aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/power/hibernate.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/power/hibernate.c')
0 files changed, 0 insertions, 0 deletions
generated by cgit v1.2.2 (git 2.25.0) at 2025-10-07 02:13:19 -0400
'>236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 
/* Bottleneck Bandwidth and RTT (BBR) congestion control
 *
 * BBR congestion control computes the sending rate based on the delivery
 * rate (throughput) estimated from ACKs. In a nutshell:
 *
 *   On each ACK, update our model of the network path:
 *      bottleneck_bandwidth = windowed_max(delivered / elapsed, 10 round trips)
 *      min_rtt = windowed_min(rtt, 10 seconds)
 *   pacing_rate = pacing_gain * bottleneck_bandwidth
 *   cwnd = max(cwnd_gain * bottleneck_bandwidth * min_rtt, 4)
 *
 * The core algorithm does not react directly to packet losses or delays,
 * although BBR may adjust the size of next send per ACK when loss is
 * observed, or adjust the sending rate if it estimates there is a
 * traffic policer, in order to keep the drop rate reasonable.
 *
 * Here is a state transition diagram for BBR:
 *
 *             |
 *             V
 *    +---> STARTUP  ----+
 *    |        |         |
 *    |        V         |
 *    |      DRAIN   ----+
 *    |        |         |
 *    |        V         |
 *    +---> PROBE_BW ----+
 *    |      ^    |      |
 *    |      |    |      |
 *    |      +----+      |
 *    |                  |
 *    +---- PROBE_RTT <--+
 *
 * A BBR flow starts in STARTUP, and ramps up its sending rate quickly.
 * When it estimates the pipe is full, it enters DRAIN to drain the queue.
 * In steady state a BBR flow only uses PROBE_BW and PROBE_RTT.
 * A long-lived BBR flow spends the vast majority of its time remaining
 * (repeatedly) in PROBE_BW, fully probing and utilizing the pipe's bandwidth
 * in a fair manner, with a small, bounded queue. *If* a flow has been
 * continuously sending for the entire min_rtt window, and hasn't seen an RTT
 * sample that matches or decreases its min_rtt estimate for 10 seconds, then
 * it briefly enters PROBE_RTT to cut inflight to a minimum value to re-probe
 * the path's two-way propagation delay (min_rtt). When exiting PROBE_RTT, if
 * we estimated that we reached the full bw of the pipe then we enter PROBE_BW;
 * otherwise we enter STARTUP to try to fill the pipe.
 *
 * BBR is described in detail in:
 *   "BBR: Congestion-Based Congestion Control",
 *   Neal Cardwell, Yuchung Cheng, C. Stephen Gunn, Soheil Hassas Yeganeh,
 *   Van Jacobson. ACM Queue, Vol. 14 No. 5, September-October 2016.
 *
 * There is a public e-mail list for discussing BBR development and testing:
 *   https://groups.google.com/forum/#!forum/bbr-dev
 *
 * NOTE: BBR might be used with the fq qdisc ("man tc-fq") with pacing enabled,
 * otherwise TCP stack falls back to an internal pacing using one high
 * resolution timer per TCP socket and may use more resources.
 */
#include <linux/module.h>
#include <net/tcp.h>
#include <linux/inet_diag.h>
#include <linux/inet.h>
#include <linux/random.h>
#include <linux/win_minmax.h>

/* Scale factor for rate in pkt/uSec unit to avoid truncation in bandwidth
 * estimation. The rate unit ~= (1500 bytes / 1 usec / 2^24) ~= 715 bps.
 * This handles bandwidths from 0.06pps (715bps) to 256Mpps (3Tbps) in a u32.
 * Since the minimum window is >=4 packets, the lower bound isn't
 * an issue. The upper bound isn't an issue with existing technologies.
 */
#define BW_SCALE 24
#define BW_UNIT (1 << BW_SCALE)

#define BBR_SCALE 8	/* scaling factor for fractions in BBR (e.g. gains) */
#define BBR_UNIT (1 << BBR_SCALE)

/* BBR has the following modes for deciding how fast to send: */
enum bbr_mode {
	BBR_STARTUP,	/* ramp up sending rate rapidly to fill pipe */
	BBR_DRAIN,	/* drain any queue created during startup */
	BBR_PROBE_BW,	/* discover, share bw: pace around estimated bw */
	BBR_PROBE_RTT,	/* cut inflight to min to probe min_rtt */
};

/* BBR congestion control block */
struct bbr {
	u32	min_rtt_us;	        /* min RTT in min_rtt_win_sec window */
	u32	min_rtt_stamp;	        /* timestamp of min_rtt_us */
	u32	probe_rtt_done_stamp;   /* end time for BBR_PROBE_RTT mode */
	struct minmax bw;	/* Max recent delivery rate in pkts/uS << 24 */
	u32	rtt_cnt;	    /* count of packet-timed rounds elapsed */
	u32     next_rtt_delivered; /* scb->tx.delivered at end of round */
	u64	cycle_mstamp;	     /* time of this cycle phase start */
	u32     mode:3,		     /* current bbr_mode in state machine */
		prev_ca_state:3,     /* CA state on previous ACK */
		packet_conservation:1,  /* use packet conservation? */
		restore_cwnd:1,	     /* decided to revert cwnd to old value */
		round_start:1,	     /* start of packet-timed tx->ack round? */
		tso_segs_goal:7,     /* segments we want in each skb we send */
		idle_restart:1,	     /* restarting after idle? */
		probe_rtt_round_done:1,  /* a BBR_PROBE_RTT round at 4 pkts? */
		unused:5,
		lt_is_sampling:1,    /* taking long-term ("LT") samples now? */
		lt_rtt_cnt:7,	     /* round trips in long-term interval */
		lt_use_bw:1;	     /* use lt_bw as our bw estimate? */
	u32	lt_bw;		     /* LT est delivery rate in pkts/uS << 24 */
	u32	lt_last_delivered;   /* LT intvl start: tp->delivered */
	u32	lt_last_stamp;	     /* LT intvl start: tp->delivered_mstamp */
	u32	lt_last_lost;	     /* LT intvl start: tp->lost */
	u32	pacing_gain:10,	/* current gain for setting pacing rate */
		cwnd_gain:10,	/* current gain for setting cwnd */
		full_bw_cnt:3,	/* number of rounds without large bw gains */
		cycle_idx:3,	/* current index in pacing_gain cycle array */
		has_seen_rtt:1, /* have we seen an RTT sample yet? */
		unused_b:5;
	u32	prior_cwnd;	/* prior cwnd upon entering loss recovery */
	u32	full_bw;	/* recent bw, to estimate if pipe is full */
};

#define CYCLE_LEN	8	/* number of phases in a pacing gain cycle */

/* Window length of bw filter (in rounds): */
static const int bbr_bw_rtts = CYCLE_LEN + 2;
/* Window length of min_rtt filter (in sec): */
static const u32 bbr_min_rtt_win_sec = 10;
/* Minimum time (in ms) spent at bbr_cwnd_min_target in BBR_PROBE_RTT mode: */
static const u32 bbr_probe_rtt_mode_ms = 200;
/* Skip TSO below the following bandwidth (bits/sec): */
static const int bbr_min_tso_rate = 1200000;

/* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain
 * that will allow a smoothly increasing pacing rate that will double each RTT
 * and send the same number of packets per RTT that an un-paced, slow-starting
 * Reno or CUBIC flow would:
 */
static const int bbr_high_gain  = BBR_UNIT * 2885 / 1000 + 1;
/* The pacing gain of 1/high_gain in BBR_DRAIN is calculated to typically drain
 * the queue created in BBR_STARTUP in a single round:
 */
static const int bbr_drain_gain = BBR_UNIT * 1000 / 2885;
/* The gain for deriving steady-state cwnd tolerates delayed/stretched ACKs: */
static const int bbr_cwnd_gain  = BBR_UNIT * 2;
/* The pacing_gain values for the PROBE_BW gain cycle, to discover/share bw: */
static const int bbr_pacing_gain[] = {
	BBR_UNIT * 5 / 4,	/* probe for more available bw */
	BBR_UNIT * 3 / 4,	/* drain queue and/or yield bw to other flows */
	BBR_UNIT, BBR_UNIT, BBR_UNIT,	/* cruise at 1.0*bw to utilize pipe, */
	BBR_UNIT, BBR_UNIT, BBR_UNIT	/* without creating excess queue... */
};
/* Randomize the starting gain cycling phase over N phases: */
static const u32 bbr_cycle_rand = 7;

/* Try to keep at least this many packets in flight, if things go smoothly. For
 * smooth functioning, a sliding window protocol ACKing every other packet
 * needs at least 4 packets in flight:
 */
static const u32 bbr_cwnd_min_target = 4;

/* To estimate if BBR_STARTUP mode (i.e. high_gain) has filled pipe... */
/* If bw has increased significantly (1.25x), there may be more bw available: */
static const u32 bbr_full_bw_thresh = BBR_UNIT * 5 / 4;
/* But after 3 rounds w/o significant bw growth, estimate pipe is full: */
static const u32 bbr_full_bw_cnt = 3;

/* "long-term" ("LT") bandwidth estimator parameters... */
/* The minimum number of rounds in an LT bw sampling interval: */
static const u32 bbr_lt_intvl_min_rtts = 4;
/* If lost/delivered ratio > 20%, interval is "lossy" and we may be policed: */
static const u32 bbr_lt_loss_thresh = 50;
/* If 2 intervals have a bw ratio <= 1/8, their bw is "consistent": */
static const u32 bbr_lt_bw_ratio = BBR_UNIT / 8;
/* If 2 intervals have a bw diff <= 4 Kbit/sec their bw is "consistent": */
static const u32 bbr_lt_bw_diff = 4000 / 8;
/* If we estimate we're policed, use lt_bw for this many round trips: */
static const u32 bbr_lt_bw_max_rtts = 48;

/* Do we estimate that STARTUP filled the pipe? */
static bool bbr_full_bw_reached(const struct sock *sk)
{
	const struct bbr *bbr = inet_csk_ca(sk);

	return bbr->full_bw_cnt >= bbr_full_bw_cnt;
}

/* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */
static u32 bbr_max_bw(const struct sock *sk)
{
	struct bbr *bbr = inet_csk_ca(sk);

	return minmax_get(&bbr->bw);
}

/* Return the estimated bandwidth of the path, in pkts/uS << BW_SCALE. */
static u32 bbr_bw(const struct sock *sk)
{
	struct bbr *bbr = inet_csk_ca(sk);

	return bbr->lt_use_bw ? bbr->lt_bw : bbr_max_bw(sk);
}

/* Return rate in bytes per second, optionally with a gain.