1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822
|
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright(c) 2018 Intel Corporation
*/
#include <stdlib.h>
#include <string.h>
#include <pthread.h>
#include <sys/time.h>
#include <rte_errno.h>
#include <rte_string_fns.h>
#include "eal_memalloc.h"
#include "eal_memcfg.h"
#include "eal_private.h"
#include "malloc_elem.h"
#include "malloc_mp.h"
#define MP_ACTION_SYNC "mp_malloc_sync"
/**< request sent by primary process to notify of changes in memory map */
#define MP_ACTION_ROLLBACK "mp_malloc_rollback"
/**< request sent by primary process to notify of changes in memory map. this is
* essentially a regular sync request, but we cannot send sync requests while
* another one is in progress, and we might have to - therefore, we do this as
* a separate callback.
*/
#define MP_ACTION_REQUEST "mp_malloc_request"
/**< request sent by secondary process to ask for allocation/deallocation */
#define MP_ACTION_RESPONSE "mp_malloc_response"
/**< response sent to secondary process to indicate result of request */
/* forward declarations */
static int
handle_sync_response(const struct rte_mp_msg *request,
const struct rte_mp_reply *reply);
static int
handle_rollback_response(const struct rte_mp_msg *request,
const struct rte_mp_reply *reply);
#define MP_TIMEOUT_S 5 /**< 5 seconds timeouts */
/* when we're allocating, we need to store some state to ensure that we can
* roll back later
*/
struct primary_alloc_req_state {
struct malloc_heap *heap;
struct rte_memseg **ms;
int ms_len;
struct malloc_elem *elem;
void *map_addr;
size_t map_len;
};
enum req_state {
REQ_STATE_INACTIVE = 0,
REQ_STATE_ACTIVE,
REQ_STATE_COMPLETE
};
struct mp_request {
TAILQ_ENTRY(mp_request) next;
struct malloc_mp_req user_req; /**< contents of request */
pthread_cond_t cond; /**< variable we use to time out on this request */
enum req_state state; /**< indicate status of this request */
struct primary_alloc_req_state alloc_state;
};
/*
* We could've used just a single request, but it may be possible for
* secondaries to timeout earlier than the primary, and send a new request while
* primary is still expecting replies to the old one. Therefore, each new
* request will get assigned a new ID, which is how we will distinguish between
* expected and unexpected messages.
*/
TAILQ_HEAD(mp_request_list, mp_request);
static struct {
struct mp_request_list list;
pthread_mutex_t lock;
} mp_request_list = {
.list = TAILQ_HEAD_INITIALIZER(mp_request_list.list),
.lock = PTHREAD_MUTEX_INITIALIZER
};
/**
* General workflow is the following:
*
* Allocation:
* S: send request to primary
* P: attempt to allocate memory
* if failed, sendmsg failure
* if success, send sync request
* S: if received msg of failure, quit
* if received sync request, synchronize memory map and reply with result
* P: if received sync request result
* if success, sendmsg success
* if failure, roll back allocation and send a rollback request
* S: if received msg of success, quit
* if received rollback request, synchronize memory map and reply with result
* P: if received sync request result
* sendmsg sync request result
* S: if received msg, quit
*
* Aside from timeouts, there are three points where we can quit:
* - if allocation failed straight away
* - if allocation and sync request succeeded
* - if allocation succeeded, sync request failed, allocation rolled back and
* rollback request received (irrespective of whether it succeeded or failed)
*
* Deallocation:
* S: send request to primary
* P: attempt to deallocate memory
* if failed, sendmsg failure
* if success, send sync request
* S: if received msg of failure, quit
* if received sync request, synchronize memory map and reply with result
* P: if received sync request result
* sendmsg sync request result
* S: if received msg, quit
*
* There is no "rollback" from deallocation, as it's safe to have some memory
* mapped in some processes - it's absent from the heap, so it won't get used.
*/
static struct mp_request *
find_request_by_id(uint64_t id)
{
struct mp_request *req;
TAILQ_FOREACH(req, &mp_request_list.list, next) {
if (req->user_req.id == id)
break;
}
return req;
}
/* this ID is, like, totally guaranteed to be absolutely unique. pinky swear. */
static uint64_t
get_unique_id(void)
{
uint64_t id;
do {
id = rte_rand();
} while (find_request_by_id(id) != NULL);
return id;
}
/* secondary will respond to sync requests thusly */
static int
handle_sync(const struct rte_mp_msg *msg, const void *peer)
{
struct rte_mp_msg reply;
const struct malloc_mp_req *req =
(const struct malloc_mp_req *)msg->param;
struct malloc_mp_req *resp =
(struct malloc_mp_req *)reply.param;
int ret;
if (req->t != REQ_TYPE_SYNC) {
EAL_LOG(ERR, "Unexpected request from primary");
return -1;
}
memset(&reply, 0, sizeof(reply));
reply.num_fds = 0;
strlcpy(reply.name, msg->name, sizeof(reply.name));
reply.len_param = sizeof(*resp);
ret = eal_memalloc_sync_with_primary();
resp->t = REQ_TYPE_SYNC;
resp->id = req->id;
resp->result = ret == 0 ? REQ_RESULT_SUCCESS : REQ_RESULT_FAIL;
return rte_mp_reply(&reply, peer);
}
static int
handle_free_request(const struct malloc_mp_req *m)
{
const struct rte_memseg_list *msl;
void *start, *end;
size_t len;
len = m->free_req.len;
start = m->free_req.addr;
end = RTE_PTR_ADD(start, len - 1);
/* check if the requested memory actually exists */
msl = rte_mem_virt2memseg_list(start);
if (msl == NULL) {
EAL_LOG(ERR, "Requested to free unknown memory");
return -1;
}
/* check if end is within the same memory region */
if (rte_mem_virt2memseg_list(end) != msl) {
EAL_LOG(ERR, "Requested to free memory spanning multiple regions");
return -1;
}
/* we're supposed to only free memory that's not external */
if (msl->external) {
EAL_LOG(ERR, "Requested to free external memory");
return -1;
}
/* now that we've validated the request, announce it */
eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
m->free_req.addr, m->free_req.len);
/* now, do the actual freeing */
return malloc_heap_free_pages(m->free_req.addr, m->free_req.len);
}
static int
handle_alloc_request(const struct malloc_mp_req *m,
struct mp_request *req)
{
struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
const struct malloc_req_alloc *ar = &m->alloc_req;
struct malloc_heap *heap;
struct malloc_elem *elem;
struct rte_memseg **ms;
size_t alloc_sz;
int n_segs;
void *map_addr;
/* this is checked by the API, but we need to prevent divide by zero */
if (ar->page_sz == 0 || !rte_is_power_of_2(ar->page_sz)) {
EAL_LOG(ERR, "Attempting to allocate with invalid page size");
return -1;
}
/* heap idx is index into the heap array, not socket ID */
if (ar->malloc_heap_idx >= RTE_MAX_HEAPS) {
EAL_LOG(ERR, "Attempting to allocate from invalid heap");
return -1;
}
heap = &mcfg->malloc_heaps[ar->malloc_heap_idx];
/*
* for allocations, we must only use internal heaps, but since the
* rte_malloc_heap_socket_is_external() is thread-safe and we're already
* read-locked, we'll have to take advantage of the fact that internal
* socket ID's are always lower than RTE_MAX_NUMA_NODES.
*/
if (heap->socket_id >= RTE_MAX_NUMA_NODES) {
EAL_LOG(ERR, "Attempting to allocate from external heap");
return -1;
}
alloc_sz = RTE_ALIGN_CEIL(RTE_ALIGN_CEIL(ar->elt_size, ar->align) +
MALLOC_ELEM_OVERHEAD, ar->page_sz);
n_segs = alloc_sz / ar->page_sz;
/* we can't know in advance how many pages we'll need, so we malloc */
ms = malloc(sizeof(*ms) * n_segs);
if (ms == NULL) {
EAL_LOG(ERR, "Couldn't allocate memory for request state");
return -1;
}
memset(ms, 0, sizeof(*ms) * n_segs);
elem = alloc_pages_on_heap(heap, ar->page_sz, ar->elt_size, ar->socket,
ar->flags, ar->align, ar->bound, ar->contig, ms,
n_segs);
if (elem == NULL)
goto fail;
map_addr = ms[0]->addr;
eal_memalloc_mem_event_notify(RTE_MEM_EVENT_ALLOC, map_addr, alloc_sz);
/* we have succeeded in allocating memory, but we still need to sync
* with other processes. however, since DPDK IPC is single-threaded, we
* send an asynchronous request and exit this callback.
*/
req->alloc_state.ms = ms;
req->alloc_state.ms_len = n_segs;
req->alloc_state.map_addr = map_addr;
req->alloc_state.map_len = alloc_sz;
req->alloc_state.elem = elem;
req->alloc_state.heap = heap;
return 0;
fail:
free(ms);
return -1;
}
/* first stage of primary handling requests from secondary */
static int
handle_request(const struct rte_mp_msg *msg, const void *peer __rte_unused)
{
const struct malloc_mp_req *m =
(const struct malloc_mp_req *)msg->param;
struct mp_request *entry;
int ret;
/* lock access to request */
pthread_mutex_lock(&mp_request_list.lock);
/* make sure it's not a dupe */
entry = find_request_by_id(m->id);
if (entry != NULL) {
EAL_LOG(ERR, "Duplicate request id");
goto fail;
}
entry = malloc(sizeof(*entry));
if (entry == NULL) {
EAL_LOG(ERR, "Unable to allocate memory for request");
goto fail;
}
/* erase all data */
memset(entry, 0, sizeof(*entry));
if (m->t == REQ_TYPE_ALLOC) {
ret = handle_alloc_request(m, entry);
} else if (m->t == REQ_TYPE_FREE) {
ret = handle_free_request(m);
} else {
EAL_LOG(ERR, "Unexpected request from secondary");
goto fail;
}
if (ret != 0) {
struct rte_mp_msg resp_msg;
struct malloc_mp_req *resp =
(struct malloc_mp_req *)resp_msg.param;
/* send failure message straight away */
resp_msg.num_fds = 0;
resp_msg.len_param = sizeof(*resp);
strlcpy(resp_msg.name, MP_ACTION_RESPONSE,
sizeof(resp_msg.name));
resp->t = m->t;
resp->result = REQ_RESULT_FAIL;
resp->id = m->id;
if (rte_mp_sendmsg(&resp_msg)) {
EAL_LOG(ERR, "Couldn't send response");
goto fail;
}
/* we did not modify the request */
free(entry);
} else {
struct rte_mp_msg sr_msg;
struct malloc_mp_req *sr =
(struct malloc_mp_req *)sr_msg.param;
struct timespec ts;
memset(&sr_msg, 0, sizeof(sr_msg));
/* we can do something, so send sync request asynchronously */
sr_msg.num_fds = 0;
sr_msg.len_param = sizeof(*sr);
strlcpy(sr_msg.name, MP_ACTION_SYNC, sizeof(sr_msg.name));
ts.tv_nsec = 0;
ts.tv_sec = MP_TIMEOUT_S;
/* sync requests carry no data */
sr->t = REQ_TYPE_SYNC;
sr->id = m->id;
/* there may be stray timeout still waiting */
do {
ret = rte_mp_request_async(&sr_msg, &ts,
handle_sync_response);
} while (ret != 0 && rte_errno == EEXIST);
if (ret != 0) {
EAL_LOG(ERR, "Couldn't send sync request");
if (m->t == REQ_TYPE_ALLOC)
free(entry->alloc_state.ms);
goto fail;
}
/* mark request as in progress */
memcpy(&entry->user_req, m, sizeof(*m));
entry->state = REQ_STATE_ACTIVE;
TAILQ_INSERT_TAIL(&mp_request_list.list, entry, next);
}
pthread_mutex_unlock(&mp_request_list.lock);
return 0;
fail:
pthread_mutex_unlock(&mp_request_list.lock);
free(entry);
return -1;
}
/* callback for asynchronous sync requests for primary. this will either do a
* sendmsg with results, or trigger rollback request.
*/
static int
handle_sync_response(const struct rte_mp_msg *request,
const struct rte_mp_reply *reply)
{
enum malloc_req_result result;
struct mp_request *entry;
const struct malloc_mp_req *mpreq =
(const struct malloc_mp_req *)request->param;
int i;
/* lock the request */
pthread_mutex_lock(&mp_request_list.lock);
entry = find_request_by_id(mpreq->id);
if (entry == NULL) {
EAL_LOG(ERR, "Wrong request ID");
goto fail;
}
result = REQ_RESULT_SUCCESS;
if (reply->nb_received != reply->nb_sent)
result = REQ_RESULT_FAIL;
for (i = 0; i < reply->nb_received; i++) {
struct malloc_mp_req *resp =
(struct malloc_mp_req *)reply->msgs[i].param;
if (resp->t != REQ_TYPE_SYNC) {
EAL_LOG(ERR, "Unexpected response to sync request");
result = REQ_RESULT_FAIL;
break;
}
if (resp->id != entry->user_req.id) {
EAL_LOG(ERR, "Response to wrong sync request");
result = REQ_RESULT_FAIL;
break;
}
if (resp->result == REQ_RESULT_FAIL) {
result = REQ_RESULT_FAIL;
break;
}
}
if (entry->user_req.t == REQ_TYPE_FREE) {
struct rte_mp_msg msg;
struct malloc_mp_req *resp = (struct malloc_mp_req *)msg.param;
memset(&msg, 0, sizeof(msg));
/* this is a free request, just sendmsg result */
resp->t = REQ_TYPE_FREE;
resp->result = result;
resp->id = entry->user_req.id;
msg.num_fds = 0;
msg.len_param = sizeof(*resp);
strlcpy(msg.name, MP_ACTION_RESPONSE, sizeof(msg.name));
if (rte_mp_sendmsg(&msg))
EAL_LOG(ERR, "Could not send message to secondary process");
TAILQ_REMOVE(&mp_request_list.list, entry, next);
free(entry);
} else if (entry->user_req.t == REQ_TYPE_ALLOC &&
result == REQ_RESULT_SUCCESS) {
struct malloc_heap *heap = entry->alloc_state.heap;
struct rte_mp_msg msg;
struct malloc_mp_req *resp =
(struct malloc_mp_req *)msg.param;
memset(&msg, 0, sizeof(msg));
heap->total_size += entry->alloc_state.map_len;
/* result is success, so just notify secondary about this */
resp->t = REQ_TYPE_ALLOC;
resp->result = result;
resp->id = entry->user_req.id;
msg.num_fds = 0;
msg.len_param = sizeof(*resp);
strlcpy(msg.name, MP_ACTION_RESPONSE, sizeof(msg.name));
if (rte_mp_sendmsg(&msg))
EAL_LOG(ERR, "Could not send message to secondary process");
TAILQ_REMOVE(&mp_request_list.list, entry, next);
free(entry->alloc_state.ms);
free(entry);
} else if (entry->user_req.t == REQ_TYPE_ALLOC &&
result == REQ_RESULT_FAIL) {
struct rte_mp_msg rb_msg;
struct malloc_mp_req *rb =
(struct malloc_mp_req *)rb_msg.param;
struct timespec ts;
struct primary_alloc_req_state *state =
&entry->alloc_state;
int ret;
memset(&rb_msg, 0, sizeof(rb_msg));
/* we've failed to sync, so do a rollback */
eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
state->map_addr, state->map_len);
rollback_expand_heap(state->ms, state->ms_len, state->elem,
state->map_addr, state->map_len);
/* send rollback request */
rb_msg.num_fds = 0;
rb_msg.len_param = sizeof(*rb);
strlcpy(rb_msg.name, MP_ACTION_ROLLBACK, sizeof(rb_msg.name));
ts.tv_nsec = 0;
ts.tv_sec = MP_TIMEOUT_S;
/* sync requests carry no data */
rb->t = REQ_TYPE_SYNC;
rb->id = entry->user_req.id;
/* there may be stray timeout still waiting */
do {
ret = rte_mp_request_async(&rb_msg, &ts,
handle_rollback_response);
} while (ret != 0 && rte_errno == EEXIST);
if (ret != 0) {
EAL_LOG(ERR, "Could not send rollback request to secondary process");
/* we couldn't send rollback request, but that's OK -
* secondary will time out, and memory has been removed
* from heap anyway.
*/
TAILQ_REMOVE(&mp_request_list.list, entry, next);
free(state->ms);
free(entry);
goto fail;
}
} else {
EAL_LOG(ERR, " to sync request of unknown type");
goto fail;
}
pthread_mutex_unlock(&mp_request_list.lock);
return 0;
fail:
pthread_mutex_unlock(&mp_request_list.lock);
return -1;
}
static int
handle_rollback_response(const struct rte_mp_msg *request,
const struct rte_mp_reply *reply __rte_unused)
{
struct rte_mp_msg msg;
struct malloc_mp_req *resp = (struct malloc_mp_req *)msg.param;
const struct malloc_mp_req *mpreq =
(const struct malloc_mp_req *)request->param;
struct mp_request *entry;
/* lock the request */
pthread_mutex_lock(&mp_request_list.lock);
memset(&msg, 0, sizeof(msg));
entry = find_request_by_id(mpreq->id);
if (entry == NULL) {
EAL_LOG(ERR, "Wrong request ID");
goto fail;
}
if (entry->user_req.t != REQ_TYPE_ALLOC) {
EAL_LOG(ERR, "Unexpected active request");
goto fail;
}
/* we don't care if rollback succeeded, request still failed */
resp->t = REQ_TYPE_ALLOC;
resp->result = REQ_RESULT_FAIL;
resp->id = mpreq->id;
msg.num_fds = 0;
msg.len_param = sizeof(*resp);
strlcpy(msg.name, MP_ACTION_RESPONSE, sizeof(msg.name));
if (rte_mp_sendmsg(&msg))
EAL_LOG(ERR, "Could not send message to secondary process");
/* clean up */
TAILQ_REMOVE(&mp_request_list.list, entry, next);
free(entry->alloc_state.ms);
free(entry);
pthread_mutex_unlock(&mp_request_list.lock);
return 0;
fail:
pthread_mutex_unlock(&mp_request_list.lock);
return -1;
}
/* final stage of the request from secondary */
static int
handle_response(const struct rte_mp_msg *msg, const void *peer __rte_unused)
{
const struct malloc_mp_req *m =
(const struct malloc_mp_req *)msg->param;
struct mp_request *entry;
pthread_mutex_lock(&mp_request_list.lock);
entry = find_request_by_id(m->id);
if (entry != NULL) {
/* update request status */
entry->user_req.result = m->result;
entry->state = REQ_STATE_COMPLETE;
/* trigger thread wakeup */
pthread_cond_signal(&entry->cond);
}
pthread_mutex_unlock(&mp_request_list.lock);
return 0;
}
/* synchronously request memory map sync, this is only called whenever primary
* process initiates the allocation.
*/
int
request_sync(void)
{
struct rte_mp_msg msg;
struct rte_mp_reply reply;
struct malloc_mp_req *req = (struct malloc_mp_req *)msg.param;
struct timespec ts;
int i, ret = -1;
memset(&msg, 0, sizeof(msg));
memset(&reply, 0, sizeof(reply));
/* no need to create tailq entries as this is entirely synchronous */
msg.num_fds = 0;
msg.len_param = sizeof(*req);
strlcpy(msg.name, MP_ACTION_SYNC, sizeof(msg.name));
/* sync request carries no data */
req->t = REQ_TYPE_SYNC;
req->id = get_unique_id();
ts.tv_nsec = 0;
ts.tv_sec = MP_TIMEOUT_S;
/* there may be stray timeout still waiting */
do {
ret = rte_mp_request_sync(&msg, &reply, &ts);
} while (ret != 0 && rte_errno == EEXIST);
if (ret != 0) {
/* if IPC is unsupported, behave as if the call succeeded */
if (rte_errno != ENOTSUP)
EAL_LOG(ERR, "Could not send sync request to secondary process");
else
ret = 0;
goto out;
}
if (reply.nb_received != reply.nb_sent) {
EAL_LOG(ERR, "Not all secondaries have responded");
goto out;
}
for (i = 0; i < reply.nb_received; i++) {
struct malloc_mp_req *resp =
(struct malloc_mp_req *)reply.msgs[i].param;
if (resp->t != REQ_TYPE_SYNC) {
EAL_LOG(ERR, "Unexpected response from secondary");
goto out;
}
if (resp->id != req->id) {
EAL_LOG(ERR, "Wrong request ID");
goto out;
}
if (resp->result != REQ_RESULT_SUCCESS) {
EAL_LOG(ERR, "Secondary process failed to synchronize");
goto out;
}
}
ret = 0;
out:
free(reply.msgs);
return ret;
}
/* this is a synchronous wrapper around a bunch of asynchronous requests to
* primary process. this will initiate a request and wait until responses come.
*/
int
request_to_primary(struct malloc_mp_req *user_req)
{
struct rte_mp_msg msg;
struct malloc_mp_req *msg_req = (struct malloc_mp_req *)msg.param;
struct mp_request *entry;
struct timespec ts;
struct timeval now;
int ret;
memset(&msg, 0, sizeof(msg));
memset(&ts, 0, sizeof(ts));
pthread_mutex_lock(&mp_request_list.lock);
entry = malloc(sizeof(*entry));
if (entry == NULL) {
EAL_LOG(ERR, "Cannot allocate memory for request");
goto fail;
}
memset(entry, 0, sizeof(*entry));
if (gettimeofday(&now, NULL) < 0) {
EAL_LOG(ERR, "Cannot get current time");
goto fail;
}
ts.tv_nsec = (now.tv_usec * 1000) % 1000000000;
ts.tv_sec = now.tv_sec + MP_TIMEOUT_S +
(now.tv_usec * 1000) / 1000000000;
/* initialize the request */
pthread_cond_init(&entry->cond, NULL);
msg.num_fds = 0;
msg.len_param = sizeof(*msg_req);
strlcpy(msg.name, MP_ACTION_REQUEST, sizeof(msg.name));
/* (attempt to) get a unique id */
user_req->id = get_unique_id();
/* copy contents of user request into the message */
memcpy(msg_req, user_req, sizeof(*msg_req));
if (rte_mp_sendmsg(&msg)) {
EAL_LOG(ERR, "Cannot send message to primary");
goto fail;
}
/* copy contents of user request into active request */
memcpy(&entry->user_req, user_req, sizeof(*user_req));
/* mark request as in progress */
entry->state = REQ_STATE_ACTIVE;
TAILQ_INSERT_TAIL(&mp_request_list.list, entry, next);
/* finally, wait on timeout */
do {
ret = pthread_cond_timedwait(&entry->cond,
&mp_request_list.lock, &ts);
} while ((ret != 0 && ret != ETIMEDOUT) &&
entry->state == REQ_STATE_ACTIVE);
if (entry->state != REQ_STATE_COMPLETE) {
EAL_LOG(ERR, "Request timed out");
ret = -1;
} else {
ret = 0;
user_req->result = entry->user_req.result;
}
TAILQ_REMOVE(&mp_request_list.list, entry, next);
free(entry);
pthread_mutex_unlock(&mp_request_list.lock);
return ret;
fail:
pthread_mutex_unlock(&mp_request_list.lock);
free(entry);
return -1;
}
int
register_mp_requests(void)
{
if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
/* it's OK for primary to not support IPC */
if (rte_mp_action_register(MP_ACTION_REQUEST, handle_request) &&
rte_errno != ENOTSUP) {
EAL_LOG(ERR, "Couldn't register '%s' action",
MP_ACTION_REQUEST);
return -1;
}
} else {
if (rte_mp_action_register(MP_ACTION_SYNC, handle_sync)) {
EAL_LOG(ERR, "Couldn't register '%s' action",
MP_ACTION_SYNC);
return -1;
}
if (rte_mp_action_register(MP_ACTION_ROLLBACK, handle_sync)) {
EAL_LOG(ERR, "Couldn't register '%s' action",
MP_ACTION_SYNC);
return -1;
}
if (rte_mp_action_register(MP_ACTION_RESPONSE,
handle_response)) {
EAL_LOG(ERR, "Couldn't register '%s' action",
MP_ACTION_RESPONSE);
return -1;
}
}
return 0;
}
void
unregister_mp_requests(void)
{
if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
rte_mp_action_unregister(MP_ACTION_REQUEST);
} else {
rte_mp_action_unregister(MP_ACTION_SYNC);
rte_mp_action_unregister(MP_ACTION_ROLLBACK);
rte_mp_action_unregister(MP_ACTION_RESPONSE);
}
}
|