if (ret == 0) { |
3153 | 7.32k | bs->flushed_gen = current_gen; |
3154 | 7.32k | } |
3155 | | |
3156 | 7.32k | qemu_mutex_lock(&bs->reqs_lock); |
3157 | 7.32k | bs->active_flush_req = false; |
3158 | | /* Return value is ignored - it's ok if wait queue is empty */ |
3159 | 7.32k | qemu_co_queue_next(&bs->flush_queue); |
3160 | 7.32k | qemu_mutex_unlock(&bs->reqs_lock); |
3161 | | |
3162 | 7.32k | early_exit: |
3163 | 7.32k | bdrv_dec_in_flight(bs); |
3164 | 7.32k | return ret; |
3165 | 7.32k | } |
3166 | | |
3167 | | int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset, |
3168 | | int64_t bytes) |
3169 | 140k | { |
3170 | 140k | BdrvTrackedRequest req; |
3171 | 140k | int ret; |
3172 | 140k | int64_t max_pdiscard; |
3173 | 140k | int head, tail, align; |
3174 | 140k | BlockDriverState *bs = child->bs; |
3175 | 140k | IO_CODE(); |
3176 | 140k | assert_bdrv_graph_readable(); |
3177 | | |
3178 | 140k | if (!bs || !bs->drv || !bdrv_co_is_inserted(bs)) { |
3179 | 0 | return -ENOMEDIUM; |
3180 | 0 | } |
3181 | | |
3182 | 140k | if (bdrv_has_readonly_bitmaps(bs)) { |
3183 | 0 | return -EPERM; |
3184 | 0 | } |
3185 | | |
3186 | 140k | ret = bdrv_check_request(offset, bytes, NULL); |
3187 | 140k | if (ret < 0) { |
3188 | 0 | return ret; |
3189 | 0 | } |
3190 | | |
3191 | | /* Do nothing if disabled. */ |
3192 | 140k | if (!(bs->open_flags & BDRV_O_UNMAP)) { |
3193 | 140k | return 0; |
3194 | 140k | } |
3195 | | |
3196 | 0 | if (!bs->drv->bdrv_co_pdiscard) { |
3197 | 0 | return 0; |
3198 | 0 | } |
3199 | | |
3200 | | /* Invalidate the cached block-status data range if this discard overlaps */ |
3201 | 0 | bdrv_bsc_invalidate_range(bs, offset, bytes); |
3202 | | |
3203 | | /* |
3204 | | * Discard is advisory, but some devices track and coalesce |
3205 | | * unaligned requests, so we must pass everything down rather than |
3206 | | * round here. Still, most devices reject unaligned requests with |
3207 | | * -EINVAL or -ENOTSUP, so we must fragment the request accordingly. |
3208 | | */ |
3209 | 0 | align = MAX(bs->bl.pdiscard_alignment, bs->bl.request_alignment); |
3210 | 0 | assert(align % bs->bl.request_alignment == 0); |
3211 | 0 | head = offset % align; |
3212 | 0 | tail = (offset + bytes) % align; |
3213 | |
|
3214 | 0 | bdrv_inc_in_flight(bs); |
3215 | 0 | tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_DISCARD); |
3216 | |
|
3217 | 0 | ret = bdrv_co_write_req_prepare(child, offset, bytes, &req, 0); |
3218 | 0 | if (ret < 0) { |
3219 | 0 | goto out; |
3220 | 0 | } |
3221 | | |
3222 | 0 | max_pdiscard = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_pdiscard, INT64_MAX), |
3223 | 0 | align); |
3224 | 0 | assert(max_pdiscard >= bs->bl.request_alignment); |
3225 | |
|
3226 | 0 | while (bytes > 0) { |
3227 | 0 | int64_t num = bytes; |
3228 | |
|
3229 | 0 | if (head) { |
3230 | | /* Make small requests to get to alignment boundaries. */ |
3231 | 0 | num = MIN(bytes, align - head); |
3232 | 0 | if (!QEMU_IS_ALIGNED(num, bs->bl.request_alignment)) { |
3233 | 0 | num %= bs->bl.request_alignment; |
3234 | 0 | } |
3235 | 0 | head = (head + num) % align; |
3236 | 0 | assert(num < max_pdiscard); |
3237 | 0 | } else if (tail) { |
3238 | 0 | if (num > align) { |
3239 | | /* Shorten the request to the last aligned cluster. */ |
3240 | 0 | num -= tail; |
3241 | 0 | } else if (!QEMU_IS_ALIGNED(tail, bs->bl.request_alignment) && |
3242 | 0 | tail > bs->bl.request_alignment) { |
3243 | 0 | tail %= bs->bl.request_alignment; |
3244 | 0 | num -= tail; |
3245 | 0 | } |
3246 | 0 | } |
3247 | | /* limit request size */ |
3248 | 0 | if (num > max_pdiscard) { |
3249 | 0 | num = max_pdiscard; |
3250 | 0 | } |
3251 | |
|
3252 | 0 | if (!bs->drv) { |
3253 | 0 | ret = -ENOMEDIUM; |
3254 | 0 | goto out; |
3255 | 0 | } |
3256 | | |
3257 | 0 | ret = bs->drv->bdrv_co_pdiscard(bs, offset, num); |
3258 | 0 | if (ret && ret != -ENOTSUP) { |
3259 | 0 | if (ret == -EINVAL && (offset % align != 0 || num % align != 0)) { |
3260 | | /* Silently skip rejected unaligned head/tail requests */ |
3261 | 0 | } else { |
3262 | 0 | goto out; /* bail out */ |
3263 | 0 | } |
3264 | 0 | } |
3265 | | |
3266 | 0 | offset += num; |
3267 | 0 | bytes -= num; |
3268 | 0 | } |
3269 | 0 | ret = 0; |
3270 | 0 | out: |
3271 | 0 | bdrv_co_write_req_finish(child, req.offset, req.bytes, &req, ret); |
3272 | 0 | tracked_request_end(&req); |
3273 | 0 | bdrv_dec_in_flight(bs); |
3274 | 0 | return ret; |
3275 | 0 | } |
3276 | | |
3277 | | int coroutine_fn bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf) |
3278 | 0 | { |
3279 | 0 | BlockDriver *drv = bs->drv; |
3280 | 0 | CoroutineIOCompletion co = { |
3281 | 0 | .coroutine = qemu_coroutine_self(), |
3282 | 0 | }; |
3283 | 0 | BlockAIOCB *acb; |
3284 | 0 | IO_CODE(); |
3285 | 0 | assert_bdrv_graph_readable(); |
3286 | |
|
3287 | 0 | bdrv_inc_in_flight(bs); |
3288 | 0 | if (!drv || (!drv->bdrv_aio_ioctl && !drv->bdrv_co_ioctl)) { |
3289 | 0 | co.ret = -ENOTSUP; |
3290 | 0 | goto out; |
3291 | 0 | } |
3292 | | |
3293 | 0 | if (drv->bdrv_co_ioctl) { |
3294 | 0 | co.ret = drv->bdrv_co_ioctl(bs, req, buf); |
3295 | 0 | } else { |
3296 | 0 | acb = drv->bdrv_aio_ioctl(bs, req, buf, bdrv_co_io_em_complete, &co); |
3297 | 0 | if (!acb) { |
3298 | 0 | co.ret = -ENOTSUP; |
3299 | 0 | goto out; |
3300 | 0 | } |
3301 | 0 | qemu_coroutine_yield(); |
3302 | 0 | } |
3303 | 0 | out: |
3304 | 0 | bdrv_dec_in_flight(bs); |
3305 | 0 | return co.ret; |
3306 | 0 | } |
3307 | | |
3308 | | int coroutine_fn bdrv_co_zone_report(BlockDriverState *bs, int64_t offset, |
3309 | | unsigned int *nr_zones, |
3310 | | BlockZoneDescriptor *zones) |
3311 | 0 | { |
3312 | 0 | BlockDriver *drv = bs->drv; |
3313 | 0 | int ret; |
3314 | 0 | IO_CODE(); |
3315 | |
|
3316 | 0 | bdrv_inc_in_flight(bs); |
3317 | 0 | if (!drv || !drv->bdrv_co_zone_report || bs->bl.zoned == BLK_Z_NONE) { |
3318 | 0 | ret = -ENOTSUP; |
3319 | 0 | goto out; |
3320 | 0 | } |
3321 | 0 | ret = drv->bdrv_co_zone_report(bs, offset, nr_zones, zones); |
3322 | 0 | out: |
3323 | 0 | bdrv_dec_in_flight(bs); |
3324 | 0 | return ret; |
3325 | 0 | } |
3326 | | |
3327 | | int coroutine_fn bdrv_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, |
3328 | | int64_t offset, int64_t len) |
3329 | 0 | { |
3330 | 0 | BlockDriver *drv = bs->drv; |
3331 | 0 | int ret; |
3332 | 0 | IO_CODE(); |
3333 | |
|
3334 | 0 | bdrv_inc_in_flight(bs); |
3335 | 0 | if (!drv || !drv->bdrv_co_zone_mgmt || bs->bl.zoned == BLK_Z_NONE) { |
3336 | 0 | ret = -ENOTSUP; |
3337 | 0 | goto out; |
3338 | 0 | } |
3339 | 0 | ret = drv->bdrv_co_zone_mgmt(bs, op, offset, len); |
3340 | 0 | out: |
3341 | 0 | bdrv_dec_in_flight(bs); |
3342 | 0 | return ret; |
3343 | 0 | } |
3344 | | |
3345 | | int coroutine_fn bdrv_co_zone_append(BlockDriverState *bs, int64_t *offset, |
3346 | | QEMUIOVector *qiov, |
3347 | | BdrvRequestFlags flags) |
3348 | 0 | { |
3349 | 0 | int ret; |
3350 | 0 | BlockDriver *drv = bs->drv; |
3351 | 0 | IO_CODE(); |
3352 | |
|
3353 | 0 | ret = bdrv_check_qiov_request(*offset, qiov->size, qiov, 0, NULL); |
3354 | 0 | if (ret < 0) { |
3355 | 0 | return ret; |
3356 | 0 | } |
3357 | | |
3358 | | /* |
3359 | | * Zone write pointers are kept and reported in units of BDRV_SECTOR_SIZE, |
3360 | | * so an append that would leave a write pointer at a finer granularity |
3361 | | * cannot be represented. Drivers may impose a coarser granularity of their |
3362 | | * own, see BlockLimits.write_granularity. |
3363 | | */ |
3364 | 0 | if (!QEMU_IS_ALIGNED(qiov->size, BDRV_SECTOR_SIZE)) { |
3365 | 0 | return -EINVAL; |
3366 | 0 | } |
3367 | | |
3368 | | /* |
3369 | | * An append cannot cross a zone boundary, so one that is larger than a |
3370 | | * zone can never be carried out, wherever the write pointer of the zone |
3371 | | * is. The exact bound is the part of the zone that is still writable, |
3372 | | * which only a driver can check, as only it holds the write pointer. |
3373 | | * zone_size is zero when the device is not zoned, which is reported as |
3374 | | * unsupported below. |
3375 | | */ |
3376 | 0 | if (bs->bl.zone_size && qiov->size > bs->bl.zone_size) { |
3377 | 0 | return -EINVAL; |
3378 | 0 | } |
3379 | | |
3380 | 0 | bdrv_inc_in_flight(bs); |
3381 | 0 | if (!drv || !drv->bdrv_co_zone_append || bs->bl.zoned == BLK_Z_NONE) { |
3382 | 0 | ret = -ENOTSUP; |
3383 | 0 | goto out; |
3384 | 0 | } |
3385 | 0 | ret = drv->bdrv_co_zone_append(bs, offset, qiov, flags); |
3386 | 0 | out: |
3387 | 0 | bdrv_dec_in_flight(bs); |
3388 | 0 | return ret; |
3389 | 0 | } |
3390 | | |
3391 | | uint32_t bdrv_zone_index(BlockDriverState *bs, uint64_t offset) |
3392 | 0 | { |
3393 | 0 | IO_CODE(); |
3394 | |
|
3395 | 0 | return offset >> bs->bl.zone_size_bits; |
3396 | 0 | } |
3397 | | |
3398 | | bool bdrv_zone_is_conv(BlockDriverState *bs, uint32_t index) |
3399 | 0 | { |
3400 | 0 | IO_CODE(); |
3401 | |
|
3402 | 0 | return BDRV_ZT_IS_CONV(bs->wps->wp[index]); |
3403 | 0 | } |
3404 | | |
3405 | | bool bdrv_zone_is_full(BlockDriverState *bs, uint32_t index) |
3406 | 0 | { |
3407 | 0 | uint64_t zone_end = MIN((uint64_t)(index + 1) * bs->bl.zone_size, |
3408 | 0 | (uint64_t)bs->total_sectors << BDRV_SECTOR_BITS); |
3409 | 0 | IO_CODE(); |
3410 | |
|
3411 | 0 | return bs->wps->wp[index] >= zone_end; |
3412 | 0 | } |
3413 | | |
3414 | | void *qemu_blockalign(BlockDriverState *bs, size_t size) |
3415 | 77.4k | { |
3416 | 77.4k | IO_CODE(); |
3417 | 77.4k | return qemu_memalign(bdrv_opt_mem_align(bs), size); |
3418 | 77.4k | } |
3419 | | |
3420 | | void *qemu_blockalign0(BlockDriverState *bs, size_t size) |
3421 | 0 | { |
3422 | 0 | IO_CODE(); |
3423 | 0 | return memset(qemu_blockalign(bs, size), 0, size); |
3424 | 0 | } |
3425 | | |
3426 | | void *qemu_try_blockalign(BlockDriverState *bs, size_t size) |
3427 | 466 | { |
3428 | 466 | size_t align = bdrv_opt_mem_align(bs); |
3429 | 466 | IO_CODE(); |
3430 | | |
3431 | | /* Ensure that NULL is never returned on success */ |
3432 | 466 | assert(align > 0); |
3433 | 466 | if (size == 0) { |
3434 | 0 | size = align; |
3435 | 0 | } |
3436 | | |
3437 | 466 | return qemu_try_memalign(align, size); |
3438 | 466 | } |
3439 | | |
3440 | | void *qemu_try_blockalign0(BlockDriverState *bs, size_t size) |
3441 | 466 | { |
3442 | 466 | void *mem = qemu_try_blockalign(bs, size); |
3443 | 466 | IO_CODE(); |
3444 | | |
3445 | 466 | if (mem) { |
3446 | 466 | memset(mem, 0, size); |
3447 | 466 | } |
3448 | | |
3449 | 466 | return mem; |
3450 | 466 | } |
3451 | | |
3452 | | /* Helper that undoes bdrv_register_buf() when it fails partway through */ |
3453 | | static void GRAPH_RDLOCK |
3454 | | bdrv_register_buf_rollback(BlockDriverState *bs, void *host, size_t size, |
3455 | | BdrvChild *final_child) |
3456 | 0 | { |
3457 | 0 | BdrvChild *child; |
3458 | |
|
3459 | 0 | GLOBAL_STATE_CODE(); |
3460 | 0 | assert_bdrv_graph_readable(); |
3461 | |
|
3462 | 0 | QLIST_FOREACH(child, &bs->children, next) { |
3463 | 0 | if (child == final_child) { |
3464 | 0 | break; |
3465 | 0 | } |
3466 | | |
3467 | 0 | bdrv_unregister_buf(child->bs, host, size); |
3468 | 0 | } |
3469 | |
|
3470 | 0 | if (bs->drv && bs->drv->bdrv_unregister_buf) { |
3471 | 0 | bs->drv->bdrv_unregister_buf(bs, host, size); |
3472 | 0 | } |
3473 | 0 | } |
3474 | | |
3475 | | bool bdrv_register_buf(BlockDriverState *bs, void *host, size_t size, |
3476 | | Error **errp) |
3477 | 36 | { |
3478 | 36 | BdrvChild *child; |
3479 | | |
3480 | 36 | GLOBAL_STATE_CODE(); |
3481 | 36 | GRAPH_RDLOCK_GUARD_MAINLOOP(); |
3482 | | |
3483 | 36 | if (bs->drv && bs->drv->bdrv_register_buf) { |
3484 | 0 | if (!bs->drv->bdrv_register_buf(bs, host, size, errp)) { |
3485 | 0 | return false; |
3486 | 0 | } |
3487 | 0 | } |
3488 | 36 | QLIST_FOREACH(child, &bs->children, next) { |
3489 | 18 | if (!bdrv_register_buf(child->bs, host, size, errp)) { |
3490 | 0 | bdrv_register_buf_rollback(bs, host, size, child); |
3491 | 0 | return false; |
3492 | 0 | } |
3493 | 18 | } |
3494 | 36 | return true; |
3495 | 36 | } |
3496 | | |
3497 | | void bdrv_unregister_buf(BlockDriverState *bs, void *host, size_t size) |
3498 | 0 | { |
3499 | 0 | BdrvChild *child; |
3500 | |
|
3501 | 0 | GLOBAL_STATE_CODE(); |
3502 | 0 | GRAPH_RDLOCK_GUARD_MAINLOOP(); |
3503 | |
|
3504 | 0 | if (bs->drv && bs->drv->bdrv_unregister_buf) { |
3505 | 0 | bs->drv->bdrv_unregister_buf(bs, host, size); |
3506 | 0 | } |
3507 | 0 | QLIST_FOREACH(child, &bs->children, next) { |
3508 | 0 | bdrv_unregister_buf(child->bs, host, size); |
3509 | 0 | } |
3510 | 0 | } |
3511 | | |
3512 | | static int coroutine_fn GRAPH_RDLOCK bdrv_co_copy_range_internal( |
3513 | | BdrvChild *src, int64_t src_offset, BdrvChild *dst, |
3514 | | int64_t dst_offset, int64_t bytes, |
3515 | | BdrvRequestFlags read_flags, BdrvRequestFlags write_flags, |
3516 | | bool recurse_src) |
3517 | 0 | { |
3518 | 0 | BdrvTrackedRequest req; |
3519 | 0 | int ret; |
3520 | 0 | assert_bdrv_graph_readable(); |
3521 | | |
3522 | | /* TODO We can support BDRV_REQ_NO_FALLBACK here */ |
3523 | 0 | assert(!(read_flags & BDRV_REQ_NO_FALLBACK)); |
3524 | 0 | assert(!(write_flags & BDRV_REQ_NO_FALLBACK)); |
3525 | 0 | assert(!(read_flags & BDRV_REQ_NO_WAIT)); |
3526 | 0 | assert(!(write_flags & BDRV_REQ_NO_WAIT)); |
3527 | |
|
3528 | 0 | if (!dst || !dst->bs || !bdrv_co_is_inserted(dst->bs)) { |
3529 | 0 | return -ENOMEDIUM; |
3530 | 0 | } |
3531 | 0 | ret = bdrv_check_request32(dst_offset, bytes, NULL, 0); |
3532 | 0 | if (ret) { |
3533 | 0 | return ret; |
3534 | 0 | } |
3535 | 0 | if (write_flags & BDRV_REQ_ZERO_WRITE) { |
3536 | 0 | return bdrv_co_pwrite_zeroes(dst, dst_offset, bytes, write_flags); |
3537 | 0 | } |
3538 | | |
3539 | 0 | if (!src || !src->bs || !bdrv_co_is_inserted(src->bs)) { |
3540 | 0 | return -ENOMEDIUM; |
3541 | 0 | } |
3542 | 0 | ret = bdrv_check_request32(src_offset, bytes, NULL, 0); |
3543 | 0 | if (ret) { |
3544 | 0 | return ret; |
3545 | 0 | } |
3546 | | |
3547 | 0 | if (!src->bs->drv->bdrv_co_copy_range_from |
3548 | 0 | || !dst->bs->drv->bdrv_co_copy_range_to |
3549 | 0 | || src->bs->encrypted || dst->bs->encrypted) { |
3550 | 0 | return -ENOTSUP; |
3551 | 0 | } |
3552 | | |
3553 | 0 | if (recurse_src) { |
3554 | 0 | bdrv_inc_in_flight(src->bs); |
3555 | 0 | tracked_request_begin(&req, src->bs, src_offset, bytes, |
3556 | 0 | BDRV_TRACKED_READ); |
3557 | | |
3558 | | /* BDRV_REQ_SERIALISING is only for write operation */ |
3559 | 0 | assert(!(read_flags & BDRV_REQ_SERIALISING)); |
3560 | |
|
3561 | 0 | ret = src->bs->drv->bdrv_co_copy_range_from(src->bs, |
3562 | 0 | src, src_offset, |
3563 | 0 | dst, dst_offset, |
3564 | 0 | bytes, |
3565 | 0 | read_flags, write_flags); |
3566 | |
|
3567 | 0 | tracked_request_end(&req); |
3568 | 0 | bdrv_dec_in_flight(src->bs); |
3569 | 0 | } else { |
3570 | 0 | bdrv_inc_in_flight(dst->bs); |
3571 | 0 | tracked_request_begin(&req, dst->bs, dst_offset, bytes, |
3572 | 0 | BDRV_TRACKED_WRITE); |
3573 | 0 | ret = bdrv_co_write_req_prepare(dst, dst_offset, bytes, &req, |
3574 | 0 | write_flags); |
3575 | 0 | if (!ret) { |
3576 | 0 | ret = dst->bs->drv->bdrv_co_copy_range_to(dst->bs, |
3577 | 0 | src, src_offset, |
3578 | 0 | dst, dst_offset, |
3579 | 0 | bytes, |
3580 | 0 | read_flags, write_flags); |
3581 | 0 | } |
3582 | 0 | bdrv_co_write_req_finish(dst, dst_offset, bytes, &req, ret); |
3583 | 0 | tracked_request_end(&req); |
3584 | 0 | bdrv_dec_in_flight(dst->bs); |
3585 | 0 | } |
3586 | |
|
3587 | 0 | return ret; |
3588 | 0 | } |
3589 | | |
3590 | | /* Copy range from @src to @dst. |
3591 | | * |
3592 | | * See the comment of bdrv_co_copy_range for the parameter and return value |
3593 | | * semantics. */ |
3594 | | int coroutine_fn bdrv_co_copy_range_from(BdrvChild *src, int64_t src_offset, |
3595 | | BdrvChild *dst, int64_t dst_offset, |
3596 | | int64_t bytes, |
3597 | | BdrvRequestFlags read_flags, |
3598 | | BdrvRequestFlags write_flags) |
3599 | 0 | { |
3600 | 0 | IO_CODE(); |
3601 | 0 | assert_bdrv_graph_readable(); |
3602 | 0 | trace_bdrv_co_copy_range_from(src, src_offset, dst, dst_offset, bytes, |
3603 | 0 | read_flags, write_flags); |
3604 | 0 | return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset, |
3605 | 0 | bytes, read_flags, write_flags, true); |
3606 | 0 | } |
3607 | | |
3608 | | /* Copy range from @src to @dst. |
3609 | | * |
3610 | | * See the comment of bdrv_co_copy_range for the parameter and return value |
3611 | | * semantics. */ |
3612 | | int coroutine_fn bdrv_co_copy_range_to(BdrvChild *src, int64_t src_offset, |
3613 | | BdrvChild *dst, int64_t dst_offset, |
3614 | | int64_t bytes, |
3615 | | BdrvRequestFlags read_flags, |
3616 | | BdrvRequestFlags write_flags) |
3617 | 0 | { |
3618 | 0 | IO_CODE(); |
3619 | 0 | assert_bdrv_graph_readable(); |
3620 | 0 | trace_bdrv_co_copy_range_to(src, src_offset, dst, dst_offset, bytes, |
3621 | 0 | read_flags, write_flags); |
3622 | 0 | return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset, |
3623 | 0 | bytes, read_flags, write_flags, false); |
3624 | 0 | } |
3625 | | |
3626 | | int coroutine_fn bdrv_co_copy_range(BdrvChild *src, int64_t src_offset, |
3627 | | BdrvChild *dst, int64_t dst_offset, |
3628 | | int64_t bytes, BdrvRequestFlags read_flags, |
3629 | | BdrvRequestFlags write_flags) |
3630 | 0 | { |
3631 | 0 | IO_CODE(); |
3632 | 0 | assert_bdrv_graph_readable(); |
3633 | |
|
3634 | 0 | return bdrv_co_copy_range_from(src, src_offset, |
3635 | 0 | dst, dst_offset, |
3636 | 0 | bytes, read_flags, write_flags); |
3637 | 0 | } |
3638 | | |
3639 | | void coroutine_fn bdrv_co_child_notify_resize(BdrvChild *c) |
3640 | 0 | { |
3641 | 0 | IO_CODE(); |
3642 | 0 | assert_bdrv_graph_readable(); |
3643 | |
|
3644 | 0 | if (c->klass->resize) { |
3645 | 0 | c->klass->resize(c); |
3646 | 0 | } |
3647 | 0 | } |
3648 | | |
3649 | | void coroutine_fn bdrv_co_parent_cb_resize(BlockDriverState *bs) |
3650 | 0 | { |
3651 | 0 | BdrvChild *c; |
3652 | |
|
3653 | 0 | IO_CODE(); |
3654 | 0 | assert_bdrv_graph_readable(); |
3655 | |
|
3656 | 0 | QLIST_FOREACH(c, &bs->parents, next_parent) { |
3657 | 0 | bdrv_co_child_notify_resize(c); |
3658 | 0 | } |
3659 | 0 | } |
3660 | | |
3661 | | /** |
3662 | | * Truncate file to 'offset' bytes (needed only for file protocols) |
3663 | | * |
3664 | | * If 'exact' is true, the file must be resized to exactly the given |
3665 | | * 'offset'. Otherwise, it is sufficient for the node to be at least |
3666 | | * 'offset' bytes in length. |
3667 | | */ |
3668 | | int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, |
3669 | | PreallocMode prealloc, BdrvRequestFlags flags, |
3670 | | Error **errp) |
3671 | 0 | { |
3672 | 0 | BlockDriverState *bs = child->bs; |
3673 | 0 | BdrvChild *filtered, *backing; |
3674 | 0 | BlockDriver *drv = bs->drv; |
3675 | 0 | BdrvTrackedRequest req; |
3676 | 0 | int64_t old_size, new_bytes; |
3677 | 0 | int ret; |
3678 | 0 | IO_CODE(); |
3679 | 0 | assert_bdrv_graph_readable(); |
3680 | | |
3681 | | /* if bs->drv == NULL, bs is closed, so there's nothing to do here */ |
3682 | 0 | if (!drv) { |
3683 | 0 | error_setg(errp, "No medium inserted"); |
3684 | 0 | return -ENOMEDIUM; |
3685 | 0 | } |
3686 | 0 | if (offset < 0) { |
3687 | 0 | error_setg(errp, "Image size cannot be negative"); |
3688 | 0 | return -EINVAL; |
3689 | 0 | } |
3690 | | |
3691 | 0 | ret = bdrv_check_request(offset, 0, errp); |
3692 | 0 | if (ret < 0) { |
3693 | 0 | return ret; |
3694 | 0 | } |
3695 | | |
3696 | 0 | old_size = bdrv_co_getlength(bs); |
3697 | 0 | if (old_size < 0) { |
3698 | 0 | error_setg_errno(errp, -old_size, "Failed to get old image size"); |
3699 | 0 | return old_size; |
3700 | 0 | } |
3701 | | |
3702 | 0 | if (bdrv_is_read_only(bs)) { |
3703 | 0 | error_setg(errp, "Image is read-only"); |
3704 | 0 | return -EACCES; |
3705 | 0 | } |
3706 | | |
3707 | 0 | if (offset > old_size) { |
3708 | 0 | new_bytes = offset - old_size; |
3709 | 0 | } else { |
3710 | 0 | new_bytes = 0; |
3711 | 0 | } |
3712 | |
|
3713 | 0 | bdrv_inc_in_flight(bs); |
3714 | 0 | tracked_request_begin(&req, bs, offset - new_bytes, new_bytes, |
3715 | 0 | BDRV_TRACKED_TRUNCATE); |
3716 | | |
3717 | | /* If we are growing the image and potentially using preallocation for the |
3718 | | * new area, we need to make sure that no write requests are made to it |
3719 | | * concurrently or they might be overwritten by preallocation. */ |
3720 | 0 | if (new_bytes) { |
3721 | 0 | bdrv_make_request_serialising(&req, 1); |
3722 | 0 | } |
3723 | 0 | ret = bdrv_co_write_req_prepare(child, offset - new_bytes, new_bytes, &req, |
3724 | 0 | 0); |
3725 | 0 | if (ret < 0) { |
3726 | 0 | error_setg_errno(errp, -ret, |
3727 | 0 | "Failed to prepare request for truncation"); |
3728 | 0 | goto out; |
3729 | 0 | } |
3730 | | |
3731 | 0 | filtered = bdrv_filter_child(bs); |
3732 | 0 | backing = bdrv_cow_child(bs); |
3733 | | |
3734 | | /* |
3735 | | * If the image has a backing file that is large enough that it would |
3736 | | * provide data for the new area, we cannot leave it unallocated because |
3737 | | * then the backing file content would become visible. Instead, zero-fill |
3738 | | * the new area. |
3739 | | * |
3740 | | * Note that if the image has a backing file, but was opened without the |
3741 | | * backing file, taking care of keeping things consistent with that backing |
3742 | | * file is the user's responsibility. |
3743 | | */ |
3744 | 0 | if (new_bytes && backing) { |
3745 | 0 | int64_t backing_len; |
3746 | |
|
3747 | 0 | backing_len = bdrv_co_getlength(backing->bs); |
3748 | 0 | if (backing_len < 0) { |
3749 | 0 | ret = backing_len; |
3750 | 0 | error_setg_errno(errp, -ret, "Could not get backing file size"); |
3751 | 0 | goto out; |
3752 | 0 | } |
3753 | | |
3754 | 0 | if (backing_len > old_size) { |
3755 | 0 | flags |= BDRV_REQ_ZERO_WRITE; |
3756 | 0 | } |
3757 | 0 | } |
3758 | | |
3759 | 0 | if (drv->bdrv_co_truncate) { |
3760 | 0 | if (flags & ~bs->supported_truncate_flags) { |
3761 | 0 | error_setg(errp, "Block driver does not support requested flags"); |
3762 | 0 | ret = -ENOTSUP; |
3763 | 0 | goto out; |
3764 | 0 | } |
3765 | 0 | ret = drv->bdrv_co_truncate(bs, offset, exact, prealloc, flags, errp); |
3766 | 0 | } else if (filtered) { |
3767 | 0 | ret = bdrv_co_truncate(filtered, offset, exact, prealloc, flags, errp); |
3768 | 0 | } else { |
3769 | 0 | error_setg(errp, "Image format driver does not support resize"); |
3770 | 0 | ret = -ENOTSUP; |
3771 | 0 | goto out; |
3772 | 0 | } |
3773 | 0 | if (ret < 0) { |
3774 | 0 | goto out; |
3775 | 0 | } |
3776 | | |
3777 | 0 | ret = bdrv_co_refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS); |
3778 | 0 | if (ret < 0) { |
3779 | 0 | error_setg_errno(errp, -ret, "Could not refresh total sector count"); |
3780 | 0 | } else { |
3781 | 0 | offset = bs->total_sectors * BDRV_SECTOR_SIZE; |
3782 | 0 | } |
3783 | | /* |
3784 | | * It's possible that truncation succeeded but bdrv_refresh_total_sectors |
3785 | | * failed, but the latter doesn't affect how we should finish the request. |
3786 | | * Pass 0 as the last parameter so that dirty bitmaps etc. are handled. |
3787 | | */ |
3788 | 0 | bdrv_co_write_req_finish(child, offset - new_bytes, new_bytes, &req, 0); |
3789 | |
|
3790 | 0 | out: |
3791 | 0 | tracked_request_end(&req); |
3792 | 0 | bdrv_dec_in_flight(bs); |
3793 | |
|
3794 | 0 | return ret; |
3795 | 0 | } |
3796 | | |
3797 | | void bdrv_cancel_in_flight(BlockDriverState *bs) |
3798 | 0 | { |
3799 | 0 | GLOBAL_STATE_CODE(); |
3800 | 0 | GRAPH_RDLOCK_GUARD_MAINLOOP(); |
3801 | |
|
3802 | 0 | if (!bs || !bs->drv) { |
3803 | 0 | return; |
3804 | 0 | } |
3805 | | |
3806 | 0 | if (bs->drv->bdrv_cancel_in_flight) { |
3807 | 0 | bs->drv->bdrv_cancel_in_flight(bs); |
3808 | 0 | } |
3809 | 0 | } |
3810 | | |
3811 | | int coroutine_fn |
3812 | | bdrv_co_preadv_snapshot(BdrvChild *child, int64_t offset, int64_t bytes, |
3813 | | QEMUIOVector *qiov, size_t qiov_offset) |
3814 | 0 | { |
3815 | 0 | BlockDriverState *bs = child->bs; |
3816 | 0 | BlockDriver *drv = bs->drv; |
3817 | 0 | int ret; |
3818 | 0 | IO_CODE(); |
3819 | 0 | assert_bdrv_graph_readable(); |
3820 | |
|
3821 | 0 | if (!drv) { |
3822 | 0 | return -ENOMEDIUM; |
3823 | 0 | } |
3824 | | |
3825 | 0 | if (!drv->bdrv_co_preadv_snapshot) { |
3826 | 0 | return -ENOTSUP; |
3827 | 0 | } |
3828 | | |
3829 | 0 | bdrv_inc_in_flight(bs); |
3830 | 0 | ret = drv->bdrv_co_preadv_snapshot(bs, offset, bytes, qiov, qiov_offset); |
3831 | 0 | bdrv_dec_in_flight(bs); |
3832 | |
|
3833 | 0 | return ret; |
3834 | 0 | } |
3835 | | |
3836 | | int coroutine_fn |
3837 | | bdrv_co_snapshot_block_status(BlockDriverState *bs, unsigned int mode, |
3838 | | int64_t offset, int64_t bytes, |
3839 | | int64_t *pnum, int64_t *map, |
3840 | | BlockDriverState **file) |
3841 | 0 | { |
3842 | 0 | BlockDriver *drv = bs->drv; |
3843 | 0 | int ret; |
3844 | 0 | IO_CODE(); |
3845 | 0 | assert_bdrv_graph_readable(); |
3846 | |
|
3847 | 0 | if (!drv) { |
3848 | 0 | return -ENOMEDIUM; |
3849 | 0 | } |
3850 | | |
3851 | 0 | if (!drv->bdrv_co_snapshot_block_status) { |
3852 | 0 | return -ENOTSUP; |
3853 | 0 | } |
3854 | | |
3855 | 0 | bdrv_inc_in_flight(bs); |
3856 | 0 | ret = drv->bdrv_co_snapshot_block_status(bs, mode, offset, bytes, |
3857 | 0 | pnum, map, file); |
3858 | 0 | bdrv_dec_in_flight(bs); |
3859 | |
|
3860 | 0 | return ret; |
3861 | 0 | } |
3862 | | |
3863 | | int coroutine_fn |
3864 | | bdrv_co_pdiscard_snapshot(BlockDriverState *bs, int64_t offset, int64_t bytes) |
3865 | 0 | { |
3866 | 0 | BlockDriver *drv = bs->drv; |
3867 | 0 | int ret; |
3868 | 0 | IO_CODE(); |
3869 | 0 | assert_bdrv_graph_readable(); |
3870 | |
|
3871 | 0 | if (!drv) { |
3872 | 0 | return -ENOMEDIUM; |
3873 | 0 | } |
3874 | | |
3875 | 0 | if (!drv->bdrv_co_pdiscard_snapshot) { |
3876 | 0 | return -ENOTSUP; |
3877 | 0 | } |
3878 | | |
3879 | 0 | bdrv_inc_in_flight(bs); |
3880 | 0 | ret = drv->bdrv_co_pdiscard_snapshot(bs, offset, bytes); |
3881 | 0 | bdrv_dec_in_flight(bs); |
3882 | |
|
3883 | 0 | return ret; |
3884 | 0 | } |