ram.c 48.8 KB
Newer Older
1 2 3 4
/*
 * QEMU System Emulator
 *
 * Copyright (c) 2003-2008 Fabrice Bellard
5 6 7 8
 * Copyright (c) 2011-2015 Red Hat Inc
 *
 * Authors:
 *  Juan Quintela <quintela@redhat.com>
9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */
#include <stdint.h>
#include <zlib.h>
#include "qemu/bitops.h"
#include "qemu/bitmap.h"
J
Juan Quintela 已提交
32 33
#include "qemu/timer.h"
#include "qemu/main-loop.h"
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
#include "migration/migration.h"
#include "exec/address-spaces.h"
#include "migration/page_cache.h"
#include "qemu/error-report.h"
#include "trace.h"
#include "exec/ram_addr.h"
#include "qemu/rcu_queue.h"

#ifdef DEBUG_MIGRATION_RAM
#define DPRINTF(fmt, ...) \
    do { fprintf(stdout, "migration_ram: " fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
    do { } while (0)
#endif

static bool mig_throttle_on;
static int dirty_rate_high_cnt;
static void check_guest_throttling(void);

static uint64_t bitmap_sync_count;

/***********************************************************/
/* ram save/restore */

#define RAM_SAVE_FLAG_FULL     0x01 /* Obsolete, not used anymore */
#define RAM_SAVE_FLAG_COMPRESS 0x02
#define RAM_SAVE_FLAG_MEM_SIZE 0x04
#define RAM_SAVE_FLAG_PAGE     0x08
#define RAM_SAVE_FLAG_EOS      0x10
#define RAM_SAVE_FLAG_CONTINUE 0x20
#define RAM_SAVE_FLAG_XBZRLE   0x40
/* 0x80 is reserved in migration.h start with 0x100 next */
#define RAM_SAVE_FLAG_COMPRESS_PAGE    0x100

static const uint8_t ZERO_TARGET_PAGE[TARGET_PAGE_SIZE];

static inline bool is_zero_range(uint8_t *p, uint64_t size)
{
    return buffer_find_nonzero_offset(p, size) == size;
}

/* struct contains XBZRLE cache and a static page
   used by the compression */
static struct {
    /* buffer used for XBZRLE encoding */
    uint8_t *encoded_buf;
    /* buffer for storing page content */
    uint8_t *current_buf;
    /* Cache for XBZRLE, Protected by lock. */
    PageCache *cache;
    QemuMutex lock;
} XBZRLE;

/* buffer used for XBZRLE decoding */
static uint8_t *xbzrle_decoded_buf;

static void XBZRLE_cache_lock(void)
{
    if (migrate_use_xbzrle())
        qemu_mutex_lock(&XBZRLE.lock);
}

static void XBZRLE_cache_unlock(void)
{
    if (migrate_use_xbzrle())
        qemu_mutex_unlock(&XBZRLE.lock);
}

/*
 * called from qmp_migrate_set_cache_size in main thread, possibly while
 * a migration is in progress.
 * A running migration maybe using the cache and might finish during this
 * call, hence changes to the cache are protected by XBZRLE.lock().
 */
int64_t xbzrle_cache_resize(int64_t new_size)
{
    PageCache *new_cache;
    int64_t ret;

    if (new_size < TARGET_PAGE_SIZE) {
        return -1;
    }

    XBZRLE_cache_lock();

    if (XBZRLE.cache != NULL) {
        if (pow2floor(new_size) == migrate_xbzrle_cache_size()) {
            goto out_new_size;
        }
        new_cache = cache_init(new_size / TARGET_PAGE_SIZE,
                                        TARGET_PAGE_SIZE);
        if (!new_cache) {
            error_report("Error creating cache");
            ret = -1;
            goto out;
        }

        cache_fini(XBZRLE.cache);
        XBZRLE.cache = new_cache;
    }

out_new_size:
    ret = pow2floor(new_size);
out:
    XBZRLE_cache_unlock();
    return ret;
}

/* accounting for migration statistics */
typedef struct AccountingInfo {
    uint64_t dup_pages;
    uint64_t skipped_pages;
    uint64_t norm_pages;
    uint64_t iterations;
    uint64_t xbzrle_bytes;
    uint64_t xbzrle_pages;
    uint64_t xbzrle_cache_miss;
    double xbzrle_cache_miss_rate;
    uint64_t xbzrle_overflows;
} AccountingInfo;

static AccountingInfo acct_info;

static void acct_clear(void)
{
    memset(&acct_info, 0, sizeof(acct_info));
}

uint64_t dup_mig_bytes_transferred(void)
{
    return acct_info.dup_pages * TARGET_PAGE_SIZE;
}

uint64_t dup_mig_pages_transferred(void)
{
    return acct_info.dup_pages;
}

uint64_t skipped_mig_bytes_transferred(void)
{
    return acct_info.skipped_pages * TARGET_PAGE_SIZE;
}

uint64_t skipped_mig_pages_transferred(void)
{
    return acct_info.skipped_pages;
}

uint64_t norm_mig_bytes_transferred(void)
{
    return acct_info.norm_pages * TARGET_PAGE_SIZE;
}

uint64_t norm_mig_pages_transferred(void)
{
    return acct_info.norm_pages;
}

uint64_t xbzrle_mig_bytes_transferred(void)
{
    return acct_info.xbzrle_bytes;
}

uint64_t xbzrle_mig_pages_transferred(void)
{
    return acct_info.xbzrle_pages;
}

uint64_t xbzrle_mig_pages_cache_miss(void)
{
    return acct_info.xbzrle_cache_miss;
}

double xbzrle_mig_cache_miss_rate(void)
{
    return acct_info.xbzrle_cache_miss_rate;
}

uint64_t xbzrle_mig_pages_overflow(void)
{
    return acct_info.xbzrle_overflows;
}

/* This is the last block that we have visited serching for dirty pages
 */
static RAMBlock *last_seen_block;
/* This is the last block from where we have sent data */
static RAMBlock *last_sent_block;
static ram_addr_t last_offset;
static unsigned long *migration_bitmap;
L
Li Zhijian 已提交
225
static QemuMutex migration_bitmap_mutex;
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
static uint64_t migration_dirty_pages;
static uint32_t last_version;
static bool ram_bulk_stage;

struct CompressParam {
    bool start;
    bool done;
    QEMUFile *file;
    QemuMutex mutex;
    QemuCond cond;
    RAMBlock *block;
    ram_addr_t offset;
};
typedef struct CompressParam CompressParam;

struct DecompressParam {
    bool start;
    QemuMutex mutex;
    QemuCond cond;
    void *des;
    uint8 *compbuf;
    int len;
};
typedef struct DecompressParam DecompressParam;

static CompressParam *comp_param;
static QemuThread *compress_threads;
/* comp_done_cond is used to wake up the migration thread when
 * one of the compression threads has finished the compression.
 * comp_done_lock is used to co-work with comp_done_cond.
 */
static QemuMutex *comp_done_lock;
static QemuCond *comp_done_cond;
/* The empty QEMUFileOps will be used by file in CompressParam */
static const QEMUFileOps empty_ops = { };

static bool compression_switch;
static bool quit_comp_thread;
static bool quit_decomp_thread;
static DecompressParam *decomp_param;
static QemuThread *decompress_threads;
static uint8_t *compressed_data_buf;

static int do_compress_ram_page(CompressParam *param);

static void *do_data_compress(void *opaque)
{
    CompressParam *param = opaque;

    while (!quit_comp_thread) {
        qemu_mutex_lock(&param->mutex);
        /* Re-check the quit_comp_thread in case of
         * terminate_compression_threads is called just before
         * qemu_mutex_lock(&param->mutex) and after
         * while(!quit_comp_thread), re-check it here can make
         * sure the compression thread terminate as expected.
         */
        while (!param->start && !quit_comp_thread) {
            qemu_cond_wait(&param->cond, &param->mutex);
        }
        if (!quit_comp_thread) {
            do_compress_ram_page(param);
        }
        param->start = false;
        qemu_mutex_unlock(&param->mutex);

        qemu_mutex_lock(comp_done_lock);
        param->done = true;
        qemu_cond_signal(comp_done_cond);
        qemu_mutex_unlock(comp_done_lock);
    }

    return NULL;
}

static inline void terminate_compression_threads(void)
{
    int idx, thread_count;

    thread_count = migrate_compress_threads();
    quit_comp_thread = true;
    for (idx = 0; idx < thread_count; idx++) {
        qemu_mutex_lock(&comp_param[idx].mutex);
        qemu_cond_signal(&comp_param[idx].cond);
        qemu_mutex_unlock(&comp_param[idx].mutex);
    }
}

void migrate_compress_threads_join(void)
{
    int i, thread_count;

    if (!migrate_use_compression()) {
        return;
    }
    terminate_compression_threads();
    thread_count = migrate_compress_threads();
    for (i = 0; i < thread_count; i++) {
        qemu_thread_join(compress_threads + i);
        qemu_fclose(comp_param[i].file);
        qemu_mutex_destroy(&comp_param[i].mutex);
        qemu_cond_destroy(&comp_param[i].cond);
    }
    qemu_mutex_destroy(comp_done_lock);
    qemu_cond_destroy(comp_done_cond);
    g_free(compress_threads);
    g_free(comp_param);
    g_free(comp_done_cond);
    g_free(comp_done_lock);
    compress_threads = NULL;
    comp_param = NULL;
    comp_done_cond = NULL;
    comp_done_lock = NULL;
}

void migrate_compress_threads_create(void)
{
    int i, thread_count;

    if (!migrate_use_compression()) {
        return;
    }
    quit_comp_thread = false;
    compression_switch = true;
    thread_count = migrate_compress_threads();
    compress_threads = g_new0(QemuThread, thread_count);
    comp_param = g_new0(CompressParam, thread_count);
    comp_done_cond = g_new0(QemuCond, 1);
    comp_done_lock = g_new0(QemuMutex, 1);
    qemu_cond_init(comp_done_cond);
    qemu_mutex_init(comp_done_lock);
    for (i = 0; i < thread_count; i++) {
        /* com_param[i].file is just used as a dummy buffer to save data, set
         * it's ops to empty.
         */
        comp_param[i].file = qemu_fopen_ops(NULL, &empty_ops);
        comp_param[i].done = true;
        qemu_mutex_init(&comp_param[i].mutex);
        qemu_cond_init(&comp_param[i].cond);
        qemu_thread_create(compress_threads + i, "compress",
                           do_data_compress, comp_param + i,
                           QEMU_THREAD_JOINABLE);
    }
}

/**
 * save_page_header: Write page header to wire
 *
 * If this is the 1st block, it also writes the block identification
 *
 * Returns: Number of bytes written
 *
 * @f: QEMUFile where to send the data
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 *          in the lower bits, it contains flags
 */
static size_t save_page_header(QEMUFile *f, RAMBlock *block, ram_addr_t offset)
{
385
    size_t size, len;
386 387 388 389 390

    qemu_put_be64(f, offset);
    size = 8;

    if (!(offset & RAM_SAVE_FLAG_CONTINUE)) {
391 392 393 394
        len = strlen(block->idstr);
        qemu_put_byte(f, len);
        qemu_put_buffer(f, (uint8_t *)block->idstr, len);
        size += 1 + len;
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
    }
    return size;
}

/* Update the xbzrle cache to reflect a page that's been sent as all 0.
 * The important thing is that a stale (not-yet-0'd) page be replaced
 * by the new data.
 * As a bonus, if the page wasn't in the cache it gets added so that
 * when a small write is made into the 0'd page it gets XBZRLE sent
 */
static void xbzrle_cache_zero_page(ram_addr_t current_addr)
{
    if (ram_bulk_stage || !migrate_use_xbzrle()) {
        return;
    }

    /* We don't care if this fails to allocate a new cache page
     * as long as it updated an old one */
    cache_insert(XBZRLE.cache, current_addr, ZERO_TARGET_PAGE,
                 bitmap_sync_count);
}

#define ENCODING_FLAG_XBZRLE 0x1

/**
 * save_xbzrle_page: compress and send current page
 *
 * Returns: 1 means that we wrote the page
 *          0 means that page is identical to the one already sent
 *          -1 means that xbzrle would be longer than normal
 *
 * @f: QEMUFile where to send the data
 * @current_data:
 * @current_addr:
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 * @last_stage: if we are at the completion stage
 * @bytes_transferred: increase it with the number of transferred bytes
 */
static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
                            ram_addr_t current_addr, RAMBlock *block,
                            ram_addr_t offset, bool last_stage,
                            uint64_t *bytes_transferred)
{
    int encoded_len = 0, bytes_xbzrle;
    uint8_t *prev_cached_page;

    if (!cache_is_cached(XBZRLE.cache, current_addr, bitmap_sync_count)) {
        acct_info.xbzrle_cache_miss++;
        if (!last_stage) {
            if (cache_insert(XBZRLE.cache, current_addr, *current_data,
                             bitmap_sync_count) == -1) {
                return -1;
            } else {
                /* update *current_data when the page has been
                   inserted into cache */
                *current_data = get_cached_data(XBZRLE.cache, current_addr);
            }
        }
        return -1;
    }

    prev_cached_page = get_cached_data(XBZRLE.cache, current_addr);

    /* save current buffer into memory */
    memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE);

    /* XBZRLE encoding (if there is no overflow) */
    encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
                                       TARGET_PAGE_SIZE, XBZRLE.encoded_buf,
                                       TARGET_PAGE_SIZE);
    if (encoded_len == 0) {
        DPRINTF("Skipping unmodified page\n");
        return 0;
    } else if (encoded_len == -1) {
        DPRINTF("Overflow\n");
        acct_info.xbzrle_overflows++;
        /* update data in the cache */
        if (!last_stage) {
            memcpy(prev_cached_page, *current_data, TARGET_PAGE_SIZE);
            *current_data = prev_cached_page;
        }
        return -1;
    }

    /* we need to update the data in the cache, in order to get the same data */
    if (!last_stage) {
        memcpy(prev_cached_page, XBZRLE.current_buf, TARGET_PAGE_SIZE);
    }

    /* Send XBZRLE based compressed page */
    bytes_xbzrle = save_page_header(f, block, offset | RAM_SAVE_FLAG_XBZRLE);
    qemu_put_byte(f, ENCODING_FLAG_XBZRLE);
    qemu_put_be16(f, encoded_len);
    qemu_put_buffer(f, XBZRLE.encoded_buf, encoded_len);
    bytes_xbzrle += encoded_len + 1 + 2;
    acct_info.xbzrle_pages++;
    acct_info.xbzrle_bytes += bytes_xbzrle;
    *bytes_transferred += bytes_xbzrle;

    return 1;
}

L
Li Zhijian 已提交
498
/* Called with rcu_read_lock() to protect migration_bitmap */
499
static inline
500
ram_addr_t migration_bitmap_find_and_reset_dirty(RAMBlock *rb,
501 502
                                                 ram_addr_t start)
{
503
    unsigned long base = rb->offset >> TARGET_PAGE_BITS;
504
    unsigned long nr = base + (start >> TARGET_PAGE_BITS);
505 506
    uint64_t rb_size = rb->used_length;
    unsigned long size = base + (rb_size >> TARGET_PAGE_BITS);
L
Li Zhijian 已提交
507
    unsigned long *bitmap;
508 509 510

    unsigned long next;

L
Li Zhijian 已提交
511
    bitmap = atomic_rcu_read(&migration_bitmap);
512 513 514
    if (ram_bulk_stage && nr > base) {
        next = nr + 1;
    } else {
L
Li Zhijian 已提交
515
        next = find_next_bit(bitmap, size, nr);
516 517 518
    }

    if (next < size) {
L
Li Zhijian 已提交
519
        clear_bit(next, bitmap);
520 521 522 523 524
        migration_dirty_pages--;
    }
    return (next - base) << TARGET_PAGE_BITS;
}

L
Li Zhijian 已提交
525
/* Called with rcu_read_lock() to protect migration_bitmap */
526 527
static void migration_bitmap_sync_range(ram_addr_t start, ram_addr_t length)
{
L
Li Zhijian 已提交
528 529
    unsigned long *bitmap;
    bitmap = atomic_rcu_read(&migration_bitmap);
530
    migration_dirty_pages +=
L
Li Zhijian 已提交
531
        cpu_physical_memory_sync_dirty_bitmap(bitmap, start, length);
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
}


/* Fix me: there are too many global variables used in migration process. */
static int64_t start_time;
static int64_t bytes_xfer_prev;
static int64_t num_dirty_pages_period;
static uint64_t xbzrle_cache_miss_prev;
static uint64_t iterations_prev;

static void migration_bitmap_sync_init(void)
{
    start_time = 0;
    bytes_xfer_prev = 0;
    num_dirty_pages_period = 0;
    xbzrle_cache_miss_prev = 0;
    iterations_prev = 0;
}

/* Called with iothread lock held, to protect ram_list.dirty_memory[] */
static void migration_bitmap_sync(void)
{
    RAMBlock *block;
    uint64_t num_dirty_pages_init = migration_dirty_pages;
    MigrationState *s = migrate_get_current();
    int64_t end_time;
    int64_t bytes_xfer_now;

    bitmap_sync_count++;

    if (!bytes_xfer_prev) {
        bytes_xfer_prev = ram_bytes_transferred();
    }

    if (!start_time) {
        start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
    }

    trace_migration_bitmap_sync_start();
    address_space_sync_dirty_bitmap(&address_space_memory);

L
Li Zhijian 已提交
573
    qemu_mutex_lock(&migration_bitmap_mutex);
574 575
    rcu_read_lock();
    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
576
        migration_bitmap_sync_range(block->offset, block->used_length);
577 578
    }
    rcu_read_unlock();
L
Li Zhijian 已提交
579
    qemu_mutex_unlock(&migration_bitmap_mutex);
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

    trace_migration_bitmap_sync_end(migration_dirty_pages
                                    - num_dirty_pages_init);
    num_dirty_pages_period += migration_dirty_pages - num_dirty_pages_init;
    end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);

    /* more than 1 second = 1000 millisecons */
    if (end_time > start_time + 1000) {
        if (migrate_auto_converge()) {
            /* The following detection logic can be refined later. For now:
               Check to see if the dirtied bytes is 50% more than the approx.
               amount of bytes that just got transferred since the last time we
               were in this routine. If that happens >N times (for now N==4)
               we turn on the throttle down logic */
            bytes_xfer_now = ram_bytes_transferred();
            if (s->dirty_pages_rate &&
               (num_dirty_pages_period * TARGET_PAGE_SIZE >
                   (bytes_xfer_now - bytes_xfer_prev)/2) &&
               (dirty_rate_high_cnt++ > 4)) {
                    trace_migration_throttle();
                    mig_throttle_on = true;
                    dirty_rate_high_cnt = 0;
             }
             bytes_xfer_prev = bytes_xfer_now;
        } else {
             mig_throttle_on = false;
        }
        if (migrate_use_xbzrle()) {
            if (iterations_prev != acct_info.iterations) {
                acct_info.xbzrle_cache_miss_rate =
                   (double)(acct_info.xbzrle_cache_miss -
                            xbzrle_cache_miss_prev) /
                   (acct_info.iterations - iterations_prev);
            }
            iterations_prev = acct_info.iterations;
            xbzrle_cache_miss_prev = acct_info.xbzrle_cache_miss;
        }
        s->dirty_pages_rate = num_dirty_pages_period * 1000
            / (end_time - start_time);
        s->dirty_bytes_rate = s->dirty_pages_rate * TARGET_PAGE_SIZE;
        start_time = end_time;
        num_dirty_pages_period = 0;
    }
    s->dirty_sync_count = bitmap_sync_count;
}

/**
 * save_zero_page: Send the zero page to the stream
 *
 * Returns: Number of pages written.
 *
 * @f: QEMUFile where to send the data
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 * @p: pointer to the page
 * @bytes_transferred: increase it with the number of transferred bytes
 */
static int save_zero_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
                          uint8_t *p, uint64_t *bytes_transferred)
{
    int pages = -1;

    if (is_zero_range(p, TARGET_PAGE_SIZE)) {
        acct_info.dup_pages++;
        *bytes_transferred += save_page_header(f, block,
                                               offset | RAM_SAVE_FLAG_COMPRESS);
        qemu_put_byte(f, 0);
        *bytes_transferred += 1;
        pages = 1;
    }

    return pages;
}

/**
 * ram_save_page: Send the given page to the stream
 *
 * Returns: Number of pages written.
 *
 * @f: QEMUFile where to send the data
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 * @last_stage: if we are at the completion stage
 * @bytes_transferred: increase it with the number of transferred bytes
 */
static int ram_save_page(QEMUFile *f, RAMBlock* block, ram_addr_t offset,
                         bool last_stage, uint64_t *bytes_transferred)
{
    int pages = -1;
    uint64_t bytes_xmit;
    ram_addr_t current_addr;
    uint8_t *p;
    int ret;
    bool send_async = true;

675
    p = block->host + offset;
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

    /* In doubt sent page as normal */
    bytes_xmit = 0;
    ret = ram_control_save_page(f, block->offset,
                           offset, TARGET_PAGE_SIZE, &bytes_xmit);
    if (bytes_xmit) {
        *bytes_transferred += bytes_xmit;
        pages = 1;
    }

    XBZRLE_cache_lock();

    current_addr = block->offset + offset;

    if (block == last_sent_block) {
        offset |= RAM_SAVE_FLAG_CONTINUE;
    }
    if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
        if (ret != RAM_SAVE_CONTROL_DELAYED) {
            if (bytes_xmit > 0) {
                acct_info.norm_pages++;
            } else if (bytes_xmit == 0) {
                acct_info.dup_pages++;
            }
        }
    } else {
        pages = save_zero_page(f, block, offset, p, bytes_transferred);
        if (pages > 0) {
            /* Must let xbzrle know, otherwise a previous (now 0'd) cached
             * page would be stale
             */
            xbzrle_cache_zero_page(current_addr);
        } else if (!ram_bulk_stage && migrate_use_xbzrle()) {
            pages = save_xbzrle_page(f, &p, current_addr, block,
                                     offset, last_stage, bytes_transferred);
            if (!last_stage) {
                /* Can't send this cached data async, since the cache page
                 * might get updated before it gets to the wire
                 */
                send_async = false;
            }
        }
    }

    /* XBZRLE overflow or normal page */
    if (pages == -1) {
        *bytes_transferred += save_page_header(f, block,
                                               offset | RAM_SAVE_FLAG_PAGE);
        if (send_async) {
            qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
        } else {
            qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
        }
        *bytes_transferred += TARGET_PAGE_SIZE;
        pages = 1;
        acct_info.norm_pages++;
    }

    XBZRLE_cache_unlock();

    return pages;
}

static int do_compress_ram_page(CompressParam *param)
{
    int bytes_sent, blen;
    uint8_t *p;
    RAMBlock *block = param->block;
    ram_addr_t offset = param->offset;

746
    p = block->host + (offset & TARGET_PAGE_MASK);
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

    bytes_sent = save_page_header(param->file, block, offset |
                                  RAM_SAVE_FLAG_COMPRESS_PAGE);
    blen = qemu_put_compression_data(param->file, p, TARGET_PAGE_SIZE,
                                     migrate_compress_level());
    bytes_sent += blen;

    return bytes_sent;
}

static inline void start_compression(CompressParam *param)
{
    param->done = false;
    qemu_mutex_lock(&param->mutex);
    param->start = true;
    qemu_cond_signal(&param->cond);
    qemu_mutex_unlock(&param->mutex);
}

static inline void start_decompression(DecompressParam *param)
{
    qemu_mutex_lock(&param->mutex);
    param->start = true;
    qemu_cond_signal(&param->cond);
    qemu_mutex_unlock(&param->mutex);
}

static uint64_t bytes_transferred;

static void flush_compressed_data(QEMUFile *f)
{
    int idx, len, thread_count;

    if (!migrate_use_compression()) {
        return;
    }
    thread_count = migrate_compress_threads();
    for (idx = 0; idx < thread_count; idx++) {
        if (!comp_param[idx].done) {
            qemu_mutex_lock(comp_done_lock);
            while (!comp_param[idx].done && !quit_comp_thread) {
                qemu_cond_wait(comp_done_cond, comp_done_lock);
            }
            qemu_mutex_unlock(comp_done_lock);
        }
        if (!quit_comp_thread) {
            len = qemu_put_qemu_file(f, comp_param[idx].file);
            bytes_transferred += len;
        }
    }
}

static inline void set_compress_params(CompressParam *param, RAMBlock *block,
                                       ram_addr_t offset)
{
    param->block = block;
    param->offset = offset;
}

static int compress_page_with_multi_thread(QEMUFile *f, RAMBlock *block,
                                           ram_addr_t offset,
                                           uint64_t *bytes_transferred)
{
    int idx, thread_count, bytes_xmit = -1, pages = -1;

    thread_count = migrate_compress_threads();
    qemu_mutex_lock(comp_done_lock);
    while (true) {
        for (idx = 0; idx < thread_count; idx++) {
            if (comp_param[idx].done) {
                bytes_xmit = qemu_put_qemu_file(f, comp_param[idx].file);
                set_compress_params(&comp_param[idx], block, offset);
                start_compression(&comp_param[idx]);
                pages = 1;
                acct_info.norm_pages++;
                *bytes_transferred += bytes_xmit;
                break;
            }
        }
        if (pages > 0) {
            break;
        } else {
            qemu_cond_wait(comp_done_cond, comp_done_lock);
        }
    }
    qemu_mutex_unlock(comp_done_lock);

    return pages;
}

/**
 * ram_save_compressed_page: compress the given page and send it to the stream
 *
 * Returns: Number of pages written.
 *
 * @f: QEMUFile where to send the data
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 * @last_stage: if we are at the completion stage
 * @bytes_transferred: increase it with the number of transferred bytes
 */
static int ram_save_compressed_page(QEMUFile *f, RAMBlock *block,
                                    ram_addr_t offset, bool last_stage,
                                    uint64_t *bytes_transferred)
{
    int pages = -1;
    uint64_t bytes_xmit;
    uint8_t *p;
    int ret;

857
    p = block->host + offset;
858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934

    bytes_xmit = 0;
    ret = ram_control_save_page(f, block->offset,
                                offset, TARGET_PAGE_SIZE, &bytes_xmit);
    if (bytes_xmit) {
        *bytes_transferred += bytes_xmit;
        pages = 1;
    }
    if (block == last_sent_block) {
        offset |= RAM_SAVE_FLAG_CONTINUE;
    }
    if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
        if (ret != RAM_SAVE_CONTROL_DELAYED) {
            if (bytes_xmit > 0) {
                acct_info.norm_pages++;
            } else if (bytes_xmit == 0) {
                acct_info.dup_pages++;
            }
        }
    } else {
        /* When starting the process of a new block, the first page of
         * the block should be sent out before other pages in the same
         * block, and all the pages in last block should have been sent
         * out, keeping this order is important, because the 'cont' flag
         * is used to avoid resending the block name.
         */
        if (block != last_sent_block) {
            flush_compressed_data(f);
            pages = save_zero_page(f, block, offset, p, bytes_transferred);
            if (pages == -1) {
                set_compress_params(&comp_param[0], block, offset);
                /* Use the qemu thread to compress the data to make sure the
                 * first page is sent out before other pages
                 */
                bytes_xmit = do_compress_ram_page(&comp_param[0]);
                acct_info.norm_pages++;
                qemu_put_qemu_file(f, comp_param[0].file);
                *bytes_transferred += bytes_xmit;
                pages = 1;
            }
        } else {
            pages = save_zero_page(f, block, offset, p, bytes_transferred);
            if (pages == -1) {
                pages = compress_page_with_multi_thread(f, block, offset,
                                                        bytes_transferred);
            }
        }
    }

    return pages;
}

/**
 * ram_find_and_save_block: Finds a dirty page and sends it to f
 *
 * Called within an RCU critical section.
 *
 * Returns:  The number of pages written
 *           0 means no dirty pages
 *
 * @f: QEMUFile where to send the data
 * @last_stage: if we are at the completion stage
 * @bytes_transferred: increase it with the number of transferred bytes
 */

static int ram_find_and_save_block(QEMUFile *f, bool last_stage,
                                   uint64_t *bytes_transferred)
{
    RAMBlock *block = last_seen_block;
    ram_addr_t offset = last_offset;
    bool complete_round = false;
    int pages = 0;

    if (!block)
        block = QLIST_FIRST_RCU(&ram_list.blocks);

    while (true) {
935
        offset = migration_bitmap_find_and_reset_dirty(block, offset);
936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024
        if (complete_round && block == last_seen_block &&
            offset >= last_offset) {
            break;
        }
        if (offset >= block->used_length) {
            offset = 0;
            block = QLIST_NEXT_RCU(block, next);
            if (!block) {
                block = QLIST_FIRST_RCU(&ram_list.blocks);
                complete_round = true;
                ram_bulk_stage = false;
                if (migrate_use_xbzrle()) {
                    /* If xbzrle is on, stop using the data compression at this
                     * point. In theory, xbzrle can do better than compression.
                     */
                    flush_compressed_data(f);
                    compression_switch = false;
                }
            }
        } else {
            if (compression_switch && migrate_use_compression()) {
                pages = ram_save_compressed_page(f, block, offset, last_stage,
                                                 bytes_transferred);
            } else {
                pages = ram_save_page(f, block, offset, last_stage,
                                      bytes_transferred);
            }

            /* if page is unmodified, continue to the next */
            if (pages > 0) {
                last_sent_block = block;
                break;
            }
        }
    }

    last_seen_block = block;
    last_offset = offset;

    return pages;
}

void acct_update_position(QEMUFile *f, size_t size, bool zero)
{
    uint64_t pages = size / TARGET_PAGE_SIZE;
    if (zero) {
        acct_info.dup_pages += pages;
    } else {
        acct_info.norm_pages += pages;
        bytes_transferred += size;
        qemu_update_position(f, size);
    }
}

static ram_addr_t ram_save_remaining(void)
{
    return migration_dirty_pages;
}

uint64_t ram_bytes_remaining(void)
{
    return ram_save_remaining() * TARGET_PAGE_SIZE;
}

uint64_t ram_bytes_transferred(void)
{
    return bytes_transferred;
}

uint64_t ram_bytes_total(void)
{
    RAMBlock *block;
    uint64_t total = 0;

    rcu_read_lock();
    QLIST_FOREACH_RCU(block, &ram_list.blocks, next)
        total += block->used_length;
    rcu_read_unlock();
    return total;
}

void free_xbzrle_decoded_buf(void)
{
    g_free(xbzrle_decoded_buf);
    xbzrle_decoded_buf = NULL;
}

static void migration_end(void)
{
L
Li Zhijian 已提交
1025 1026 1027 1028 1029 1030
    /* caller have hold iothread lock or is in a bh, so there is
     * no writing race against this migration_bitmap
     */
    unsigned long *bitmap = migration_bitmap;
    atomic_rcu_set(&migration_bitmap, NULL);
    if (bitmap) {
1031
        memory_global_dirty_log_stop();
L
Li Zhijian 已提交
1032 1033
        synchronize_rcu();
        g_free(bitmap);
1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063
    }

    XBZRLE_cache_lock();
    if (XBZRLE.cache) {
        cache_fini(XBZRLE.cache);
        g_free(XBZRLE.encoded_buf);
        g_free(XBZRLE.current_buf);
        XBZRLE.cache = NULL;
        XBZRLE.encoded_buf = NULL;
        XBZRLE.current_buf = NULL;
    }
    XBZRLE_cache_unlock();
}

static void ram_migration_cancel(void *opaque)
{
    migration_end();
}

static void reset_ram_globals(void)
{
    last_seen_block = NULL;
    last_sent_block = NULL;
    last_offset = 0;
    last_version = ram_list.version;
    ram_bulk_stage = true;
}

#define MAX_WAIT 50 /* ms, half buffered_file limit */

L
Li Zhijian 已提交
1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087
void migration_bitmap_extend(ram_addr_t old, ram_addr_t new)
{
    /* called in qemu main thread, so there is
     * no writing race against this migration_bitmap
     */
    if (migration_bitmap) {
        unsigned long *old_bitmap = migration_bitmap, *bitmap;
        bitmap = bitmap_new(new);

        /* prevent migration_bitmap content from being set bit
         * by migration_bitmap_sync_range() at the same time.
         * it is safe to migration if migration_bitmap is cleared bit
         * at the same time.
         */
        qemu_mutex_lock(&migration_bitmap_mutex);
        bitmap_copy(bitmap, old_bitmap, old);
        bitmap_set(bitmap, old, new - old);
        atomic_rcu_set(&migration_bitmap, bitmap);
        qemu_mutex_unlock(&migration_bitmap_mutex);
        migration_dirty_pages += new - old;
        synchronize_rcu();
        g_free(old_bitmap);
    }
}
1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103

/* Each of ram_save_setup, ram_save_iterate and ram_save_complete has
 * long-running RCU critical section.  When rcu-reclaims in the code
 * start to become numerous it will be necessary to reduce the
 * granularity of these critical sections.
 */

static int ram_save_setup(QEMUFile *f, void *opaque)
{
    RAMBlock *block;
    int64_t ram_bitmap_pages; /* Size of bitmap in pages, including gaps */

    mig_throttle_on = false;
    dirty_rate_high_cnt = 0;
    bitmap_sync_count = 0;
    migration_bitmap_sync_init();
L
Li Zhijian 已提交
1104
    qemu_mutex_init(&migration_bitmap_mutex);
1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266

    if (migrate_use_xbzrle()) {
        XBZRLE_cache_lock();
        XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
                                  TARGET_PAGE_SIZE,
                                  TARGET_PAGE_SIZE);
        if (!XBZRLE.cache) {
            XBZRLE_cache_unlock();
            error_report("Error creating cache");
            return -1;
        }
        XBZRLE_cache_unlock();

        /* We prefer not to abort if there is no memory */
        XBZRLE.encoded_buf = g_try_malloc0(TARGET_PAGE_SIZE);
        if (!XBZRLE.encoded_buf) {
            error_report("Error allocating encoded_buf");
            return -1;
        }

        XBZRLE.current_buf = g_try_malloc(TARGET_PAGE_SIZE);
        if (!XBZRLE.current_buf) {
            error_report("Error allocating current_buf");
            g_free(XBZRLE.encoded_buf);
            XBZRLE.encoded_buf = NULL;
            return -1;
        }

        acct_clear();
    }

    /* iothread lock needed for ram_list.dirty_memory[] */
    qemu_mutex_lock_iothread();
    qemu_mutex_lock_ramlist();
    rcu_read_lock();
    bytes_transferred = 0;
    reset_ram_globals();

    ram_bitmap_pages = last_ram_offset() >> TARGET_PAGE_BITS;
    migration_bitmap = bitmap_new(ram_bitmap_pages);
    bitmap_set(migration_bitmap, 0, ram_bitmap_pages);

    /*
     * Count the total number of pages used by ram blocks not including any
     * gaps due to alignment or unplugs.
     */
    migration_dirty_pages = ram_bytes_total() >> TARGET_PAGE_BITS;

    memory_global_dirty_log_start();
    migration_bitmap_sync();
    qemu_mutex_unlock_ramlist();
    qemu_mutex_unlock_iothread();

    qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);

    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
        qemu_put_byte(f, strlen(block->idstr));
        qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr));
        qemu_put_be64(f, block->used_length);
    }

    rcu_read_unlock();

    ram_control_before_iterate(f, RAM_CONTROL_SETUP);
    ram_control_after_iterate(f, RAM_CONTROL_SETUP);

    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);

    return 0;
}

static int ram_save_iterate(QEMUFile *f, void *opaque)
{
    int ret;
    int i;
    int64_t t0;
    int pages_sent = 0;

    rcu_read_lock();
    if (ram_list.version != last_version) {
        reset_ram_globals();
    }

    /* Read version before ram_list.blocks */
    smp_rmb();

    ram_control_before_iterate(f, RAM_CONTROL_ROUND);

    t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
    i = 0;
    while ((ret = qemu_file_rate_limit(f)) == 0) {
        int pages;

        pages = ram_find_and_save_block(f, false, &bytes_transferred);
        /* no more pages to sent */
        if (pages == 0) {
            break;
        }
        pages_sent += pages;
        acct_info.iterations++;
        check_guest_throttling();
        /* we want to check in the 1st loop, just in case it was the 1st time
           and we had to sync the dirty bitmap.
           qemu_get_clock_ns() is a bit expensive, so we only check each some
           iterations
        */
        if ((i & 63) == 0) {
            uint64_t t1 = (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - t0) / 1000000;
            if (t1 > MAX_WAIT) {
                DPRINTF("big wait: %" PRIu64 " milliseconds, %d iterations\n",
                        t1, i);
                break;
            }
        }
        i++;
    }
    flush_compressed_data(f);
    rcu_read_unlock();

    /*
     * Must occur before EOS (or any QEMUFile operation)
     * because of RDMA protocol.
     */
    ram_control_after_iterate(f, RAM_CONTROL_ROUND);

    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
    bytes_transferred += 8;

    ret = qemu_file_get_error(f);
    if (ret < 0) {
        return ret;
    }

    return pages_sent;
}

/* Called with iothread lock */
static int ram_save_complete(QEMUFile *f, void *opaque)
{
    rcu_read_lock();

    migration_bitmap_sync();

    ram_control_before_iterate(f, RAM_CONTROL_FINISH);

    /* try transferring iterative blocks of memory */

    /* flush all remaining blocks regardless of rate limiting */
    while (true) {
        int pages;

        pages = ram_find_and_save_block(f, true, &bytes_transferred);
        /* no more blocks to sent */
        if (pages == 0) {
            break;
        }
    }

    flush_compressed_data(f);
    ram_control_after_iterate(f, RAM_CONTROL_FINISH);

    rcu_read_unlock();
P
Paolo Bonzini 已提交
1267 1268

    migration_end();
1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342
    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);

    return 0;
}

static uint64_t ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
{
    uint64_t remaining_size;

    remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;

    if (remaining_size < max_size) {
        qemu_mutex_lock_iothread();
        rcu_read_lock();
        migration_bitmap_sync();
        rcu_read_unlock();
        qemu_mutex_unlock_iothread();
        remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
    }
    return remaining_size;
}

static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
{
    unsigned int xh_len;
    int xh_flags;

    if (!xbzrle_decoded_buf) {
        xbzrle_decoded_buf = g_malloc(TARGET_PAGE_SIZE);
    }

    /* extract RLE header */
    xh_flags = qemu_get_byte(f);
    xh_len = qemu_get_be16(f);

    if (xh_flags != ENCODING_FLAG_XBZRLE) {
        error_report("Failed to load XBZRLE page - wrong compression!");
        return -1;
    }

    if (xh_len > TARGET_PAGE_SIZE) {
        error_report("Failed to load XBZRLE page - len overflow!");
        return -1;
    }
    /* load data and decode */
    qemu_get_buffer(f, xbzrle_decoded_buf, xh_len);

    /* decode RLE */
    if (xbzrle_decode_buffer(xbzrle_decoded_buf, xh_len, host,
                             TARGET_PAGE_SIZE) == -1) {
        error_report("Failed to load XBZRLE page - decode error!");
        return -1;
    }

    return 0;
}

/* Must be called from within a rcu critical section.
 * Returns a pointer from within the RCU-protected ram_list.
 */
static inline void *host_from_stream_offset(QEMUFile *f,
                                            ram_addr_t offset,
                                            int flags)
{
    static RAMBlock *block = NULL;
    char id[256];
    uint8_t len;

    if (flags & RAM_SAVE_FLAG_CONTINUE) {
        if (!block || block->max_length <= offset) {
            error_report("Ack, bad migration stream!");
            return NULL;
        }

1343
        return block->host + offset;
1344 1345 1346 1347 1348 1349 1350 1351 1352
    }

    len = qemu_get_byte(f);
    qemu_get_buffer(f, (uint8_t *)id, len);
    id[len] = 0;

    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
        if (!strncmp(id, block->idstr, sizeof(id)) &&
            block->max_length > offset) {
1353
            return block->host + offset;
1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515
        }
    }

    error_report("Can't find block %s!", id);
    return NULL;
}

/*
 * If a page (or a whole RDMA chunk) has been
 * determined to be zero, then zap it.
 */
void ram_handle_compressed(void *host, uint8_t ch, uint64_t size)
{
    if (ch != 0 || !is_zero_range(host, size)) {
        memset(host, ch, size);
    }
}

static void *do_data_decompress(void *opaque)
{
    DecompressParam *param = opaque;
    unsigned long pagesize;

    while (!quit_decomp_thread) {
        qemu_mutex_lock(&param->mutex);
        while (!param->start && !quit_decomp_thread) {
            qemu_cond_wait(&param->cond, &param->mutex);
            pagesize = TARGET_PAGE_SIZE;
            if (!quit_decomp_thread) {
                /* uncompress() will return failed in some case, especially
                 * when the page is dirted when doing the compression, it's
                 * not a problem because the dirty page will be retransferred
                 * and uncompress() won't break the data in other pages.
                 */
                uncompress((Bytef *)param->des, &pagesize,
                           (const Bytef *)param->compbuf, param->len);
            }
            param->start = false;
        }
        qemu_mutex_unlock(&param->mutex);
    }

    return NULL;
}

void migrate_decompress_threads_create(void)
{
    int i, thread_count;

    thread_count = migrate_decompress_threads();
    decompress_threads = g_new0(QemuThread, thread_count);
    decomp_param = g_new0(DecompressParam, thread_count);
    compressed_data_buf = g_malloc0(compressBound(TARGET_PAGE_SIZE));
    quit_decomp_thread = false;
    for (i = 0; i < thread_count; i++) {
        qemu_mutex_init(&decomp_param[i].mutex);
        qemu_cond_init(&decomp_param[i].cond);
        decomp_param[i].compbuf = g_malloc0(compressBound(TARGET_PAGE_SIZE));
        qemu_thread_create(decompress_threads + i, "decompress",
                           do_data_decompress, decomp_param + i,
                           QEMU_THREAD_JOINABLE);
    }
}

void migrate_decompress_threads_join(void)
{
    int i, thread_count;

    quit_decomp_thread = true;
    thread_count = migrate_decompress_threads();
    for (i = 0; i < thread_count; i++) {
        qemu_mutex_lock(&decomp_param[i].mutex);
        qemu_cond_signal(&decomp_param[i].cond);
        qemu_mutex_unlock(&decomp_param[i].mutex);
    }
    for (i = 0; i < thread_count; i++) {
        qemu_thread_join(decompress_threads + i);
        qemu_mutex_destroy(&decomp_param[i].mutex);
        qemu_cond_destroy(&decomp_param[i].cond);
        g_free(decomp_param[i].compbuf);
    }
    g_free(decompress_threads);
    g_free(decomp_param);
    g_free(compressed_data_buf);
    decompress_threads = NULL;
    decomp_param = NULL;
    compressed_data_buf = NULL;
}

static void decompress_data_with_multi_threads(uint8_t *compbuf,
                                               void *host, int len)
{
    int idx, thread_count;

    thread_count = migrate_decompress_threads();
    while (true) {
        for (idx = 0; idx < thread_count; idx++) {
            if (!decomp_param[idx].start) {
                memcpy(decomp_param[idx].compbuf, compbuf, len);
                decomp_param[idx].des = host;
                decomp_param[idx].len = len;
                start_decompression(&decomp_param[idx]);
                break;
            }
        }
        if (idx < thread_count) {
            break;
        }
    }
}

static int ram_load(QEMUFile *f, void *opaque, int version_id)
{
    int flags = 0, ret = 0;
    static uint64_t seq_iter;
    int len = 0;

    seq_iter++;

    if (version_id != 4) {
        ret = -EINVAL;
    }

    /* This RCU critical section can be very long running.
     * When RCU reclaims in the code start to become numerous,
     * it will be necessary to reduce the granularity of this
     * critical section.
     */
    rcu_read_lock();
    while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
        ram_addr_t addr, total_ram_bytes;
        void *host;
        uint8_t ch;

        addr = qemu_get_be64(f);
        flags = addr & ~TARGET_PAGE_MASK;
        addr &= TARGET_PAGE_MASK;

        switch (flags & ~RAM_SAVE_FLAG_CONTINUE) {
        case RAM_SAVE_FLAG_MEM_SIZE:
            /* Synchronize RAM block list */
            total_ram_bytes = addr;
            while (!ret && total_ram_bytes) {
                RAMBlock *block;
                char id[256];
                ram_addr_t length;

                len = qemu_get_byte(f);
                qemu_get_buffer(f, (uint8_t *)id, len);
                id[len] = 0;
                length = qemu_get_be64(f);

                QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
                    if (!strncmp(id, block->idstr, sizeof(id))) {
                        if (length != block->used_length) {
                            Error *local_err = NULL;

                            ret = qemu_ram_resize(block->offset, length, &local_err);
                            if (local_err) {
                                error_report_err(local_err);
                            }
                        }
1516 1517
                        ram_control_load_hook(f, RAM_CONTROL_BLOCK_REG,
                                              block->idstr);
1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585
                        break;
                    }
                }

                if (!block) {
                    error_report("Unknown ramblock \"%s\", cannot "
                                 "accept migration", id);
                    ret = -EINVAL;
                }

                total_ram_bytes -= length;
            }
            break;
        case RAM_SAVE_FLAG_COMPRESS:
            host = host_from_stream_offset(f, addr, flags);
            if (!host) {
                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                ret = -EINVAL;
                break;
            }
            ch = qemu_get_byte(f);
            ram_handle_compressed(host, ch, TARGET_PAGE_SIZE);
            break;
        case RAM_SAVE_FLAG_PAGE:
            host = host_from_stream_offset(f, addr, flags);
            if (!host) {
                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                ret = -EINVAL;
                break;
            }
            qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
            break;
        case RAM_SAVE_FLAG_COMPRESS_PAGE:
            host = host_from_stream_offset(f, addr, flags);
            if (!host) {
                error_report("Invalid RAM offset " RAM_ADDR_FMT, addr);
                ret = -EINVAL;
                break;
            }

            len = qemu_get_be32(f);
            if (len < 0 || len > compressBound(TARGET_PAGE_SIZE)) {
                error_report("Invalid compressed data length: %d", len);
                ret = -EINVAL;
                break;
            }
            qemu_get_buffer(f, compressed_data_buf, len);
            decompress_data_with_multi_threads(compressed_data_buf, host, len);
            break;
        case RAM_SAVE_FLAG_XBZRLE:
            host = host_from_stream_offset(f, addr, flags);
            if (!host) {
                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                ret = -EINVAL;
                break;
            }
            if (load_xbzrle(f, addr, host) < 0) {
                error_report("Failed to decompress XBZRLE page at "
                             RAM_ADDR_FMT, addr);
                ret = -EINVAL;
                break;
            }
            break;
        case RAM_SAVE_FLAG_EOS:
            /* normal exit */
            break;
        default:
            if (flags & RAM_SAVE_FLAG_HOOK) {
1586
                ram_control_load_hook(f, RAM_CONTROL_HOOK, NULL);
1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666
            } else {
                error_report("Unknown combination of migration flags: %#x",
                             flags);
                ret = -EINVAL;
            }
        }
        if (!ret) {
            ret = qemu_file_get_error(f);
        }
    }

    rcu_read_unlock();
    DPRINTF("Completed load of VM with exit code %d seq iteration "
            "%" PRIu64 "\n", ret, seq_iter);
    return ret;
}

static SaveVMHandlers savevm_ram_handlers = {
    .save_live_setup = ram_save_setup,
    .save_live_iterate = ram_save_iterate,
    .save_live_complete = ram_save_complete,
    .save_live_pending = ram_save_pending,
    .load_state = ram_load,
    .cancel = ram_migration_cancel,
};

void ram_mig_init(void)
{
    qemu_mutex_init(&XBZRLE.lock);
    register_savevm_live(NULL, "ram", 0, 4, &savevm_ram_handlers, NULL);
}
/* Stub function that's gets run on the vcpu when its brought out of the
   VM to run inside qemu via async_run_on_cpu()*/

static void mig_sleep_cpu(void *opq)
{
    qemu_mutex_unlock_iothread();
    g_usleep(30*1000);
    qemu_mutex_lock_iothread();
}

/* To reduce the dirty rate explicitly disallow the VCPUs from spending
   much time in the VM. The migration thread will try to catchup.
   Workload will experience a performance drop.
*/
static void mig_throttle_guest_down(void)
{
    CPUState *cpu;

    qemu_mutex_lock_iothread();
    CPU_FOREACH(cpu) {
        async_run_on_cpu(cpu, mig_sleep_cpu, NULL);
    }
    qemu_mutex_unlock_iothread();
}

static void check_guest_throttling(void)
{
    static int64_t t0;
    int64_t        t1;

    if (!mig_throttle_on) {
        return;
    }

    if (!t0)  {
        t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
        return;
    }

    t1 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);

    /* If it has been more than 40 ms since the last time the guest
     * was throttled then do it again.
     */
    if (40 < (t1-t0)/1000000) {
        mig_throttle_guest_down();
        t0 = t1;
    }
}