Loading...
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 | /*
* GPL HEADER START
*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 only,
* as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License version 2 for more details (a copy is included
* in the LICENSE file that accompanied this code).
*
* You should have received a copy of the GNU General Public License
* version 2 along with this program; If not, see
* http://www.sun.com/software/products/lustre/docs/GPLv2.pdf
*
* Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
* CA 95054 USA or visit www.sun.com if you need additional information or
* have any questions.
*
* GPL HEADER END
*/
/*
* Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
* Copyright (c) 2011, 2012, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
* Lustre is a trademark of Sun Microsystems, Inc.
*
* lustre/ptlrpc/sec_bulk.c
*
* Author: Eric Mei <ericm@clusterfs.com>
*/
#define DEBUG_SUBSYSTEM S_SEC
#include "../../include/linux/libcfs/libcfs.h"
#include <linux/crypto.h>
#include "../include/obd.h"
#include "../include/obd_cksum.h"
#include "../include/obd_class.h"
#include "../include/obd_support.h"
#include "../include/lustre_net.h"
#include "../include/lustre_import.h"
#include "../include/lustre_dlm.h"
#include "../include/lustre_sec.h"
#include "ptlrpc_internal.h"
/****************************************
* bulk encryption page pools *
****************************************/
#define POINTERS_PER_PAGE (PAGE_CACHE_SIZE / sizeof(void *))
#define PAGES_PER_POOL (POINTERS_PER_PAGE)
#define IDLE_IDX_MAX (100)
#define IDLE_IDX_WEIGHT (3)
#define CACHE_QUIESCENT_PERIOD (20)
static struct ptlrpc_enc_page_pool {
/*
* constants
*/
unsigned long epp_max_pages; /* maximum pages can hold, const */
unsigned int epp_max_pools; /* number of pools, const */
/*
* wait queue in case of not enough free pages.
*/
wait_queue_head_t epp_waitq; /* waiting threads */
unsigned int epp_waitqlen; /* wait queue length */
unsigned long epp_pages_short; /* # of pages wanted of in-q users */
unsigned int epp_growing:1; /* during adding pages */
/*
* indicating how idle the pools are, from 0 to MAX_IDLE_IDX
* this is counted based on each time when getting pages from
* the pools, not based on time. which means in case that system
* is idled for a while but the idle_idx might still be low if no
* activities happened in the pools.
*/
unsigned long epp_idle_idx;
/* last shrink time due to mem tight */
long epp_last_shrink;
long epp_last_access;
/*
* in-pool pages bookkeeping
*/
spinlock_t epp_lock; /* protect following fields */
unsigned long epp_total_pages; /* total pages in pools */
unsigned long epp_free_pages; /* current pages available */
/*
* statistics
*/
unsigned long epp_st_max_pages; /* # of pages ever reached */
unsigned int epp_st_grows; /* # of grows */
unsigned int epp_st_grow_fails; /* # of add pages failures */
unsigned int epp_st_shrinks; /* # of shrinks */
unsigned long epp_st_access; /* # of access */
unsigned long epp_st_missings; /* # of cache missing */
unsigned long epp_st_lowfree; /* lowest free pages reached */
unsigned int epp_st_max_wqlen; /* highest waitqueue length */
unsigned long epp_st_max_wait; /* in jiffies */
/*
* pointers to pools
*/
struct page ***epp_pools;
} page_pools;
/*
* /proc/fs/lustre/sptlrpc/encrypt_page_pools
*/
int sptlrpc_proc_enc_pool_seq_show(struct seq_file *m, void *v)
{
spin_lock(&page_pools.epp_lock);
seq_printf(m,
"physical pages: %lu\n"
"pages per pool: %lu\n"
"max pages: %lu\n"
"max pools: %u\n"
"total pages: %lu\n"
"total free: %lu\n"
"idle index: %lu/100\n"
"last shrink: %lds\n"
"last access: %lds\n"
"max pages reached: %lu\n"
"grows: %u\n"
"grows failure: %u\n"
"shrinks: %u\n"
"cache access: %lu\n"
"cache missing: %lu\n"
"low free mark: %lu\n"
"max waitqueue depth: %u\n"
"max wait time: " CFS_TIME_T "/%u\n",
totalram_pages,
PAGES_PER_POOL,
page_pools.epp_max_pages,
page_pools.epp_max_pools,
page_pools.epp_total_pages,
page_pools.epp_free_pages,
page_pools.epp_idle_idx,
get_seconds() - page_pools.epp_last_shrink,
get_seconds() - page_pools.epp_last_access,
page_pools.epp_st_max_pages,
page_pools.epp_st_grows,
page_pools.epp_st_grow_fails,
page_pools.epp_st_shrinks,
page_pools.epp_st_access,
page_pools.epp_st_missings,
page_pools.epp_st_lowfree,
page_pools.epp_st_max_wqlen,
page_pools.epp_st_max_wait,
HZ);
spin_unlock(&page_pools.epp_lock);
return 0;
}
static void enc_pools_release_free_pages(long npages)
{
int p_idx, g_idx;
int p_idx_max1, p_idx_max2;
LASSERT(npages > 0);
LASSERT(npages <= page_pools.epp_free_pages);
LASSERT(page_pools.epp_free_pages <= page_pools.epp_total_pages);
/* max pool index before the release */
p_idx_max2 = (page_pools.epp_total_pages - 1) / PAGES_PER_POOL;
page_pools.epp_free_pages -= npages;
page_pools.epp_total_pages -= npages;
/* max pool index after the release */
p_idx_max1 = page_pools.epp_total_pages == 0 ? -1 :
((page_pools.epp_total_pages - 1) / PAGES_PER_POOL);
p_idx = page_pools.epp_free_pages / PAGES_PER_POOL;
g_idx = page_pools.epp_free_pages % PAGES_PER_POOL;
LASSERT(page_pools.epp_pools[p_idx]);
while (npages--) {
LASSERT(page_pools.epp_pools[p_idx]);
LASSERT(page_pools.epp_pools[p_idx][g_idx] != NULL);
__free_page(page_pools.epp_pools[p_idx][g_idx]);
page_pools.epp_pools[p_idx][g_idx] = NULL;
if (++g_idx == PAGES_PER_POOL) {
p_idx++;
g_idx = 0;
}
}
/* free unused pools */
while (p_idx_max1 < p_idx_max2) {
LASSERT(page_pools.epp_pools[p_idx_max2]);
OBD_FREE(page_pools.epp_pools[p_idx_max2], PAGE_CACHE_SIZE);
page_pools.epp_pools[p_idx_max2] = NULL;
p_idx_max2--;
}
}
/*
* we try to keep at least PTLRPC_MAX_BRW_PAGES pages in the pool.
*/
static unsigned long enc_pools_shrink_count(struct shrinker *s,
struct shrink_control *sc)
{
/*
* if no pool access for a long time, we consider it's fully idle.
* a little race here is fine.
*/
if (unlikely(get_seconds() - page_pools.epp_last_access >
CACHE_QUIESCENT_PERIOD)) {
spin_lock(&page_pools.epp_lock);
page_pools.epp_idle_idx = IDLE_IDX_MAX;
spin_unlock(&page_pools.epp_lock);
}
LASSERT(page_pools.epp_idle_idx <= IDLE_IDX_MAX);
return max((int)page_pools.epp_free_pages - PTLRPC_MAX_BRW_PAGES, 0) *
(IDLE_IDX_MAX - page_pools.epp_idle_idx) / IDLE_IDX_MAX;
}
/*
* we try to keep at least PTLRPC_MAX_BRW_PAGES pages in the pool.
*/
static unsigned long enc_pools_shrink_scan(struct shrinker *s,
struct shrink_control *sc)
{
spin_lock(&page_pools.epp_lock);
sc->nr_to_scan = min_t(unsigned long, sc->nr_to_scan,
page_pools.epp_free_pages - PTLRPC_MAX_BRW_PAGES);
if (sc->nr_to_scan > 0) {
enc_pools_release_free_pages(sc->nr_to_scan);
CDEBUG(D_SEC, "released %ld pages, %ld left\n",
(long)sc->nr_to_scan, page_pools.epp_free_pages);
page_pools.epp_st_shrinks++;
page_pools.epp_last_shrink = get_seconds();
}
spin_unlock(&page_pools.epp_lock);
/*
* if no pool access for a long time, we consider it's fully idle.
* a little race here is fine.
*/
if (unlikely(get_seconds() - page_pools.epp_last_access >
CACHE_QUIESCENT_PERIOD)) {
spin_lock(&page_pools.epp_lock);
page_pools.epp_idle_idx = IDLE_IDX_MAX;
spin_unlock(&page_pools.epp_lock);
}
LASSERT(page_pools.epp_idle_idx <= IDLE_IDX_MAX);
return sc->nr_to_scan;
}
static inline
int npages_to_npools(unsigned long npages)
{
return (int) ((npages + PAGES_PER_POOL - 1) / PAGES_PER_POOL);
}
/*
* return how many pages cleaned up.
*/
static unsigned long enc_pools_cleanup(struct page ***pools, int npools)
{
unsigned long cleaned = 0;
int i, j;
for (i = 0; i < npools; i++) {
if (pools[i]) {
for (j = 0; j < PAGES_PER_POOL; j++) {
if (pools[i][j]) {
__free_page(pools[i][j]);
cleaned++;
}
}
OBD_FREE(pools[i], PAGE_CACHE_SIZE);
pools[i] = NULL;
}
}
return cleaned;
}
/*
* merge @npools pointed by @pools which contains @npages new pages
* into current pools.
*
* we have options to avoid most memory copy with some tricks. but we choose
* the simplest way to avoid complexity. It's not frequently called.
*/
static void enc_pools_insert(struct page ***pools, int npools, int npages)
{
int freeslot;
int op_idx, np_idx, og_idx, ng_idx;
int cur_npools, end_npools;
LASSERT(npages > 0);
LASSERT(page_pools.epp_total_pages+npages <= page_pools.epp_max_pages);
LASSERT(npages_to_npools(npages) == npools);
LASSERT(page_pools.epp_growing);
spin_lock(&page_pools.epp_lock);
/*
* (1) fill all the free slots of current pools.
*/
/* free slots are those left by rent pages, and the extra ones with
* index >= total_pages, locate at the tail of last pool. */
freeslot = page_pools.epp_total_pages % PAGES_PER_POOL;
if (freeslot != 0)
freeslot = PAGES_PER_POOL - freeslot;
freeslot += page_pools.epp_total_pages - page_pools.epp_free_pages;
op_idx = page_pools.epp_free_pages / PAGES_PER_POOL;
og_idx = page_pools.epp_free_pages % PAGES_PER_POOL;
np_idx = npools - 1;
ng_idx = (npages - 1) % PAGES_PER_POOL;
while (freeslot) {
LASSERT(page_pools.epp_pools[op_idx][og_idx] == NULL);
LASSERT(pools[np_idx][ng_idx] != NULL);
page_pools.epp_pools[op_idx][og_idx] = pools[np_idx][ng_idx];
pools[np_idx][ng_idx] = NULL;
freeslot--;
if (++og_idx == PAGES_PER_POOL) {
op_idx++;
og_idx = 0;
}
if (--ng_idx < 0) {
if (np_idx == 0)
break;
np_idx--;
ng_idx = PAGES_PER_POOL - 1;
}
}
/*
* (2) add pools if needed.
*/
cur_npools = (page_pools.epp_total_pages + PAGES_PER_POOL - 1) /
PAGES_PER_POOL;
end_npools = (page_pools.epp_total_pages + npages + PAGES_PER_POOL - 1)
/ PAGES_PER_POOL;
LASSERT(end_npools <= page_pools.epp_max_pools);
np_idx = 0;
while (cur_npools < end_npools) {
LASSERT(page_pools.epp_pools[cur_npools] == NULL);
LASSERT(np_idx < npools);
LASSERT(pools[np_idx] != NULL);
page_pools.epp_pools[cur_npools++] = pools[np_idx];
pools[np_idx++] = NULL;
}
page_pools.epp_total_pages += npages;
page_pools.epp_free_pages += npages;
page_pools.epp_st_lowfree = page_pools.epp_free_pages;
if (page_pools.epp_total_pages > page_pools.epp_st_max_pages)
page_pools.epp_st_max_pages = page_pools.epp_total_pages;
CDEBUG(D_SEC, "add %d pages to total %lu\n", npages,
page_pools.epp_total_pages);
spin_unlock(&page_pools.epp_lock);
}
static int enc_pools_add_pages(int npages)
{
static DEFINE_MUTEX(add_pages_mutex);
struct page ***pools;
int npools, alloced = 0;
int i, j, rc = -ENOMEM;
if (npages < PTLRPC_MAX_BRW_PAGES)
npages = PTLRPC_MAX_BRW_PAGES;
mutex_lock(&add_pages_mutex);
if (npages + page_pools.epp_total_pages > page_pools.epp_max_pages)
npages = page_pools.epp_max_pages - page_pools.epp_total_pages;
LASSERT(npages > 0);
page_pools.epp_st_grows++;
npools = npages_to_npools(npages);
OBD_ALLOC(pools, npools * sizeof(*pools));
if (pools == NULL)
goto out;
for (i = 0; i < npools; i++) {
OBD_ALLOC(pools[i], PAGE_CACHE_SIZE);
if (pools[i] == NULL)
goto out_pools;
for (j = 0; j < PAGES_PER_POOL && alloced < npages; j++) {
pools[i][j] = alloc_page(GFP_NOFS |
__GFP_HIGHMEM);
if (pools[i][j] == NULL)
goto out_pools;
alloced++;
}
}
LASSERT(alloced == npages);
enc_pools_insert(pools, npools, npages);
CDEBUG(D_SEC, "added %d pages into pools\n", npages);
rc = 0;
out_pools:
enc_pools_cleanup(pools, npools);
OBD_FREE(pools, npools * sizeof(*pools));
out:
if (rc) {
page_pools.epp_st_grow_fails++;
CERROR("Failed to allocate %d enc pages\n", npages);
}
mutex_unlock(&add_pages_mutex);
return rc;
}
static inline void enc_pools_wakeup(void)
{
assert_spin_locked(&page_pools.epp_lock);
LASSERT(page_pools.epp_waitqlen >= 0);
if (unlikely(page_pools.epp_waitqlen)) {
LASSERT(waitqueue_active(&page_pools.epp_waitq));
wake_up_all(&page_pools.epp_waitq);
}
}
static int enc_pools_should_grow(int page_needed, long now)
{
/* don't grow if someone else is growing the pools right now,
* or the pools has reached its full capacity
*/
if (page_pools.epp_growing ||
page_pools.epp_total_pages == page_pools.epp_max_pages)
return 0;
/* if total pages is not enough, we need to grow */
if (page_pools.epp_total_pages < page_needed)
return 1;
/*
* we wanted to return 0 here if there was a shrink just happened
* moment ago, but this may cause deadlock if both client and ost
* live on single node.
*/
#if 0
if (now - page_pools.epp_last_shrink < 2)
return 0;
#endif
/*
* here we perhaps need consider other factors like wait queue
* length, idle index, etc. ?
*/
/* grow the pools in any other cases */
return 1;
}
/*
* we allocate the requested pages atomically.
*/
int sptlrpc_enc_pool_get_pages(struct ptlrpc_bulk_desc *desc)
{
wait_queue_t waitlink;
unsigned long this_idle = -1;
unsigned long tick = 0;
long now;
int p_idx, g_idx;
int i;
LASSERT(desc->bd_iov_count > 0);
LASSERT(desc->bd_iov_count <= page_pools.epp_max_pages);
/* resent bulk, enc iov might have been allocated previously */
if (desc->bd_enc_iov != NULL)
return 0;
OBD_ALLOC(desc->bd_enc_iov,
desc->bd_iov_count * sizeof(*desc->bd_enc_iov));
if (desc->bd_enc_iov == NULL)
return -ENOMEM;
spin_lock(&page_pools.epp_lock);
page_pools.epp_st_access++;
again:
if (unlikely(page_pools.epp_free_pages < desc->bd_iov_count)) {
if (tick == 0)
tick = cfs_time_current();
now = get_seconds();
page_pools.epp_st_missings++;
page_pools.epp_pages_short += desc->bd_iov_count;
if (enc_pools_should_grow(desc->bd_iov_count, now)) {
page_pools.epp_growing = 1;
spin_unlock(&page_pools.epp_lock);
enc_pools_add_pages(page_pools.epp_pages_short / 2);
spin_lock(&page_pools.epp_lock);
page_pools.epp_growing = 0;
enc_pools_wakeup();
} else {
if (++page_pools.epp_waitqlen >
page_pools.epp_st_max_wqlen)
page_pools.epp_st_max_wqlen =
page_pools.epp_waitqlen;
set_current_state(TASK_UNINTERRUPTIBLE);
init_waitqueue_entry(&waitlink, current);
add_wait_queue(&page_pools.epp_waitq, &waitlink);
spin_unlock(&page_pools.epp_lock);
schedule();
remove_wait_queue(&page_pools.epp_waitq, &waitlink);
LASSERT(page_pools.epp_waitqlen > 0);
spin_lock(&page_pools.epp_lock);
page_pools.epp_waitqlen--;
}
LASSERT(page_pools.epp_pages_short >= desc->bd_iov_count);
page_pools.epp_pages_short -= desc->bd_iov_count;
this_idle = 0;
goto again;
}
/* record max wait time */
if (unlikely(tick != 0)) {
tick = cfs_time_current() - tick;
if (tick > page_pools.epp_st_max_wait)
page_pools.epp_st_max_wait = tick;
}
/* proceed with rest of allocation */
page_pools.epp_free_pages -= desc->bd_iov_count;
p_idx = page_pools.epp_free_pages / PAGES_PER_POOL;
g_idx = page_pools.epp_free_pages % PAGES_PER_POOL;
for (i = 0; i < desc->bd_iov_count; i++) {
LASSERT(page_pools.epp_pools[p_idx][g_idx] != NULL);
desc->bd_enc_iov[i].kiov_page =
page_pools.epp_pools[p_idx][g_idx];
page_pools.epp_pools[p_idx][g_idx] = NULL;
if (++g_idx == PAGES_PER_POOL) {
p_idx++;
g_idx = 0;
}
}
if (page_pools.epp_free_pages < page_pools.epp_st_lowfree)
page_pools.epp_st_lowfree = page_pools.epp_free_pages;
/*
* new idle index = (old * weight + new) / (weight + 1)
*/
if (this_idle == -1) {
this_idle = page_pools.epp_free_pages * IDLE_IDX_MAX /
page_pools.epp_total_pages;
}
page_pools.epp_idle_idx = (page_pools.epp_idle_idx * IDLE_IDX_WEIGHT +
this_idle) /
(IDLE_IDX_WEIGHT + 1);
page_pools.epp_last_access = get_seconds();
spin_unlock(&page_pools.epp_lock);
return 0;
}
EXPORT_SYMBOL(sptlrpc_enc_pool_get_pages);
void sptlrpc_enc_pool_put_pages(struct ptlrpc_bulk_desc *desc)
{
int p_idx, g_idx;
int i;
if (desc->bd_enc_iov == NULL)
return;
LASSERT(desc->bd_iov_count > 0);
spin_lock(&page_pools.epp_lock);
p_idx = page_pools.epp_free_pages / PAGES_PER_POOL;
g_idx = page_pools.epp_free_pages % PAGES_PER_POOL;
LASSERT(page_pools.epp_free_pages + desc->bd_iov_count <=
page_pools.epp_total_pages);
LASSERT(page_pools.epp_pools[p_idx]);
for (i = 0; i < desc->bd_iov_count; i++) {
LASSERT(desc->bd_enc_iov[i].kiov_page != NULL);
LASSERT(g_idx != 0 || page_pools.epp_pools[p_idx]);
LASSERT(page_pools.epp_pools[p_idx][g_idx] == NULL);
page_pools.epp_pools[p_idx][g_idx] =
desc->bd_enc_iov[i].kiov_page;
if (++g_idx == PAGES_PER_POOL) {
p_idx++;
g_idx = 0;
}
}
page_pools.epp_free_pages += desc->bd_iov_count;
enc_pools_wakeup();
spin_unlock(&page_pools.epp_lock);
OBD_FREE(desc->bd_enc_iov,
desc->bd_iov_count * sizeof(*desc->bd_enc_iov));
desc->bd_enc_iov = NULL;
}
EXPORT_SYMBOL(sptlrpc_enc_pool_put_pages);
/*
* we don't do much stuff for add_user/del_user anymore, except adding some
* initial pages in add_user() if current pools are empty, rest would be
* handled by the pools's self-adaption.
*/
int sptlrpc_enc_pool_add_user(void)
{
int need_grow = 0;
spin_lock(&page_pools.epp_lock);
if (page_pools.epp_growing == 0 && page_pools.epp_total_pages == 0) {
page_pools.epp_growing = 1;
need_grow = 1;
}
spin_unlock(&page_pools.epp_lock);
if (need_grow) {
enc_pools_add_pages(PTLRPC_MAX_BRW_PAGES +
PTLRPC_MAX_BRW_PAGES);
spin_lock(&page_pools.epp_lock);
page_pools.epp_growing = 0;
enc_pools_wakeup();
spin_unlock(&page_pools.epp_lock);
}
return 0;
}
EXPORT_SYMBOL(sptlrpc_enc_pool_add_user);
int sptlrpc_enc_pool_del_user(void)
{
return 0;
}
EXPORT_SYMBOL(sptlrpc_enc_pool_del_user);
static inline void enc_pools_alloc(void)
{
LASSERT(page_pools.epp_max_pools);
OBD_ALLOC_LARGE(page_pools.epp_pools,
page_pools.epp_max_pools *
sizeof(*page_pools.epp_pools));
}
static inline void enc_pools_free(void)
{
LASSERT(page_pools.epp_max_pools);
LASSERT(page_pools.epp_pools);
OBD_FREE_LARGE(page_pools.epp_pools,
page_pools.epp_max_pools *
sizeof(*page_pools.epp_pools));
}
static struct shrinker pools_shrinker = {
.count_objects = enc_pools_shrink_count,
.scan_objects = enc_pools_shrink_scan,
.seeks = DEFAULT_SEEKS,
};
int sptlrpc_enc_pool_init(void)
{
/*
* maximum capacity is 1/8 of total physical memory.
* is the 1/8 a good number?
*/
page_pools.epp_max_pages = totalram_pages / 8;
page_pools.epp_max_pools = npages_to_npools(page_pools.epp_max_pages);
init_waitqueue_head(&page_pools.epp_waitq);
page_pools.epp_waitqlen = 0;
page_pools.epp_pages_short = 0;
page_pools.epp_growing = 0;
page_pools.epp_idle_idx = 0;
page_pools.epp_last_shrink = get_seconds();
page_pools.epp_last_access = get_seconds();
spin_lock_init(&page_pools.epp_lock);
page_pools.epp_total_pages = 0;
page_pools.epp_free_pages = 0;
page_pools.epp_st_max_pages = 0;
page_pools.epp_st_grows = 0;
page_pools.epp_st_grow_fails = 0;
page_pools.epp_st_shrinks = 0;
page_pools.epp_st_access = 0;
page_pools.epp_st_missings = 0;
page_pools.epp_st_lowfree = 0;
page_pools.epp_st_max_wqlen = 0;
page_pools.epp_st_max_wait = 0;
enc_pools_alloc();
if (page_pools.epp_pools == NULL)
return -ENOMEM;
register_shrinker(&pools_shrinker);
return 0;
}
void sptlrpc_enc_pool_fini(void)
{
unsigned long cleaned, npools;
LASSERT(page_pools.epp_pools);
LASSERT(page_pools.epp_total_pages == page_pools.epp_free_pages);
unregister_shrinker(&pools_shrinker);
npools = npages_to_npools(page_pools.epp_total_pages);
cleaned = enc_pools_cleanup(page_pools.epp_pools, npools);
LASSERT(cleaned == page_pools.epp_total_pages);
enc_pools_free();
if (page_pools.epp_st_access > 0) {
CDEBUG(D_SEC,
"max pages %lu, grows %u, grow fails %u, shrinks %u, access %lu, missing %lu, max qlen %u, max wait "
CFS_TIME_T"/%d\n",
page_pools.epp_st_max_pages, page_pools.epp_st_grows,
page_pools.epp_st_grow_fails,
page_pools.epp_st_shrinks, page_pools.epp_st_access,
page_pools.epp_st_missings, page_pools.epp_st_max_wqlen,
page_pools.epp_st_max_wait, HZ);
}
}
static int cfs_hash_alg_id[] = {
[BULK_HASH_ALG_NULL] = CFS_HASH_ALG_NULL,
[BULK_HASH_ALG_ADLER32] = CFS_HASH_ALG_ADLER32,
[BULK_HASH_ALG_CRC32] = CFS_HASH_ALG_CRC32,
[BULK_HASH_ALG_MD5] = CFS_HASH_ALG_MD5,
[BULK_HASH_ALG_SHA1] = CFS_HASH_ALG_SHA1,
[BULK_HASH_ALG_SHA256] = CFS_HASH_ALG_SHA256,
[BULK_HASH_ALG_SHA384] = CFS_HASH_ALG_SHA384,
[BULK_HASH_ALG_SHA512] = CFS_HASH_ALG_SHA512,
};
const char *sptlrpc_get_hash_name(__u8 hash_alg)
{
return cfs_crypto_hash_name(cfs_hash_alg_id[hash_alg]);
}
EXPORT_SYMBOL(sptlrpc_get_hash_name);
__u8 sptlrpc_get_hash_alg(const char *algname)
{
return cfs_crypto_hash_alg(algname);
}
EXPORT_SYMBOL(sptlrpc_get_hash_alg);
int bulk_sec_desc_unpack(struct lustre_msg *msg, int offset, int swabbed)
{
struct ptlrpc_bulk_sec_desc *bsd;
int size = msg->lm_buflens[offset];
bsd = lustre_msg_buf(msg, offset, sizeof(*bsd));
if (bsd == NULL) {
CERROR("Invalid bulk sec desc: size %d\n", size);
return -EINVAL;
}
if (swabbed)
__swab32s(&bsd->bsd_nob);
if (unlikely(bsd->bsd_version != 0)) {
CERROR("Unexpected version %u\n", bsd->bsd_version);
return -EPROTO;
}
if (unlikely(bsd->bsd_type >= SPTLRPC_BULK_MAX)) {
CERROR("Invalid type %u\n", bsd->bsd_type);
return -EPROTO;
}
/* FIXME more sanity check here */
if (unlikely(bsd->bsd_svc != SPTLRPC_BULK_SVC_NULL &&
bsd->bsd_svc != SPTLRPC_BULK_SVC_INTG &&
bsd->bsd_svc != SPTLRPC_BULK_SVC_PRIV)) {
CERROR("Invalid svc %u\n", bsd->bsd_svc);
return -EPROTO;
}
return 0;
}
EXPORT_SYMBOL(bulk_sec_desc_unpack);
int sptlrpc_get_bulk_checksum(struct ptlrpc_bulk_desc *desc, __u8 alg,
void *buf, int buflen)
{
struct cfs_crypto_hash_desc *hdesc;
int hashsize;
char hashbuf[64];
unsigned int bufsize;
int i, err;
LASSERT(alg > BULK_HASH_ALG_NULL && alg < BULK_HASH_ALG_MAX);
LASSERT(buflen >= 4);
hdesc = cfs_crypto_hash_init(cfs_hash_alg_id[alg], NULL, 0);
if (IS_ERR(hdesc)) {
CERROR("Unable to initialize checksum hash %s\n",
cfs_crypto_hash_name(cfs_hash_alg_id[alg]));
return PTR_ERR(hdesc);
}
hashsize = cfs_crypto_hash_digestsize(cfs_hash_alg_id[alg]);
for (i = 0; i < desc->bd_iov_count; i++) {
cfs_crypto_hash_update_page(hdesc, desc->bd_iov[i].kiov_page,
desc->bd_iov[i].kiov_offset & ~CFS_PAGE_MASK,
desc->bd_iov[i].kiov_len);
}
if (hashsize > buflen) {
bufsize = sizeof(hashbuf);
err = cfs_crypto_hash_final(hdesc, (unsigned char *)hashbuf,
&bufsize);
memcpy(buf, hashbuf, buflen);
} else {
bufsize = buflen;
err = cfs_crypto_hash_final(hdesc, (unsigned char *)buf,
&bufsize);
}
if (err)
cfs_crypto_hash_final(hdesc, NULL, NULL);
return err;
}
EXPORT_SYMBOL(sptlrpc_get_bulk_checksum);
|