Line | Count | Source |
1 | | /* |
2 | | * QEMU Block driver for NBD |
3 | | * |
4 | | * Copyright (c) 2019 Virtuozzo International GmbH. |
5 | | * Copyright Red Hat |
6 | | * Copyright (C) 2008 Bull S.A.S. |
7 | | * Author: Laurent Vivier <Laurent.Vivier@bull.net> |
8 | | * |
9 | | * Some parts: |
10 | | * Copyright (C) 2007 Anthony Liguori <anthony@codemonkey.ws> |
11 | | * |
12 | | * Permission is hereby granted, free of charge, to any person obtaining a copy |
13 | | * of this software and associated documentation files (the "Software"), to deal |
14 | | * in the Software without restriction, including without limitation the rights |
15 | | * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
16 | | * copies of the Software, and to permit persons to whom the Software is |
17 | | * furnished to do so, subject to the following conditions: |
18 | | * |
19 | | * The above copyright notice and this permission notice shall be included in |
20 | | * all copies or substantial portions of the Software. |
21 | | * |
22 | | * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
23 | | * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
24 | | * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL |
25 | | * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
26 | | * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
27 | | * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN |
28 | | * THE SOFTWARE. |
29 | | */ |
30 | | |
31 | | #include "qemu/osdep.h" |
32 | | |
33 | | #include "trace.h" |
34 | | #include "qemu/option.h" |
35 | | #include "qemu/cutils.h" |
36 | | #include "qemu/main-loop.h" |
37 | | |
38 | | #include "qapi/qapi-visit-sockets.h" |
39 | | #include "qobject/qstring.h" |
40 | | #include "qapi/clone-visitor.h" |
41 | | |
42 | | #include "block/qdict.h" |
43 | | #include "block/nbd.h" |
44 | | #include "block/block_int.h" |
45 | | #include "block/coroutines.h" |
46 | | |
47 | | #include "qemu/yank.h" |
48 | | |
49 | 0 | #define EN_OPTSTR ":exportname=" |
50 | 0 | #define MAX_NBD_REQUESTS 16 |
51 | | |
52 | 0 | #define COOKIE_TO_INDEX(cookie) ((cookie) - 1) |
53 | 0 | #define INDEX_TO_COOKIE(index) ((index) + 1) |
54 | | |
55 | | typedef struct { |
56 | | Coroutine *coroutine; |
57 | | uint64_t offset; /* original offset of the request */ |
58 | | bool receiving; /* sleeping in the yield in nbd_receive_replies */ |
59 | | } NBDClientRequest; |
60 | | |
61 | | typedef enum NBDClientState { |
62 | | NBD_CLIENT_CONNECTING_WAIT, |
63 | | NBD_CLIENT_CONNECTING_NOWAIT, |
64 | | NBD_CLIENT_CONNECTED, |
65 | | NBD_CLIENT_QUIT |
66 | | } NBDClientState; |
67 | | |
68 | | typedef struct BDRVNBDState { |
69 | | QIOChannel *ioc; /* The current I/O channel */ |
70 | | NBDExportInfo info; |
71 | | |
72 | | /* |
73 | | * Protects state, free_sema, in_flight, requests[].coroutine, |
74 | | * reconnect_delay_timer. |
75 | | */ |
76 | | QemuMutex requests_lock; |
77 | | NBDClientState state; |
78 | | CoQueue free_sema; |
79 | | unsigned in_flight; |
80 | | NBDClientRequest requests[MAX_NBD_REQUESTS]; |
81 | | QEMUTimer *reconnect_delay_timer; |
82 | | |
83 | | /* Protects sending data on the socket. */ |
84 | | CoMutex send_mutex; |
85 | | |
86 | | /* |
87 | | * Protects receiving reply headers from the socket, as well as the |
88 | | * fields reply and requests[].receiving |
89 | | */ |
90 | | CoMutex receive_mutex; |
91 | | NBDReply reply; |
92 | | |
93 | | QEMUTimer *open_timer; |
94 | | |
95 | | BlockDriverState *bs; |
96 | | |
97 | | /* Connection parameters */ |
98 | | uint32_t reconnect_delay; |
99 | | uint32_t open_timeout; |
100 | | SocketAddress *saddr; |
101 | | char *export; |
102 | | char *tlscredsid; |
103 | | QCryptoTLSCreds *tlscreds; |
104 | | char *tlshostname; |
105 | | char *x_dirty_bitmap; |
106 | | bool alloc_depth; |
107 | | |
108 | | NBDClientConnection *conn; |
109 | | } BDRVNBDState; |
110 | | |
111 | | static void nbd_yank(void *opaque); |
112 | | |
113 | | static void nbd_clear_bdrvstate(BlockDriverState *bs) |
114 | 0 | { |
115 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
116 | |
|
117 | 0 | nbd_client_connection_release(s->conn); |
118 | 0 | s->conn = NULL; |
119 | |
|
120 | 0 | yank_unregister_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name)); |
121 | | |
122 | | /* Must not leave timers behind that would access freed data */ |
123 | 0 | assert(!s->reconnect_delay_timer); |
124 | 0 | assert(!s->open_timer); |
125 | |
|
126 | 0 | object_unref(OBJECT(s->tlscreds)); |
127 | 0 | qapi_free_SocketAddress(s->saddr); |
128 | 0 | s->saddr = NULL; |
129 | 0 | g_free(s->export); |
130 | 0 | s->export = NULL; |
131 | 0 | g_free(s->tlscredsid); |
132 | 0 | s->tlscredsid = NULL; |
133 | 0 | g_free(s->tlshostname); |
134 | 0 | s->tlshostname = NULL; |
135 | 0 | g_free(s->x_dirty_bitmap); |
136 | 0 | s->x_dirty_bitmap = NULL; |
137 | 0 | } |
138 | | |
139 | | static NBDClientRequest *nbd_request_by_cookie(BDRVNBDState *s, uint64_t cookie, |
140 | | Error **errp) |
141 | 0 | { |
142 | 0 | uint64_t ind = COOKIE_TO_INDEX(cookie); |
143 | |
|
144 | 0 | if (ind >= MAX_NBD_REQUESTS || !s->requests[ind].coroutine) { |
145 | 0 | error_setg(errp, "unexpected cookie value"); |
146 | 0 | return NULL; |
147 | 0 | } |
148 | | |
149 | 0 | return &s->requests[ind]; |
150 | 0 | } |
151 | | |
152 | | /* Called with s->receive_mutex taken. */ |
153 | | static bool coroutine_fn nbd_recv_coroutine_wake_one(NBDClientRequest *req) |
154 | 0 | { |
155 | 0 | if (req->receiving) { |
156 | 0 | req->receiving = false; |
157 | 0 | aio_co_wake(req->coroutine); |
158 | 0 | return true; |
159 | 0 | } |
160 | | |
161 | 0 | return false; |
162 | 0 | } |
163 | | |
164 | | /* Called with s->receive_mutex taken. */ |
165 | | static void coroutine_fn nbd_recv_coroutines_wake(BDRVNBDState *s) |
166 | 0 | { |
167 | 0 | int i; |
168 | |
|
169 | 0 | for (i = 0; i < MAX_NBD_REQUESTS; i++) { |
170 | 0 | if (nbd_recv_coroutine_wake_one(&s->requests[i])) { |
171 | 0 | return; |
172 | 0 | } |
173 | 0 | } |
174 | 0 | } |
175 | | |
176 | | /* Called with s->requests_lock held. */ |
177 | | static void coroutine_fn nbd_channel_error_locked(BDRVNBDState *s, int ret) |
178 | 0 | { |
179 | 0 | if (s->state == NBD_CLIENT_CONNECTED) { |
180 | 0 | qio_channel_shutdown(s->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); |
181 | 0 | } |
182 | |
|
183 | 0 | if (ret == -EIO) { |
184 | 0 | if (s->state == NBD_CLIENT_CONNECTED) { |
185 | 0 | s->state = s->reconnect_delay ? NBD_CLIENT_CONNECTING_WAIT : |
186 | 0 | NBD_CLIENT_CONNECTING_NOWAIT; |
187 | 0 | } |
188 | 0 | } else { |
189 | 0 | s->state = NBD_CLIENT_QUIT; |
190 | 0 | } |
191 | 0 | } |
192 | | |
193 | | static void coroutine_fn nbd_channel_error(BDRVNBDState *s, int ret) |
194 | 0 | { |
195 | 0 | QEMU_LOCK_GUARD(&s->requests_lock); |
196 | 0 | nbd_channel_error_locked(s, ret); |
197 | 0 | } |
198 | | |
199 | | static void reconnect_delay_timer_del(BDRVNBDState *s) |
200 | 0 | { |
201 | 0 | if (s->reconnect_delay_timer) { |
202 | 0 | timer_free(s->reconnect_delay_timer); |
203 | 0 | s->reconnect_delay_timer = NULL; |
204 | 0 | } |
205 | 0 | } |
206 | | |
207 | | static void reconnect_delay_timer_cb(void *opaque) |
208 | 0 | { |
209 | 0 | BDRVNBDState *s = opaque; |
210 | |
|
211 | 0 | reconnect_delay_timer_del(s); |
212 | 0 | WITH_QEMU_LOCK_GUARD(&s->requests_lock) { |
213 | 0 | if (s->state != NBD_CLIENT_CONNECTING_WAIT) { |
214 | 0 | return; |
215 | 0 | } |
216 | 0 | s->state = NBD_CLIENT_CONNECTING_NOWAIT; |
217 | 0 | } |
218 | 0 | nbd_co_establish_connection_cancel(s->conn); |
219 | 0 | } |
220 | | |
221 | | static void reconnect_delay_timer_init(BDRVNBDState *s, uint64_t expire_time_ns) |
222 | 0 | { |
223 | 0 | assert(!s->reconnect_delay_timer); |
224 | 0 | s->reconnect_delay_timer = aio_timer_new(bdrv_get_aio_context(s->bs), |
225 | 0 | QEMU_CLOCK_REALTIME, |
226 | 0 | SCALE_NS, |
227 | 0 | reconnect_delay_timer_cb, s); |
228 | 0 | timer_mod(s->reconnect_delay_timer, expire_time_ns); |
229 | 0 | } |
230 | | |
231 | | static void nbd_teardown_connection(BlockDriverState *bs) |
232 | 0 | { |
233 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
234 | |
|
235 | 0 | assert(!s->in_flight); |
236 | |
|
237 | 0 | if (s->ioc) { |
238 | 0 | qio_channel_shutdown(s->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); |
239 | 0 | yank_unregister_function(BLOCKDEV_YANK_INSTANCE(s->bs->node_name), |
240 | 0 | nbd_yank, s->bs); |
241 | 0 | object_unref(OBJECT(s->ioc)); |
242 | 0 | s->ioc = NULL; |
243 | 0 | } |
244 | |
|
245 | 0 | WITH_QEMU_LOCK_GUARD(&s->requests_lock) { |
246 | 0 | s->state = NBD_CLIENT_QUIT; |
247 | 0 | } |
248 | 0 | } |
249 | | |
250 | | static void open_timer_del(BDRVNBDState *s) |
251 | 0 | { |
252 | 0 | if (s->open_timer) { |
253 | 0 | timer_free(s->open_timer); |
254 | 0 | s->open_timer = NULL; |
255 | 0 | } |
256 | 0 | } |
257 | | |
258 | | static void open_timer_cb(void *opaque) |
259 | 0 | { |
260 | 0 | BDRVNBDState *s = opaque; |
261 | |
|
262 | 0 | nbd_co_establish_connection_cancel(s->conn); |
263 | 0 | open_timer_del(s); |
264 | 0 | } |
265 | | |
266 | | static void open_timer_init(BDRVNBDState *s, uint64_t expire_time_ns) |
267 | 0 | { |
268 | 0 | assert(!s->open_timer); |
269 | 0 | s->open_timer = aio_timer_new(bdrv_get_aio_context(s->bs), |
270 | 0 | QEMU_CLOCK_REALTIME, |
271 | 0 | SCALE_NS, |
272 | 0 | open_timer_cb, s); |
273 | 0 | timer_mod(s->open_timer, expire_time_ns); |
274 | 0 | } |
275 | | |
276 | | static bool nbd_client_will_reconnect(BDRVNBDState *s) |
277 | 0 | { |
278 | | /* |
279 | | * Called only after a socket error, so this is not performance sensitive. |
280 | | */ |
281 | 0 | QEMU_LOCK_GUARD(&s->requests_lock); |
282 | 0 | return s->state == NBD_CLIENT_CONNECTING_WAIT; |
283 | 0 | } |
284 | | |
285 | | /* |
286 | | * Update @bs with information learned during a completed negotiation process. |
287 | | * Return failure if the server's advertised options are incompatible with the |
288 | | * client's needs. |
289 | | */ |
290 | | static int coroutine_fn GRAPH_RDLOCK |
291 | | nbd_handle_updated_info(BlockDriverState *bs, Error **errp) |
292 | 0 | { |
293 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
294 | 0 | int ret; |
295 | |
|
296 | 0 | if (s->x_dirty_bitmap) { |
297 | 0 | if (!s->info.base_allocation) { |
298 | 0 | error_setg(errp, "requested x-dirty-bitmap %s not found", |
299 | 0 | s->x_dirty_bitmap); |
300 | 0 | return -EINVAL; |
301 | 0 | } |
302 | 0 | if (strcmp(s->x_dirty_bitmap, "qemu:allocation-depth") == 0) { |
303 | 0 | s->alloc_depth = true; |
304 | 0 | } |
305 | 0 | } |
306 | | |
307 | 0 | if (s->info.flags & NBD_FLAG_READ_ONLY) { |
308 | 0 | ret = bdrv_apply_auto_read_only(bs, "NBD export is read-only", errp); |
309 | 0 | if (ret < 0) { |
310 | 0 | return ret; |
311 | 0 | } |
312 | 0 | } |
313 | | |
314 | 0 | if (s->info.flags & NBD_FLAG_SEND_FUA) { |
315 | 0 | bs->supported_write_flags = BDRV_REQ_FUA; |
316 | 0 | bs->supported_zero_flags |= BDRV_REQ_FUA; |
317 | 0 | } |
318 | |
|
319 | 0 | if (s->info.flags & NBD_FLAG_SEND_WRITE_ZEROES) { |
320 | 0 | bs->supported_zero_flags |= BDRV_REQ_MAY_UNMAP; |
321 | 0 | if (s->info.flags & NBD_FLAG_SEND_FAST_ZERO) { |
322 | 0 | bs->supported_zero_flags |= BDRV_REQ_NO_FALLBACK; |
323 | 0 | } |
324 | 0 | } |
325 | |
|
326 | 0 | trace_nbd_client_handshake_success(s->export); |
327 | |
|
328 | 0 | return 0; |
329 | 0 | } |
330 | | |
331 | | int coroutine_fn nbd_co_do_establish_connection(BlockDriverState *bs, |
332 | | bool blocking, Error **errp) |
333 | 0 | { |
334 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
335 | 0 | int ret; |
336 | 0 | IO_CODE(); |
337 | |
|
338 | 0 | assert_bdrv_graph_readable(); |
339 | 0 | assert(!s->ioc); |
340 | |
|
341 | 0 | s->ioc = nbd_co_establish_connection(s->conn, &s->info, blocking, errp); |
342 | 0 | if (!s->ioc) { |
343 | 0 | return -ECONNREFUSED; |
344 | 0 | } |
345 | | |
346 | 0 | yank_register_function(BLOCKDEV_YANK_INSTANCE(s->bs->node_name), nbd_yank, |
347 | 0 | bs); |
348 | |
|
349 | 0 | ret = nbd_handle_updated_info(s->bs, NULL); |
350 | 0 | if (ret < 0) { |
351 | | /* |
352 | | * We have connected, but must fail for other reasons. |
353 | | * Send NBD_CMD_DISC as a courtesy to the server. |
354 | | */ |
355 | 0 | NBDRequest request = { .type = NBD_CMD_DISC, .mode = s->info.mode }; |
356 | |
|
357 | 0 | nbd_send_request(s->ioc, &request); |
358 | |
|
359 | 0 | yank_unregister_function(BLOCKDEV_YANK_INSTANCE(s->bs->node_name), |
360 | 0 | nbd_yank, bs); |
361 | 0 | object_unref(OBJECT(s->ioc)); |
362 | 0 | s->ioc = NULL; |
363 | |
|
364 | 0 | return ret; |
365 | 0 | } |
366 | | |
367 | 0 | if (!qio_channel_set_blocking(s->ioc, false, errp)) { |
368 | 0 | return -EINVAL; |
369 | 0 | } |
370 | 0 | qio_channel_set_follow_coroutine_ctx(s->ioc, true); |
371 | | |
372 | | /* successfully connected */ |
373 | 0 | WITH_QEMU_LOCK_GUARD(&s->requests_lock) { |
374 | 0 | s->state = NBD_CLIENT_CONNECTED; |
375 | 0 | } |
376 | |
|
377 | 0 | return 0; |
378 | 0 | } |
379 | | |
380 | | /* Called with s->requests_lock held. */ |
381 | | static bool nbd_client_connecting(BDRVNBDState *s) |
382 | 0 | { |
383 | 0 | return s->state == NBD_CLIENT_CONNECTING_WAIT || |
384 | 0 | s->state == NBD_CLIENT_CONNECTING_NOWAIT; |
385 | 0 | } |
386 | | |
387 | | /* Called with s->requests_lock taken. */ |
388 | | static void coroutine_fn GRAPH_RDLOCK nbd_reconnect_attempt(BDRVNBDState *s) |
389 | 0 | { |
390 | 0 | int ret; |
391 | 0 | bool blocking = s->state == NBD_CLIENT_CONNECTING_WAIT; |
392 | | |
393 | | /* |
394 | | * Now we are sure that nobody is accessing the channel, and no one will |
395 | | * try until we set the state to CONNECTED. |
396 | | */ |
397 | 0 | assert(nbd_client_connecting(s)); |
398 | 0 | assert(s->in_flight == 1); |
399 | |
|
400 | 0 | trace_nbd_reconnect_attempt(s->bs->in_flight); |
401 | |
|
402 | 0 | if (blocking && !s->reconnect_delay_timer) { |
403 | | /* |
404 | | * It's the first reconnect attempt after switching to |
405 | | * NBD_CLIENT_CONNECTING_WAIT |
406 | | */ |
407 | 0 | g_assert(s->reconnect_delay); |
408 | 0 | reconnect_delay_timer_init(s, |
409 | 0 | qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + |
410 | 0 | s->reconnect_delay * NANOSECONDS_PER_SECOND); |
411 | 0 | } |
412 | | |
413 | | /* Finalize previous connection if any */ |
414 | 0 | if (s->ioc) { |
415 | 0 | yank_unregister_function(BLOCKDEV_YANK_INSTANCE(s->bs->node_name), |
416 | 0 | nbd_yank, s->bs); |
417 | 0 | object_unref(OBJECT(s->ioc)); |
418 | 0 | s->ioc = NULL; |
419 | 0 | } |
420 | |
|
421 | 0 | qemu_mutex_unlock(&s->requests_lock); |
422 | 0 | ret = nbd_co_do_establish_connection(s->bs, blocking, NULL); |
423 | 0 | trace_nbd_reconnect_attempt_result(ret, s->bs->in_flight); |
424 | 0 | qemu_mutex_lock(&s->requests_lock); |
425 | | |
426 | | /* |
427 | | * The reconnect attempt is done (maybe successfully, maybe not), so |
428 | | * we no longer need this timer. Delete it so it will not outlive |
429 | | * this I/O request (so draining removes all timers). |
430 | | */ |
431 | 0 | reconnect_delay_timer_del(s); |
432 | 0 | } |
433 | | |
434 | | static coroutine_fn int nbd_receive_replies(BDRVNBDState *s, uint64_t cookie, |
435 | | Error **errp) |
436 | 0 | { |
437 | 0 | int ret; |
438 | 0 | NBDClientRequest *req = nbd_request_by_cookie(s, cookie, &error_abort); |
439 | 0 | NBDClientRequest *owner; |
440 | 0 | QEMU_LOCK_GUARD(&s->receive_mutex); |
441 | |
|
442 | 0 | while (true) { |
443 | 0 | if (s->reply.cookie == cookie) { |
444 | | /* We are done */ |
445 | 0 | return 0; |
446 | 0 | } |
447 | | |
448 | 0 | if (s->reply.cookie != 0) { |
449 | | /* |
450 | | * Some other request is being handled now. It should already be |
451 | | * woken by whoever set s->reply.cookie (or never wait in this |
452 | | * yield). So, we should not wake it here. |
453 | | */ |
454 | 0 | owner = nbd_request_by_cookie(s, s->reply.cookie, &error_abort); |
455 | 0 | assert(!owner->receiving); |
456 | |
|
457 | 0 | req->receiving = true; |
458 | 0 | qemu_co_mutex_unlock(&s->receive_mutex); |
459 | |
|
460 | 0 | qemu_coroutine_yield(); |
461 | | /* |
462 | | * We may be woken for 2 reasons: |
463 | | * 1. From this function, executing in parallel coroutine, when our |
464 | | * cookie is received. |
465 | | * 2. From nbd_co_receive_one_chunk(), when previous request is |
466 | | * finished and s->reply.cookie set to 0. |
467 | | * Anyway, it's OK to lock the mutex and go to the next iteration. |
468 | | */ |
469 | |
|
470 | 0 | qemu_co_mutex_lock(&s->receive_mutex); |
471 | 0 | assert(!req->receiving); |
472 | 0 | continue; |
473 | 0 | } |
474 | | |
475 | | /* We are under mutex and cookie is 0. We have to do the dirty work. */ |
476 | 0 | assert(s->reply.cookie == 0); |
477 | 0 | ret = nbd_receive_reply(s->bs, s->ioc, &s->reply, s->info.mode, errp); |
478 | 0 | if (ret == 0) { |
479 | 0 | ret = -EIO; |
480 | 0 | error_setg(errp, "server dropped connection"); |
481 | 0 | } |
482 | 0 | if (ret < 0) { |
483 | 0 | goto err; |
484 | 0 | } |
485 | 0 | if (nbd_reply_is_structured(&s->reply) && |
486 | 0 | s->info.mode < NBD_MODE_STRUCTURED) { |
487 | 0 | ret = -EINVAL; |
488 | 0 | error_setg(errp, "unexpected structured reply"); |
489 | 0 | goto err; |
490 | 0 | } |
491 | 0 | owner = nbd_request_by_cookie(s, s->reply.cookie, errp); |
492 | 0 | if (!owner) { |
493 | 0 | ret = -EINVAL; |
494 | 0 | goto err; |
495 | 0 | } |
496 | 0 | if (s->reply.cookie == cookie) { |
497 | | /* We are done */ |
498 | 0 | return 0; |
499 | 0 | } |
500 | 0 | nbd_recv_coroutine_wake_one(owner); |
501 | 0 | } |
502 | | |
503 | 0 | err: |
504 | | /* Waiters look at this cookie, so do not leave a rejected one behind. */ |
505 | 0 | s->reply.cookie = 0; |
506 | 0 | nbd_channel_error(s, ret); |
507 | |
|
508 | 0 | return ret; |
509 | 0 | } |
510 | | |
511 | | static int coroutine_fn GRAPH_RDLOCK |
512 | | nbd_co_send_request(BlockDriverState *bs, NBDRequest *request, |
513 | | QEMUIOVector *qiov) |
514 | 0 | { |
515 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
516 | 0 | int rc, i = -1; |
517 | |
|
518 | 0 | qemu_mutex_lock(&s->requests_lock); |
519 | 0 | while (s->in_flight == MAX_NBD_REQUESTS || |
520 | 0 | (s->state != NBD_CLIENT_CONNECTED && s->in_flight > 0)) { |
521 | 0 | qemu_co_queue_wait(&s->free_sema, &s->requests_lock); |
522 | 0 | } |
523 | |
|
524 | 0 | s->in_flight++; |
525 | 0 | if (s->state != NBD_CLIENT_CONNECTED) { |
526 | 0 | if (nbd_client_connecting(s)) { |
527 | 0 | nbd_reconnect_attempt(s); |
528 | 0 | qemu_co_queue_restart_all(&s->free_sema); |
529 | 0 | } |
530 | 0 | if (s->state != NBD_CLIENT_CONNECTED) { |
531 | 0 | rc = -EIO; |
532 | 0 | goto err; |
533 | 0 | } |
534 | 0 | } |
535 | | |
536 | 0 | for (i = 0; i < MAX_NBD_REQUESTS; i++) { |
537 | 0 | if (s->requests[i].coroutine == NULL) { |
538 | 0 | break; |
539 | 0 | } |
540 | 0 | } |
541 | |
|
542 | 0 | assert(i < MAX_NBD_REQUESTS); |
543 | 0 | s->requests[i].coroutine = qemu_coroutine_self(); |
544 | 0 | s->requests[i].offset = request->from; |
545 | 0 | s->requests[i].receiving = false; |
546 | 0 | qemu_mutex_unlock(&s->requests_lock); |
547 | |
|
548 | 0 | qemu_co_mutex_lock(&s->send_mutex); |
549 | 0 | request->cookie = INDEX_TO_COOKIE(i); |
550 | 0 | request->mode = s->info.mode; |
551 | |
|
552 | 0 | assert(s->ioc); |
553 | |
|
554 | 0 | if (qiov) { |
555 | 0 | qio_channel_set_cork(s->ioc, true); |
556 | 0 | rc = nbd_send_request(s->ioc, request); |
557 | 0 | if (rc >= 0 && qio_channel_writev_all(s->ioc, qiov->iov, qiov->niov, |
558 | 0 | NULL) < 0) { |
559 | 0 | rc = -EIO; |
560 | 0 | } |
561 | 0 | qio_channel_set_cork(s->ioc, false); |
562 | 0 | } else { |
563 | 0 | rc = nbd_send_request(s->ioc, request); |
564 | 0 | } |
565 | 0 | qemu_co_mutex_unlock(&s->send_mutex); |
566 | |
|
567 | 0 | if (rc < 0) { |
568 | 0 | qemu_mutex_lock(&s->requests_lock); |
569 | 0 | err: |
570 | 0 | nbd_channel_error_locked(s, rc); |
571 | 0 | if (i != -1) { |
572 | 0 | s->requests[i].coroutine = NULL; |
573 | 0 | } |
574 | 0 | s->in_flight--; |
575 | 0 | qemu_co_queue_next(&s->free_sema); |
576 | 0 | qemu_mutex_unlock(&s->requests_lock); |
577 | 0 | } |
578 | 0 | return rc; |
579 | 0 | } |
580 | | |
581 | | /* Consume a field of payload, while swapping it in place to host-endian. */ |
582 | | static inline uint16_t payload_advance16(uint8_t **payload) |
583 | 0 | { |
584 | 0 | uint16_t value = lduw_be_p(*payload); |
585 | 0 | stw_he_p(*payload, value); |
586 | 0 | *payload += 2; |
587 | 0 | return value; |
588 | 0 | } |
589 | | |
590 | | static inline uint32_t payload_advance32(uint8_t **payload) |
591 | 0 | { |
592 | 0 | uint32_t value = ldl_be_p(*payload); |
593 | 0 | stl_he_p(*payload, value); |
594 | 0 | *payload += 4; |
595 | 0 | return value; |
596 | 0 | } |
597 | | |
598 | | static inline uint64_t payload_advance64(uint8_t **payload) |
599 | 0 | { |
600 | 0 | uint64_t value = ldq_be_p(*payload); |
601 | 0 | stq_he_p(*payload, value); |
602 | 0 | *payload += 8; |
603 | 0 | return value; |
604 | 0 | } |
605 | | |
606 | | /* |
607 | | * nbd_parse_offset_hole_payload: |
608 | | * Parse a chunk for NBD_REPLY_TYPE_OFFSET_HOLE, updating payload in |
609 | | * place to a host-endian description of the region described. |
610 | | */ |
611 | | static int nbd_parse_offset_hole_payload(BDRVNBDState *s, |
612 | | NBDStructuredReplyChunk *chunk, |
613 | | uint8_t *payload, uint64_t orig_offset, |
614 | | QEMUIOVector *qiov, Error **errp) |
615 | 0 | { |
616 | 0 | uint64_t offset; |
617 | 0 | uint32_t hole_size; |
618 | |
|
619 | 0 | if (chunk->length != sizeof(offset) + sizeof(hole_size)) { |
620 | 0 | error_setg(errp, "Protocol error: invalid payload for " |
621 | 0 | "NBD_REPLY_TYPE_OFFSET_HOLE"); |
622 | 0 | return -EINVAL; |
623 | 0 | } |
624 | | |
625 | 0 | offset = payload_advance64(&payload); |
626 | 0 | hole_size = payload_advance32(&payload); |
627 | |
|
628 | 0 | if (!hole_size || offset < orig_offset || hole_size > qiov->size || |
629 | 0 | offset > orig_offset + qiov->size - hole_size) { |
630 | 0 | error_setg(errp, "Protocol error: server sent chunk exceeding requested" |
631 | 0 | " region"); |
632 | 0 | return -EINVAL; |
633 | 0 | } |
634 | 0 | if (s->info.min_block && |
635 | 0 | !QEMU_IS_ALIGNED(hole_size, s->info.min_block)) { |
636 | 0 | trace_nbd_structured_read_compliance("hole"); |
637 | 0 | } |
638 | |
|
639 | 0 | qemu_iovec_memset(qiov, offset - orig_offset, 0, hole_size); |
640 | |
|
641 | 0 | return 0; |
642 | 0 | } |
643 | | |
644 | | /* |
645 | | * nbd_parse_blockstatus_payload |
646 | | * Based on our request, we expect only one extent in reply, for the |
647 | | * base:allocation context. |
648 | | */ |
649 | | static int nbd_parse_blockstatus_payload(BDRVNBDState *s, |
650 | | NBDStructuredReplyChunk *chunk, |
651 | | uint8_t *payload, bool wide, |
652 | | uint64_t orig_length, |
653 | | NBDExtent64 *extent, Error **errp) |
654 | 0 | { |
655 | 0 | uint32_t context_id; |
656 | 0 | uint32_t count; |
657 | 0 | size_t ext_len = wide ? sizeof(*extent) : sizeof(NBDExtent32); |
658 | 0 | size_t pay_len = sizeof(context_id) + wide * sizeof(count) + ext_len; |
659 | | |
660 | | /* The server succeeded, so it must have sent [at least] one extent */ |
661 | 0 | if (chunk->length < pay_len) { |
662 | 0 | error_setg(errp, "Protocol error: invalid payload for " |
663 | 0 | "NBD_REPLY_TYPE_BLOCK_STATUS"); |
664 | 0 | return -EINVAL; |
665 | 0 | } |
666 | | |
667 | 0 | context_id = payload_advance32(&payload); |
668 | 0 | if (s->info.context_id != context_id) { |
669 | 0 | error_setg(errp, "Protocol error: unexpected context id %d for " |
670 | 0 | "NBD_REPLY_TYPE_BLOCK_STATUS, when negotiated context " |
671 | 0 | "id is %d", context_id, |
672 | 0 | s->info.context_id); |
673 | 0 | return -EINVAL; |
674 | 0 | } |
675 | | |
676 | 0 | if (wide) { |
677 | 0 | count = payload_advance32(&payload); |
678 | 0 | extent->length = payload_advance64(&payload); |
679 | 0 | extent->flags = payload_advance64(&payload); |
680 | 0 | } else { |
681 | 0 | count = 0; |
682 | 0 | extent->length = payload_advance32(&payload); |
683 | 0 | extent->flags = payload_advance32(&payload); |
684 | 0 | } |
685 | |
|
686 | 0 | if (extent->length == 0) { |
687 | 0 | error_setg(errp, "Protocol error: server sent status chunk with " |
688 | 0 | "zero length"); |
689 | 0 | return -EINVAL; |
690 | 0 | } |
691 | | |
692 | | /* |
693 | | * A server sending unaligned block status is in violation of the |
694 | | * protocol, but as qemu-nbd 3.1 is such a server (at least for |
695 | | * POSIX files that are not a multiple of 512 bytes, since qemu |
696 | | * rounds files up to 512-byte multiples but lseek(SEEK_HOLE) |
697 | | * still sees an implicit hole beyond the real EOF), it's nicer to |
698 | | * work around the misbehaving server. If the request included |
699 | | * more than the final unaligned block, truncate it back to an |
700 | | * aligned result; if the request was only the final block, round |
701 | | * up to the full block and change the status to fully-allocated |
702 | | * (always a safe status, even if it loses information). |
703 | | */ |
704 | 0 | if (s->info.min_block && !QEMU_IS_ALIGNED(extent->length, |
705 | 0 | s->info.min_block)) { |
706 | 0 | trace_nbd_parse_blockstatus_compliance("extent length is unaligned"); |
707 | 0 | if (extent->length > s->info.min_block) { |
708 | 0 | extent->length = QEMU_ALIGN_DOWN(extent->length, |
709 | 0 | s->info.min_block); |
710 | 0 | } else { |
711 | 0 | extent->length = s->info.min_block; |
712 | 0 | extent->flags = 0; |
713 | 0 | } |
714 | 0 | } |
715 | | |
716 | | /* |
717 | | * We used NBD_CMD_FLAG_REQ_ONE, so the server should not have |
718 | | * sent us any more than one extent, nor should it have included |
719 | | * status beyond our request in that extent. Furthermore, a wide |
720 | | * server should have replied with an accurate count (we left |
721 | | * count at 0 for a narrow server). However, it's easy enough to |
722 | | * ignore the server's noncompliance without killing the |
723 | | * connection; just ignore trailing extents, and clamp things to |
724 | | * the length of our request. |
725 | | */ |
726 | 0 | if (count != wide || chunk->length > pay_len) { |
727 | 0 | trace_nbd_parse_blockstatus_compliance("unexpected extent count"); |
728 | 0 | } |
729 | 0 | if (extent->length > orig_length) { |
730 | 0 | extent->length = orig_length; |
731 | 0 | trace_nbd_parse_blockstatus_compliance("extent length too large"); |
732 | 0 | } |
733 | | |
734 | | /* |
735 | | * HACK: if we are using x-dirty-bitmaps to access |
736 | | * qemu:allocation-depth, treat all depths > 2 the same as 2, |
737 | | * since nbd_client_co_block_status is only expecting the low two |
738 | | * bits to be set. |
739 | | */ |
740 | 0 | if (s->alloc_depth && extent->flags > 2) { |
741 | 0 | extent->flags = 2; |
742 | 0 | } |
743 | |
|
744 | 0 | return 0; |
745 | 0 | } |
746 | | |
747 | | /* |
748 | | * nbd_parse_error_payload |
749 | | * on success @errp contains message describing nbd error reply |
750 | | */ |
751 | | static int nbd_parse_error_payload(NBDStructuredReplyChunk *chunk, |
752 | | uint8_t *payload, int *request_ret, |
753 | | Error **errp) |
754 | 0 | { |
755 | 0 | uint32_t error; |
756 | 0 | uint16_t message_size; |
757 | |
|
758 | 0 | assert(chunk->type & (1 << 15)); |
759 | |
|
760 | 0 | if (chunk->length < sizeof(error) + sizeof(message_size)) { |
761 | 0 | error_setg(errp, |
762 | 0 | "Protocol error: invalid payload for structured error"); |
763 | 0 | return -EINVAL; |
764 | 0 | } |
765 | | |
766 | 0 | error = nbd_errno_to_system_errno(payload_advance32(&payload)); |
767 | 0 | if (error == 0) { |
768 | 0 | error_setg(errp, "Protocol error: server sent structured error chunk " |
769 | 0 | "with error = 0"); |
770 | 0 | return -EINVAL; |
771 | 0 | } |
772 | | |
773 | 0 | *request_ret = -error; |
774 | 0 | message_size = payload_advance16(&payload); |
775 | |
|
776 | 0 | if (message_size > chunk->length - sizeof(error) - sizeof(message_size)) { |
777 | 0 | error_setg(errp, "Protocol error: server sent structured error chunk " |
778 | 0 | "with incorrect message size"); |
779 | 0 | return -EINVAL; |
780 | 0 | } |
781 | | |
782 | | /* TODO: Add a trace point to mention the server complaint */ |
783 | | |
784 | | /* TODO handle ERROR_OFFSET */ |
785 | | |
786 | 0 | return 0; |
787 | 0 | } |
788 | | |
789 | | /* |
790 | | * nbd_co_receive_offset_data_payload: |
791 | | * Helper to nbd_co_do_receive_one_chunk when server replies with |
792 | | * structured reply to NBD_CMD_READ with an OFFSET_DATA chunk. On |
793 | | * success, synthesize an NBDStructuredReadHole into @payload |
794 | | * describing the same region that was populated into @qiov. |
795 | | */ |
796 | | static int coroutine_fn |
797 | | nbd_co_receive_offset_data_payload(BDRVNBDState *s, uint64_t orig_offset, |
798 | | QEMUIOVector *qiov, void **payload, |
799 | | Error **errp) |
800 | 0 | { |
801 | 0 | QEMUIOVector sub_qiov; |
802 | 0 | uint64_t offset; |
803 | 0 | size_t data_size; |
804 | 0 | int ret; |
805 | 0 | NBDStructuredReplyChunk *chunk = &s->reply.structured; |
806 | |
|
807 | 0 | assert(nbd_reply_is_structured(&s->reply)); |
808 | 0 | assert(payload); |
809 | | |
810 | | /* The NBD spec requires at least one byte of payload */ |
811 | 0 | if (chunk->length <= sizeof(offset)) { |
812 | 0 | error_setg(errp, "Protocol error: invalid payload for " |
813 | 0 | "NBD_REPLY_TYPE_OFFSET_DATA"); |
814 | 0 | return -EINVAL; |
815 | 0 | } |
816 | | |
817 | 0 | if (nbd_read64(s->ioc, &offset, "OFFSET_DATA offset", errp) < 0) { |
818 | 0 | return -EIO; |
819 | 0 | } |
820 | | |
821 | 0 | data_size = chunk->length - sizeof(offset); |
822 | 0 | assert(data_size); |
823 | 0 | if (offset < orig_offset || data_size > qiov->size || |
824 | 0 | offset > orig_offset + qiov->size - data_size) { |
825 | 0 | error_setg(errp, "Protocol error: server sent chunk exceeding requested" |
826 | 0 | " region"); |
827 | 0 | return -EINVAL; |
828 | 0 | } |
829 | 0 | if (s->info.min_block && !QEMU_IS_ALIGNED(data_size, s->info.min_block)) { |
830 | 0 | trace_nbd_structured_read_compliance("data"); |
831 | 0 | } |
832 | |
|
833 | 0 | qemu_iovec_init(&sub_qiov, qiov->niov); |
834 | 0 | qemu_iovec_concat(&sub_qiov, qiov, offset - orig_offset, data_size); |
835 | 0 | ret = qio_channel_readv_all(s->ioc, sub_qiov.iov, sub_qiov.niov, errp); |
836 | 0 | qemu_iovec_destroy(&sub_qiov); |
837 | |
|
838 | 0 | if (ret == 0) { |
839 | | /* |
840 | | * Give the caller a struct describing the same region we |
841 | | * populated here, to allow for easier followup accounting |
842 | | * between data and hole reads. |
843 | | */ |
844 | 0 | NBDStructuredReadHole *synth = g_new(NBDStructuredReadHole, 1); |
845 | 0 | synth->offset = offset; |
846 | 0 | synth->length = data_size; |
847 | 0 | *payload = synth; |
848 | 0 | } |
849 | |
|
850 | 0 | return ret < 0 ? -EIO : 0; |
851 | 0 | } |
852 | | |
853 | 0 | #define NBD_MAX_MALLOC_PAYLOAD 1000 |
854 | | static coroutine_fn int nbd_co_receive_structured_payload( |
855 | | BDRVNBDState *s, void **payload, Error **errp) |
856 | 0 | { |
857 | 0 | int ret; |
858 | 0 | uint32_t len; |
859 | |
|
860 | 0 | assert(nbd_reply_is_structured(&s->reply)); |
861 | |
|
862 | 0 | len = s->reply.structured.length; |
863 | |
|
864 | 0 | if (len == 0) { |
865 | 0 | return 0; |
866 | 0 | } |
867 | | |
868 | 0 | if (payload == NULL) { |
869 | 0 | error_setg(errp, "Unexpected structured payload"); |
870 | 0 | return -EINVAL; |
871 | 0 | } |
872 | | |
873 | 0 | if (len > NBD_MAX_MALLOC_PAYLOAD) { |
874 | 0 | error_setg(errp, "Payload too large"); |
875 | 0 | return -EINVAL; |
876 | 0 | } |
877 | | |
878 | 0 | *payload = g_new(char, len); |
879 | 0 | ret = nbd_read(s->ioc, *payload, len, "structured payload", errp); |
880 | 0 | if (ret < 0) { |
881 | 0 | g_free(*payload); |
882 | 0 | *payload = NULL; |
883 | 0 | return ret; |
884 | 0 | } |
885 | | |
886 | 0 | return 0; |
887 | 0 | } |
888 | | |
889 | | /* |
890 | | * nbd_co_do_receive_one_chunk |
891 | | * @qiov is non-NULL for NBD_CMD_READ, NULL for all other commands. |
892 | | * for simple reply: |
893 | | * set request_ret to received reply error |
894 | | * if qiov is not NULL: read data to @qiov |
895 | | * either way, @payload stays NULL |
896 | | * for structured reply chunk: |
897 | | * if error chunk: read chunk payload, set @request_ret, @payload is NULL |
898 | | * else if offset_data chunk and @qiov: read data to @qiov, allocate |
899 | | * @payload as NBDStructuredReadHole describing region just populated |
900 | | * else: read payload to @payload; caller checks size and contents |
901 | | * |
902 | | * If function fails, @errp contains corresponding error message, @payload |
903 | | * is NULL, and the connection with the server is suspect. If it returns 0, |
904 | | * then the transaction succeeded (although @request_ret may be a negative |
905 | | * errno corresponding to the server's error reply), and errp is unchanged. |
906 | | */ |
907 | | static coroutine_fn int nbd_co_do_receive_one_chunk( |
908 | | BDRVNBDState *s, uint64_t cookie, bool only_structured, |
909 | | int *request_ret, QEMUIOVector *qiov, void **payload, Error **errp) |
910 | 0 | { |
911 | 0 | ERRP_GUARD(); |
912 | 0 | int ret; |
913 | 0 | void *local_payload = NULL; |
914 | 0 | NBDStructuredReplyChunk *chunk; |
915 | |
|
916 | 0 | if (payload) { |
917 | 0 | *payload = NULL; |
918 | 0 | } |
919 | 0 | *request_ret = 0; |
920 | |
|
921 | 0 | ret = nbd_receive_replies(s, cookie, errp); |
922 | 0 | if (ret < 0) { |
923 | 0 | error_prepend(errp, "Connection closed: "); |
924 | 0 | return -EIO; |
925 | 0 | } |
926 | 0 | assert(s->ioc); |
927 | |
|
928 | 0 | assert(s->reply.cookie == cookie); |
929 | |
|
930 | 0 | if (nbd_reply_is_simple(&s->reply)) { |
931 | 0 | if (only_structured) { |
932 | 0 | error_setg(errp, "Protocol error: simple reply when structured " |
933 | 0 | "reply chunk was expected"); |
934 | 0 | return -EINVAL; |
935 | 0 | } |
936 | | |
937 | 0 | *request_ret = -nbd_errno_to_system_errno(s->reply.simple.error); |
938 | 0 | if (*request_ret < 0 || !qiov) { |
939 | 0 | return 0; |
940 | 0 | } |
941 | | |
942 | 0 | return qio_channel_readv_all(s->ioc, qiov->iov, qiov->niov, |
943 | 0 | errp) < 0 ? -EIO : 0; |
944 | 0 | } |
945 | | |
946 | | /* handle structured reply chunk */ |
947 | 0 | assert(s->info.mode >= NBD_MODE_STRUCTURED); |
948 | 0 | chunk = &s->reply.structured; |
949 | |
|
950 | 0 | if (chunk->type == NBD_REPLY_TYPE_NONE) { |
951 | 0 | if (!(chunk->flags & NBD_REPLY_FLAG_DONE)) { |
952 | 0 | error_setg(errp, "Protocol error: NBD_REPLY_TYPE_NONE chunk without" |
953 | 0 | " NBD_REPLY_FLAG_DONE flag set"); |
954 | 0 | return -EINVAL; |
955 | 0 | } |
956 | 0 | if (chunk->length) { |
957 | 0 | error_setg(errp, "Protocol error: NBD_REPLY_TYPE_NONE chunk with" |
958 | 0 | " nonzero length"); |
959 | 0 | return -EINVAL; |
960 | 0 | } |
961 | 0 | return 0; |
962 | 0 | } |
963 | | |
964 | 0 | if (chunk->type == NBD_REPLY_TYPE_OFFSET_DATA) { |
965 | 0 | if (!qiov) { |
966 | 0 | error_setg(errp, "Unexpected NBD_REPLY_TYPE_OFFSET_DATA chunk"); |
967 | 0 | return -EINVAL; |
968 | 0 | } |
969 | | |
970 | 0 | return nbd_co_receive_offset_data_payload( |
971 | 0 | s, nbd_request_by_cookie(s, cookie, &error_abort)->offset, |
972 | 0 | qiov, payload, errp); |
973 | 0 | } |
974 | | |
975 | 0 | if (nbd_reply_type_is_error(chunk->type)) { |
976 | 0 | payload = &local_payload; |
977 | 0 | } |
978 | |
|
979 | 0 | ret = nbd_co_receive_structured_payload(s, payload, errp); |
980 | 0 | if (ret < 0) { |
981 | 0 | return ret; |
982 | 0 | } |
983 | | |
984 | 0 | if (nbd_reply_type_is_error(chunk->type)) { |
985 | 0 | ret = nbd_parse_error_payload(chunk, local_payload, request_ret, errp); |
986 | 0 | g_free(local_payload); |
987 | 0 | return ret; |
988 | 0 | } |
989 | | |
990 | 0 | return 0; |
991 | 0 | } |
992 | | |
993 | | /* |
994 | | * nbd_co_receive_one_chunk |
995 | | * Read reply, wake up connection_co and set s->quit if needed. |
996 | | * Return value is a fatal error code or normal nbd reply error code |
997 | | */ |
998 | | static coroutine_fn int nbd_co_receive_one_chunk( |
999 | | BDRVNBDState *s, uint64_t cookie, bool only_structured, |
1000 | | int *request_ret, QEMUIOVector *qiov, NBDReply *reply, void **payload, |
1001 | | Error **errp) |
1002 | 0 | { |
1003 | 0 | int ret = nbd_co_do_receive_one_chunk(s, cookie, only_structured, |
1004 | 0 | request_ret, qiov, payload, errp); |
1005 | |
|
1006 | 0 | if (ret < 0) { |
1007 | 0 | memset(reply, 0, sizeof(*reply)); |
1008 | 0 | nbd_channel_error(s, ret); |
1009 | 0 | } else { |
1010 | | /* For assert at loop start in nbd_connection_entry */ |
1011 | 0 | *reply = s->reply; |
1012 | 0 | } |
1013 | |
|
1014 | 0 | WITH_QEMU_LOCK_GUARD(&s->receive_mutex) { |
1015 | 0 | s->reply.cookie = 0; |
1016 | 0 | nbd_recv_coroutines_wake(s); |
1017 | 0 | } |
1018 | |
|
1019 | 0 | return ret; |
1020 | 0 | } |
1021 | | |
1022 | | typedef struct NBDReplyChunkIter { |
1023 | | int ret; |
1024 | | int request_ret; |
1025 | | Error *err; |
1026 | | bool done, only_structured; |
1027 | | } NBDReplyChunkIter; |
1028 | | |
1029 | | static void nbd_iter_channel_error(NBDReplyChunkIter *iter, |
1030 | | int ret, Error **local_err) |
1031 | 0 | { |
1032 | 0 | assert(local_err && *local_err); |
1033 | 0 | assert(ret < 0); |
1034 | |
|
1035 | 0 | if (!iter->ret) { |
1036 | 0 | iter->ret = ret; |
1037 | 0 | error_propagate(&iter->err, *local_err); |
1038 | 0 | } else { |
1039 | 0 | error_free(*local_err); |
1040 | 0 | } |
1041 | |
|
1042 | 0 | *local_err = NULL; |
1043 | 0 | } |
1044 | | |
1045 | | static void nbd_iter_request_error(NBDReplyChunkIter *iter, int ret) |
1046 | 0 | { |
1047 | 0 | assert(ret < 0); |
1048 | |
|
1049 | 0 | if (!iter->request_ret) { |
1050 | 0 | iter->request_ret = ret; |
1051 | 0 | } |
1052 | 0 | } |
1053 | | |
1054 | | /* |
1055 | | * NBD_FOREACH_REPLY_CHUNK |
1056 | | * The pointer stored in @payload requires g_free() to free it. |
1057 | | */ |
1058 | | #define NBD_FOREACH_REPLY_CHUNK(s, iter, cookie, structured, \ |
1059 | | qiov, reply, payload) \ |
1060 | 0 | for (iter = (NBDReplyChunkIter) { .only_structured = structured }; \ |
1061 | 0 | nbd_reply_chunk_iter_receive(s, &iter, cookie, qiov, reply, payload);) |
1062 | | |
1063 | | /* |
1064 | | * nbd_reply_chunk_iter_receive |
1065 | | * The pointer stored in @payload requires g_free() to free it. |
1066 | | */ |
1067 | | static bool coroutine_fn nbd_reply_chunk_iter_receive(BDRVNBDState *s, |
1068 | | NBDReplyChunkIter *iter, |
1069 | | uint64_t cookie, |
1070 | | QEMUIOVector *qiov, |
1071 | | NBDReply *reply, |
1072 | | void **payload) |
1073 | 0 | { |
1074 | 0 | int ret, request_ret; |
1075 | 0 | NBDReply local_reply; |
1076 | 0 | NBDStructuredReplyChunk *chunk; |
1077 | 0 | Error *local_err = NULL; |
1078 | |
|
1079 | 0 | if (iter->done) { |
1080 | | /* Previous iteration was last. */ |
1081 | 0 | goto break_loop; |
1082 | 0 | } |
1083 | | |
1084 | 0 | if (reply == NULL) { |
1085 | 0 | reply = &local_reply; |
1086 | 0 | } |
1087 | |
|
1088 | 0 | ret = nbd_co_receive_one_chunk(s, cookie, iter->only_structured, |
1089 | 0 | &request_ret, qiov, reply, payload, |
1090 | 0 | &local_err); |
1091 | 0 | if (ret < 0) { |
1092 | 0 | nbd_iter_channel_error(iter, ret, &local_err); |
1093 | 0 | } else if (request_ret < 0) { |
1094 | 0 | nbd_iter_request_error(iter, request_ret); |
1095 | 0 | } |
1096 | | |
1097 | | /* Do not execute the body of NBD_FOREACH_REPLY_CHUNK for simple reply. */ |
1098 | 0 | if (nbd_reply_is_simple(reply) || iter->ret < 0) { |
1099 | 0 | goto break_loop; |
1100 | 0 | } |
1101 | | |
1102 | 0 | chunk = &reply->structured; |
1103 | 0 | iter->only_structured = true; |
1104 | |
|
1105 | 0 | if (chunk->type == NBD_REPLY_TYPE_NONE) { |
1106 | | /* NBD_REPLY_FLAG_DONE is already checked in nbd_co_receive_one_chunk */ |
1107 | 0 | assert(chunk->flags & NBD_REPLY_FLAG_DONE); |
1108 | 0 | goto break_loop; |
1109 | 0 | } |
1110 | | |
1111 | 0 | if (chunk->flags & NBD_REPLY_FLAG_DONE) { |
1112 | | /* This iteration is last. */ |
1113 | 0 | iter->done = true; |
1114 | 0 | } |
1115 | | |
1116 | | /* Execute the loop body */ |
1117 | 0 | return true; |
1118 | | |
1119 | 0 | break_loop: |
1120 | 0 | assert(payload == NULL || *payload == NULL); |
1121 | 0 | qemu_mutex_lock(&s->requests_lock); |
1122 | 0 | nbd_request_by_cookie(s, cookie, &error_abort)->coroutine = NULL; |
1123 | 0 | s->in_flight--; |
1124 | 0 | qemu_co_queue_next(&s->free_sema); |
1125 | 0 | qemu_mutex_unlock(&s->requests_lock); |
1126 | |
|
1127 | 0 | return false; |
1128 | 0 | } |
1129 | | |
1130 | | static int coroutine_fn |
1131 | | nbd_co_receive_return_code(BDRVNBDState *s, uint64_t cookie, |
1132 | | int *request_ret, Error **errp) |
1133 | 0 | { |
1134 | 0 | NBDReplyChunkIter iter; |
1135 | |
|
1136 | 0 | NBD_FOREACH_REPLY_CHUNK(s, iter, cookie, false, NULL, NULL, NULL) { |
1137 | | /* nbd_reply_chunk_iter_receive does all the work */ |
1138 | 0 | } |
1139 | |
|
1140 | 0 | error_propagate(errp, iter.err); |
1141 | 0 | *request_ret = iter.request_ret; |
1142 | 0 | return iter.ret; |
1143 | 0 | } |
1144 | | |
1145 | | static int coroutine_fn |
1146 | | nbd_co_receive_cmdread_reply(BDRVNBDState *s, uint64_t cookie, |
1147 | | uint64_t offset, QEMUIOVector *qiov, |
1148 | | int *request_ret, Error **errp) |
1149 | 0 | { |
1150 | 0 | NBDReplyChunkIter iter; |
1151 | 0 | NBDReply reply; |
1152 | 0 | void *payload = NULL; |
1153 | 0 | Error *local_err = NULL; |
1154 | 0 | uint64_t highwater = offset; |
1155 | |
|
1156 | 0 | NBD_FOREACH_REPLY_CHUNK(s, iter, cookie, |
1157 | 0 | s->info.mode >= NBD_MODE_STRUCTURED, |
1158 | 0 | qiov, &reply, &payload) |
1159 | 0 | { |
1160 | 0 | int ret; |
1161 | 0 | NBDStructuredReplyChunk *chunk = &reply.structured; |
1162 | 0 | NBDStructuredReadHole *slice = NULL; |
1163 | |
|
1164 | 0 | assert(nbd_reply_is_structured(&reply)); |
1165 | |
|
1166 | 0 | switch (chunk->type) { |
1167 | 0 | case NBD_REPLY_TYPE_OFFSET_DATA: |
1168 | | /* |
1169 | | * special cased in nbd_co_receive_one_chunk, data is already |
1170 | | * in qiov, and payload is host-endian offset+length. |
1171 | | */ |
1172 | 0 | slice = payload; |
1173 | 0 | break; |
1174 | 0 | case NBD_REPLY_TYPE_OFFSET_HOLE: |
1175 | 0 | ret = nbd_parse_offset_hole_payload(s, &reply.structured, payload, |
1176 | 0 | offset, qiov, &local_err); |
1177 | 0 | if (ret < 0) { |
1178 | 0 | nbd_channel_error(s, ret); |
1179 | 0 | nbd_iter_channel_error(&iter, ret, &local_err); |
1180 | 0 | } else { |
1181 | | /* Successful parse swapped payload to host-endian. */ |
1182 | 0 | slice = payload; |
1183 | 0 | } |
1184 | 0 | break; |
1185 | 0 | default: |
1186 | 0 | if (!nbd_reply_type_is_error(chunk->type)) { |
1187 | | /* not allowed reply type */ |
1188 | 0 | nbd_channel_error(s, -EINVAL); |
1189 | 0 | error_setg(&local_err, |
1190 | 0 | "Unexpected reply type: %d (%s) for CMD_READ", |
1191 | 0 | chunk->type, nbd_reply_type_lookup(chunk->type)); |
1192 | 0 | nbd_iter_channel_error(&iter, -EINVAL, &local_err); |
1193 | 0 | } |
1194 | 0 | } |
1195 | | |
1196 | | /* Initialize any region skipped by a malicious server. */ |
1197 | 0 | if (slice) { |
1198 | 0 | if (slice->offset > highwater) { |
1199 | 0 | qemu_iovec_memset(qiov, highwater - offset, 0, |
1200 | 0 | slice->offset - highwater); |
1201 | 0 | } |
1202 | 0 | highwater = MAX(highwater, slice->offset + slice->length); |
1203 | 0 | } |
1204 | |
|
1205 | 0 | g_free(payload); |
1206 | 0 | payload = NULL; |
1207 | 0 | } |
1208 | | |
1209 | | /* Initialize any trailing region not touched by server. */ |
1210 | 0 | if (iter.only_structured && iter.ret == 0 && |
1211 | 0 | highwater < offset + qiov->size) { |
1212 | 0 | qemu_iovec_memset(qiov, highwater - offset, 0, |
1213 | 0 | offset + qiov->size - highwater); |
1214 | 0 | } |
1215 | |
|
1216 | 0 | error_propagate(errp, iter.err); |
1217 | 0 | *request_ret = iter.request_ret; |
1218 | 0 | return iter.ret; |
1219 | 0 | } |
1220 | | |
1221 | | static int coroutine_fn |
1222 | | nbd_co_receive_blockstatus_reply(BDRVNBDState *s, uint64_t cookie, |
1223 | | uint64_t length, NBDExtent64 *extent, |
1224 | | int *request_ret, Error **errp) |
1225 | 0 | { |
1226 | 0 | NBDReplyChunkIter iter; |
1227 | 0 | NBDReply reply; |
1228 | 0 | void *payload = NULL; |
1229 | 0 | Error *local_err = NULL; |
1230 | 0 | bool received = false; |
1231 | |
|
1232 | 0 | assert(!extent->length); |
1233 | 0 | NBD_FOREACH_REPLY_CHUNK(s, iter, cookie, false, NULL, &reply, &payload) { |
1234 | 0 | int ret; |
1235 | 0 | NBDStructuredReplyChunk *chunk = &reply.structured; |
1236 | 0 | bool wide; |
1237 | |
|
1238 | 0 | assert(nbd_reply_is_structured(&reply)); |
1239 | |
|
1240 | 0 | switch (chunk->type) { |
1241 | 0 | case NBD_REPLY_TYPE_BLOCK_STATUS_EXT: |
1242 | 0 | case NBD_REPLY_TYPE_BLOCK_STATUS: |
1243 | 0 | wide = chunk->type == NBD_REPLY_TYPE_BLOCK_STATUS_EXT; |
1244 | 0 | if ((s->info.mode >= NBD_MODE_EXTENDED) != wide) { |
1245 | 0 | trace_nbd_extended_headers_compliance("block_status"); |
1246 | 0 | } |
1247 | 0 | if (received) { |
1248 | 0 | nbd_channel_error(s, -EINVAL); |
1249 | 0 | error_setg(&local_err, "Several BLOCK_STATUS chunks in reply"); |
1250 | 0 | nbd_iter_channel_error(&iter, -EINVAL, &local_err); |
1251 | 0 | } |
1252 | 0 | received = true; |
1253 | |
|
1254 | 0 | ret = nbd_parse_blockstatus_payload( |
1255 | 0 | s, &reply.structured, payload, wide, |
1256 | 0 | length, extent, &local_err); |
1257 | 0 | if (ret < 0) { |
1258 | 0 | nbd_channel_error(s, ret); |
1259 | 0 | nbd_iter_channel_error(&iter, ret, &local_err); |
1260 | 0 | } |
1261 | 0 | break; |
1262 | 0 | default: |
1263 | 0 | if (!nbd_reply_type_is_error(chunk->type)) { |
1264 | 0 | nbd_channel_error(s, -EINVAL); |
1265 | 0 | error_setg(&local_err, |
1266 | 0 | "Unexpected reply type: %d (%s) " |
1267 | 0 | "for CMD_BLOCK_STATUS", |
1268 | 0 | chunk->type, nbd_reply_type_lookup(chunk->type)); |
1269 | 0 | nbd_iter_channel_error(&iter, -EINVAL, &local_err); |
1270 | 0 | } |
1271 | 0 | } |
1272 | | |
1273 | 0 | g_free(payload); |
1274 | 0 | payload = NULL; |
1275 | 0 | } |
1276 | | |
1277 | 0 | if (!extent->length && !iter.request_ret) { |
1278 | 0 | error_setg(&local_err, "Server did not reply with any status extents"); |
1279 | 0 | nbd_iter_channel_error(&iter, -EIO, &local_err); |
1280 | 0 | } |
1281 | |
|
1282 | 0 | error_propagate(errp, iter.err); |
1283 | 0 | *request_ret = iter.request_ret; |
1284 | 0 | return iter.ret; |
1285 | 0 | } |
1286 | | |
1287 | | static int coroutine_fn GRAPH_RDLOCK |
1288 | | nbd_co_request(BlockDriverState *bs, NBDRequest *request, |
1289 | | QEMUIOVector *write_qiov) |
1290 | 0 | { |
1291 | 0 | int ret, request_ret; |
1292 | 0 | Error *local_err = NULL; |
1293 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
1294 | |
|
1295 | 0 | assert(request->type != NBD_CMD_READ); |
1296 | 0 | if (write_qiov) { |
1297 | 0 | assert(request->type == NBD_CMD_WRITE); |
1298 | 0 | assert(request->len == iov_size(write_qiov->iov, write_qiov->niov)); |
1299 | 0 | } else { |
1300 | 0 | assert(request->type != NBD_CMD_WRITE); |
1301 | 0 | } |
1302 | |
|
1303 | 0 | do { |
1304 | 0 | ret = nbd_co_send_request(bs, request, write_qiov); |
1305 | 0 | if (ret < 0) { |
1306 | 0 | continue; |
1307 | 0 | } |
1308 | | |
1309 | 0 | ret = nbd_co_receive_return_code(s, request->cookie, |
1310 | 0 | &request_ret, &local_err); |
1311 | 0 | if (local_err) { |
1312 | 0 | trace_nbd_co_request_fail(request->from, request->len, |
1313 | 0 | request->cookie, request->flags, |
1314 | 0 | request->type, |
1315 | 0 | nbd_cmd_lookup(request->type), |
1316 | 0 | ret, error_get_pretty(local_err)); |
1317 | 0 | error_free(local_err); |
1318 | 0 | local_err = NULL; |
1319 | 0 | } |
1320 | 0 | } while (ret < 0 && nbd_client_will_reconnect(s)); |
1321 | |
|
1322 | 0 | return ret ? ret : request_ret; |
1323 | 0 | } |
1324 | | |
1325 | | static int coroutine_fn GRAPH_RDLOCK |
1326 | | nbd_client_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes, |
1327 | | QEMUIOVector *qiov, BdrvRequestFlags flags) |
1328 | 0 | { |
1329 | 0 | int ret, request_ret; |
1330 | 0 | Error *local_err = NULL; |
1331 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
1332 | 0 | NBDRequest request = { |
1333 | 0 | .type = NBD_CMD_READ, |
1334 | 0 | .from = offset, |
1335 | 0 | .len = bytes, |
1336 | 0 | }; |
1337 | |
|
1338 | 0 | assert(bytes <= NBD_MAX_BUFFER_SIZE); |
1339 | |
|
1340 | 0 | if (!bytes) { |
1341 | 0 | return 0; |
1342 | 0 | } |
1343 | | /* |
1344 | | * Work around the fact that the block layer doesn't do |
1345 | | * byte-accurate sizing yet - if the read exceeds the server's |
1346 | | * advertised size because the block layer rounded size up, then |
1347 | | * truncate the request to the server and tail-pad with zero. |
1348 | | */ |
1349 | 0 | if (offset >= s->info.size) { |
1350 | 0 | assert(bytes < BDRV_SECTOR_SIZE); |
1351 | 0 | qemu_iovec_memset(qiov, 0, 0, bytes); |
1352 | 0 | return 0; |
1353 | 0 | } |
1354 | 0 | if (offset + bytes > s->info.size) { |
1355 | 0 | uint64_t slop = offset + bytes - s->info.size; |
1356 | |
|
1357 | 0 | assert(slop < BDRV_SECTOR_SIZE); |
1358 | 0 | qemu_iovec_memset(qiov, bytes - slop, 0, slop); |
1359 | 0 | request.len -= slop; |
1360 | 0 | } |
1361 | |
|
1362 | 0 | do { |
1363 | 0 | ret = nbd_co_send_request(bs, &request, NULL); |
1364 | 0 | if (ret < 0) { |
1365 | 0 | continue; |
1366 | 0 | } |
1367 | | |
1368 | 0 | ret = nbd_co_receive_cmdread_reply(s, request.cookie, offset, qiov, |
1369 | 0 | &request_ret, &local_err); |
1370 | 0 | if (local_err) { |
1371 | 0 | trace_nbd_co_request_fail(request.from, request.len, request.cookie, |
1372 | 0 | request.flags, request.type, |
1373 | 0 | nbd_cmd_lookup(request.type), |
1374 | 0 | ret, error_get_pretty(local_err)); |
1375 | 0 | error_free(local_err); |
1376 | 0 | local_err = NULL; |
1377 | 0 | } |
1378 | 0 | } while (ret < 0 && nbd_client_will_reconnect(s)); |
1379 | |
|
1380 | 0 | return ret ? ret : request_ret; |
1381 | 0 | } |
1382 | | |
1383 | | static int coroutine_fn GRAPH_RDLOCK |
1384 | | nbd_client_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes, |
1385 | | QEMUIOVector *qiov, BdrvRequestFlags flags) |
1386 | 0 | { |
1387 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
1388 | 0 | NBDRequest request = { |
1389 | 0 | .type = NBD_CMD_WRITE, |
1390 | 0 | .from = offset, |
1391 | 0 | .len = bytes, |
1392 | 0 | }; |
1393 | |
|
1394 | 0 | assert(!(s->info.flags & NBD_FLAG_READ_ONLY)); |
1395 | 0 | if (flags & BDRV_REQ_FUA) { |
1396 | 0 | assert(s->info.flags & NBD_FLAG_SEND_FUA); |
1397 | 0 | request.flags |= NBD_CMD_FLAG_FUA; |
1398 | 0 | } |
1399 | |
|
1400 | 0 | assert(bytes <= NBD_MAX_BUFFER_SIZE); |
1401 | |
|
1402 | 0 | if (!bytes) { |
1403 | 0 | return 0; |
1404 | 0 | } |
1405 | 0 | return nbd_co_request(bs, &request, qiov); |
1406 | 0 | } |
1407 | | |
1408 | | static int coroutine_fn GRAPH_RDLOCK |
1409 | | nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int64_t bytes, |
1410 | | BdrvRequestFlags flags) |
1411 | 0 | { |
1412 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
1413 | 0 | NBDRequest request = { |
1414 | 0 | .type = NBD_CMD_WRITE_ZEROES, |
1415 | 0 | .from = offset, |
1416 | 0 | .len = bytes, |
1417 | 0 | }; |
1418 | | |
1419 | | /* rely on max_pwrite_zeroes */ |
1420 | 0 | assert(bytes <= UINT32_MAX || s->info.mode >= NBD_MODE_EXTENDED); |
1421 | |
|
1422 | 0 | assert(!(s->info.flags & NBD_FLAG_READ_ONLY)); |
1423 | 0 | if (!(s->info.flags & NBD_FLAG_SEND_WRITE_ZEROES)) { |
1424 | 0 | return -ENOTSUP; |
1425 | 0 | } |
1426 | | |
1427 | 0 | if (flags & BDRV_REQ_FUA) { |
1428 | 0 | assert(s->info.flags & NBD_FLAG_SEND_FUA); |
1429 | 0 | request.flags |= NBD_CMD_FLAG_FUA; |
1430 | 0 | } |
1431 | 0 | if (!(flags & BDRV_REQ_MAY_UNMAP)) { |
1432 | 0 | request.flags |= NBD_CMD_FLAG_NO_HOLE; |
1433 | 0 | } |
1434 | 0 | if (flags & BDRV_REQ_NO_FALLBACK) { |
1435 | 0 | assert(s->info.flags & NBD_FLAG_SEND_FAST_ZERO); |
1436 | 0 | request.flags |= NBD_CMD_FLAG_FAST_ZERO; |
1437 | 0 | } |
1438 | |
|
1439 | 0 | if (!bytes) { |
1440 | 0 | return 0; |
1441 | 0 | } |
1442 | 0 | return nbd_co_request(bs, &request, NULL); |
1443 | 0 | } |
1444 | | |
1445 | | static int coroutine_fn GRAPH_RDLOCK nbd_client_co_flush(BlockDriverState *bs) |
1446 | 0 | { |
1447 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
1448 | 0 | NBDRequest request = { .type = NBD_CMD_FLUSH }; |
1449 | |
|
1450 | 0 | if (!(s->info.flags & NBD_FLAG_SEND_FLUSH)) { |
1451 | 0 | return 0; |
1452 | 0 | } |
1453 | | |
1454 | 0 | request.from = 0; |
1455 | 0 | request.len = 0; |
1456 | |
|
1457 | 0 | return nbd_co_request(bs, &request, NULL); |
1458 | 0 | } |
1459 | | |
1460 | | static int coroutine_fn GRAPH_RDLOCK |
1461 | | nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes) |
1462 | 0 | { |
1463 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
1464 | 0 | NBDRequest request = { |
1465 | 0 | .type = NBD_CMD_TRIM, |
1466 | 0 | .from = offset, |
1467 | 0 | .len = bytes, |
1468 | 0 | }; |
1469 | | |
1470 | | /* rely on max_pdiscard */ |
1471 | 0 | assert(bytes <= UINT32_MAX || s->info.mode >= NBD_MODE_EXTENDED); |
1472 | |
|
1473 | 0 | assert(!(s->info.flags & NBD_FLAG_READ_ONLY)); |
1474 | 0 | if (!(s->info.flags & NBD_FLAG_SEND_TRIM) || !bytes) { |
1475 | 0 | return 0; |
1476 | 0 | } |
1477 | | |
1478 | 0 | return nbd_co_request(bs, &request, NULL); |
1479 | 0 | } |
1480 | | |
1481 | | static int coroutine_fn GRAPH_RDLOCK nbd_client_co_block_status( |
1482 | | BlockDriverState *bs, unsigned int mode, int64_t offset, |
1483 | | int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file) |
1484 | 0 | { |
1485 | 0 | int ret, request_ret; |
1486 | 0 | NBDExtent64 extent = { 0 }; |
1487 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
1488 | 0 | Error *local_err = NULL; |
1489 | |
|
1490 | 0 | NBDRequest request = { |
1491 | 0 | .type = NBD_CMD_BLOCK_STATUS, |
1492 | 0 | .from = offset, |
1493 | 0 | .len = MIN(bytes, s->info.size - offset), |
1494 | 0 | .flags = NBD_CMD_FLAG_REQ_ONE, |
1495 | 0 | }; |
1496 | |
|
1497 | 0 | if (!s->info.base_allocation) { |
1498 | 0 | *pnum = bytes; |
1499 | 0 | *map = offset; |
1500 | 0 | *file = bs; |
1501 | 0 | return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID; |
1502 | 0 | } |
1503 | 0 | if (s->info.mode < NBD_MODE_EXTENDED) { |
1504 | 0 | request.len = MIN(QEMU_ALIGN_DOWN(INT_MAX, bs->bl.request_alignment), |
1505 | 0 | request.len); |
1506 | 0 | } |
1507 | | |
1508 | | /* |
1509 | | * Work around the fact that the block layer doesn't do |
1510 | | * byte-accurate sizing yet - if the status request exceeds the |
1511 | | * server's advertised size because the block layer rounded size |
1512 | | * up, we truncated the request to the server (above), or are |
1513 | | * called on just the hole. |
1514 | | */ |
1515 | 0 | if (offset >= s->info.size) { |
1516 | 0 | *pnum = bytes; |
1517 | 0 | assert(bytes < BDRV_SECTOR_SIZE); |
1518 | | /* Intentionally don't report offset_valid for the hole */ |
1519 | 0 | return BDRV_BLOCK_ZERO; |
1520 | 0 | } |
1521 | | |
1522 | 0 | if (s->info.min_block) { |
1523 | 0 | assert(QEMU_IS_ALIGNED(request.len, s->info.min_block)); |
1524 | 0 | } |
1525 | 0 | do { |
1526 | 0 | ret = nbd_co_send_request(bs, &request, NULL); |
1527 | 0 | if (ret < 0) { |
1528 | 0 | continue; |
1529 | 0 | } |
1530 | | |
1531 | 0 | ret = nbd_co_receive_blockstatus_reply(s, request.cookie, bytes, |
1532 | 0 | &extent, &request_ret, |
1533 | 0 | &local_err); |
1534 | 0 | if (local_err) { |
1535 | 0 | trace_nbd_co_request_fail(request.from, request.len, request.cookie, |
1536 | 0 | request.flags, request.type, |
1537 | 0 | nbd_cmd_lookup(request.type), |
1538 | 0 | ret, error_get_pretty(local_err)); |
1539 | 0 | error_free(local_err); |
1540 | 0 | local_err = NULL; |
1541 | 0 | } |
1542 | 0 | } while (ret < 0 && nbd_client_will_reconnect(s)); |
1543 | |
|
1544 | 0 | if (ret < 0 || request_ret < 0) { |
1545 | 0 | return ret ? ret : request_ret; |
1546 | 0 | } |
1547 | | |
1548 | 0 | assert(extent.length); |
1549 | 0 | *pnum = extent.length; |
1550 | 0 | *map = offset; |
1551 | 0 | *file = bs; |
1552 | 0 | return (extent.flags & NBD_STATE_HOLE ? 0 : BDRV_BLOCK_DATA) | |
1553 | 0 | (extent.flags & NBD_STATE_ZERO ? BDRV_BLOCK_ZERO : 0) | |
1554 | 0 | BDRV_BLOCK_OFFSET_VALID; |
1555 | 0 | } |
1556 | | |
1557 | | static int nbd_client_reopen_prepare(BDRVReopenState *state, |
1558 | | BlockReopenQueue *queue, Error **errp) |
1559 | 0 | { |
1560 | 0 | BDRVNBDState *s = (BDRVNBDState *)state->bs->opaque; |
1561 | |
|
1562 | 0 | if ((state->flags & BDRV_O_RDWR) && (s->info.flags & NBD_FLAG_READ_ONLY)) { |
1563 | 0 | error_setg(errp, "Can't reopen read-only NBD mount as read/write"); |
1564 | 0 | return -EACCES; |
1565 | 0 | } |
1566 | 0 | return 0; |
1567 | 0 | } |
1568 | | |
1569 | | static void nbd_yank(void *opaque) |
1570 | 0 | { |
1571 | 0 | BlockDriverState *bs = opaque; |
1572 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
1573 | |
|
1574 | 0 | QEMU_LOCK_GUARD(&s->requests_lock); |
1575 | 0 | qio_channel_shutdown(s->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); |
1576 | 0 | s->state = NBD_CLIENT_QUIT; |
1577 | 0 | } |
1578 | | |
1579 | | static void nbd_client_close(BlockDriverState *bs) |
1580 | 0 | { |
1581 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
1582 | 0 | NBDRequest request = { .type = NBD_CMD_DISC, .mode = s->info.mode }; |
1583 | |
|
1584 | 0 | if (s->ioc) { |
1585 | 0 | nbd_send_request(s->ioc, &request); |
1586 | 0 | } |
1587 | |
|
1588 | 0 | nbd_teardown_connection(bs); |
1589 | 0 | } |
1590 | | |
1591 | | |
1592 | | /* |
1593 | | * Parse nbd_open options |
1594 | | */ |
1595 | | |
1596 | | static int nbd_parse_uri(const char *filename, QDict *options) |
1597 | 0 | { |
1598 | 0 | g_autoptr(GUri) uri = g_uri_parse(filename, G_URI_FLAGS_NONE, NULL); |
1599 | 0 | g_autoptr(GHashTable) qp = NULL; |
1600 | 0 | const char *p; |
1601 | 0 | int qp_n; |
1602 | 0 | bool is_unix; |
1603 | 0 | const char *uri_scheme, *uri_query, *uri_server; |
1604 | 0 | int uri_port; |
1605 | |
|
1606 | 0 | if (!uri) { |
1607 | 0 | return -EINVAL; |
1608 | 0 | } |
1609 | | |
1610 | | /* transport */ |
1611 | 0 | uri_scheme = g_uri_get_scheme(uri); |
1612 | 0 | if (!g_strcmp0(uri_scheme, "nbd")) { |
1613 | 0 | is_unix = false; |
1614 | 0 | } else if (!g_strcmp0(uri_scheme, "nbd+tcp")) { |
1615 | 0 | is_unix = false; |
1616 | 0 | } else if (!g_strcmp0(uri_scheme, "nbd+unix")) { |
1617 | 0 | is_unix = true; |
1618 | 0 | } else { |
1619 | 0 | return -EINVAL; |
1620 | 0 | } |
1621 | | |
1622 | 0 | p = g_uri_get_path(uri) ?: ""; |
1623 | 0 | if (p[0] == '/') { |
1624 | 0 | p++; |
1625 | 0 | } |
1626 | 0 | if (p[0]) { |
1627 | 0 | qdict_put_str(options, "export", p); |
1628 | 0 | } |
1629 | |
|
1630 | 0 | uri_query = g_uri_get_query(uri); |
1631 | 0 | if (uri_query) { |
1632 | 0 | qp = g_uri_parse_params(uri_query, -1, "&", G_URI_PARAMS_NONE, NULL); |
1633 | 0 | if (!qp) { |
1634 | 0 | return -EINVAL; |
1635 | 0 | } |
1636 | 0 | qp_n = g_hash_table_size(qp); |
1637 | 0 | if (qp_n > 1 || (is_unix && !qp_n) || (!is_unix && qp_n)) { |
1638 | 0 | return -EINVAL; |
1639 | 0 | } |
1640 | 0 | } |
1641 | | |
1642 | 0 | uri_server = g_uri_get_host(uri); |
1643 | 0 | if (uri_server && !uri_server[0]) { |
1644 | 0 | uri_server = NULL; |
1645 | 0 | } |
1646 | 0 | uri_port = g_uri_get_port(uri); |
1647 | |
|
1648 | 0 | if (is_unix) { |
1649 | | /* nbd+unix:///export?socket=path */ |
1650 | 0 | const char *uri_socket = g_hash_table_lookup(qp, "socket"); |
1651 | 0 | if (uri_server || uri_port != -1 || !uri_socket) { |
1652 | 0 | return -EINVAL; |
1653 | 0 | } |
1654 | 0 | qdict_put_str(options, "server.type", "unix"); |
1655 | 0 | qdict_put_str(options, "server.path", uri_socket); |
1656 | 0 | } else { |
1657 | 0 | char *port_str; |
1658 | | |
1659 | | /* nbd[+tcp]://host[:port]/export */ |
1660 | 0 | if (!uri_server) { |
1661 | 0 | return -EINVAL; |
1662 | 0 | } |
1663 | | |
1664 | 0 | qdict_put_str(options, "server.type", "inet"); |
1665 | 0 | qdict_put_str(options, "server.host", uri_server); |
1666 | |
|
1667 | 0 | port_str = g_strdup_printf("%d", uri_port > 0 ? uri_port |
1668 | 0 | : NBD_DEFAULT_PORT); |
1669 | 0 | qdict_put_str(options, "server.port", port_str); |
1670 | 0 | g_free(port_str); |
1671 | 0 | } |
1672 | | |
1673 | 0 | return 0; |
1674 | 0 | } |
1675 | | |
1676 | | static bool nbd_has_filename_options_conflict(QDict *options, Error **errp) |
1677 | 0 | { |
1678 | 0 | const QDictEntry *e; |
1679 | |
|
1680 | 0 | for (e = qdict_first(options); e; e = qdict_next(options, e)) { |
1681 | 0 | if (!strcmp(e->key, "host") || |
1682 | 0 | !strcmp(e->key, "port") || |
1683 | 0 | !strcmp(e->key, "path") || |
1684 | 0 | !strcmp(e->key, "export") || |
1685 | 0 | strstart(e->key, "server.", NULL)) |
1686 | 0 | { |
1687 | 0 | error_setg(errp, "Option '%s' cannot be used with a file name", |
1688 | 0 | e->key); |
1689 | 0 | return true; |
1690 | 0 | } |
1691 | 0 | } |
1692 | | |
1693 | 0 | return false; |
1694 | 0 | } |
1695 | | |
1696 | | static void nbd_parse_filename(const char *filename, QDict *options, |
1697 | | Error **errp) |
1698 | 0 | { |
1699 | 0 | g_autofree char *file = NULL; |
1700 | 0 | char *export_name; |
1701 | 0 | const char *host_spec; |
1702 | 0 | const char *unixpath; |
1703 | |
|
1704 | 0 | if (nbd_has_filename_options_conflict(options, errp)) { |
1705 | 0 | return; |
1706 | 0 | } |
1707 | | |
1708 | 0 | if (strstr(filename, "://")) { |
1709 | 0 | int ret = nbd_parse_uri(filename, options); |
1710 | 0 | if (ret < 0) { |
1711 | 0 | error_setg(errp, "No valid URL specified"); |
1712 | 0 | } |
1713 | 0 | return; |
1714 | 0 | } |
1715 | | |
1716 | 0 | file = g_strdup(filename); |
1717 | |
|
1718 | 0 | export_name = strstr(file, EN_OPTSTR); |
1719 | 0 | if (export_name) { |
1720 | 0 | if (export_name[strlen(EN_OPTSTR)] == 0) { |
1721 | 0 | return; |
1722 | 0 | } |
1723 | 0 | export_name[0] = 0; /* truncate 'file' */ |
1724 | 0 | export_name += strlen(EN_OPTSTR); |
1725 | |
|
1726 | 0 | qdict_put_str(options, "export", export_name); |
1727 | 0 | } |
1728 | | |
1729 | | /* extract the host_spec - fail if it's not nbd:... */ |
1730 | 0 | if (!strstart(file, "nbd:", &host_spec)) { |
1731 | 0 | error_setg(errp, "File name string for NBD must start with 'nbd:'"); |
1732 | 0 | return; |
1733 | 0 | } |
1734 | | |
1735 | 0 | if (!*host_spec) { |
1736 | 0 | return; |
1737 | 0 | } |
1738 | | |
1739 | | /* are we a UNIX or TCP socket? */ |
1740 | 0 | if (strstart(host_spec, "unix:", &unixpath)) { |
1741 | 0 | qdict_put_str(options, "server.type", "unix"); |
1742 | 0 | qdict_put_str(options, "server.path", unixpath); |
1743 | 0 | } else { |
1744 | 0 | InetSocketAddress *addr = g_new(InetSocketAddress, 1); |
1745 | |
|
1746 | 0 | if (inet_parse(addr, host_spec, errp)) { |
1747 | 0 | goto out_inet; |
1748 | 0 | } |
1749 | | |
1750 | 0 | qdict_put_str(options, "server.type", "inet"); |
1751 | 0 | qdict_put_str(options, "server.host", addr->host); |
1752 | 0 | qdict_put_str(options, "server.port", addr->port); |
1753 | 0 | out_inet: |
1754 | 0 | qapi_free_InetSocketAddress(addr); |
1755 | 0 | } |
1756 | 0 | } |
1757 | | |
1758 | | static bool nbd_process_legacy_socket_options(QDict *output_options, |
1759 | | QemuOpts *legacy_opts, |
1760 | | Error **errp) |
1761 | 0 | { |
1762 | 0 | const char *path = qemu_opt_get(legacy_opts, "path"); |
1763 | 0 | const char *host = qemu_opt_get(legacy_opts, "host"); |
1764 | 0 | const char *port = qemu_opt_get(legacy_opts, "port"); |
1765 | 0 | const QDictEntry *e; |
1766 | |
|
1767 | 0 | if (!path && !host && !port) { |
1768 | 0 | return true; |
1769 | 0 | } |
1770 | | |
1771 | 0 | for (e = qdict_first(output_options); e; e = qdict_next(output_options, e)) |
1772 | 0 | { |
1773 | 0 | if (strstart(e->key, "server.", NULL)) { |
1774 | 0 | error_setg(errp, "Cannot use 'server' and path/host/port at the " |
1775 | 0 | "same time"); |
1776 | 0 | return false; |
1777 | 0 | } |
1778 | 0 | } |
1779 | | |
1780 | 0 | if (path && host) { |
1781 | 0 | error_setg(errp, "path and host may not be used at the same time"); |
1782 | 0 | return false; |
1783 | 0 | } else if (path) { |
1784 | 0 | if (port) { |
1785 | 0 | error_setg(errp, "port may not be used without host"); |
1786 | 0 | return false; |
1787 | 0 | } |
1788 | | |
1789 | 0 | qdict_put_str(output_options, "server.type", "unix"); |
1790 | 0 | qdict_put_str(output_options, "server.path", path); |
1791 | 0 | } else if (host) { |
1792 | 0 | qdict_put_str(output_options, "server.type", "inet"); |
1793 | 0 | qdict_put_str(output_options, "server.host", host); |
1794 | 0 | qdict_put_str(output_options, "server.port", |
1795 | 0 | port ?: stringify(NBD_DEFAULT_PORT)); |
1796 | 0 | } |
1797 | | |
1798 | 0 | return true; |
1799 | 0 | } |
1800 | | |
1801 | | static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options, |
1802 | | Error **errp) |
1803 | 0 | { |
1804 | 0 | SocketAddress *saddr = NULL; |
1805 | 0 | QDict *addr = NULL; |
1806 | 0 | Visitor *iv = NULL; |
1807 | |
|
1808 | 0 | qdict_extract_subqdict(options, &addr, "server."); |
1809 | 0 | if (!qdict_size(addr)) { |
1810 | 0 | error_setg(errp, "NBD server address missing"); |
1811 | 0 | goto done; |
1812 | 0 | } |
1813 | | |
1814 | 0 | iv = qobject_input_visitor_new_flat_confused(addr, errp); |
1815 | 0 | if (!iv) { |
1816 | 0 | goto done; |
1817 | 0 | } |
1818 | | |
1819 | 0 | if (!visit_type_SocketAddress(iv, NULL, &saddr, errp)) { |
1820 | 0 | goto done; |
1821 | 0 | } |
1822 | | |
1823 | 0 | if (socket_address_parse_named_fd(saddr, errp) < 0) { |
1824 | 0 | qapi_free_SocketAddress(saddr); |
1825 | 0 | saddr = NULL; |
1826 | 0 | goto done; |
1827 | 0 | } |
1828 | | |
1829 | 0 | done: |
1830 | 0 | qobject_unref(addr); |
1831 | 0 | visit_free(iv); |
1832 | 0 | return saddr; |
1833 | 0 | } |
1834 | | |
1835 | | static QCryptoTLSCreds *nbd_get_tls_creds(const char *id, Error **errp) |
1836 | 0 | { |
1837 | 0 | Object *obj; |
1838 | 0 | QCryptoTLSCreds *creds; |
1839 | |
|
1840 | 0 | obj = object_resolve_path_component( |
1841 | 0 | object_get_objects_root(), id); |
1842 | 0 | if (!obj) { |
1843 | 0 | error_setg(errp, "No TLS credentials with id '%s'", |
1844 | 0 | id); |
1845 | 0 | return NULL; |
1846 | 0 | } |
1847 | 0 | creds = (QCryptoTLSCreds *) |
1848 | 0 | object_dynamic_cast(obj, TYPE_QCRYPTO_TLS_CREDS); |
1849 | 0 | if (!creds) { |
1850 | 0 | error_setg(errp, "Object with id '%s' is not TLS credentials", |
1851 | 0 | id); |
1852 | 0 | return NULL; |
1853 | 0 | } |
1854 | | |
1855 | 0 | if (!qcrypto_tls_creds_check_endpoint(creds, |
1856 | 0 | QCRYPTO_TLS_CREDS_ENDPOINT_CLIENT, |
1857 | 0 | errp)) { |
1858 | 0 | return NULL; |
1859 | 0 | } |
1860 | 0 | object_ref(obj); |
1861 | 0 | return creds; |
1862 | 0 | } |
1863 | | |
1864 | | |
1865 | | static QemuOptsList nbd_runtime_opts = { |
1866 | | .name = "nbd", |
1867 | | .head = QTAILQ_HEAD_INITIALIZER(nbd_runtime_opts.head), |
1868 | | .desc = { |
1869 | | { |
1870 | | .name = "host", |
1871 | | .type = QEMU_OPT_STRING, |
1872 | | .help = "TCP host to connect to", |
1873 | | }, |
1874 | | { |
1875 | | .name = "port", |
1876 | | .type = QEMU_OPT_STRING, |
1877 | | .help = "TCP port to connect to", |
1878 | | }, |
1879 | | { |
1880 | | .name = "path", |
1881 | | .type = QEMU_OPT_STRING, |
1882 | | .help = "Unix socket path to connect to", |
1883 | | }, |
1884 | | { |
1885 | | .name = "export", |
1886 | | .type = QEMU_OPT_STRING, |
1887 | | .help = "Name of the NBD export to open", |
1888 | | }, |
1889 | | { |
1890 | | .name = "tls-creds", |
1891 | | .type = QEMU_OPT_STRING, |
1892 | | .help = "ID of the TLS credentials to use", |
1893 | | }, |
1894 | | { |
1895 | | .name = "tls-hostname", |
1896 | | .type = QEMU_OPT_STRING, |
1897 | | .help = "Override hostname for validating TLS x509 certificate", |
1898 | | }, |
1899 | | { |
1900 | | .name = "x-dirty-bitmap", |
1901 | | .type = QEMU_OPT_STRING, |
1902 | | .help = "experimental: expose named dirty bitmap in place of " |
1903 | | "block status", |
1904 | | }, |
1905 | | { |
1906 | | .name = "reconnect-delay", |
1907 | | .type = QEMU_OPT_NUMBER, |
1908 | | .help = "On an unexpected disconnect, the nbd client tries to " |
1909 | | "connect again until succeeding or encountering a serious " |
1910 | | "error. During the first @reconnect-delay seconds, all " |
1911 | | "requests are paused and will be rerun on a successful " |
1912 | | "reconnect. After that time, any delayed requests and all " |
1913 | | "future requests before a successful reconnect will " |
1914 | | "immediately fail. Default 0", |
1915 | | }, |
1916 | | { |
1917 | | .name = "open-timeout", |
1918 | | .type = QEMU_OPT_NUMBER, |
1919 | | .help = "In seconds. If zero, the nbd driver tries the connection " |
1920 | | "only once, and fails to open if the connection fails. " |
1921 | | "If non-zero, the nbd driver will repeat connection " |
1922 | | "attempts until successful or until @open-timeout seconds " |
1923 | | "have elapsed. Default 0", |
1924 | | }, |
1925 | | { /* end of list */ } |
1926 | | }, |
1927 | | }; |
1928 | | |
1929 | | static int nbd_process_options(BlockDriverState *bs, QDict *options, |
1930 | | Error **errp) |
1931 | 0 | { |
1932 | 0 | BDRVNBDState *s = bs->opaque; |
1933 | 0 | QemuOpts *opts; |
1934 | 0 | int ret = -EINVAL; |
1935 | |
|
1936 | 0 | opts = qemu_opts_create(&nbd_runtime_opts, NULL, 0, &error_abort); |
1937 | 0 | if (!qemu_opts_absorb_qdict(opts, options, errp)) { |
1938 | 0 | goto error; |
1939 | 0 | } |
1940 | | |
1941 | | /* Translate @host, @port, and @path to a SocketAddress */ |
1942 | 0 | if (!nbd_process_legacy_socket_options(options, opts, errp)) { |
1943 | 0 | goto error; |
1944 | 0 | } |
1945 | | |
1946 | | /* Pop the config into our state object. Exit if invalid. */ |
1947 | 0 | s->saddr = nbd_config(s, options, errp); |
1948 | 0 | if (!s->saddr) { |
1949 | 0 | goto error; |
1950 | 0 | } |
1951 | | |
1952 | 0 | s->export = g_strdup(qemu_opt_get(opts, "export")); |
1953 | 0 | if (s->export && strlen(s->export) > NBD_MAX_STRING_SIZE) { |
1954 | 0 | error_setg(errp, "export name too long to send to server"); |
1955 | 0 | goto error; |
1956 | 0 | } |
1957 | | |
1958 | 0 | s->tlscredsid = g_strdup(qemu_opt_get(opts, "tls-creds")); |
1959 | 0 | if (s->tlscredsid) { |
1960 | 0 | s->tlscreds = nbd_get_tls_creds(s->tlscredsid, errp); |
1961 | 0 | if (!s->tlscreds) { |
1962 | 0 | goto error; |
1963 | 0 | } |
1964 | | |
1965 | 0 | s->tlshostname = g_strdup(qemu_opt_get(opts, "tls-hostname")); |
1966 | 0 | if (!s->tlshostname && |
1967 | 0 | s->saddr->type == SOCKET_ADDRESS_TYPE_INET) { |
1968 | 0 | s->tlshostname = g_strdup(s->saddr->u.inet.host); |
1969 | 0 | } |
1970 | 0 | } |
1971 | | |
1972 | 0 | s->x_dirty_bitmap = g_strdup(qemu_opt_get(opts, "x-dirty-bitmap")); |
1973 | 0 | if (s->x_dirty_bitmap && strlen(s->x_dirty_bitmap) > NBD_MAX_STRING_SIZE) { |
1974 | 0 | error_setg(errp, "x-dirty-bitmap query too long to send to server"); |
1975 | 0 | goto error; |
1976 | 0 | } |
1977 | | |
1978 | 0 | s->reconnect_delay = qemu_opt_get_number(opts, "reconnect-delay", 0); |
1979 | 0 | s->open_timeout = qemu_opt_get_number(opts, "open-timeout", 0); |
1980 | |
|
1981 | 0 | ret = 0; |
1982 | |
|
1983 | 0 | error: |
1984 | 0 | qemu_opts_del(opts); |
1985 | 0 | return ret; |
1986 | 0 | } |
1987 | | |
1988 | | static int nbd_open(BlockDriverState *bs, QDict *options, int flags, |
1989 | | Error **errp) |
1990 | 0 | { |
1991 | 0 | int ret; |
1992 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
1993 | |
|
1994 | 0 | s->bs = bs; |
1995 | 0 | qemu_mutex_init(&s->requests_lock); |
1996 | 0 | qemu_co_queue_init(&s->free_sema); |
1997 | 0 | qemu_co_mutex_init(&s->send_mutex); |
1998 | 0 | qemu_co_mutex_init(&s->receive_mutex); |
1999 | |
|
2000 | 0 | if (!yank_register_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name), errp)) { |
2001 | 0 | return -EEXIST; |
2002 | 0 | } |
2003 | | |
2004 | 0 | ret = nbd_process_options(bs, options, errp); |
2005 | 0 | if (ret < 0) { |
2006 | 0 | goto fail; |
2007 | 0 | } |
2008 | | |
2009 | 0 | s->conn = nbd_client_connection_new(s->saddr, true, s->export, |
2010 | 0 | s->x_dirty_bitmap, s->tlscreds, |
2011 | 0 | s->tlshostname); |
2012 | |
|
2013 | 0 | if (s->open_timeout) { |
2014 | 0 | nbd_client_connection_enable_retry(s->conn); |
2015 | 0 | open_timer_init(s, qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + |
2016 | 0 | s->open_timeout * NANOSECONDS_PER_SECOND); |
2017 | 0 | } |
2018 | |
|
2019 | 0 | s->state = NBD_CLIENT_CONNECTING_WAIT; |
2020 | 0 | ret = nbd_do_establish_connection(bs, true, errp); |
2021 | 0 | if (ret < 0) { |
2022 | 0 | goto fail; |
2023 | 0 | } |
2024 | | |
2025 | | /* |
2026 | | * The connect attempt is done, so we no longer need this timer. |
2027 | | * Delete it, because we do not want it to be around when this node |
2028 | | * is drained or closed. |
2029 | | */ |
2030 | 0 | open_timer_del(s); |
2031 | |
|
2032 | 0 | nbd_client_connection_enable_retry(s->conn); |
2033 | |
|
2034 | 0 | return 0; |
2035 | | |
2036 | 0 | fail: |
2037 | 0 | open_timer_del(s); |
2038 | 0 | nbd_clear_bdrvstate(bs); |
2039 | 0 | return ret; |
2040 | 0 | } |
2041 | | |
2042 | | static void nbd_refresh_limits(BlockDriverState *bs, Error **errp) |
2043 | 0 | { |
2044 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
2045 | 0 | uint32_t min = s->info.min_block; |
2046 | 0 | uint32_t max = MIN_NON_ZERO(NBD_MAX_BUFFER_SIZE, s->info.max_block); |
2047 | | |
2048 | | /* |
2049 | | * If the server did not advertise an alignment: |
2050 | | * - a size that is not sector-aligned implies that an alignment |
2051 | | * of 1 can be used to access those tail bytes |
2052 | | * - advertisement of block status requires an alignment of 1, so |
2053 | | * that we don't violate block layer constraints that block |
2054 | | * status is always aligned (as we can't control whether the |
2055 | | * server will report sub-sector extents, such as a hole at EOF |
2056 | | * on an unaligned POSIX file) |
2057 | | * - otherwise, assume the server is so old that we are safer avoiding |
2058 | | * sub-sector requests |
2059 | | */ |
2060 | 0 | if (!min) { |
2061 | 0 | min = (!QEMU_IS_ALIGNED(s->info.size, BDRV_SECTOR_SIZE) || |
2062 | 0 | s->info.base_allocation) ? 1 : BDRV_SECTOR_SIZE; |
2063 | 0 | } |
2064 | |
|
2065 | 0 | bs->bl.request_alignment = min; |
2066 | 0 | bs->bl.max_pdiscard = QEMU_ALIGN_DOWN(INT_MAX, min); |
2067 | 0 | bs->bl.max_pwrite_zeroes = max; |
2068 | 0 | bs->bl.max_transfer = max; |
2069 | | |
2070 | | /* |
2071 | | * Assume that if the server supports extended headers, it also |
2072 | | * supports unlimited size zero and trim commands. |
2073 | | */ |
2074 | 0 | if (s->info.mode >= NBD_MODE_EXTENDED) { |
2075 | 0 | bs->bl.max_pdiscard = bs->bl.max_pwrite_zeroes = 0; |
2076 | 0 | } |
2077 | |
|
2078 | 0 | if (s->info.opt_block && |
2079 | 0 | s->info.opt_block > bs->bl.opt_transfer) { |
2080 | 0 | bs->bl.opt_transfer = s->info.opt_block; |
2081 | 0 | } |
2082 | 0 | } |
2083 | | |
2084 | | static void nbd_close(BlockDriverState *bs) |
2085 | 0 | { |
2086 | 0 | nbd_client_close(bs); |
2087 | 0 | nbd_clear_bdrvstate(bs); |
2088 | 0 | } |
2089 | | |
2090 | | /* |
2091 | | * NBD cannot truncate, but if the caller asks to truncate to the same size, or |
2092 | | * to a smaller size with exact=false, there is no reason to fail the |
2093 | | * operation. |
2094 | | * |
2095 | | * Preallocation mode is ignored since it does not seems useful to fail when |
2096 | | * we never change anything. |
2097 | | */ |
2098 | | static int coroutine_fn nbd_co_truncate(BlockDriverState *bs, int64_t offset, |
2099 | | bool exact, PreallocMode prealloc, |
2100 | | BdrvRequestFlags flags, Error **errp) |
2101 | 0 | { |
2102 | 0 | BDRVNBDState *s = bs->opaque; |
2103 | |
|
2104 | 0 | if (offset != s->info.size && exact) { |
2105 | 0 | error_setg(errp, "Cannot resize NBD nodes"); |
2106 | 0 | return -ENOTSUP; |
2107 | 0 | } |
2108 | | |
2109 | 0 | if (offset > s->info.size) { |
2110 | 0 | error_setg(errp, "Cannot grow NBD nodes"); |
2111 | 0 | return -EINVAL; |
2112 | 0 | } |
2113 | | |
2114 | 0 | return 0; |
2115 | 0 | } |
2116 | | |
2117 | | static int64_t coroutine_fn nbd_co_getlength(BlockDriverState *bs) |
2118 | 0 | { |
2119 | 0 | BDRVNBDState *s = bs->opaque; |
2120 | |
|
2121 | 0 | return s->info.size; |
2122 | 0 | } |
2123 | | |
2124 | | static void nbd_refresh_filename(BlockDriverState *bs) |
2125 | 0 | { |
2126 | 0 | BDRVNBDState *s = bs->opaque; |
2127 | 0 | const char *host = NULL, *port = NULL, *path = NULL; |
2128 | 0 | size_t len = 0; |
2129 | |
|
2130 | 0 | if (s->saddr->type == SOCKET_ADDRESS_TYPE_INET) { |
2131 | 0 | const InetSocketAddress *inet = &s->saddr->u.inet; |
2132 | 0 | if (!inet->has_ipv4 && !inet->has_ipv6 && !inet->has_to) { |
2133 | 0 | host = inet->host; |
2134 | 0 | port = inet->port; |
2135 | 0 | } |
2136 | 0 | } else if (s->saddr->type == SOCKET_ADDRESS_TYPE_UNIX) { |
2137 | 0 | path = s->saddr->u.q_unix.path; |
2138 | 0 | } /* else can't represent as pseudo-filename */ |
2139 | |
|
2140 | 0 | if (path && s->export) { |
2141 | 0 | len = snprintf(bs->exact_filename, sizeof(bs->exact_filename), |
2142 | 0 | "nbd+unix:///%s?socket=%s", s->export, path); |
2143 | 0 | } else if (path && !s->export) { |
2144 | 0 | len = snprintf(bs->exact_filename, sizeof(bs->exact_filename), |
2145 | 0 | "nbd+unix://?socket=%s", path); |
2146 | 0 | } else if (host && s->export) { |
2147 | 0 | len = snprintf(bs->exact_filename, sizeof(bs->exact_filename), |
2148 | 0 | "nbd://%s:%s/%s", host, port, s->export); |
2149 | 0 | } else if (host && !s->export) { |
2150 | 0 | len = snprintf(bs->exact_filename, sizeof(bs->exact_filename), |
2151 | 0 | "nbd://%s:%s", host, port); |
2152 | 0 | } |
2153 | 0 | if (len >= sizeof(bs->exact_filename)) { |
2154 | | /* Name is too long to represent exactly, so leave it empty. */ |
2155 | 0 | bs->exact_filename[0] = '\0'; |
2156 | 0 | } |
2157 | 0 | } |
2158 | | |
2159 | | static char *nbd_dirname(BlockDriverState *bs, Error **errp) |
2160 | 0 | { |
2161 | | /* The generic bdrv_dirname() implementation is able to work out some |
2162 | | * directory name for NBD nodes, but that would be wrong. So far there is no |
2163 | | * specification for how "export paths" would work, so NBD does not have |
2164 | | * directory names. */ |
2165 | 0 | error_setg(errp, "Cannot generate a base directory for NBD nodes"); |
2166 | 0 | return NULL; |
2167 | 0 | } |
2168 | | |
2169 | | static const char *const nbd_strong_runtime_opts[] = { |
2170 | | "path", |
2171 | | "host", |
2172 | | "port", |
2173 | | "export", |
2174 | | "tls-creds", |
2175 | | "tls-hostname", |
2176 | | "server.", |
2177 | | |
2178 | | NULL |
2179 | | }; |
2180 | | |
2181 | | static void nbd_cancel_in_flight(BlockDriverState *bs) |
2182 | 0 | { |
2183 | 0 | BDRVNBDState *s = (BDRVNBDState *)bs->opaque; |
2184 | |
|
2185 | 0 | reconnect_delay_timer_del(s); |
2186 | |
|
2187 | 0 | qemu_mutex_lock(&s->requests_lock); |
2188 | 0 | if (s->state == NBD_CLIENT_CONNECTING_WAIT) { |
2189 | 0 | s->state = NBD_CLIENT_CONNECTING_NOWAIT; |
2190 | 0 | } |
2191 | 0 | qemu_mutex_unlock(&s->requests_lock); |
2192 | |
|
2193 | 0 | nbd_co_establish_connection_cancel(s->conn); |
2194 | 0 | } |
2195 | | |
2196 | | static void nbd_attach_aio_context(BlockDriverState *bs, |
2197 | | AioContext *new_context) |
2198 | 0 | { |
2199 | 0 | BDRVNBDState *s = bs->opaque; |
2200 | | |
2201 | | /* The open_timer is used only during nbd_open() */ |
2202 | 0 | assert(!s->open_timer); |
2203 | | |
2204 | | /* |
2205 | | * The reconnect_delay_timer is scheduled in I/O paths when the |
2206 | | * connection is lost, to cancel the reconnection attempt after a |
2207 | | * given time. Once this attempt is done (successfully or not), |
2208 | | * nbd_reconnect_attempt() ensures the timer is deleted before the |
2209 | | * respective I/O request is resumed. |
2210 | | * Since the AioContext can only be changed when a node is drained, |
2211 | | * the reconnect_delay_timer cannot be active here. |
2212 | | */ |
2213 | 0 | assert(!s->reconnect_delay_timer); |
2214 | 0 | } |
2215 | | |
2216 | | static void nbd_detach_aio_context(BlockDriverState *bs) |
2217 | 0 | { |
2218 | 0 | BDRVNBDState *s = bs->opaque; |
2219 | |
|
2220 | 0 | assert(!s->open_timer); |
2221 | 0 | assert(!s->reconnect_delay_timer); |
2222 | 0 | } |
2223 | | |
2224 | | static BlockDriver bdrv_nbd = { |
2225 | | .format_name = "nbd", |
2226 | | .protocol_name = "nbd", |
2227 | | .instance_size = sizeof(BDRVNBDState), |
2228 | | .bdrv_parse_filename = nbd_parse_filename, |
2229 | | .bdrv_co_create_opts = bdrv_co_create_opts_simple, |
2230 | | .create_opts = &bdrv_create_opts_simple, |
2231 | | .bdrv_open = nbd_open, |
2232 | | .bdrv_reopen_prepare = nbd_client_reopen_prepare, |
2233 | | .bdrv_co_preadv = nbd_client_co_preadv, |
2234 | | .bdrv_co_pwritev = nbd_client_co_pwritev, |
2235 | | .bdrv_co_pwrite_zeroes = nbd_client_co_pwrite_zeroes, |
2236 | | .bdrv_close = nbd_close, |
2237 | | .bdrv_co_flush_to_os = nbd_client_co_flush, |
2238 | | .bdrv_co_pdiscard = nbd_client_co_pdiscard, |
2239 | | .bdrv_refresh_limits = nbd_refresh_limits, |
2240 | | .bdrv_co_truncate = nbd_co_truncate, |
2241 | | .bdrv_co_getlength = nbd_co_getlength, |
2242 | | .bdrv_refresh_filename = nbd_refresh_filename, |
2243 | | .bdrv_co_block_status = nbd_client_co_block_status, |
2244 | | .bdrv_dirname = nbd_dirname, |
2245 | | .strong_runtime_opts = nbd_strong_runtime_opts, |
2246 | | .bdrv_cancel_in_flight = nbd_cancel_in_flight, |
2247 | | |
2248 | | .bdrv_attach_aio_context = nbd_attach_aio_context, |
2249 | | .bdrv_detach_aio_context = nbd_detach_aio_context, |
2250 | | }; |
2251 | | |
2252 | | static BlockDriver bdrv_nbd_tcp = { |
2253 | | .format_name = "nbd", |
2254 | | .protocol_name = "nbd+tcp", |
2255 | | .instance_size = sizeof(BDRVNBDState), |
2256 | | .bdrv_parse_filename = nbd_parse_filename, |
2257 | | .bdrv_co_create_opts = bdrv_co_create_opts_simple, |
2258 | | .create_opts = &bdrv_create_opts_simple, |
2259 | | .bdrv_open = nbd_open, |
2260 | | .bdrv_reopen_prepare = nbd_client_reopen_prepare, |
2261 | | .bdrv_co_preadv = nbd_client_co_preadv, |
2262 | | .bdrv_co_pwritev = nbd_client_co_pwritev, |
2263 | | .bdrv_co_pwrite_zeroes = nbd_client_co_pwrite_zeroes, |
2264 | | .bdrv_close = nbd_close, |
2265 | | .bdrv_co_flush_to_os = nbd_client_co_flush, |
2266 | | .bdrv_co_pdiscard = nbd_client_co_pdiscard, |
2267 | | .bdrv_refresh_limits = nbd_refresh_limits, |
2268 | | .bdrv_co_truncate = nbd_co_truncate, |
2269 | | .bdrv_co_getlength = nbd_co_getlength, |
2270 | | .bdrv_refresh_filename = nbd_refresh_filename, |
2271 | | .bdrv_co_block_status = nbd_client_co_block_status, |
2272 | | .bdrv_dirname = nbd_dirname, |
2273 | | .strong_runtime_opts = nbd_strong_runtime_opts, |
2274 | | .bdrv_cancel_in_flight = nbd_cancel_in_flight, |
2275 | | |
2276 | | .bdrv_attach_aio_context = nbd_attach_aio_context, |
2277 | | .bdrv_detach_aio_context = nbd_detach_aio_context, |
2278 | | }; |
2279 | | |
2280 | | static BlockDriver bdrv_nbd_unix = { |
2281 | | .format_name = "nbd", |
2282 | | .protocol_name = "nbd+unix", |
2283 | | .instance_size = sizeof(BDRVNBDState), |
2284 | | .bdrv_parse_filename = nbd_parse_filename, |
2285 | | .bdrv_co_create_opts = bdrv_co_create_opts_simple, |
2286 | | .create_opts = &bdrv_create_opts_simple, |
2287 | | .bdrv_open = nbd_open, |
2288 | | .bdrv_reopen_prepare = nbd_client_reopen_prepare, |
2289 | | .bdrv_co_preadv = nbd_client_co_preadv, |
2290 | | .bdrv_co_pwritev = nbd_client_co_pwritev, |
2291 | | .bdrv_co_pwrite_zeroes = nbd_client_co_pwrite_zeroes, |
2292 | | .bdrv_close = nbd_close, |
2293 | | .bdrv_co_flush_to_os = nbd_client_co_flush, |
2294 | | .bdrv_co_pdiscard = nbd_client_co_pdiscard, |
2295 | | .bdrv_refresh_limits = nbd_refresh_limits, |
2296 | | .bdrv_co_truncate = nbd_co_truncate, |
2297 | | .bdrv_co_getlength = nbd_co_getlength, |
2298 | | .bdrv_refresh_filename = nbd_refresh_filename, |
2299 | | .bdrv_co_block_status = nbd_client_co_block_status, |
2300 | | .bdrv_dirname = nbd_dirname, |
2301 | | .strong_runtime_opts = nbd_strong_runtime_opts, |
2302 | | .bdrv_cancel_in_flight = nbd_cancel_in_flight, |
2303 | | |
2304 | | .bdrv_attach_aio_context = nbd_attach_aio_context, |
2305 | | .bdrv_detach_aio_context = nbd_detach_aio_context, |
2306 | | }; |
2307 | | |
2308 | | static void bdrv_nbd_init(void) |
2309 | 63 | { |
2310 | 63 | bdrv_register(&bdrv_nbd); |
2311 | 63 | bdrv_register(&bdrv_nbd_tcp); |
2312 | 63 | bdrv_register(&bdrv_nbd_unix); |
2313 | 63 | } |
2314 | | |
2315 | | block_init(bdrv_nbd_init); |