bfq-iosched.c 182.7 KB
Newer Older
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
/*
 * Budget Fair Queueing (BFQ) I/O scheduler.
 *
 * Based on ideas and code from CFQ:
 * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
 *
 * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
 *		      Paolo Valente <paolo.valente@unimore.it>
 *
 * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
 *                    Arianna Avanzini <avanzini@google.com>
 *
 * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License as
 *  published by the Free Software Foundation; either version 2 of the
 *  License, or (at your option) any later version.
 *
 *  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 for more details.
 *
 * BFQ is a proportional-share I/O scheduler, with some extra
 * low-latency capabilities. BFQ also supports full hierarchical
 * scheduling through cgroups. Next paragraphs provide an introduction
 * on BFQ inner workings. Details on BFQ benefits, usage and
 * limitations can be found in Documentation/block/bfq-iosched.txt.
 *
 * BFQ is a proportional-share storage-I/O scheduling algorithm based
 * on the slice-by-slice service scheme of CFQ. But BFQ assigns
 * budgets, measured in number of sectors, to processes instead of
 * time slices. The device is not granted to the in-service process
 * for a given time slice, but until it has exhausted its assigned
 * budget. This change from the time to the service domain enables BFQ
 * to distribute the device throughput among processes as desired,
 * without any distortion due to throughput fluctuations, or to device
 * internal queueing. BFQ uses an ad hoc internal scheduler, called
 * B-WF2Q+, to schedule processes according to their budgets. More
 * precisely, BFQ schedules queues associated with processes. Each
 * process/queue is assigned a user-configurable weight, and B-WF2Q+
 * guarantees that each queue receives a fraction of the throughput
 * proportional to its weight. Thanks to the accurate policy of
 * B-WF2Q+, BFQ can afford to assign high budgets to I/O-bound
 * processes issuing sequential requests (to boost the throughput),
 * and yet guarantee a low latency to interactive and soft real-time
 * applications.
 *
 * In particular, to provide these low-latency guarantees, BFQ
 * explicitly privileges the I/O of two classes of time-sensitive
 * applications: interactive and soft real-time. This feature enables
 * BFQ to provide applications in these classes with a very low
 * latency. Finally, BFQ also features additional heuristics for
 * preserving both a low latency and a high throughput on NCQ-capable,
 * rotational or flash-based devices, and to get the job done quickly
 * for applications consisting in many I/O-bound processes.
 *
59 60 61 62 63
 * NOTE: if the main or only goal, with a given device, is to achieve
 * the maximum-possible throughput at all times, then do switch off
 * all low-latency heuristics for that device, by setting low_latency
 * to 0.
 *
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
 * BFQ is described in [1], where also a reference to the initial, more
 * theoretical paper on BFQ can be found. The interested reader can find
 * in the latter paper full details on the main algorithm, as well as
 * formulas of the guarantees and formal proofs of all the properties.
 * With respect to the version of BFQ presented in these papers, this
 * implementation adds a few more heuristics, such as the one that
 * guarantees a low latency to soft real-time applications, and a
 * hierarchical extension based on H-WF2Q+.
 *
 * B-WF2Q+ is based on WF2Q+, which is described in [2], together with
 * H-WF2Q+, while the augmented tree used here to implement B-WF2Q+
 * with O(log N) complexity derives from the one introduced with EEVDF
 * in [3].
 *
 * [1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
 *     Scheduler", Proceedings of the First Workshop on Mobile System
 *     Technologies (MST-2015), May 2015.
 *     http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
 *
 * [2] Jon C.R. Bennett and H. Zhang, "Hierarchical Packet Fair Queueing
 *     Algorithms", IEEE/ACM Transactions on Networking, 5(5):675-689,
 *     Oct 1997.
 *
 * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz
 *
 * [3] I. Stoica and H. Abdel-Wahab, "Earliest Eligible Virtual Deadline
 *     First: A Flexible and Accurate Mechanism for Proportional Share
 *     Resource Allocation", technical report.
 *
 * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf
 */
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
98
#include <linux/cgroup.h>
99 100 101 102 103 104 105 106 107 108 109
#include <linux/elevator.h>
#include <linux/ktime.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/sbitmap.h>
#include <linux/delay.h>

#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"
#include "blk-mq-sched.h"
110
#include "bfq-iosched.h"
111
#include "blk-wbt.h"
112

113 114 115 116 117 118 119 120 121 122 123 124
#define BFQ_BFQQ_FNS(name)						\
void bfq_mark_bfqq_##name(struct bfq_queue *bfqq)			\
{									\
	__set_bit(BFQQF_##name, &(bfqq)->flags);			\
}									\
void bfq_clear_bfqq_##name(struct bfq_queue *bfqq)			\
{									\
	__clear_bit(BFQQF_##name, &(bfqq)->flags);		\
}									\
int bfq_bfqq_##name(const struct bfq_queue *bfqq)			\
{									\
	return test_bit(BFQQF_##name, &(bfqq)->flags);		\
125 126
}

127 128 129 130 131
BFQ_BFQQ_FNS(just_created);
BFQ_BFQQ_FNS(busy);
BFQ_BFQQ_FNS(wait_request);
BFQ_BFQQ_FNS(non_blocking_wait_rq);
BFQ_BFQQ_FNS(fifo_expire);
132
BFQ_BFQQ_FNS(has_short_ttime);
133 134 135 136 137 138 139
BFQ_BFQQ_FNS(sync);
BFQ_BFQQ_FNS(IO_bound);
BFQ_BFQQ_FNS(in_large_burst);
BFQ_BFQQ_FNS(coop);
BFQ_BFQQ_FNS(split_coop);
BFQ_BFQQ_FNS(softrt_update);
#undef BFQ_BFQQ_FNS						\
140

141 142
/* Expiration time of sync (0) and async (1) requests, in ns. */
static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
143

144 145
/* Maximum backwards seek (magic number lifted from CFQ), in KiB. */
static const int bfq_back_max = 16 * 1024;
146

147 148
/* Penalty of a backwards seek, in number of sectors. */
static const int bfq_back_penalty = 2;
149

150 151
/* Idling period duration, in ns. */
static u64 bfq_slice_idle = NSEC_PER_SEC / 125;
152

153 154
/* Minimum number of assigned budgets for which stats are safe to compute. */
static const int bfq_stats_min_budgets = 194;
155

156 157
/* Default maximum budget values, in sectors and number of requests. */
static const int bfq_default_max_budget = 16 * 1024;
158

159 160 161 162 163 164
/*
 * Async to sync throughput distribution is controlled as follows:
 * when an async request is served, the entity is charged the number
 * of sectors of the request, multiplied by the factor below
 */
static const int bfq_async_charge_factor = 10;
165

166 167
/* Default timeout values, in jiffies, approximating CFQ defaults. */
const int bfq_timeout = HZ / 8;
168

169 170 171 172 173 174 175 176 177 178 179 180 181 182
/*
 * Time limit for merging (see comments in bfq_setup_cooperator). Set
 * to the slowest value that, in our tests, proved to be effective in
 * removing false positives, while not causing true positives to miss
 * queue merging.
 *
 * As can be deduced from the low time limit below, queue merging, if
 * successful, happens at the very beggining of the I/O of the involved
 * cooperating processes, as a consequence of the arrival of the very
 * first requests from each cooperator.  After that, there is very
 * little chance to find cooperators.
 */
static const unsigned long bfq_merge_time_limit = HZ/10;

183
static struct kmem_cache *bfq_pool;
184

185 186
/* Below this threshold (in ns), we consider thinktime immediate. */
#define BFQ_MIN_TT		(2 * NSEC_PER_MSEC)
187

188 189 190
/* hw_tag detection: parallel requests threshold and min samples needed. */
#define BFQ_HW_QUEUE_THRESHOLD	4
#define BFQ_HW_QUEUE_SAMPLES	32
191

192 193 194
#define BFQQ_SEEK_THR		(sector_t)(8 * 100)
#define BFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
#define BFQQ_CLOSE_THR		(sector_t)(8 * 1024)
195
#define BFQQ_SEEKY(bfqq)	(hweight32(bfqq->seek_history) > 19)
196

197 198 199 200 201 202
/* Min number of samples required to perform peak-rate update */
#define BFQ_RATE_MIN_SAMPLES	32
/* Min observation time interval required to perform a peak-rate update (ns) */
#define BFQ_RATE_MIN_INTERVAL	(300*NSEC_PER_MSEC)
/* Target observation time interval for a peak-rate update (ns) */
#define BFQ_RATE_REF_INTERVAL	NSEC_PER_SEC
203

204 205 206 207 208 209 210 211 212 213 214 215 216 217
/*
 * Shift used for peak-rate fixed precision calculations.
 * With
 * - the current shift: 16 positions
 * - the current type used to store rate: u32
 * - the current unit of measure for rate: [sectors/usec], or, more precisely,
 *   [(sectors/usec) / 2^BFQ_RATE_SHIFT] to take into account the shift,
 * the range of rates that can be stored is
 * [1 / 2^BFQ_RATE_SHIFT, 2^(32 - BFQ_RATE_SHIFT)] sectors/usec =
 * [1 / 2^16, 2^16] sectors/usec = [15e-6, 65536] sectors/usec =
 * [15, 65G] sectors/sec
 * Which, assuming a sector size of 512B, corresponds to a range of
 * [7.5K, 33T] B/sec
 */
218
#define BFQ_RATE_SHIFT		16
219

220 221 222 223 224
/*
 * By default, BFQ computes the duration of the weight raising for
 * interactive applications automatically, using the following formula:
 * duration = (R / r) * T, where r is the peak rate of the device, and
 * R and T are two reference parameters.
225 226 227 228 229 230 231 232 233 234 235
 * In particular, R is the peak rate of the reference device (see
 * below), and T is a reference time: given the systems that are
 * likely to be installed on the reference device according to its
 * speed class, T is about the maximum time needed, under BFQ and
 * while reading two files in parallel, to load typical large
 * applications on these systems (see the comments on
 * max_service_from_wr below, for more details on how T is obtained).
 * In practice, the slower/faster the device at hand is, the more/less
 * it takes to load applications with respect to the reference device.
 * Accordingly, the longer/shorter BFQ grants weight raising to
 * interactive applications.
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
 *
 * BFQ uses four different reference pairs (R, T), depending on:
 * . whether the device is rotational or non-rotational;
 * . whether the device is slow, such as old or portable HDDs, as well as
 *   SD cards, or fast, such as newer HDDs and SSDs.
 *
 * The device's speed class is dynamically (re)detected in
 * bfq_update_peak_rate() every time the estimated peak rate is updated.
 *
 * In the following definitions, R_slow[0]/R_fast[0] and
 * T_slow[0]/T_fast[0] are the reference values for a slow/fast
 * rotational device, whereas R_slow[1]/R_fast[1] and
 * T_slow[1]/T_fast[1] are the reference values for a slow/fast
 * non-rotational device. Finally, device_speed_thresh are the
 * thresholds used to switch between speed classes. The reference
 * rates are not the actual peak rates of the devices used as a
 * reference, but slightly lower values. The reason for using these
 * slightly lower values is that the peak-rate estimator tends to
 * yield slightly lower values than the actual peak rate (it can yield
 * the actual peak rate only if there is only one process doing I/O,
 * and the process does sequential I/O).
 *
 * Both the reference peak rates and the thresholds are measured in
 * sectors/usec, left-shifted by BFQ_RATE_SHIFT.
 */
static int R_slow[2] = {1000, 10700};
static int R_fast[2] = {14000, 33000};
/*
 * To improve readability, a conversion function is used to initialize the
 * following arrays, which entails that they can be initialized only in a
 * function.
 */
static int T_slow[2];
static int T_fast[2];
static int device_speed_thresh[2];
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
/*
 * BFQ uses the above-detailed, time-based weight-raising mechanism to
 * privilege interactive tasks. This mechanism is vulnerable to the
 * following false positives: I/O-bound applications that will go on
 * doing I/O for much longer than the duration of weight
 * raising. These applications have basically no benefit from being
 * weight-raised at the beginning of their I/O. On the opposite end,
 * while being weight-raised, these applications
 * a) unjustly steal throughput to applications that may actually need
 * low latency;
 * b) make BFQ uselessly perform device idling; device idling results
 * in loss of device throughput with most flash-based storage, and may
 * increase latencies when used purposelessly.
 *
 * BFQ tries to reduce these problems, by adopting the following
 * countermeasure. To introduce this countermeasure, we need first to
 * finish explaining how the duration of weight-raising for
 * interactive tasks is computed.
 *
 * For a bfq_queue deemed as interactive, the duration of weight
 * raising is dynamically adjusted, as a function of the estimated
 * peak rate of the device, so as to be equal to the time needed to
 * execute the 'largest' interactive task we benchmarked so far. By
 * largest task, we mean the task for which each involved process has
 * to do more I/O than for any of the other tasks we benchmarked. This
 * reference interactive task is the start-up of LibreOffice Writer,
 * and in this task each process/bfq_queue needs to have at most ~110K
 * sectors transferred.
 *
 * This last piece of information enables BFQ to reduce the actual
 * duration of weight-raising for at least one class of I/O-bound
 * applications: those doing sequential or quasi-sequential I/O. An
 * example is file copy. In fact, once started, the main I/O-bound
 * processes of these applications usually consume the above 110K
 * sectors in much less time than the processes of an application that
 * is starting, because these I/O-bound processes will greedily devote
 * almost all their CPU cycles only to their target,
 * throughput-friendly I/O operations. This is even more true if BFQ
 * happens to be underestimating the device peak rate, and thus
 * overestimating the duration of weight raising. But, according to
 * our measurements, once transferred 110K sectors, these processes
 * have no right to be weight-raised any longer.
 *
 * Basing on the last consideration, BFQ ends weight-raising for a
 * bfq_queue if the latter happens to have received an amount of
 * service at least equal to the following constant. The constant is
 * set to slightly more than 110K, to have a minimum safety margin.
 *
 * This early ending of weight-raising reduces the amount of time
 * during which interactive false positives cause the two problems
 * described at the beginning of these comments.
 */
static const unsigned long max_service_from_wr = 120000;

326
#define RQ_BIC(rq)		icq_to_bic((rq)->elv.priv[0])
327
#define RQ_BFQQ(rq)		((rq)->elv.priv[1])
328

329
struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
330
{
331
	return bic->bfqq[is_sync];
332 333
}

334
void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync)
335
{
336
	bic->bfqq[is_sync] = bfqq;
337 338
}

339
struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
340
{
341
	return bic->icq.q->elevator->elevator_data;
342
}
343

344 345 346 347 348
/**
 * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
 * @icq: the iocontext queue.
 */
static struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
349
{
350 351
	/* bic->icq is the first member, %NULL will convert to %NULL */
	return container_of(icq, struct bfq_io_cq, icq);
352
}
353

354 355 356 357 358 359 360 361 362
/**
 * bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
 * @bfqd: the lookup key.
 * @ioc: the io_context of the process doing I/O.
 * @q: the request queue.
 */
static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
					struct io_context *ioc,
					struct request_queue *q)
363
{
364 365 366
	if (ioc) {
		unsigned long flags;
		struct bfq_io_cq *icq;
367

368 369 370
		spin_lock_irqsave(q->queue_lock, flags);
		icq = icq_to_bic(ioc_lookup_icq(ioc, q));
		spin_unlock_irqrestore(q->queue_lock, flags);
371

372
		return icq;
373 374
	}

375
	return NULL;
376 377
}

378 379 380 381 382
/*
 * Scheduler run of queue, if there are requests pending and no one in the
 * driver that will restart queueing.
 */
void bfq_schedule_dispatch(struct bfq_data *bfqd)
383
{
384 385 386
	if (bfqd->queued != 0) {
		bfq_log(bfqd, "schedule dispatch");
		blk_mq_run_hw_queues(bfqd->queue, true);
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
}

#define bfq_class_idle(bfqq)	((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
#define bfq_class_rt(bfqq)	((bfqq)->ioprio_class == IOPRIO_CLASS_RT)

#define bfq_sample_valid(samples)	((samples) > 80)

/*
 * Lifted from AS - choose which of rq1 and rq2 that is best served now.
 * We choose the request that is closesr to the head right now.  Distance
 * behind the head is penalized and only allowed to a certain extent.
 */
static struct request *bfq_choose_req(struct bfq_data *bfqd,
				      struct request *rq1,
				      struct request *rq2,
				      sector_t last)
{
	sector_t s1, s2, d1 = 0, d2 = 0;
	unsigned long back_max;
#define BFQ_RQ1_WRAP	0x01 /* request 1 wraps */
#define BFQ_RQ2_WRAP	0x02 /* request 2 wraps */
	unsigned int wrap = 0; /* bit mask: requests behind the disk head? */

	if (!rq1 || rq1 == rq2)
		return rq2;
	if (!rq2)
		return rq1;

	if (rq_is_sync(rq1) && !rq_is_sync(rq2))
		return rq1;
	else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
		return rq2;
	if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
		return rq1;
	else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META))
		return rq2;

	s1 = blk_rq_pos(rq1);
	s2 = blk_rq_pos(rq2);

	/*
	 * By definition, 1KiB is 2 sectors.
	 */
	back_max = bfqd->bfq_back_max * 2;

	/*
	 * Strict one way elevator _except_ in the case where we allow
	 * short backward seeks which are biased as twice the cost of a
	 * similar forward seek.
	 */
	if (s1 >= last)
		d1 = s1 - last;
	else if (s1 + back_max >= last)
		d1 = (last - s1) * bfqd->bfq_back_penalty;
	else
		wrap |= BFQ_RQ1_WRAP;

	if (s2 >= last)
		d2 = s2 - last;
	else if (s2 + back_max >= last)
		d2 = (last - s2) * bfqd->bfq_back_penalty;
	else
		wrap |= BFQ_RQ2_WRAP;

	/* Found required data */

	/*
	 * By doing switch() on the bit mask "wrap" we avoid having to
	 * check two variables for all permutations: --> faster!
	 */
	switch (wrap) {
	case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
		if (d1 < d2)
			return rq1;
		else if (d2 < d1)
			return rq2;

		if (s1 >= s2)
			return rq1;
		else
			return rq2;

	case BFQ_RQ2_WRAP:
		return rq1;
	case BFQ_RQ1_WRAP:
		return rq2;
	case BFQ_RQ1_WRAP|BFQ_RQ2_WRAP: /* both rqs wrapped */
	default:
		/*
		 * Since both rqs are wrapped,
		 * start with the one that's further behind head
		 * (--> only *one* back seek required),
		 * since back seek takes more time than forward.
		 */
		if (s1 <= s2)
			return rq1;
		else
			return rq2;
	}
}

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
/*
 * See the comments on bfq_limit_depth for the purpose of
 * the depths set in the function.
 */
static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
{
	bfqd->sb_shift = bt->sb.shift;

	/*
	 * In-word depths if no bfq_queue is being weight-raised:
	 * leaving 25% of tags only for sync reads.
	 *
	 * In next formulas, right-shift the value
	 * (1U<<bfqd->sb_shift), instead of computing directly
	 * (1U<<(bfqd->sb_shift - something)), to be robust against
	 * any possible value of bfqd->sb_shift, without having to
	 * limit 'something'.
	 */
	/* no more than 50% of tags for async I/O */
	bfqd->word_depths[0][0] = max((1U<<bfqd->sb_shift)>>1, 1U);
	/*
	 * no more than 75% of tags for sync writes (25% extra tags
	 * w.r.t. async I/O, to prevent async I/O from starving sync
	 * writes)
	 */
	bfqd->word_depths[0][1] = max(((1U<<bfqd->sb_shift) * 3)>>2, 1U);

	/*
	 * In-word depths in case some bfq_queue is being weight-
	 * raised: leaving ~63% of tags for sync reads. This is the
	 * highest percentage for which, in our tests, application
	 * start-up times didn't suffer from any regression due to tag
	 * shortage.
	 */
	/* no more than ~18% of tags for async I/O */
	bfqd->word_depths[1][0] = max(((1U<<bfqd->sb_shift) * 3)>>4, 1U);
	/* no more than ~37% of tags for sync writes (~20% extra tags) */
	bfqd->word_depths[1][1] = max(((1U<<bfqd->sb_shift) * 6)>>4, 1U);
}

/*
 * Async I/O can easily starve sync I/O (both sync reads and sync
 * writes), by consuming all tags. Similarly, storms of sync writes,
 * such as those that sync(2) may trigger, can starve sync reads.
 * Limit depths of async I/O and sync writes so as to counter both
 * problems.
 */
static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
{
	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
	struct bfq_data *bfqd = data->q->elevator->elevator_data;
	struct sbitmap_queue *bt;

	if (op_is_sync(op) && !op_is_write(op))
		return;

	if (data->flags & BLK_MQ_REQ_RESERVED) {
		if (unlikely(!tags->nr_reserved_tags)) {
			WARN_ON_ONCE(1);
			return;
		}
		bt = &tags->breserved_tags;
	} else
		bt = &tags->bitmap_tags;

	if (unlikely(bfqd->sb_shift != bt->sb.shift))
		bfq_update_depths(bfqd, bt);

	data->shallow_depth =
		bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)];

	bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u",
			__func__, bfqd->wr_busy_queues, op_is_sync(op),
			data->shallow_depth);
}

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
static struct bfq_queue *
bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
		     sector_t sector, struct rb_node **ret_parent,
		     struct rb_node ***rb_link)
{
	struct rb_node **p, *parent;
	struct bfq_queue *bfqq = NULL;

	parent = NULL;
	p = &root->rb_node;
	while (*p) {
		struct rb_node **n;

		parent = *p;
		bfqq = rb_entry(parent, struct bfq_queue, pos_node);

		/*
		 * Sort strictly based on sector. Smallest to the left,
		 * largest to the right.
		 */
		if (sector > blk_rq_pos(bfqq->next_rq))
			n = &(*p)->rb_right;
		else if (sector < blk_rq_pos(bfqq->next_rq))
			n = &(*p)->rb_left;
		else
			break;
		p = n;
		bfqq = NULL;
	}

	*ret_parent = parent;
	if (rb_link)
		*rb_link = p;

	bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
		(unsigned long long)sector,
		bfqq ? bfqq->pid : 0);

	return bfqq;
}

606 607 608 609 610 611 612
static bool bfq_too_late_for_merging(struct bfq_queue *bfqq)
{
	return bfqq->service_from_backlogged > 0 &&
		time_is_before_jiffies(bfqq->first_IO_time +
				       bfq_merge_time_limit);
}

613
void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
614 615 616 617 618 619 620 621 622
{
	struct rb_node **p, *parent;
	struct bfq_queue *__bfqq;

	if (bfqq->pos_root) {
		rb_erase(&bfqq->pos_node, bfqq->pos_root);
		bfqq->pos_root = NULL;
	}

623 624 625 626 627 628 629 630
	/*
	 * bfqq cannot be merged any longer (see comments in
	 * bfq_setup_cooperator): no point in adding bfqq into the
	 * position tree.
	 */
	if (bfq_too_late_for_merging(bfqq))
		return;

631 632 633 634 635 636 637 638 639 640 641 642 643 644 645
	if (bfq_class_idle(bfqq))
		return;
	if (!bfqq->next_rq)
		return;

	bfqq->pos_root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
	__bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
			blk_rq_pos(bfqq->next_rq), &parent, &p);
	if (!__bfqq) {
		rb_link_node(&bfqq->pos_node, parent, p);
		rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
	} else
		bfqq->pos_root = NULL;
}

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
/*
 * Tell whether there are active queues or groups with differentiated weights.
 */
static bool bfq_differentiated_weights(struct bfq_data *bfqd)
{
	/*
	 * For weights to differ, at least one of the trees must contain
	 * at least two nodes.
	 */
	return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
		(bfqd->queue_weights_tree.rb_node->rb_left ||
		 bfqd->queue_weights_tree.rb_node->rb_right)
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	       ) ||
	       (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
		(bfqd->group_weights_tree.rb_node->rb_left ||
		 bfqd->group_weights_tree.rb_node->rb_right)
#endif
	       );
}

/*
 * The following function returns true if every queue must receive the
 * same share of the throughput (this condition is used when deciding
 * whether idling may be disabled, see the comments in the function
 * bfq_bfqq_may_idle()).
 *
 * Such a scenario occurs when:
 * 1) all active queues have the same weight,
 * 2) all active groups at the same level in the groups tree have the same
 *    weight,
 * 3) all active groups at the same level in the groups tree have the same
 *    number of children.
 *
 * Unfortunately, keeping the necessary state for evaluating exactly the
 * above symmetry conditions would be quite complex and time-consuming.
 * Therefore this function evaluates, instead, the following stronger
 * sub-conditions, for which it is much easier to maintain the needed
 * state:
 * 1) all active queues have the same weight,
 * 2) all active groups have the same weight,
 * 3) all active groups have at most one active child each.
 * In particular, the last two conditions are always true if hierarchical
 * support and the cgroups interface are not enabled, thus no state needs
 * to be maintained in this case.
 */
static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
{
	return !bfq_differentiated_weights(bfqd);
}

/*
 * If the weight-counter tree passed as input contains no counter for
 * the weight of the input entity, then add that counter; otherwise just
 * increment the existing counter.
 *
 * Note that weight-counter trees contain few nodes in mostly symmetric
 * scenarios. For example, if all queues have the same weight, then the
 * weight-counter tree for the queues may contain at most one node.
 * This holds even if low_latency is on, because weight-raised queues
 * are not inserted in the tree.
 * In most scenarios, the rate at which nodes are created/destroyed
 * should be low too.
 */
710 711
void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
			  struct rb_root *root)
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
{
	struct rb_node **new = &(root->rb_node), *parent = NULL;

	/*
	 * Do not insert if the entity is already associated with a
	 * counter, which happens if:
	 *   1) the entity is associated with a queue,
	 *   2) a request arrival has caused the queue to become both
	 *      non-weight-raised, and hence change its weight, and
	 *      backlogged; in this respect, each of the two events
	 *      causes an invocation of this function,
	 *   3) this is the invocation of this function caused by the
	 *      second event. This second invocation is actually useless,
	 *      and we handle this fact by exiting immediately. More
	 *      efficient or clearer solutions might possibly be adopted.
	 */
	if (entity->weight_counter)
		return;

	while (*new) {
		struct bfq_weight_counter *__counter = container_of(*new,
						struct bfq_weight_counter,
						weights_node);
		parent = *new;

		if (entity->weight == __counter->weight) {
			entity->weight_counter = __counter;
			goto inc_counter;
		}
		if (entity->weight < __counter->weight)
			new = &((*new)->rb_left);
		else
			new = &((*new)->rb_right);
	}

	entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
					 GFP_ATOMIC);

	/*
	 * In the unlucky event of an allocation failure, we just
	 * exit. This will cause the weight of entity to not be
	 * considered in bfq_differentiated_weights, which, in its
	 * turn, causes the scenario to be deemed wrongly symmetric in
	 * case entity's weight would have been the only weight making
	 * the scenario asymmetric. On the bright side, no unbalance
	 * will however occur when entity becomes inactive again (the
	 * invocation of this function is triggered by an activation
	 * of entity). In fact, bfq_weights_tree_remove does nothing
	 * if !entity->weight_counter.
	 */
	if (unlikely(!entity->weight_counter))
		return;

	entity->weight_counter->weight = entity->weight;
	rb_link_node(&entity->weight_counter->weights_node, parent, new);
	rb_insert_color(&entity->weight_counter->weights_node, root);

inc_counter:
	entity->weight_counter->num_active++;
}

/*
 * Decrement the weight counter associated with the entity, and, if the
 * counter reaches 0, remove the counter from the tree.
 * See the comments to the function bfq_weights_tree_add() for considerations
 * about overhead.
 */
779 780
void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
			     struct rb_root *root)
781 782 783 784 785 786 787 788 789 790 791 792 793 794 795
{
	if (!entity->weight_counter)
		return;

	entity->weight_counter->num_active--;
	if (entity->weight_counter->num_active > 0)
		goto reset_entity_pointer;

	rb_erase(&entity->weight_counter->weights_node, root);
	kfree(entity->weight_counter);

reset_entity_pointer:
	entity->weight_counter = NULL;
}

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
/*
 * Return expired entry, or NULL to just start from scratch in rbtree.
 */
static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
				      struct request *last)
{
	struct request *rq;

	if (bfq_bfqq_fifo_expire(bfqq))
		return NULL;

	bfq_mark_bfqq_fifo_expire(bfqq);

	rq = rq_entry_fifo(bfqq->fifo.next);

	if (rq == last || ktime_get_ns() < rq->fifo_time)
		return NULL;

	bfq_log_bfqq(bfqq->bfqd, bfqq, "check_fifo: returned %p", rq);
	return rq;
}

static struct request *bfq_find_next_rq(struct bfq_data *bfqd,
					struct bfq_queue *bfqq,
					struct request *last)
{
	struct rb_node *rbnext = rb_next(&last->rb_node);
	struct rb_node *rbprev = rb_prev(&last->rb_node);
	struct request *next, *prev = NULL;

	/* Follow expired path, else get first next available. */
	next = bfq_check_fifo(bfqq, last);
	if (next)
		return next;

	if (rbprev)
		prev = rb_entry_rq(rbprev);

	if (rbnext)
		next = rb_entry_rq(rbnext);
	else {
		rbnext = rb_first(&bfqq->sort_list);
		if (rbnext && rbnext != &last->rb_node)
			next = rb_entry_rq(rbnext);
	}

	return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last));
}

845
/* see the definition of bfq_async_charge_factor for details */
846 847 848
static unsigned long bfq_serv_to_charge(struct request *rq,
					struct bfq_queue *bfqq)
{
849
	if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1)
850 851
		return blk_rq_sectors(rq);

852 853 854 855 856 857 858 859 860 861
	/*
	 * If there are no weight-raised queues, then amplify service
	 * by just the async charge factor; otherwise amplify service
	 * by twice the async charge factor, to further reduce latency
	 * for weight-raised queues.
	 */
	if (bfqq->bfqd->wr_busy_queues == 0)
		return blk_rq_sectors(rq) * bfq_async_charge_factor;

	return blk_rq_sectors(rq) * 2 * bfq_async_charge_factor;
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
}

/**
 * bfq_updated_next_req - update the queue after a new next_rq selection.
 * @bfqd: the device data the queue belongs to.
 * @bfqq: the queue to update.
 *
 * If the first request of a queue changes we make sure that the queue
 * has enough budget to serve at least its first request (if the
 * request has grown).  We do this because if the queue has not enough
 * budget for its first request, it has to go through two dispatch
 * rounds to actually get it dispatched.
 */
static void bfq_updated_next_req(struct bfq_data *bfqd,
				 struct bfq_queue *bfqq)
{
	struct bfq_entity *entity = &bfqq->entity;
	struct request *next_rq = bfqq->next_rq;
	unsigned long new_budget;

	if (!next_rq)
		return;

	if (bfqq == bfqd->in_service_queue)
		/*
		 * In order not to break guarantees, budgets cannot be
		 * changed after an entity has been selected.
		 */
		return;

	new_budget = max_t(unsigned long, bfqq->max_budget,
			   bfq_serv_to_charge(next_rq, bfqq));
	if (entity->budget != new_budget) {
		entity->budget = new_budget;
		bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
					 new_budget);
898
		bfq_requeue_bfqq(bfqd, bfqq, false);
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
static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
{
	u64 dur;

	if (bfqd->bfq_wr_max_time > 0)
		return bfqd->bfq_wr_max_time;

	dur = bfqd->RT_prod;
	do_div(dur, bfqd->peak_rate);

	/*
	 * Limit duration between 3 and 13 seconds. Tests show that
	 * higher values than 13 seconds often yield the opposite of
	 * the desired result, i.e., worsen responsiveness by letting
	 * non-interactive and non-soft-real-time applications
	 * preserve weight raising for a too long time interval.
	 *
	 * On the other end, lower values than 3 seconds make it
	 * difficult for most interactive tasks to complete their jobs
	 * before weight-raising finishes.
	 */
	if (dur > msecs_to_jiffies(13000))
		dur = msecs_to_jiffies(13000);
	else if (dur < msecs_to_jiffies(3000))
		dur = msecs_to_jiffies(3000);

	return dur;
}

/* switch back from soft real-time to interactive weight raising */
static void switch_back_to_interactive_wr(struct bfq_queue *bfqq,
					  struct bfq_data *bfqd)
{
	bfqq->wr_coeff = bfqd->bfq_wr_coeff;
	bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
	bfqq->last_wr_start_finish = bfqq->wr_start_at_switch_to_srt;
}

940
static void
941 942
bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
		      struct bfq_io_cq *bic, bool bfq_already_existing)
943
{
944 945 946
	unsigned int old_wr_coeff = bfqq->wr_coeff;
	bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);

947 948
	if (bic->saved_has_short_ttime)
		bfq_mark_bfqq_has_short_ttime(bfqq);
949
	else
950
		bfq_clear_bfqq_has_short_ttime(bfqq);
951 952 953 954 955 956 957 958 959 960 961 962

	if (bic->saved_IO_bound)
		bfq_mark_bfqq_IO_bound(bfqq);
	else
		bfq_clear_bfqq_IO_bound(bfqq);

	bfqq->ttime = bic->saved_ttime;
	bfqq->wr_coeff = bic->saved_wr_coeff;
	bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
	bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
	bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;

963
	if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
964
	    time_is_before_jiffies(bfqq->last_wr_start_finish +
965
				   bfqq->wr_cur_max_time))) {
966 967 968 969 970 971 972 973 974 975
		if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
		    !bfq_bfqq_in_large_burst(bfqq) &&
		    time_is_after_eq_jiffies(bfqq->wr_start_at_switch_to_srt +
					     bfq_wr_duration(bfqd))) {
			switch_back_to_interactive_wr(bfqq, bfqd);
		} else {
			bfqq->wr_coeff = 1;
			bfq_log_bfqq(bfqq->bfqd, bfqq,
				     "resume state: switching off wr");
		}
976 977 978 979
	}

	/* make sure weight will be updated, however we got here */
	bfqq->entity.prio_changed = 1;
980 981 982 983 984 985 986 987

	if (likely(!busy))
		return;

	if (old_wr_coeff == 1 && bfqq->wr_coeff > 1)
		bfqd->wr_busy_queues++;
	else if (old_wr_coeff > 1 && bfqq->wr_coeff == 1)
		bfqd->wr_busy_queues--;
988 989 990 991 992 993 994
}

static int bfqq_process_refs(struct bfq_queue *bfqq)
{
	return bfqq->ref - bfqq->allocated - bfqq->entity.on_st;
}

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 1025 1026 1027 1028 1029 1030 1031 1032 1033 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 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 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
/* Empty burst list and add just bfqq (see comments on bfq_handle_burst) */
static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
	struct bfq_queue *item;
	struct hlist_node *n;

	hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
		hlist_del_init(&item->burst_list_node);
	hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
	bfqd->burst_size = 1;
	bfqd->burst_parent_entity = bfqq->entity.parent;
}

/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */
static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
	/* Increment burst size to take into account also bfqq */
	bfqd->burst_size++;

	if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) {
		struct bfq_queue *pos, *bfqq_item;
		struct hlist_node *n;

		/*
		 * Enough queues have been activated shortly after each
		 * other to consider this burst as large.
		 */
		bfqd->large_burst = true;

		/*
		 * We can now mark all queues in the burst list as
		 * belonging to a large burst.
		 */
		hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
				     burst_list_node)
			bfq_mark_bfqq_in_large_burst(bfqq_item);
		bfq_mark_bfqq_in_large_burst(bfqq);

		/*
		 * From now on, and until the current burst finishes, any
		 * new queue being activated shortly after the last queue
		 * was inserted in the burst can be immediately marked as
		 * belonging to a large burst. So the burst list is not
		 * needed any more. Remove it.
		 */
		hlist_for_each_entry_safe(pos, n, &bfqd->burst_list,
					  burst_list_node)
			hlist_del_init(&pos->burst_list_node);
	} else /*
		* Burst not yet large: add bfqq to the burst list. Do
		* not increment the ref counter for bfqq, because bfqq
		* is removed from the burst list before freeing bfqq
		* in put_queue.
		*/
		hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
}

/*
 * If many queues belonging to the same group happen to be created
 * shortly after each other, then the processes associated with these
 * queues have typically a common goal. In particular, bursts of queue
 * creations are usually caused by services or applications that spawn
 * many parallel threads/processes. Examples are systemd during boot,
 * or git grep. To help these processes get their job done as soon as
 * possible, it is usually better to not grant either weight-raising
 * or device idling to their queues.
 *
 * In this comment we describe, firstly, the reasons why this fact
 * holds, and, secondly, the next function, which implements the main
 * steps needed to properly mark these queues so that they can then be
 * treated in a different way.
 *
 * The above services or applications benefit mostly from a high
 * throughput: the quicker the requests of the activated queues are
 * cumulatively served, the sooner the target job of these queues gets
 * completed. As a consequence, weight-raising any of these queues,
 * which also implies idling the device for it, is almost always
 * counterproductive. In most cases it just lowers throughput.
 *
 * On the other hand, a burst of queue creations may be caused also by
 * the start of an application that does not consist of a lot of
 * parallel I/O-bound threads. In fact, with a complex application,
 * several short processes may need to be executed to start-up the
 * application. In this respect, to start an application as quickly as
 * possible, the best thing to do is in any case to privilege the I/O
 * related to the application with respect to all other
 * I/O. Therefore, the best strategy to start as quickly as possible
 * an application that causes a burst of queue creations is to
 * weight-raise all the queues created during the burst. This is the
 * exact opposite of the best strategy for the other type of bursts.
 *
 * In the end, to take the best action for each of the two cases, the
 * two types of bursts need to be distinguished. Fortunately, this
 * seems relatively easy, by looking at the sizes of the bursts. In
 * particular, we found a threshold such that only bursts with a
 * larger size than that threshold are apparently caused by
 * services or commands such as systemd or git grep. For brevity,
 * hereafter we call just 'large' these bursts. BFQ *does not*
 * weight-raise queues whose creation occurs in a large burst. In
 * addition, for each of these queues BFQ performs or does not perform
 * idling depending on which choice boosts the throughput more. The
 * exact choice depends on the device and request pattern at
 * hand.
 *
 * Unfortunately, false positives may occur while an interactive task
 * is starting (e.g., an application is being started). The
 * consequence is that the queues associated with the task do not
 * enjoy weight raising as expected. Fortunately these false positives
 * are very rare. They typically occur if some service happens to
 * start doing I/O exactly when the interactive task starts.
 *
 * Turning back to the next function, it implements all the steps
 * needed to detect the occurrence of a large burst and to properly
 * mark all the queues belonging to it (so that they can then be
 * treated in a different way). This goal is achieved by maintaining a
 * "burst list" that holds, temporarily, the queues that belong to the
 * burst in progress. The list is then used to mark these queues as
 * belonging to a large burst if the burst does become large. The main
 * steps are the following.
 *
 * . when the very first queue is created, the queue is inserted into the
 *   list (as it could be the first queue in a possible burst)
 *
 * . if the current burst has not yet become large, and a queue Q that does
 *   not yet belong to the burst is activated shortly after the last time
 *   at which a new queue entered the burst list, then the function appends
 *   Q to the burst list
 *
 * . if, as a consequence of the previous step, the burst size reaches
 *   the large-burst threshold, then
 *
 *     . all the queues in the burst list are marked as belonging to a
 *       large burst
 *
 *     . the burst list is deleted; in fact, the burst list already served
 *       its purpose (keeping temporarily track of the queues in a burst,
 *       so as to be able to mark them as belonging to a large burst in the
 *       previous sub-step), and now is not needed any more
 *
 *     . the device enters a large-burst mode
 *
 * . if a queue Q that does not belong to the burst is created while
 *   the device is in large-burst mode and shortly after the last time
 *   at which a queue either entered the burst list or was marked as
 *   belonging to the current large burst, then Q is immediately marked
 *   as belonging to a large burst.
 *
 * . if a queue Q that does not belong to the burst is created a while
 *   later, i.e., not shortly after, than the last time at which a queue
 *   either entered the burst list or was marked as belonging to the
 *   current large burst, then the current burst is deemed as finished and:
 *
 *        . the large-burst mode is reset if set
 *
 *        . the burst list is emptied
 *
 *        . Q is inserted in the burst list, as Q may be the first queue
 *          in a possible new burst (then the burst list contains just Q
 *          after this step).
 */
static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
	/*
	 * If bfqq is already in the burst list or is part of a large
	 * burst, or finally has just been split, then there is
	 * nothing else to do.
	 */
	if (!hlist_unhashed(&bfqq->burst_list_node) ||
	    bfq_bfqq_in_large_burst(bfqq) ||
	    time_is_after_eq_jiffies(bfqq->split_time +
				     msecs_to_jiffies(10)))
		return;

	/*
	 * If bfqq's creation happens late enough, or bfqq belongs to
	 * a different group than the burst group, then the current
	 * burst is finished, and related data structures must be
	 * reset.
	 *
	 * In this respect, consider the special case where bfqq is
	 * the very first queue created after BFQ is selected for this
	 * device. In this case, last_ins_in_burst and
	 * burst_parent_entity are not yet significant when we get
	 * here. But it is easy to verify that, whether or not the
	 * following condition is true, bfqq will end up being
	 * inserted into the burst list. In particular the list will
	 * happen to contain only bfqq. And this is exactly what has
	 * to happen, as bfqq may be the first queue of the first
	 * burst.
	 */
	if (time_is_before_jiffies(bfqd->last_ins_in_burst +
	    bfqd->bfq_burst_interval) ||
	    bfqq->entity.parent != bfqd->burst_parent_entity) {
		bfqd->large_burst = false;
		bfq_reset_burst_list(bfqd, bfqq);
		goto end;
	}

	/*
	 * If we get here, then bfqq is being activated shortly after the
	 * last queue. So, if the current burst is also large, we can mark
	 * bfqq as belonging to this large burst immediately.
	 */
	if (bfqd->large_burst) {
		bfq_mark_bfqq_in_large_burst(bfqq);
		goto end;
	}

	/*
	 * If we get here, then a large-burst state has not yet been
	 * reached, but bfqq is being activated shortly after the last
	 * queue. Then we add bfqq to the burst.
	 */
	bfq_add_to_burst(bfqd, bfqq);
end:
	/*
	 * At this point, bfqq either has been added to the current
	 * burst or has caused the current burst to terminate and a
	 * possible new burst to start. In particular, in the second
	 * case, bfqq has become the first queue in the possible new
	 * burst.  In both cases last_ins_in_burst needs to be moved
	 * forward.
	 */
	bfqd->last_ins_in_burst = jiffies;
}

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
static int bfq_bfqq_budget_left(struct bfq_queue *bfqq)
{
	struct bfq_entity *entity = &bfqq->entity;

	return entity->budget - entity->service;
}

/*
 * If enough samples have been computed, return the current max budget
 * stored in bfqd, which is dynamically updated according to the
 * estimated disk peak rate; otherwise return the default max budget
 */
static int bfq_max_budget(struct bfq_data *bfqd)
{
	if (bfqd->budgets_assigned < bfq_stats_min_budgets)
		return bfq_default_max_budget;
	else
		return bfqd->bfq_max_budget;
}

/*
 * Return min budget, which is a fraction of the current or default
 * max budget (trying with 1/32)
 */
static int bfq_min_budget(struct bfq_data *bfqd)
{
	if (bfqd->budgets_assigned < bfq_stats_min_budgets)
		return bfq_default_max_budget / 32;
	else
		return bfqd->bfq_max_budget / 32;
}

/*
 * The next function, invoked after the input queue bfqq switches from
 * idle to busy, updates the budget of bfqq. The function also tells
 * whether the in-service queue should be expired, by returning
 * true. The purpose of expiring the in-service queue is to give bfqq
 * the chance to possibly preempt the in-service queue, and the reason
1259 1260
 * for preempting the in-service queue is to achieve one of the two
 * goals below.
1261
 *
1262 1263 1264
 * 1. Guarantee to bfqq its reserved bandwidth even if bfqq has
 * expired because it has remained idle. In particular, bfqq may have
 * expired for one of the following two reasons:
1265 1266 1267 1268 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
 *
 * - BFQQE_NO_MORE_REQUESTS bfqq did not enjoy any device idling
 *   and did not make it to issue a new request before its last
 *   request was served;
 *
 * - BFQQE_TOO_IDLE bfqq did enjoy device idling, but did not issue
 *   a new request before the expiration of the idling-time.
 *
 * Even if bfqq has expired for one of the above reasons, the process
 * associated with the queue may be however issuing requests greedily,
 * and thus be sensitive to the bandwidth it receives (bfqq may have
 * remained idle for other reasons: CPU high load, bfqq not enjoying
 * idling, I/O throttling somewhere in the path from the process to
 * the I/O scheduler, ...). But if, after every expiration for one of
 * the above two reasons, bfqq has to wait for the service of at least
 * one full budget of another queue before being served again, then
 * bfqq is likely to get a much lower bandwidth or resource time than
 * its reserved ones. To address this issue, two countermeasures need
 * to be taken.
 *
 * First, the budget and the timestamps of bfqq need to be updated in
 * a special way on bfqq reactivation: they need to be updated as if
 * bfqq did not remain idle and did not expire. In fact, if they are
 * computed as if bfqq expired and remained idle until reactivation,
 * then the process associated with bfqq is treated as if, instead of
 * being greedy, it stopped issuing requests when bfqq remained idle,
 * and restarts issuing requests only on this reactivation. In other
 * words, the scheduler does not help the process recover the "service
 * hole" between bfqq expiration and reactivation. As a consequence,
 * the process receives a lower bandwidth than its reserved one. In
 * contrast, to recover this hole, the budget must be updated as if
 * bfqq was not expired at all before this reactivation, i.e., it must
 * be set to the value of the remaining budget when bfqq was
 * expired. Along the same line, timestamps need to be assigned the
 * value they had the last time bfqq was selected for service, i.e.,
 * before last expiration. Thus timestamps need to be back-shifted
 * with respect to their normal computation (see [1] for more details
 * on this tricky aspect).
 *
 * Secondly, to allow the process to recover the hole, the in-service
 * queue must be expired too, to give bfqq the chance to preempt it
 * immediately. In fact, if bfqq has to wait for a full budget of the
 * in-service queue to be completed, then it may become impossible to
 * let the process recover the hole, even if the back-shifted
 * timestamps of bfqq are lower than those of the in-service queue. If
 * this happens for most or all of the holes, then the process may not
 * receive its reserved bandwidth. In this respect, it is worth noting
 * that, being the service of outstanding requests unpreemptible, a
 * little fraction of the holes may however be unrecoverable, thereby
 * causing a little loss of bandwidth.
 *
 * The last important point is detecting whether bfqq does need this
 * bandwidth recovery. In this respect, the next function deems the
 * process associated with bfqq greedy, and thus allows it to recover
 * the hole, if: 1) the process is waiting for the arrival of a new
 * request (which implies that bfqq expired for one of the above two
 * reasons), and 2) such a request has arrived soon. The first
 * condition is controlled through the flag non_blocking_wait_rq,
 * while the second through the flag arrived_in_time. If both
 * conditions hold, then the function computes the budget in the
 * above-described special way, and signals that the in-service queue
 * should be expired. Timestamp back-shifting is done later in
 * __bfq_activate_entity.
1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352
 *
 * 2. Reduce latency. Even if timestamps are not backshifted to let
 * the process associated with bfqq recover a service hole, bfqq may
 * however happen to have, after being (re)activated, a lower finish
 * timestamp than the in-service queue.	 That is, the next budget of
 * bfqq may have to be completed before the one of the in-service
 * queue. If this is the case, then preempting the in-service queue
 * allows this goal to be achieved, apart from the unpreemptible,
 * outstanding requests mentioned above.
 *
 * Unfortunately, regardless of which of the above two goals one wants
 * to achieve, service trees need first to be updated to know whether
 * the in-service queue must be preempted. To have service trees
 * correctly updated, the in-service queue must be expired and
 * rescheduled, and bfqq must be scheduled too. This is one of the
 * most costly operations (in future versions, the scheduling
 * mechanism may be re-designed in such a way to make it possible to
 * know whether preemption is needed without needing to update service
 * trees). In addition, queue preemptions almost always cause random
 * I/O, and thus loss of throughput. Because of these facts, the next
 * function adopts the following simple scheme to avoid both costly
 * operations and too frequent preemptions: it requests the expiration
 * of the in-service queue (unconditionally) only for queues that need
 * to recover a hole, or that either are weight-raised or deserve to
 * be weight-raised.
1353 1354 1355
 */
static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
						struct bfq_queue *bfqq,
1356 1357
						bool arrived_in_time,
						bool wr_or_deserves_wr)
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
{
	struct bfq_entity *entity = &bfqq->entity;

	if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time) {
		/*
		 * We do not clear the flag non_blocking_wait_rq here, as
		 * the latter is used in bfq_activate_bfqq to signal
		 * that timestamps need to be back-shifted (and is
		 * cleared right after).
		 */

		/*
		 * In next assignment we rely on that either
		 * entity->service or entity->budget are not updated
		 * on expiration if bfqq is empty (see
		 * __bfq_bfqq_recalc_budget). Thus both quantities
		 * remain unchanged after such an expiration, and the
		 * following statement therefore assigns to
		 * entity->budget the remaining budget on such an
		 * expiration. For clarity, entity->service is not
		 * updated on expiration in any case, and, in normal
		 * operation, is reset only when bfqq is selected for
		 * service (see bfq_get_next_queue).
		 */
		entity->budget = min_t(unsigned long,
				       bfq_bfqq_budget_left(bfqq),
				       bfqq->max_budget);

		return true;
	}

	entity->budget = max_t(unsigned long, bfqq->max_budget,
			       bfq_serv_to_charge(bfqq->next_rq, bfqq));
	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
1392 1393 1394
	return wr_or_deserves_wr;
}

1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412
/*
 * Return the farthest future time instant according to jiffies
 * macros.
 */
static unsigned long bfq_greatest_from_now(void)
{
	return jiffies + MAX_JIFFY_OFFSET;
}

/*
 * Return the farthest past time instant according to jiffies
 * macros.
 */
static unsigned long bfq_smallest_from_now(void)
{
	return jiffies - MAX_JIFFY_OFFSET;
}

1413 1414 1415 1416
static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
					     struct bfq_queue *bfqq,
					     unsigned int old_wr_coeff,
					     bool wr_or_deserves_wr,
1417
					     bool interactive,
1418
					     bool in_burst,
1419
					     bool soft_rt)
1420 1421 1422
{
	if (old_wr_coeff == 1 && wr_or_deserves_wr) {
		/* start a weight-raising period */
1423
		if (interactive) {
1424
			bfqq->service_from_wr = 0;
1425 1426 1427
			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
		} else {
1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440
			/*
			 * No interactive weight raising in progress
			 * here: assign minus infinity to
			 * wr_start_at_switch_to_srt, to make sure
			 * that, at the end of the soft-real-time
			 * weight raising periods that is starting
			 * now, no interactive weight-raising period
			 * may be wrongly considered as still in
			 * progress (and thus actually started by
			 * mistake).
			 */
			bfqq->wr_start_at_switch_to_srt =
				bfq_smallest_from_now();
1441 1442 1443 1444 1445
			bfqq->wr_coeff = bfqd->bfq_wr_coeff *
				BFQ_SOFTRT_WEIGHT_FACTOR;
			bfqq->wr_cur_max_time =
				bfqd->bfq_wr_rt_max_time;
		}
1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459

		/*
		 * If needed, further reduce budget to make sure it is
		 * close to bfqq's backlog, so as to reduce the
		 * scheduling-error component due to a too large
		 * budget. Do not care about throughput consequences,
		 * but only about latency. Finally, do not assign a
		 * too small budget either, to avoid increasing
		 * latency by causing too frequent expirations.
		 */
		bfqq->entity.budget = min_t(unsigned long,
					    bfqq->entity.budget,
					    2 * bfq_min_budget(bfqd));
	} else if (old_wr_coeff > 1) {
1460 1461 1462
		if (interactive) { /* update wr coeff and duration */
			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
1463 1464 1465
		} else if (in_burst)
			bfqq->wr_coeff = 1;
		else if (soft_rt) {
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
			/*
			 * The application is now or still meeting the
			 * requirements for being deemed soft rt.  We
			 * can then correctly and safely (re)charge
			 * the weight-raising duration for the
			 * application with the weight-raising
			 * duration for soft rt applications.
			 *
			 * In particular, doing this recharge now, i.e.,
			 * before the weight-raising period for the
			 * application finishes, reduces the probability
			 * of the following negative scenario:
			 * 1) the weight of a soft rt application is
			 *    raised at startup (as for any newly
			 *    created application),
			 * 2) since the application is not interactive,
			 *    at a certain time weight-raising is
			 *    stopped for the application,
			 * 3) at that time the application happens to
			 *    still have pending requests, and hence
			 *    is destined to not have a chance to be
			 *    deemed soft rt before these requests are
			 *    completed (see the comments to the
			 *    function bfq_bfqq_softrt_next_start()
			 *    for details on soft rt detection),
			 * 4) these pending requests experience a high
			 *    latency because the application is not
			 *    weight-raised while they are pending.
			 */
			if (bfqq->wr_cur_max_time !=
				bfqd->bfq_wr_rt_max_time) {
				bfqq->wr_start_at_switch_to_srt =
					bfqq->last_wr_start_finish;

				bfqq->wr_cur_max_time =
					bfqd->bfq_wr_rt_max_time;
				bfqq->wr_coeff = bfqd->bfq_wr_coeff *
					BFQ_SOFTRT_WEIGHT_FACTOR;
			}
			bfqq->last_wr_start_finish = jiffies;
		}
1507 1508 1509 1510 1511 1512 1513 1514 1515 1516
	}
}

static bool bfq_bfqq_idle_for_long_time(struct bfq_data *bfqd,
					struct bfq_queue *bfqq)
{
	return bfqq->dispatched == 0 &&
		time_is_before_jiffies(
			bfqq->budget_timeout +
			bfqd->bfq_wr_min_idle_time);
1517 1518 1519 1520
}

static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
					     struct bfq_queue *bfqq,
1521 1522 1523
					     int old_wr_coeff,
					     struct request *rq,
					     bool *interactive)
1524
{
1525 1526
	bool soft_rt, in_burst,	wr_or_deserves_wr,
		bfqq_wants_to_preempt,
1527
		idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq),
1528 1529 1530 1531 1532 1533 1534 1535 1536
		/*
		 * See the comments on
		 * bfq_bfqq_update_budg_for_activation for
		 * details on the usage of the next variable.
		 */
		arrived_in_time =  ktime_get_ns() <=
			bfqq->ttime.last_end_request +
			bfqd->bfq_slice_idle * 3;

1537

1538
	/*
1539 1540
	 * bfqq deserves to be weight-raised if:
	 * - it is sync,
1541
	 * - it does not belong to a large burst,
1542 1543
	 * - it has been idle for enough time or is soft real-time,
	 * - is linked to a bfq_io_cq (it is not shared in any sense).
1544
	 */
1545
	in_burst = bfq_bfqq_in_large_burst(bfqq);
1546
	soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
1547
		!in_burst &&
1548
		time_is_before_jiffies(bfqq->soft_rt_next_start);
1549
	*interactive = !in_burst && idle_for_long_time;
1550 1551
	wr_or_deserves_wr = bfqd->low_latency &&
		(bfqq->wr_coeff > 1 ||
1552 1553
		 (bfq_bfqq_sync(bfqq) &&
		  bfqq->bic && (*interactive || soft_rt)));
1554 1555 1556 1557

	/*
	 * Using the last flag, update budget and check whether bfqq
	 * may want to preempt the in-service queue.
1558 1559 1560
	 */
	bfqq_wants_to_preempt =
		bfq_bfqq_update_budg_for_activation(bfqd, bfqq,
1561 1562
						    arrived_in_time,
						    wr_or_deserves_wr);
1563

1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588
	/*
	 * If bfqq happened to be activated in a burst, but has been
	 * idle for much more than an interactive queue, then we
	 * assume that, in the overall I/O initiated in the burst, the
	 * I/O associated with bfqq is finished. So bfqq does not need
	 * to be treated as a queue belonging to a burst
	 * anymore. Accordingly, we reset bfqq's in_large_burst flag
	 * if set, and remove bfqq from the burst list if it's
	 * there. We do not decrement burst_size, because the fact
	 * that bfqq does not need to belong to the burst list any
	 * more does not invalidate the fact that bfqq was created in
	 * a burst.
	 */
	if (likely(!bfq_bfqq_just_created(bfqq)) &&
	    idle_for_long_time &&
	    time_is_before_jiffies(
		    bfqq->budget_timeout +
		    msecs_to_jiffies(10000))) {
		hlist_del_init(&bfqq->burst_list_node);
		bfq_clear_bfqq_in_large_burst(bfqq);
	}

	bfq_clear_bfqq_just_created(bfqq);


1589 1590 1591 1592 1593 1594 1595 1596 1597 1598
	if (!bfq_bfqq_IO_bound(bfqq)) {
		if (arrived_in_time) {
			bfqq->requests_within_timer++;
			if (bfqq->requests_within_timer >=
			    bfqd->bfq_requests_within_timer)
				bfq_mark_bfqq_IO_bound(bfqq);
		} else
			bfqq->requests_within_timer = 0;
	}

1599
	if (bfqd->low_latency) {
1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610
		if (unlikely(time_is_after_jiffies(bfqq->split_time)))
			/* wraparound */
			bfqq->split_time =
				jiffies - bfqd->bfq_wr_min_idle_time - 1;

		if (time_is_before_jiffies(bfqq->split_time +
					   bfqd->bfq_wr_min_idle_time)) {
			bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq,
							 old_wr_coeff,
							 wr_or_deserves_wr,
							 *interactive,
1611
							 in_burst,
1612 1613 1614 1615 1616
							 soft_rt);

			if (old_wr_coeff != bfqq->wr_coeff)
				bfqq->entity.prio_changed = 1;
		}
1617 1618
	}

1619 1620 1621 1622
	bfqq->last_idle_bklogged = jiffies;
	bfqq->service_from_backlogged = 0;
	bfq_clear_bfqq_softrt_update(bfqq);

1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635
	bfq_add_bfqq_busy(bfqd, bfqq);

	/*
	 * Expire in-service queue only if preemption may be needed
	 * for guarantees. In this respect, the function
	 * next_queue_may_preempt just checks a simple, necessary
	 * condition, and not a sufficient condition based on
	 * timestamps. In fact, for the latter condition to be
	 * evaluated, timestamps would need first to be updated, and
	 * this operation is quite costly (see the comments on the
	 * function bfq_bfqq_update_budg_for_activation).
	 */
	if (bfqd->in_service_queue && bfqq_wants_to_preempt &&
1636
	    bfqd->in_service_queue->wr_coeff < bfqq->wr_coeff &&
1637 1638 1639 1640 1641 1642 1643 1644 1645 1646
	    next_queue_may_preempt(bfqd))
		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
				false, BFQQE_PREEMPTED);
}

static void bfq_add_request(struct request *rq)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq);
	struct bfq_data *bfqd = bfqq->bfqd;
	struct request *next_rq, *prev;
1647 1648
	unsigned int old_wr_coeff = bfqq->wr_coeff;
	bool interactive = false;
1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662

	bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
	bfqq->queued[rq_is_sync(rq)]++;
	bfqd->queued++;

	elv_rb_add(&bfqq->sort_list, rq);

	/*
	 * Check if this request is a better next-serve candidate.
	 */
	prev = bfqq->next_rq;
	next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
	bfqq->next_rq = next_rq;

1663 1664 1665 1666 1667 1668
	/*
	 * Adjust priority tree position, if next_rq changes.
	 */
	if (prev != bfqq->next_rq)
		bfq_pos_tree_add_move(bfqd, bfqq);

1669
	if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
1670 1671 1672 1673 1674 1675 1676 1677 1678 1679
		bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff,
						 rq, &interactive);
	else {
		if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) &&
		    time_is_before_jiffies(
				bfqq->last_wr_start_finish +
				bfqd->bfq_wr_min_inter_arr_async)) {
			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);

1680
			bfqd->wr_busy_queues++;
1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705
			bfqq->entity.prio_changed = 1;
		}
		if (prev != bfqq->next_rq)
			bfq_updated_next_req(bfqd, bfqq);
	}

	/*
	 * Assign jiffies to last_wr_start_finish in the following
	 * cases:
	 *
	 * . if bfqq is not going to be weight-raised, because, for
	 *   non weight-raised queues, last_wr_start_finish stores the
	 *   arrival time of the last request; as of now, this piece
	 *   of information is used only for deciding whether to
	 *   weight-raise async queues
	 *
	 * . if bfqq is not weight-raised, because, if bfqq is now
	 *   switching to weight-raised, then last_wr_start_finish
	 *   stores the time when weight-raising starts
	 *
	 * . if bfqq is interactive, because, regardless of whether
	 *   bfqq is currently weight-raised, the weight-raising
	 *   period must start or restart (this case is considered
	 *   separately because it is not detected by the above
	 *   conditions, if bfqq is already weight-raised)
1706 1707 1708 1709 1710 1711
	 *
	 * last_wr_start_finish has to be updated also if bfqq is soft
	 * real-time, because the weight-raising period is constantly
	 * restarted on idle-to-busy transitions for these queues, but
	 * this is already done in bfq_bfqq_handle_idle_busy_switch if
	 * needed.
1712 1713 1714 1715
	 */
	if (bfqd->low_latency &&
		(old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive))
		bfqq->last_wr_start_finish = jiffies;
1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730
}

static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
					  struct bio *bio,
					  struct request_queue *q)
{
	struct bfq_queue *bfqq = bfqd->bio_bfqq;


	if (bfqq)
		return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));

	return NULL;
}

1731 1732 1733 1734 1735 1736 1737 1738
static sector_t get_sdist(sector_t last_pos, struct request *rq)
{
	if (last_pos)
		return abs(blk_rq_pos(rq) - last_pos);

	return 0;
}

1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780
#if 0 /* Still not clear if we can do without next two functions */
static void bfq_activate_request(struct request_queue *q, struct request *rq)
{
	struct bfq_data *bfqd = q->elevator->elevator_data;

	bfqd->rq_in_driver++;
}

static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
{
	struct bfq_data *bfqd = q->elevator->elevator_data;

	bfqd->rq_in_driver--;
}
#endif

static void bfq_remove_request(struct request_queue *q,
			       struct request *rq)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq);
	struct bfq_data *bfqd = bfqq->bfqd;
	const int sync = rq_is_sync(rq);

	if (bfqq->next_rq == rq) {
		bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq);
		bfq_updated_next_req(bfqd, bfqq);
	}

	if (rq->queuelist.prev != &rq->queuelist)
		list_del_init(&rq->queuelist);
	bfqq->queued[sync]--;
	bfqd->queued--;
	elv_rb_del(&bfqq->sort_list, rq);

	elv_rqhash_del(q, rq);
	if (q->last_merge == rq)
		q->last_merge = NULL;

	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
		bfqq->next_rq = NULL;

		if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) {
1781
			bfq_del_bfqq_busy(bfqd, bfqq, false);
1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796
			/*
			 * bfqq emptied. In normal operation, when
			 * bfqq is empty, bfqq->entity.service and
			 * bfqq->entity.budget must contain,
			 * respectively, the service received and the
			 * budget used last time bfqq emptied. These
			 * facts do not hold in this case, as at least
			 * this last removal occurred while bfqq is
			 * not in service. To avoid inconsistencies,
			 * reset both bfqq->entity.service and
			 * bfqq->entity.budget, if bfqq has still a
			 * process that may issue I/O requests to it.
			 */
			bfqq->entity.budget = bfqq->entity.service = 0;
		}
1797 1798 1799 1800 1801 1802 1803 1804

		/*
		 * Remove queue from request-position tree as it is empty.
		 */
		if (bfqq->pos_root) {
			rb_erase(&bfqq->pos_node, bfqq->pos_root);
			bfqq->pos_root = NULL;
		}
1805 1806
	} else {
		bfq_pos_tree_add_move(bfqd, bfqq);
1807 1808 1809 1810
	}

	if (rq->cmd_flags & REQ_META)
		bfqq->meta_pending--;
1811

1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882
}

static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
{
	struct request_queue *q = hctx->queue;
	struct bfq_data *bfqd = q->elevator->elevator_data;
	struct request *free = NULL;
	/*
	 * bfq_bic_lookup grabs the queue_lock: invoke it now and
	 * store its return value for later use, to avoid nesting
	 * queue_lock inside the bfqd->lock. We assume that the bic
	 * returned by bfq_bic_lookup does not go away before
	 * bfqd->lock is taken.
	 */
	struct bfq_io_cq *bic = bfq_bic_lookup(bfqd, current->io_context, q);
	bool ret;

	spin_lock_irq(&bfqd->lock);

	if (bic)
		bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
	else
		bfqd->bio_bfqq = NULL;
	bfqd->bio_bic = bic;

	ret = blk_mq_sched_try_merge(q, bio, &free);

	if (free)
		blk_mq_free_request(free);
	spin_unlock_irq(&bfqd->lock);

	return ret;
}

static int bfq_request_merge(struct request_queue *q, struct request **req,
			     struct bio *bio)
{
	struct bfq_data *bfqd = q->elevator->elevator_data;
	struct request *__rq;

	__rq = bfq_find_rq_fmerge(bfqd, bio, q);
	if (__rq && elv_bio_merge_ok(__rq, bio)) {
		*req = __rq;
		return ELEVATOR_FRONT_MERGE;
	}

	return ELEVATOR_NO_MERGE;
}

static void bfq_request_merged(struct request_queue *q, struct request *req,
			       enum elv_merge type)
{
	if (type == ELEVATOR_FRONT_MERGE &&
	    rb_prev(&req->rb_node) &&
	    blk_rq_pos(req) <
	    blk_rq_pos(container_of(rb_prev(&req->rb_node),
				    struct request, rb_node))) {
		struct bfq_queue *bfqq = RQ_BFQQ(req);
		struct bfq_data *bfqd = bfqq->bfqd;
		struct request *prev, *next_rq;

		/* Reposition request in its sort_list */
		elv_rb_del(&bfqq->sort_list, req);
		elv_rb_add(&bfqq->sort_list, req);

		/* Choose next request to be served for bfqq */
		prev = bfqq->next_rq;
		next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req,
					 bfqd->last_position);
		bfqq->next_rq = next_rq;
		/*
1883 1884 1885
		 * If next_rq changes, update both the queue's budget to
		 * fit the new request and the queue's position in its
		 * rq_pos_tree.
1886
		 */
1887
		if (prev != bfqq->next_rq) {
1888
			bfq_updated_next_req(bfqd, bfqq);
1889 1890
			bfq_pos_tree_add_move(bfqd, bfqq);
		}
1891 1892 1893 1894 1895 1896 1897 1898 1899
	}
}

static void bfq_requests_merged(struct request_queue *q, struct request *rq,
				struct request *next)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);

	if (!RB_EMPTY_NODE(&rq->rb_node))
1900
		goto end;
1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923
	spin_lock_irq(&bfqq->bfqd->lock);

	/*
	 * If next and rq belong to the same bfq_queue and next is older
	 * than rq, then reposition rq in the fifo (by substituting next
	 * with rq). Otherwise, if next and rq belong to different
	 * bfq_queues, never reposition rq: in fact, we would have to
	 * reposition it with respect to next's position in its own fifo,
	 * which would most certainly be too expensive with respect to
	 * the benefits.
	 */
	if (bfqq == next_bfqq &&
	    !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
	    next->fifo_time < rq->fifo_time) {
		list_del_init(&rq->queuelist);
		list_replace_init(&next->queuelist, &rq->queuelist);
		rq->fifo_time = next->fifo_time;
	}

	if (bfqq->next_rq == next)
		bfqq->next_rq = rq;

	bfq_remove_request(q, next);
1924
	bfqg_stats_update_io_remove(bfqq_group(bfqq), next->cmd_flags);
1925 1926

	spin_unlock_irq(&bfqq->bfqd->lock);
1927 1928
end:
	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
1929 1930
}

1931 1932 1933
/* Must be called with bfqq != NULL */
static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
{
1934 1935
	if (bfq_bfqq_busy(bfqq))
		bfqq->bfqd->wr_busy_queues--;
1936 1937
	bfqq->wr_coeff = 1;
	bfqq->wr_cur_max_time = 0;
1938
	bfqq->last_wr_start_finish = jiffies;
1939 1940 1941 1942 1943 1944 1945
	/*
	 * Trigger a weight change on the next invocation of
	 * __bfq_entity_update_weight_prio.
	 */
	bfqq->entity.prio_changed = 1;
}

1946 1947
void bfq_end_wr_async_queues(struct bfq_data *bfqd,
			     struct bfq_group *bfqg)
1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973
{
	int i, j;

	for (i = 0; i < 2; i++)
		for (j = 0; j < IOPRIO_BE_NR; j++)
			if (bfqg->async_bfqq[i][j])
				bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]);
	if (bfqg->async_idle_bfqq)
		bfq_bfqq_end_wr(bfqg->async_idle_bfqq);
}

static void bfq_end_wr(struct bfq_data *bfqd)
{
	struct bfq_queue *bfqq;

	spin_lock_irq(&bfqd->lock);

	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
		bfq_bfqq_end_wr(bfqq);
	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
		bfq_bfqq_end_wr(bfqq);
	bfq_end_wr_async(bfqd);

	spin_unlock_irq(&bfqd->lock);
}

1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091
static sector_t bfq_io_struct_pos(void *io_struct, bool request)
{
	if (request)
		return blk_rq_pos(io_struct);
	else
		return ((struct bio *)io_struct)->bi_iter.bi_sector;
}

static int bfq_rq_close_to_sector(void *io_struct, bool request,
				  sector_t sector)
{
	return abs(bfq_io_struct_pos(io_struct, request) - sector) <=
	       BFQQ_CLOSE_THR;
}

static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd,
					 struct bfq_queue *bfqq,
					 sector_t sector)
{
	struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
	struct rb_node *parent, *node;
	struct bfq_queue *__bfqq;

	if (RB_EMPTY_ROOT(root))
		return NULL;

	/*
	 * First, if we find a request starting at the end of the last
	 * request, choose it.
	 */
	__bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL);
	if (__bfqq)
		return __bfqq;

	/*
	 * If the exact sector wasn't found, the parent of the NULL leaf
	 * will contain the closest sector (rq_pos_tree sorted by
	 * next_request position).
	 */
	__bfqq = rb_entry(parent, struct bfq_queue, pos_node);
	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
		return __bfqq;

	if (blk_rq_pos(__bfqq->next_rq) < sector)
		node = rb_next(&__bfqq->pos_node);
	else
		node = rb_prev(&__bfqq->pos_node);
	if (!node)
		return NULL;

	__bfqq = rb_entry(node, struct bfq_queue, pos_node);
	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
		return __bfqq;

	return NULL;
}

static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd,
						   struct bfq_queue *cur_bfqq,
						   sector_t sector)
{
	struct bfq_queue *bfqq;

	/*
	 * We shall notice if some of the queues are cooperating,
	 * e.g., working closely on the same area of the device. In
	 * that case, we can group them together and: 1) don't waste
	 * time idling, and 2) serve the union of their requests in
	 * the best possible order for throughput.
	 */
	bfqq = bfqq_find_close(bfqd, cur_bfqq, sector);
	if (!bfqq || bfqq == cur_bfqq)
		return NULL;

	return bfqq;
}

static struct bfq_queue *
bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
{
	int process_refs, new_process_refs;
	struct bfq_queue *__bfqq;

	/*
	 * If there are no process references on the new_bfqq, then it is
	 * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
	 * may have dropped their last reference (not just their last process
	 * reference).
	 */
	if (!bfqq_process_refs(new_bfqq))
		return NULL;

	/* Avoid a circular list and skip interim queue merges. */
	while ((__bfqq = new_bfqq->new_bfqq)) {
		if (__bfqq == bfqq)
			return NULL;
		new_bfqq = __bfqq;
	}

	process_refs = bfqq_process_refs(bfqq);
	new_process_refs = bfqq_process_refs(new_bfqq);
	/*
	 * If the process for the bfqq has gone away, there is no
	 * sense in merging the queues.
	 */
	if (process_refs == 0 || new_process_refs == 0)
		return NULL;

	bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
		new_bfqq->pid);

	/*
	 * Merging is just a redirection: the requests of the process
	 * owning one of the two queues are redirected to the other queue.
	 * The latter queue, in its turn, is set as shared if this is the
	 * first time that the requests of some process are redirected to
	 * it.
	 *
2092 2093 2094 2095 2096 2097
	 * We redirect bfqq to new_bfqq and not the opposite, because
	 * we are in the context of the process owning bfqq, thus we
	 * have the io_cq of this process. So we can immediately
	 * configure this io_cq to redirect the requests of the
	 * process to new_bfqq. In contrast, the io_cq of new_bfqq is
	 * not available any more (new_bfqq->bic == NULL).
2098
	 *
2099 2100 2101 2102 2103
	 * Anyway, even in case new_bfqq coincides with the in-service
	 * queue, redirecting requests the in-service queue is the
	 * best option, as we feed the in-service queue with new
	 * requests close to the last request served and, by doing so,
	 * are likely to increase the throughput.
2104 2105 2106 2107 2108 2109 2110 2111 2112
	 */
	bfqq->new_bfqq = new_bfqq;
	new_bfqq->ref += process_refs;
	return new_bfqq;
}

static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
					struct bfq_queue *new_bfqq)
{
2113 2114 2115
	if (bfq_too_late_for_merging(new_bfqq))
		return false;

2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164
	if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) ||
	    (bfqq->ioprio_class != new_bfqq->ioprio_class))
		return false;

	/*
	 * If either of the queues has already been detected as seeky,
	 * then merging it with the other queue is unlikely to lead to
	 * sequential I/O.
	 */
	if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq))
		return false;

	/*
	 * Interleaved I/O is known to be done by (some) applications
	 * only for reads, so it does not make sense to merge async
	 * queues.
	 */
	if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq))
		return false;

	return true;
}

/*
 * Attempt to schedule a merge of bfqq with the currently in-service
 * queue or with a close queue among the scheduled queues.  Return
 * NULL if no merge was scheduled, a pointer to the shared bfq_queue
 * structure otherwise.
 *
 * The OOM queue is not allowed to participate to cooperation: in fact, since
 * the requests temporarily redirected to the OOM queue could be redirected
 * again to dedicated queues at any time, the state needed to correctly
 * handle merging with the OOM queue would be quite complex and expensive
 * to maintain. Besides, in such a critical condition as an out of memory,
 * the benefits of queue merging may be little relevant, or even negligible.
 *
 * WARNING: queue merging may impair fairness among non-weight raised
 * queues, for at least two reasons: 1) the original weight of a
 * merged queue may change during the merged state, 2) even being the
 * weight the same, a merged queue may be bloated with many more
 * requests than the ones produced by its originally-associated
 * process.
 */
static struct bfq_queue *
bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
		     void *io_struct, bool request)
{
	struct bfq_queue *in_service_bfqq, *new_bfqq;

2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178
	/*
	 * Prevent bfqq from being merged if it has been created too
	 * long ago. The idea is that true cooperating processes, and
	 * thus their associated bfq_queues, are supposed to be
	 * created shortly after each other. This is the case, e.g.,
	 * for KVM/QEMU and dump I/O threads. Basing on this
	 * assumption, the following filtering greatly reduces the
	 * probability that two non-cooperating processes, which just
	 * happen to do close I/O for some short time interval, have
	 * their queues merged by mistake.
	 */
	if (bfq_too_late_for_merging(bfqq))
		return NULL;

2179 2180 2181
	if (bfqq->new_bfqq)
		return bfqq->new_bfqq;

2182
	if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq))
2183 2184 2185 2186 2187 2188 2189 2190
		return NULL;

	/* If there is only one backlogged queue, don't search. */
	if (bfqd->busy_queues == 1)
		return NULL;

	in_service_bfqq = bfqd->in_service_queue;

2191 2192 2193
	if (in_service_bfqq && in_service_bfqq != bfqq &&
	    likely(in_service_bfqq != &bfqd->oom_bfqq) &&
	    bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207
	    bfqq->entity.parent == in_service_bfqq->entity.parent &&
	    bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) {
		new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
		if (new_bfqq)
			return new_bfqq;
	}
	/*
	 * Check whether there is a cooperator among currently scheduled
	 * queues. The only thing we need is that the bio/request is not
	 * NULL, as we need it to establish whether a cooperator exists.
	 */
	new_bfqq = bfq_find_close_cooperator(bfqd, bfqq,
			bfq_io_struct_pos(io_struct, request));

2208
	if (new_bfqq && likely(new_bfqq != &bfqd->oom_bfqq) &&
2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227
	    bfq_may_be_close_cooperator(bfqq, new_bfqq))
		return bfq_setup_merge(bfqq, new_bfqq);

	return NULL;
}

static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
{
	struct bfq_io_cq *bic = bfqq->bic;

	/*
	 * If !bfqq->bic, the queue is already shared or its requests
	 * have already been redirected to a shared queue; both idle window
	 * and weight raising state have already been saved. Do nothing.
	 */
	if (!bic)
		return;

	bic->saved_ttime = bfqq->ttime;
2228
	bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq);
2229
	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
2230 2231
	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
2232
	if (unlikely(bfq_bfqq_just_created(bfqq) &&
2233 2234
		     !bfq_bfqq_in_large_burst(bfqq) &&
		     bfqq->bfqd->low_latency)) {
2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253
		/*
		 * bfqq being merged right after being created: bfqq
		 * would have deserved interactive weight raising, but
		 * did not make it to be set in a weight-raised state,
		 * because of this early merge.	Store directly the
		 * weight-raising state that would have been assigned
		 * to bfqq, so that to avoid that bfqq unjustly fails
		 * to enjoy weight raising if split soon.
		 */
		bic->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff;
		bic->saved_wr_cur_max_time = bfq_wr_duration(bfqq->bfqd);
		bic->saved_last_wr_start_finish = jiffies;
	} else {
		bic->saved_wr_coeff = bfqq->wr_coeff;
		bic->saved_wr_start_at_switch_to_srt =
			bfqq->wr_start_at_switch_to_srt;
		bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
		bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
	}
2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274
}

static void
bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
{
	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
		(unsigned long)new_bfqq->pid);
	/* Save weight raising and idle window of the merged queues */
	bfq_bfqq_save_state(bfqq);
	bfq_bfqq_save_state(new_bfqq);
	if (bfq_bfqq_IO_bound(bfqq))
		bfq_mark_bfqq_IO_bound(new_bfqq);
	bfq_clear_bfqq_IO_bound(bfqq);

	/*
	 * If bfqq is weight-raised, then let new_bfqq inherit
	 * weight-raising. To reduce false positives, neglect the case
	 * where bfqq has just been created, but has not yet made it
	 * to be weight-raised (which may happen because EQM may merge
	 * bfqq even before bfq_add_request is executed for the first
2275 2276
	 * time for bfqq). Handling this case would however be very
	 * easy, thanks to the flag just_created.
2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319
	 */
	if (new_bfqq->wr_coeff == 1 && bfqq->wr_coeff > 1) {
		new_bfqq->wr_coeff = bfqq->wr_coeff;
		new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time;
		new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish;
		new_bfqq->wr_start_at_switch_to_srt =
			bfqq->wr_start_at_switch_to_srt;
		if (bfq_bfqq_busy(new_bfqq))
			bfqd->wr_busy_queues++;
		new_bfqq->entity.prio_changed = 1;
	}

	if (bfqq->wr_coeff > 1) { /* bfqq has given its wr to new_bfqq */
		bfqq->wr_coeff = 1;
		bfqq->entity.prio_changed = 1;
		if (bfq_bfqq_busy(bfqq))
			bfqd->wr_busy_queues--;
	}

	bfq_log_bfqq(bfqd, new_bfqq, "merge_bfqqs: wr_busy %d",
		     bfqd->wr_busy_queues);

	/*
	 * Merge queues (that is, let bic redirect its requests to new_bfqq)
	 */
	bic_set_bfqq(bic, new_bfqq, 1);
	bfq_mark_bfqq_coop(new_bfqq);
	/*
	 * new_bfqq now belongs to at least two bics (it is a shared queue):
	 * set new_bfqq->bic to NULL. bfqq either:
	 * - does not belong to any bic any more, and hence bfqq->bic must
	 *   be set to NULL, or
	 * - is a queue whose owning bics have already been redirected to a
	 *   different queue, hence the queue is destined to not belong to
	 *   any bic soon and bfqq->bic is already NULL (therefore the next
	 *   assignment causes no harm).
	 */
	new_bfqq->bic = NULL;
	bfqq->bic = NULL;
	/* release process reference to bfqq */
	bfq_put_queue(bfqq);
}

2320 2321 2322 2323 2324
static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
				struct bio *bio)
{
	struct bfq_data *bfqd = q->elevator->elevator_data;
	bool is_sync = op_is_sync(bio->bi_opf);
2325
	struct bfq_queue *bfqq = bfqd->bio_bfqq, *new_bfqq;
2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339

	/*
	 * Disallow merge of a sync bio into an async request.
	 */
	if (is_sync && !rq_is_sync(rq))
		return false;

	/*
	 * Lookup the bfqq that this bio will be queued with. Allow
	 * merge only if rq is queued there.
	 */
	if (!bfqq)
		return false;

2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370
	/*
	 * We take advantage of this function to perform an early merge
	 * of the queues of possible cooperating processes.
	 */
	new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
	if (new_bfqq) {
		/*
		 * bic still points to bfqq, then it has not yet been
		 * redirected to some other bfq_queue, and a queue
		 * merge beween bfqq and new_bfqq can be safely
		 * fulfillled, i.e., bic can be redirected to new_bfqq
		 * and bfqq can be put.
		 */
		bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq,
				new_bfqq);
		/*
		 * If we get here, bio will be queued into new_queue,
		 * so use new_bfqq to decide whether bio and rq can be
		 * merged.
		 */
		bfqq = new_bfqq;

		/*
		 * Change also bqfd->bio_bfqq, as
		 * bfqd->bio_bic now points to new_bfqq, and
		 * this function may be invoked again (and then may
		 * use again bqfd->bio_bfqq).
		 */
		bfqd->bio_bfqq = bfqq;
	}

2371 2372 2373
	return bfqq == RQ_BFQQ(rq);
}

2374 2375 2376 2377 2378 2379 2380 2381 2382
/*
 * Set the maximum time for the in-service queue to consume its
 * budget. This prevents seeky processes from lowering the throughput.
 * In practice, a time-slice service scheme is used with seeky
 * processes.
 */
static void bfq_set_budget_timeout(struct bfq_data *bfqd,
				   struct bfq_queue *bfqq)
{
2383 2384 2385 2386 2387 2388 2389
	unsigned int timeout_coeff;

	if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time)
		timeout_coeff = 1;
	else
		timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;

2390 2391 2392
	bfqd->last_budget_start = ktime_get();

	bfqq->budget_timeout = jiffies +
2393
		bfqd->bfq_timeout * timeout_coeff;
2394 2395
}

2396 2397 2398 2399 2400 2401 2402 2403
static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
				       struct bfq_queue *bfqq)
{
	if (bfqq) {
		bfq_clear_bfqq_fifo_expire(bfqq);

		bfqd->budgets_assigned = (bfqd->budgets_assigned * 7 + 256) / 8;

2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439
		if (time_is_before_jiffies(bfqq->last_wr_start_finish) &&
		    bfqq->wr_coeff > 1 &&
		    bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
		    time_is_before_jiffies(bfqq->budget_timeout)) {
			/*
			 * For soft real-time queues, move the start
			 * of the weight-raising period forward by the
			 * time the queue has not received any
			 * service. Otherwise, a relatively long
			 * service delay is likely to cause the
			 * weight-raising period of the queue to end,
			 * because of the short duration of the
			 * weight-raising period of a soft real-time
			 * queue.  It is worth noting that this move
			 * is not so dangerous for the other queues,
			 * because soft real-time queues are not
			 * greedy.
			 *
			 * To not add a further variable, we use the
			 * overloaded field budget_timeout to
			 * determine for how long the queue has not
			 * received service, i.e., how much time has
			 * elapsed since the queue expired. However,
			 * this is a little imprecise, because
			 * budget_timeout is set to jiffies if bfqq
			 * not only expires, but also remains with no
			 * request.
			 */
			if (time_after(bfqq->budget_timeout,
				       bfqq->last_wr_start_finish))
				bfqq->last_wr_start_finish +=
					jiffies - bfqq->budget_timeout;
			else
				bfqq->last_wr_start_finish = jiffies;
		}

2440
		bfq_set_budget_timeout(bfqd, bfqq);
2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473
		bfq_log_bfqq(bfqd, bfqq,
			     "set_in_service_queue, cur-budget = %d",
			     bfqq->entity.budget);
	}

	bfqd->in_service_queue = bfqq;
}

/*
 * Get and set a new queue for service.
 */
static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd)
{
	struct bfq_queue *bfqq = bfq_get_next_queue(bfqd);

	__bfq_set_in_service_queue(bfqd, bfqq);
	return bfqq;
}

static void bfq_arm_slice_timer(struct bfq_data *bfqd)
{
	struct bfq_queue *bfqq = bfqd->in_service_queue;
	u32 sl;

	bfq_mark_bfqq_wait_request(bfqq);

	/*
	 * We don't want to idle for seeks, but we do want to allow
	 * fair distribution of slice time for a process doing back-to-back
	 * seeks. So allow a little bit of time for him to submit a new rq.
	 */
	sl = bfqd->bfq_slice_idle;
	/*
2474 2475 2476 2477 2478 2479 2480 2481
	 * Unless the queue is being weight-raised or the scenario is
	 * asymmetric, grant only minimum idle time if the queue
	 * is seeky. A long idling is preserved for a weight-raised
	 * queue, or, more in general, in an asymmetric scenario,
	 * because a long idling is needed for guaranteeing to a queue
	 * its reserved share of the throughput (in particular, it is
	 * needed if the queue has a higher weight than some other
	 * queue).
2482
	 */
2483 2484
	if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
	    bfq_symmetric_scenario(bfqd))
2485 2486 2487 2488 2489
		sl = min_t(u64, sl, BFQ_MIN_TT);

	bfqd->last_idling_start = ktime_get();
	hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
		      HRTIMER_MODE_REL);
2490
	bfqg_stats_set_start_idle_time(bfqq_group(bfqq));
2491 2492
}

2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505
/*
 * In autotuning mode, max_budget is dynamically recomputed as the
 * amount of sectors transferred in timeout at the estimated peak
 * rate. This enables BFQ to utilize a full timeslice with a full
 * budget, even if the in-service queue is served at peak rate. And
 * this maximises throughput with sequential workloads.
 */
static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
{
	return (u64)bfqd->peak_rate * USEC_PER_MSEC *
		jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT;
}

2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541
/*
 * Update parameters related to throughput and responsiveness, as a
 * function of the estimated peak rate. See comments on
 * bfq_calc_max_budget(), and on T_slow and T_fast arrays.
 */
static void update_thr_responsiveness_params(struct bfq_data *bfqd)
{
	int dev_type = blk_queue_nonrot(bfqd->queue);

	if (bfqd->bfq_user_max_budget == 0)
		bfqd->bfq_max_budget =
			bfq_calc_max_budget(bfqd);

	if (bfqd->device_speed == BFQ_BFQD_FAST &&
	    bfqd->peak_rate < device_speed_thresh[dev_type]) {
		bfqd->device_speed = BFQ_BFQD_SLOW;
		bfqd->RT_prod = R_slow[dev_type] *
			T_slow[dev_type];
	} else if (bfqd->device_speed == BFQ_BFQD_SLOW &&
		   bfqd->peak_rate > device_speed_thresh[dev_type]) {
		bfqd->device_speed = BFQ_BFQD_FAST;
		bfqd->RT_prod = R_fast[dev_type] *
			T_fast[dev_type];
	}

	bfq_log(bfqd,
"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec",
		dev_type == 0 ? "ROT" : "NONROT",
		bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW",
		bfqd->device_speed == BFQ_BFQD_FAST ?
		(USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT :
		(USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT,
		(USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>>
		BFQ_RATE_SHIFT);
}

2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652
static void bfq_reset_rate_computation(struct bfq_data *bfqd,
				       struct request *rq)
{
	if (rq != NULL) { /* new rq dispatch now, reset accordingly */
		bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns();
		bfqd->peak_rate_samples = 1;
		bfqd->sequential_samples = 0;
		bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size =
			blk_rq_sectors(rq);
	} else /* no new rq dispatched, just reset the number of samples */
		bfqd->peak_rate_samples = 0; /* full re-init on next disp. */

	bfq_log(bfqd,
		"reset_rate_computation at end, sample %u/%u tot_sects %llu",
		bfqd->peak_rate_samples, bfqd->sequential_samples,
		bfqd->tot_sectors_dispatched);
}

static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq)
{
	u32 rate, weight, divisor;

	/*
	 * For the convergence property to hold (see comments on
	 * bfq_update_peak_rate()) and for the assessment to be
	 * reliable, a minimum number of samples must be present, and
	 * a minimum amount of time must have elapsed. If not so, do
	 * not compute new rate. Just reset parameters, to get ready
	 * for a new evaluation attempt.
	 */
	if (bfqd->peak_rate_samples < BFQ_RATE_MIN_SAMPLES ||
	    bfqd->delta_from_first < BFQ_RATE_MIN_INTERVAL)
		goto reset_computation;

	/*
	 * If a new request completion has occurred after last
	 * dispatch, then, to approximate the rate at which requests
	 * have been served by the device, it is more precise to
	 * extend the observation interval to the last completion.
	 */
	bfqd->delta_from_first =
		max_t(u64, bfqd->delta_from_first,
		      bfqd->last_completion - bfqd->first_dispatch);

	/*
	 * Rate computed in sects/usec, and not sects/nsec, for
	 * precision issues.
	 */
	rate = div64_ul(bfqd->tot_sectors_dispatched<<BFQ_RATE_SHIFT,
			div_u64(bfqd->delta_from_first, NSEC_PER_USEC));

	/*
	 * Peak rate not updated if:
	 * - the percentage of sequential dispatches is below 3/4 of the
	 *   total, and rate is below the current estimated peak rate
	 * - rate is unreasonably high (> 20M sectors/sec)
	 */
	if ((bfqd->sequential_samples < (3 * bfqd->peak_rate_samples)>>2 &&
	     rate <= bfqd->peak_rate) ||
		rate > 20<<BFQ_RATE_SHIFT)
		goto reset_computation;

	/*
	 * We have to update the peak rate, at last! To this purpose,
	 * we use a low-pass filter. We compute the smoothing constant
	 * of the filter as a function of the 'weight' of the new
	 * measured rate.
	 *
	 * As can be seen in next formulas, we define this weight as a
	 * quantity proportional to how sequential the workload is,
	 * and to how long the observation time interval is.
	 *
	 * The weight runs from 0 to 8. The maximum value of the
	 * weight, 8, yields the minimum value for the smoothing
	 * constant. At this minimum value for the smoothing constant,
	 * the measured rate contributes for half of the next value of
	 * the estimated peak rate.
	 *
	 * So, the first step is to compute the weight as a function
	 * of how sequential the workload is. Note that the weight
	 * cannot reach 9, because bfqd->sequential_samples cannot
	 * become equal to bfqd->peak_rate_samples, which, in its
	 * turn, holds true because bfqd->sequential_samples is not
	 * incremented for the first sample.
	 */
	weight = (9 * bfqd->sequential_samples) / bfqd->peak_rate_samples;

	/*
	 * Second step: further refine the weight as a function of the
	 * duration of the observation interval.
	 */
	weight = min_t(u32, 8,
		       div_u64(weight * bfqd->delta_from_first,
			       BFQ_RATE_REF_INTERVAL));

	/*
	 * Divisor ranging from 10, for minimum weight, to 2, for
	 * maximum weight.
	 */
	divisor = 10 - weight;

	/*
	 * Finally, update peak rate:
	 *
	 * peak_rate = peak_rate * (divisor-1) / divisor  +  rate / divisor
	 */
	bfqd->peak_rate *= divisor-1;
	bfqd->peak_rate /= divisor;
	rate /= divisor; /* smoothing constant alpha = 1/divisor */

	bfqd->peak_rate += rate;
2653 2654 2655 2656 2657 2658 2659 2660 2661 2662

	/*
	 * For a very slow device, bfqd->peak_rate can reach 0 (see
	 * the minimum representable values reported in the comments
	 * on BFQ_RATE_SHIFT). Push to 1 if this happens, to avoid
	 * divisions by zero where bfqd->peak_rate is used as a
	 * divisor.
	 */
	bfqd->peak_rate = max_t(u32, 1, bfqd->peak_rate);

2663
	update_thr_responsiveness_params(bfqd);
2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757

reset_computation:
	bfq_reset_rate_computation(bfqd, rq);
}

/*
 * Update the read/write peak rate (the main quantity used for
 * auto-tuning, see update_thr_responsiveness_params()).
 *
 * It is not trivial to estimate the peak rate (correctly): because of
 * the presence of sw and hw queues between the scheduler and the
 * device components that finally serve I/O requests, it is hard to
 * say exactly when a given dispatched request is served inside the
 * device, and for how long. As a consequence, it is hard to know
 * precisely at what rate a given set of requests is actually served
 * by the device.
 *
 * On the opposite end, the dispatch time of any request is trivially
 * available, and, from this piece of information, the "dispatch rate"
 * of requests can be immediately computed. So, the idea in the next
 * function is to use what is known, namely request dispatch times
 * (plus, when useful, request completion times), to estimate what is
 * unknown, namely in-device request service rate.
 *
 * The main issue is that, because of the above facts, the rate at
 * which a certain set of requests is dispatched over a certain time
 * interval can vary greatly with respect to the rate at which the
 * same requests are then served. But, since the size of any
 * intermediate queue is limited, and the service scheme is lossless
 * (no request is silently dropped), the following obvious convergence
 * property holds: the number of requests dispatched MUST become
 * closer and closer to the number of requests completed as the
 * observation interval grows. This is the key property used in
 * the next function to estimate the peak service rate as a function
 * of the observed dispatch rate. The function assumes to be invoked
 * on every request dispatch.
 */
static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
{
	u64 now_ns = ktime_get_ns();

	if (bfqd->peak_rate_samples == 0) { /* first dispatch */
		bfq_log(bfqd, "update_peak_rate: goto reset, samples %d",
			bfqd->peak_rate_samples);
		bfq_reset_rate_computation(bfqd, rq);
		goto update_last_values; /* will add one sample */
	}

	/*
	 * Device idle for very long: the observation interval lasting
	 * up to this dispatch cannot be a valid observation interval
	 * for computing a new peak rate (similarly to the late-
	 * completion event in bfq_completed_request()). Go to
	 * update_rate_and_reset to have the following three steps
	 * taken:
	 * - close the observation interval at the last (previous)
	 *   request dispatch or completion
	 * - compute rate, if possible, for that observation interval
	 * - start a new observation interval with this dispatch
	 */
	if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC &&
	    bfqd->rq_in_driver == 0)
		goto update_rate_and_reset;

	/* Update sampling information */
	bfqd->peak_rate_samples++;

	if ((bfqd->rq_in_driver > 0 ||
		now_ns - bfqd->last_completion < BFQ_MIN_TT)
	     && get_sdist(bfqd->last_position, rq) < BFQQ_SEEK_THR)
		bfqd->sequential_samples++;

	bfqd->tot_sectors_dispatched += blk_rq_sectors(rq);

	/* Reset max observed rq size every 32 dispatches */
	if (likely(bfqd->peak_rate_samples % 32))
		bfqd->last_rq_max_size =
			max_t(u32, blk_rq_sectors(rq), bfqd->last_rq_max_size);
	else
		bfqd->last_rq_max_size = blk_rq_sectors(rq);

	bfqd->delta_from_first = now_ns - bfqd->first_dispatch;

	/* Target observation interval not yet reached, go on sampling */
	if (bfqd->delta_from_first < BFQ_RATE_REF_INTERVAL)
		goto update_last_values;

update_rate_and_reset:
	bfq_update_rate_reset(bfqd, rq);
update_last_values:
	bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
	bfqd->last_dispatch = now_ns;
}

2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777
/*
 * Remove request from internal lists.
 */
static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq);

	/*
	 * For consistency, the next instruction should have been
	 * executed after removing the request from the queue and
	 * dispatching it.  We execute instead this instruction before
	 * bfq_remove_request() (and hence introduce a temporary
	 * inconsistency), for efficiency.  In fact, should this
	 * dispatch occur for a non in-service bfqq, this anticipated
	 * increment prevents two counters related to bfqq->dispatched
	 * from risking to be, first, uselessly decremented, and then
	 * incremented again when the (new) value of bfqq->dispatched
	 * happens to be taken into account.
	 */
	bfqq->dispatched++;
2778
	bfq_update_peak_rate(q->elevator->elevator_data, rq);
2779 2780 2781 2782 2783 2784

	bfq_remove_request(q, rq);
}

static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
2785 2786 2787 2788 2789 2790 2791 2792 2793
	/*
	 * If this bfqq is shared between multiple processes, check
	 * to make sure that those processes are still issuing I/Os
	 * within the mean seek distance. If not, it may be time to
	 * break the queues apart again.
	 */
	if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq))
		bfq_mark_bfqq_split_coop(bfqq);

2794 2795 2796 2797 2798 2799 2800 2801 2802 2803
	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
		if (bfqq->dispatched == 0)
			/*
			 * Overloading budget_timeout field to store
			 * the time at which the queue remains with no
			 * backlog and no outstanding request; used by
			 * the weight-raising mechanism.
			 */
			bfqq->budget_timeout = jiffies;

2804
		bfq_del_bfqq_busy(bfqd, bfqq, true);
2805
	} else {
2806
		bfq_requeue_bfqq(bfqd, bfqq, true);
2807 2808 2809 2810 2811
		/*
		 * Resort priority tree of potential close cooperators.
		 */
		bfq_pos_tree_add_move(bfqd, bfqq);
	}
2812 2813 2814 2815 2816 2817 2818

	/*
	 * All in-service entities must have been properly deactivated
	 * or requeued before executing the next function, which
	 * resets all in-service entites as no more in service.
	 */
	__bfq_bfqd_reset_in_service(bfqd);
2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838
}

/**
 * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior.
 * @bfqd: device data.
 * @bfqq: queue to update.
 * @reason: reason for expiration.
 *
 * Handle the feedback on @bfqq budget at queue expiration.
 * See the body for detailed comments.
 */
static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
				     struct bfq_queue *bfqq,
				     enum bfqq_expiration reason)
{
	struct request *next_rq;
	int budget, min_budget;

	min_budget = bfq_min_budget(bfqd);

2839 2840 2841 2842 2843 2844 2845 2846 2847 2848
	if (bfqq->wr_coeff == 1)
		budget = bfqq->max_budget;
	else /*
	      * Use a constant, low budget for weight-raised queues,
	      * to help achieve a low latency. Keep it slightly higher
	      * than the minimum possible budget, to cause a little
	      * bit fewer expirations.
	      */
		budget = 2 * min_budget;

2849 2850 2851 2852 2853 2854 2855
	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %d, budg left %d",
		bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %d, min budg %d",
		budget, bfq_min_budget(bfqd));
	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: sync %d, seeky %d",
		bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue));

2856
	if (bfq_bfqq_sync(bfqq) && bfqq->wr_coeff == 1) {
2857 2858 2859 2860 2861 2862
		switch (reason) {
		/*
		 * Caveat: in all the following cases we trade latency
		 * for throughput.
		 */
		case BFQQE_TOO_IDLE:
2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894
			/*
			 * This is the only case where we may reduce
			 * the budget: if there is no request of the
			 * process still waiting for completion, then
			 * we assume (tentatively) that the timer has
			 * expired because the batch of requests of
			 * the process could have been served with a
			 * smaller budget.  Hence, betting that
			 * process will behave in the same way when it
			 * becomes backlogged again, we reduce its
			 * next budget.  As long as we guess right,
			 * this budget cut reduces the latency
			 * experienced by the process.
			 *
			 * However, if there are still outstanding
			 * requests, then the process may have not yet
			 * issued its next request just because it is
			 * still waiting for the completion of some of
			 * the still outstanding ones.  So in this
			 * subcase we do not reduce its budget, on the
			 * contrary we increase it to possibly boost
			 * the throughput, as discussed in the
			 * comments to the BUDGET_TIMEOUT case.
			 */
			if (bfqq->dispatched > 0) /* still outstanding reqs */
				budget = min(budget * 2, bfqd->bfq_max_budget);
			else {
				if (budget > 5 * min_budget)
					budget -= 4 * min_budget;
				else
					budget = min_budget;
			}
2895 2896
			break;
		case BFQQE_BUDGET_TIMEOUT:
2897 2898 2899 2900 2901 2902 2903
			/*
			 * We double the budget here because it gives
			 * the chance to boost the throughput if this
			 * is not a seeky process (and has bumped into
			 * this timeout because of, e.g., ZBR).
			 */
			budget = min(budget * 2, bfqd->bfq_max_budget);
2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914
			break;
		case BFQQE_BUDGET_EXHAUSTED:
			/*
			 * The process still has backlog, and did not
			 * let either the budget timeout or the disk
			 * idling timeout expire. Hence it is not
			 * seeky, has a short thinktime and may be
			 * happy with a higher budget too. So
			 * definitely increase the budget of this good
			 * candidate to boost the disk throughput.
			 */
2915
			budget = min(budget * 4, bfqd->bfq_max_budget);
2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954
			break;
		case BFQQE_NO_MORE_REQUESTS:
			/*
			 * For queues that expire for this reason, it
			 * is particularly important to keep the
			 * budget close to the actual service they
			 * need. Doing so reduces the timestamp
			 * misalignment problem described in the
			 * comments in the body of
			 * __bfq_activate_entity. In fact, suppose
			 * that a queue systematically expires for
			 * BFQQE_NO_MORE_REQUESTS and presents a
			 * new request in time to enjoy timestamp
			 * back-shifting. The larger the budget of the
			 * queue is with respect to the service the
			 * queue actually requests in each service
			 * slot, the more times the queue can be
			 * reactivated with the same virtual finish
			 * time. It follows that, even if this finish
			 * time is pushed to the system virtual time
			 * to reduce the consequent timestamp
			 * misalignment, the queue unjustly enjoys for
			 * many re-activations a lower finish time
			 * than all newly activated queues.
			 *
			 * The service needed by bfqq is measured
			 * quite precisely by bfqq->entity.service.
			 * Since bfqq does not enjoy device idling,
			 * bfqq->entity.service is equal to the number
			 * of sectors that the process associated with
			 * bfqq requested to read/write before waiting
			 * for request completions, or blocking for
			 * other reasons.
			 */
			budget = max_t(int, bfqq->entity.service, min_budget);
			break;
		default:
			return;
		}
2955
	} else if (!bfq_bfqq_sync(bfqq)) {
2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991
		/*
		 * Async queues get always the maximum possible
		 * budget, as for them we do not care about latency
		 * (in addition, their ability to dispatch is limited
		 * by the charging factor).
		 */
		budget = bfqd->bfq_max_budget;
	}

	bfqq->max_budget = budget;

	if (bfqd->budgets_assigned >= bfq_stats_min_budgets &&
	    !bfqd->bfq_user_max_budget)
		bfqq->max_budget = min(bfqq->max_budget, bfqd->bfq_max_budget);

	/*
	 * If there is still backlog, then assign a new budget, making
	 * sure that it is large enough for the next request.  Since
	 * the finish time of bfqq must be kept in sync with the
	 * budget, be sure to call __bfq_bfqq_expire() *after* this
	 * update.
	 *
	 * If there is no backlog, then no need to update the budget;
	 * it will be updated on the arrival of a new request.
	 */
	next_rq = bfqq->next_rq;
	if (next_rq)
		bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
					    bfq_serv_to_charge(next_rq, bfqq));

	bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d",
			next_rq ? blk_rq_sectors(next_rq) : 0,
			bfqq->entity.budget);
}

/*
2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020
 * Return true if the process associated with bfqq is "slow". The slow
 * flag is used, in addition to the budget timeout, to reduce the
 * amount of service provided to seeky processes, and thus reduce
 * their chances to lower the throughput. More details in the comments
 * on the function bfq_bfqq_expire().
 *
 * An important observation is in order: as discussed in the comments
 * on the function bfq_update_peak_rate(), with devices with internal
 * queues, it is hard if ever possible to know when and for how long
 * an I/O request is processed by the device (apart from the trivial
 * I/O pattern where a new request is dispatched only after the
 * previous one has been completed). This makes it hard to evaluate
 * the real rate at which the I/O requests of each bfq_queue are
 * served.  In fact, for an I/O scheduler like BFQ, serving a
 * bfq_queue means just dispatching its requests during its service
 * slot (i.e., until the budget of the queue is exhausted, or the
 * queue remains idle, or, finally, a timeout fires). But, during the
 * service slot of a bfq_queue, around 100 ms at most, the device may
 * be even still processing requests of bfq_queues served in previous
 * service slots. On the opposite end, the requests of the in-service
 * bfq_queue may be completed after the service slot of the queue
 * finishes.
 *
 * Anyway, unless more sophisticated solutions are used
 * (where possible), the sum of the sizes of the requests dispatched
 * during the service slot of a bfq_queue is probably the only
 * approximation available for the service received by the bfq_queue
 * during its service slot. And this sum is the quantity used in this
 * function to evaluate the I/O speed of a process.
3021
 */
3022 3023 3024
static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
				 bool compensate, enum bfqq_expiration reason,
				 unsigned long *delta_ms)
3025
{
3026 3027 3028
	ktime_t delta_ktime;
	u32 delta_usecs;
	bool slow = BFQQ_SEEKY(bfqq); /* if delta too short, use seekyness */
3029

3030
	if (!bfq_bfqq_sync(bfqq))
3031 3032 3033
		return false;

	if (compensate)
3034
		delta_ktime = bfqd->last_idling_start;
3035
	else
3036 3037 3038
		delta_ktime = ktime_get();
	delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start);
	delta_usecs = ktime_to_us(delta_ktime);
3039 3040

	/* don't use too short time intervals */
3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052
	if (delta_usecs < 1000) {
		if (blk_queue_nonrot(bfqd->queue))
			 /*
			  * give same worst-case guarantees as idling
			  * for seeky
			  */
			*delta_ms = BFQ_MIN_TT / NSEC_PER_MSEC;
		else /* charge at least one seek */
			*delta_ms = bfq_slice_idle / NSEC_PER_MSEC;

		return slow;
	}
3053

3054
	*delta_ms = delta_usecs / USEC_PER_MSEC;
3055 3056

	/*
3057 3058
	 * Use only long (> 20ms) intervals to filter out excessive
	 * spikes in service rate estimation.
3059
	 */
3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071
	if (delta_usecs > 20000) {
		/*
		 * Caveat for rotational devices: processes doing I/O
		 * in the slower disk zones tend to be slow(er) even
		 * if not seeky. In this respect, the estimated peak
		 * rate is likely to be an average over the disk
		 * surface. Accordingly, to not be too harsh with
		 * unlucky processes, a process is deemed slow only if
		 * its rate has been lower than half of the estimated
		 * peak rate.
		 */
		slow = bfqq->entity.service < bfqd->bfq_max_budget / 2;
3072 3073
	}

3074
	bfq_log_bfqq(bfqd, bfqq, "bfq_bfqq_is_slow: slow %d", slow);
3075

3076
	return slow;
3077 3078
}

3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098
/*
 * To be deemed as soft real-time, an application must meet two
 * requirements. First, the application must not require an average
 * bandwidth higher than the approximate bandwidth required to playback or
 * record a compressed high-definition video.
 * The next function is invoked on the completion of the last request of a
 * batch, to compute the next-start time instant, soft_rt_next_start, such
 * that, if the next request of the application does not arrive before
 * soft_rt_next_start, then the above requirement on the bandwidth is met.
 *
 * The second requirement is that the request pattern of the application is
 * isochronous, i.e., that, after issuing a request or a batch of requests,
 * the application stops issuing new requests until all its pending requests
 * have been completed. After that, the application may issue a new batch,
 * and so on.
 * For this reason the next function is invoked to compute
 * soft_rt_next_start only for applications that meet this requirement,
 * whereas soft_rt_next_start is set to infinity for applications that do
 * not.
 *
3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162
 * Unfortunately, even a greedy (i.e., I/O-bound) application may
 * happen to meet, occasionally or systematically, both the above
 * bandwidth and isochrony requirements. This may happen at least in
 * the following circumstances. First, if the CPU load is high. The
 * application may stop issuing requests while the CPUs are busy
 * serving other processes, then restart, then stop again for a while,
 * and so on. The other circumstances are related to the storage
 * device: the storage device is highly loaded or reaches a low-enough
 * throughput with the I/O of the application (e.g., because the I/O
 * is random and/or the device is slow). In all these cases, the
 * I/O of the application may be simply slowed down enough to meet
 * the bandwidth and isochrony requirements. To reduce the probability
 * that greedy applications are deemed as soft real-time in these
 * corner cases, a further rule is used in the computation of
 * soft_rt_next_start: the return value of this function is forced to
 * be higher than the maximum between the following two quantities.
 *
 * (a) Current time plus: (1) the maximum time for which the arrival
 *     of a request is waited for when a sync queue becomes idle,
 *     namely bfqd->bfq_slice_idle, and (2) a few extra jiffies. We
 *     postpone for a moment the reason for adding a few extra
 *     jiffies; we get back to it after next item (b).  Lower-bounding
 *     the return value of this function with the current time plus
 *     bfqd->bfq_slice_idle tends to filter out greedy applications,
 *     because the latter issue their next request as soon as possible
 *     after the last one has been completed. In contrast, a soft
 *     real-time application spends some time processing data, after a
 *     batch of its requests has been completed.
 *
 * (b) Current value of bfqq->soft_rt_next_start. As pointed out
 *     above, greedy applications may happen to meet both the
 *     bandwidth and isochrony requirements under heavy CPU or
 *     storage-device load. In more detail, in these scenarios, these
 *     applications happen, only for limited time periods, to do I/O
 *     slowly enough to meet all the requirements described so far,
 *     including the filtering in above item (a). These slow-speed
 *     time intervals are usually interspersed between other time
 *     intervals during which these applications do I/O at a very high
 *     speed. Fortunately, exactly because of the high speed of the
 *     I/O in the high-speed intervals, the values returned by this
 *     function happen to be so high, near the end of any such
 *     high-speed interval, to be likely to fall *after* the end of
 *     the low-speed time interval that follows. These high values are
 *     stored in bfqq->soft_rt_next_start after each invocation of
 *     this function. As a consequence, if the last value of
 *     bfqq->soft_rt_next_start is constantly used to lower-bound the
 *     next value that this function may return, then, from the very
 *     beginning of a low-speed interval, bfqq->soft_rt_next_start is
 *     likely to be constantly kept so high that any I/O request
 *     issued during the low-speed interval is considered as arriving
 *     to soon for the application to be deemed as soft
 *     real-time. Then, in the high-speed interval that follows, the
 *     application will not be deemed as soft real-time, just because
 *     it will do I/O at a high speed. And so on.
 *
 * Getting back to the filtering in item (a), in the following two
 * cases this filtering might be easily passed by a greedy
 * application, if the reference quantity was just
 * bfqd->bfq_slice_idle:
 * 1) HZ is so low that the duration of a jiffy is comparable to or
 *    higher than bfqd->bfq_slice_idle. This happens, e.g., on slow
 *    devices with HZ=100. The time granularity may be so coarse
 *    that the approximation, in jiffies, of bfqd->bfq_slice_idle
 *    is rather lower than the exact value.
3163 3164 3165
 * 2) jiffies, instead of increasing at a constant rate, may stop increasing
 *    for a while, then suddenly 'jump' by several units to recover the lost
 *    increments. This seems to happen, e.g., inside virtual machines.
3166 3167 3168 3169 3170
 * To address this issue, in the filtering in (a) we do not use as a
 * reference time interval just bfqd->bfq_slice_idle, but
 * bfqd->bfq_slice_idle plus a few jiffies. In particular, we add the
 * minimum number of jiffies for which the filter seems to be quite
 * precise also in embedded systems and KVM/QEMU virtual machines.
3171 3172 3173 3174
 */
static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
						struct bfq_queue *bfqq)
{
3175 3176 3177 3178 3179
	return max3(bfqq->soft_rt_next_start,
		    bfqq->last_idle_bklogged +
		    HZ * bfqq->service_from_backlogged /
		    bfqd->bfq_wr_max_softrt_rate,
		    jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
3180 3181
}

3182 3183 3184 3185 3186 3187 3188
/**
 * bfq_bfqq_expire - expire a queue.
 * @bfqd: device owning the queue.
 * @bfqq: the queue to expire.
 * @compensate: if true, compensate for the time spent idling.
 * @reason: the reason causing the expiration.
 *
3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201
 * If the process associated with bfqq does slow I/O (e.g., because it
 * issues random requests), we charge bfqq with the time it has been
 * in service instead of the service it has received (see
 * bfq_bfqq_charge_time for details on how this goal is achieved). As
 * a consequence, bfqq will typically get higher timestamps upon
 * reactivation, and hence it will be rescheduled as if it had
 * received more service than what it has actually received. In the
 * end, bfqq receives less service in proportion to how slowly its
 * associated process consumes its budgets (and hence how seriously it
 * tends to lower the throughput). In addition, this time-charging
 * strategy guarantees time fairness among slow processes. In
 * contrast, if the process associated with bfqq is not slow, we
 * charge bfqq exactly with the service it has received.
3202
 *
3203 3204 3205 3206
 * Charging time to the first type of queues and the exact service to
 * the other has the effect of using the WF2Q+ policy to schedule the
 * former on a timeslice basis, without violating service domain
 * guarantees among the latter.
3207
 */
3208 3209 3210 3211
void bfq_bfqq_expire(struct bfq_data *bfqd,
		     struct bfq_queue *bfqq,
		     bool compensate,
		     enum bfqq_expiration reason)
3212 3213
{
	bool slow;
3214 3215
	unsigned long delta = 0;
	struct bfq_entity *entity = &bfqq->entity;
3216 3217 3218
	int ref;

	/*
3219
	 * Check whether the process is slow (see bfq_bfqq_is_slow).
3220
	 */
3221
	slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta);
3222 3223

	/*
3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236
	 * As above explained, charge slow (typically seeky) and
	 * timed-out queues with the time and not the service
	 * received, to favor sequential workloads.
	 *
	 * Processes doing I/O in the slower disk zones will tend to
	 * be slow(er) even if not seeky. Therefore, since the
	 * estimated peak rate is actually an average over the disk
	 * surface, these processes may timeout just for bad luck. To
	 * avoid punishing them, do not charge time to processes that
	 * succeeded in consuming at least 2/3 of their budget. This
	 * allows BFQ to preserve enough elasticity to still perform
	 * bandwidth, and not time, distribution with little unlucky
	 * or quasi-sequential processes.
3237
	 */
3238 3239 3240 3241
	if (bfqq->wr_coeff == 1 &&
	    (slow ||
	     (reason == BFQQE_BUDGET_TIMEOUT &&
	      bfq_bfqq_budget_left(bfqq) >=  entity->budget / 3)))
3242
		bfq_bfqq_charge_time(bfqd, bfqq, delta);
3243 3244

	if (reason == BFQQE_TOO_IDLE &&
3245
	    entity->service <= 2 * entity->budget / 10)
3246 3247
		bfq_clear_bfqq_IO_bound(bfqq);

3248 3249 3250
	if (bfqd->low_latency && bfqq->wr_coeff == 1)
		bfqq->last_wr_start_finish = jiffies;

3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292
	if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 &&
	    RB_EMPTY_ROOT(&bfqq->sort_list)) {
		/*
		 * If we get here, and there are no outstanding
		 * requests, then the request pattern is isochronous
		 * (see the comments on the function
		 * bfq_bfqq_softrt_next_start()). Thus we can compute
		 * soft_rt_next_start. If, instead, the queue still
		 * has outstanding requests, then we have to wait for
		 * the completion of all the outstanding requests to
		 * discover whether the request pattern is actually
		 * isochronous.
		 */
		if (bfqq->dispatched == 0)
			bfqq->soft_rt_next_start =
				bfq_bfqq_softrt_next_start(bfqd, bfqq);
		else {
			/*
			 * The application is still waiting for the
			 * completion of one or more requests:
			 * prevent it from possibly being incorrectly
			 * deemed as soft real-time by setting its
			 * soft_rt_next_start to infinity. In fact,
			 * without this assignment, the application
			 * would be incorrectly deemed as soft
			 * real-time if:
			 * 1) it issued a new request before the
			 *    completion of all its in-flight
			 *    requests, and
			 * 2) at that time, its soft_rt_next_start
			 *    happened to be in the past.
			 */
			bfqq->soft_rt_next_start =
				bfq_greatest_from_now();
			/*
			 * Schedule an update of soft_rt_next_start to when
			 * the task may be discovered to be isochronous.
			 */
			bfq_mark_bfqq_softrt_update(bfqq);
		}
	}

3293
	bfq_log_bfqq(bfqd, bfqq,
3294 3295
		"expire (%d, slow %d, num_disp %d, short_ttime %d)", reason,
		slow, bfqq->dispatched, bfq_bfqq_has_short_ttime(bfqq));
3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318

	/*
	 * Increase, decrease or leave budget unchanged according to
	 * reason.
	 */
	__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
	ref = bfqq->ref;
	__bfq_bfqq_expire(bfqd, bfqq);

	/* mark bfqq as waiting a request only if a bic still points to it */
	if (ref > 1 && !bfq_bfqq_busy(bfqq) &&
	    reason != BFQQE_BUDGET_TIMEOUT &&
	    reason != BFQQE_BUDGET_EXHAUSTED)
		bfq_mark_bfqq_non_blocking_wait_rq(bfqq);
}

/*
 * Budget timeout is not implemented through a dedicated timer, but
 * just checked on request arrivals and completions, as well as on
 * idle timer expirations.
 */
static bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq)
{
3319
	return time_is_before_eq_jiffies(bfqq->budget_timeout);
3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345
}

/*
 * If we expire a queue that is actively waiting (i.e., with the
 * device idled) for the arrival of a new request, then we may incur
 * the timestamp misalignment problem described in the body of the
 * function __bfq_activate_entity. Hence we return true only if this
 * condition does not hold, or if the queue is slow enough to deserve
 * only to be kicked off for preserving a high throughput.
 */
static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
{
	bfq_log_bfqq(bfqq->bfqd, bfqq,
		"may_budget_timeout: wait_request %d left %d timeout %d",
		bfq_bfqq_wait_request(bfqq),
			bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3,
		bfq_bfqq_budget_timeout(bfqq));

	return (!bfq_bfqq_wait_request(bfqq) ||
		bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3)
		&&
		bfq_bfqq_budget_timeout(bfqq);
}

/*
 * For a queue that becomes empty, device idling is allowed only if
3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365
 * this function returns true for the queue. As a consequence, since
 * device idling plays a critical role in both throughput boosting and
 * service guarantees, the return value of this function plays a
 * critical role in both these aspects as well.
 *
 * In a nutshell, this function returns true only if idling is
 * beneficial for throughput or, even if detrimental for throughput,
 * idling is however necessary to preserve service guarantees (low
 * latency, desired throughput distribution, ...). In particular, on
 * NCQ-capable devices, this function tries to return false, so as to
 * help keep the drives' internal queues full, whenever this helps the
 * device boost the throughput without causing any service-guarantee
 * issue.
 *
 * In more detail, the return value of this function is obtained by,
 * first, computing a number of boolean variables that take into
 * account throughput and service-guarantee issues, and, then,
 * combining these variables in a logical expression. Most of the
 * issues taken into account are not trivial. We discuss these issues
 * individually while introducing the variables.
3366 3367 3368 3369
 */
static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
{
	struct bfq_data *bfqd = bfqq->bfqd;
3370 3371 3372 3373
	bool rot_without_queueing =
		!blk_queue_nonrot(bfqd->queue) && !bfqd->hw_tag,
		bfqq_sequential_and_IO_bound,
		idling_boosts_thr, idling_boosts_thr_without_issues,
3374
		idling_needed_for_service_guarantees,
3375
		asymmetric_scenario;
3376 3377 3378 3379

	if (bfqd->strict_guarantees)
		return true;

3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391
	/*
	 * Idling is performed only if slice_idle > 0. In addition, we
	 * do not idle if
	 * (a) bfqq is async
	 * (b) bfqq is in the idle io prio class: in this case we do
	 * not idle because we want to minimize the bandwidth that
	 * queues in this class can steal to higher-priority queues
	 */
	if (bfqd->bfq_slice_idle == 0 || !bfq_bfqq_sync(bfqq) ||
	    bfq_class_idle(bfqq))
		return false;

3392 3393 3394
	bfqq_sequential_and_IO_bound = !BFQQ_SEEKY(bfqq) &&
		bfq_bfqq_IO_bound(bfqq) && bfq_bfqq_has_short_ttime(bfqq);

3395
	/*
3396 3397 3398
	 * The next variable takes into account the cases where idling
	 * boosts the throughput.
	 *
3399 3400
	 * The value of the variable is computed considering, first, that
	 * idling is virtually always beneficial for the throughput if:
3401 3402 3403 3404 3405 3406
	 * (a) the device is not NCQ-capable and rotational, or
	 * (b) regardless of the presence of NCQ, the device is rotational and
	 *     the request pattern for bfqq is I/O-bound and sequential, or
	 * (c) regardless of whether it is rotational, the device is
	 *     not NCQ-capable and the request pattern for bfqq is
	 *     I/O-bound and sequential.
3407 3408 3409
	 *
	 * Secondly, and in contrast to the above item (b), idling an
	 * NCQ-capable flash-based device would not boost the
3410
	 * throughput even with sequential I/O; rather it would lower
3411 3412
	 * the throughput in proportion to how fast the device
	 * is. Accordingly, the next variable is true if any of the
3413 3414 3415
	 * above conditions (a), (b) or (c) is true, and, in
	 * particular, happens to be false if bfqd is an NCQ-capable
	 * flash-based device.
3416
	 */
3417 3418 3419
	idling_boosts_thr = rot_without_queueing ||
		((!blk_queue_nonrot(bfqd->queue) || !bfqd->hw_tag) &&
		 bfqq_sequential_and_IO_bound);
3420

3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458
	/*
	 * The value of the next variable,
	 * idling_boosts_thr_without_issues, is equal to that of
	 * idling_boosts_thr, unless a special case holds. In this
	 * special case, described below, idling may cause problems to
	 * weight-raised queues.
	 *
	 * When the request pool is saturated (e.g., in the presence
	 * of write hogs), if the processes associated with
	 * non-weight-raised queues ask for requests at a lower rate,
	 * then processes associated with weight-raised queues have a
	 * higher probability to get a request from the pool
	 * immediately (or at least soon) when they need one. Thus
	 * they have a higher probability to actually get a fraction
	 * of the device throughput proportional to their high
	 * weight. This is especially true with NCQ-capable drives,
	 * which enqueue several requests in advance, and further
	 * reorder internally-queued requests.
	 *
	 * For this reason, we force to false the value of
	 * idling_boosts_thr_without_issues if there are weight-raised
	 * busy queues. In this case, and if bfqq is not weight-raised,
	 * this guarantees that the device is not idled for bfqq (if,
	 * instead, bfqq is weight-raised, then idling will be
	 * guaranteed by another variable, see below). Combined with
	 * the timestamping rules of BFQ (see [1] for details), this
	 * behavior causes bfqq, and hence any sync non-weight-raised
	 * queue, to get a lower number of requests served, and thus
	 * to ask for a lower number of requests from the request
	 * pool, before the busy weight-raised queues get served
	 * again. This often mitigates starvation problems in the
	 * presence of heavy write workloads and NCQ, thereby
	 * guaranteeing a higher application and system responsiveness
	 * in these hostile scenarios.
	 */
	idling_boosts_thr_without_issues = idling_boosts_thr &&
		bfqd->wr_busy_queues == 0;

3459
	/*
3460 3461 3462 3463 3464 3465
	 * There is then a case where idling must be performed not
	 * for throughput concerns, but to preserve service
	 * guarantees.
	 *
	 * To introduce this case, we can note that allowing the drive
	 * to enqueue more than one request at a time, and hence
3466
	 * delegating de facto final scheduling decisions to the
3467
	 * drive's internal scheduler, entails loss of control on the
3468
	 * actual request service order. In particular, the critical
3469
	 * situation is when requests from different processes happen
3470 3471 3472 3473 3474 3475 3476 3477 3478 3479
	 * to be present, at the same time, in the internal queue(s)
	 * of the drive. In such a situation, the drive, by deciding
	 * the service order of the internally-queued requests, does
	 * determine also the actual throughput distribution among
	 * these processes. But the drive typically has no notion or
	 * concern about per-process throughput distribution, and
	 * makes its decisions only on a per-request basis. Therefore,
	 * the service distribution enforced by the drive's internal
	 * scheduler is likely to coincide with the desired
	 * device-throughput distribution only in a completely
3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540
	 * symmetric scenario where:
	 * (i)  each of these processes must get the same throughput as
	 *      the others;
	 * (ii) all these processes have the same I/O pattern
		(either sequential or random).
	 * In fact, in such a scenario, the drive will tend to treat
	 * the requests of each of these processes in about the same
	 * way as the requests of the others, and thus to provide
	 * each of these processes with about the same throughput
	 * (which is exactly the desired throughput distribution). In
	 * contrast, in any asymmetric scenario, device idling is
	 * certainly needed to guarantee that bfqq receives its
	 * assigned fraction of the device throughput (see [1] for
	 * details).
	 *
	 * We address this issue by controlling, actually, only the
	 * symmetry sub-condition (i), i.e., provided that
	 * sub-condition (i) holds, idling is not performed,
	 * regardless of whether sub-condition (ii) holds. In other
	 * words, only if sub-condition (i) holds, then idling is
	 * allowed, and the device tends to be prevented from queueing
	 * many requests, possibly of several processes. The reason
	 * for not controlling also sub-condition (ii) is that we
	 * exploit preemption to preserve guarantees in case of
	 * symmetric scenarios, even if (ii) does not hold, as
	 * explained in the next two paragraphs.
	 *
	 * Even if a queue, say Q, is expired when it remains idle, Q
	 * can still preempt the new in-service queue if the next
	 * request of Q arrives soon (see the comments on
	 * bfq_bfqq_update_budg_for_activation). If all queues and
	 * groups have the same weight, this form of preemption,
	 * combined with the hole-recovery heuristic described in the
	 * comments on function bfq_bfqq_update_budg_for_activation,
	 * are enough to preserve a correct bandwidth distribution in
	 * the mid term, even without idling. In fact, even if not
	 * idling allows the internal queues of the device to contain
	 * many requests, and thus to reorder requests, we can rather
	 * safely assume that the internal scheduler still preserves a
	 * minimum of mid-term fairness. The motivation for using
	 * preemption instead of idling is that, by not idling,
	 * service guarantees are preserved without minimally
	 * sacrificing throughput. In other words, both a high
	 * throughput and its desired distribution are obtained.
	 *
	 * More precisely, this preemption-based, idleless approach
	 * provides fairness in terms of IOPS, and not sectors per
	 * second. This can be seen with a simple example. Suppose
	 * that there are two queues with the same weight, but that
	 * the first queue receives requests of 8 sectors, while the
	 * second queue receives requests of 1024 sectors. In
	 * addition, suppose that each of the two queues contains at
	 * most one request at a time, which implies that each queue
	 * always remains idle after it is served. Finally, after
	 * remaining idle, each queue receives very quickly a new
	 * request. It follows that the two queues are served
	 * alternatively, preempting each other if needed. This
	 * implies that, although both queues have the same weight,
	 * the queue with large requests receives a service that is
	 * 1024/8 times as high as the service received by the other
	 * queue.
3541
	 *
3542 3543 3544 3545 3546 3547 3548
	 * On the other hand, device idling is performed, and thus
	 * pure sector-domain guarantees are provided, for the
	 * following queues, which are likely to need stronger
	 * throughput guarantees: weight-raised queues, and queues
	 * with a higher weight than other queues. When such queues
	 * are active, sub-condition (i) is false, which triggers
	 * device idling.
3549
	 *
3550 3551 3552 3553 3554 3555 3556 3557
	 * According to the above considerations, the next variable is
	 * true (only) if sub-condition (i) holds. To compute the
	 * value of this variable, we not only use the return value of
	 * the function bfq_symmetric_scenario(), but also check
	 * whether bfqq is being weight-raised, because
	 * bfq_symmetric_scenario() does not take into account also
	 * weight-raised queues (see comments on
	 * bfq_weights_tree_add()).
3558 3559 3560 3561
	 *
	 * As a side note, it is worth considering that the above
	 * device-idling countermeasures may however fail in the
	 * following unlucky scenario: if idling is (correctly)
3562 3563
	 * disabled in a time period during which all symmetry
	 * sub-conditions hold, and hence the device is allowed to
3564 3565 3566 3567 3568
	 * enqueue many requests, but at some later point in time some
	 * sub-condition stops to hold, then it may become impossible
	 * to let requests be served in the desired order until all
	 * the requests already queued in the device have been served.
	 */
3569 3570
	asymmetric_scenario = bfqq->wr_coeff > 1 ||
		!bfq_symmetric_scenario(bfqd);
3571

3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588
	/*
	 * Finally, there is a case where maximizing throughput is the
	 * best choice even if it may cause unfairness toward
	 * bfqq. Such a case is when bfqq became active in a burst of
	 * queue activations. Queues that became active during a large
	 * burst benefit only from throughput, as discussed in the
	 * comments on bfq_handle_burst. Thus, if bfqq became active
	 * in a burst and not idling the device maximizes throughput,
	 * then the device must no be idled, because not idling the
	 * device provides bfqq and all other queues in the burst with
	 * maximum benefit. Combining this and the above case, we can
	 * now establish when idling is actually needed to preserve
	 * service guarantees.
	 */
	idling_needed_for_service_guarantees =
		asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);

3589
	/*
3590 3591 3592 3593
	 * We have now all the components we need to compute the
	 * return value of the function, which is true only if idling
	 * either boosts the throughput (without issues), or is
	 * necessary to preserve service guarantees.
3594
	 */
3595 3596
	return idling_boosts_thr_without_issues ||
		idling_needed_for_service_guarantees;
3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611
}

/*
 * If the in-service queue is empty but the function bfq_bfqq_may_idle
 * returns true, then:
 * 1) the queue must remain in service and cannot be expired, and
 * 2) the device must be idled to wait for the possible arrival of a new
 *    request for the queue.
 * See the comments on the function bfq_bfqq_may_idle for the reasons
 * why performing device idling is the best choice to boost the throughput
 * and preserve service guarantees when bfq_bfqq_may_idle itself
 * returns true.
 */
static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
{
3612
	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_may_idle(bfqq);
3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714
}

/*
 * Select a queue for service.  If we have a current queue in service,
 * check whether to continue servicing it, or retrieve and set a new one.
 */
static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
{
	struct bfq_queue *bfqq;
	struct request *next_rq;
	enum bfqq_expiration reason = BFQQE_BUDGET_TIMEOUT;

	bfqq = bfqd->in_service_queue;
	if (!bfqq)
		goto new_queue;

	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");

	if (bfq_may_expire_for_budg_timeout(bfqq) &&
	    !bfq_bfqq_wait_request(bfqq) &&
	    !bfq_bfqq_must_idle(bfqq))
		goto expire;

check_queue:
	/*
	 * This loop is rarely executed more than once. Even when it
	 * happens, it is much more convenient to re-execute this loop
	 * than to return NULL and trigger a new dispatch to get a
	 * request served.
	 */
	next_rq = bfqq->next_rq;
	/*
	 * If bfqq has requests queued and it has enough budget left to
	 * serve them, keep the queue, otherwise expire it.
	 */
	if (next_rq) {
		if (bfq_serv_to_charge(next_rq, bfqq) >
			bfq_bfqq_budget_left(bfqq)) {
			/*
			 * Expire the queue for budget exhaustion,
			 * which makes sure that the next budget is
			 * enough to serve the next request, even if
			 * it comes from the fifo expired path.
			 */
			reason = BFQQE_BUDGET_EXHAUSTED;
			goto expire;
		} else {
			/*
			 * The idle timer may be pending because we may
			 * not disable disk idling even when a new request
			 * arrives.
			 */
			if (bfq_bfqq_wait_request(bfqq)) {
				/*
				 * If we get here: 1) at least a new request
				 * has arrived but we have not disabled the
				 * timer because the request was too small,
				 * 2) then the block layer has unplugged
				 * the device, causing the dispatch to be
				 * invoked.
				 *
				 * Since the device is unplugged, now the
				 * requests are probably large enough to
				 * provide a reasonable throughput.
				 * So we disable idling.
				 */
				bfq_clear_bfqq_wait_request(bfqq);
				hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
			}
			goto keep_queue;
		}
	}

	/*
	 * No requests pending. However, if the in-service queue is idling
	 * for a new request, or has requests waiting for a completion and
	 * may idle after their completion, then keep it anyway.
	 */
	if (bfq_bfqq_wait_request(bfqq) ||
	    (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
		bfqq = NULL;
		goto keep_queue;
	}

	reason = BFQQE_NO_MORE_REQUESTS;
expire:
	bfq_bfqq_expire(bfqd, bfqq, false, reason);
new_queue:
	bfqq = bfq_set_in_service_queue(bfqd);
	if (bfqq) {
		bfq_log_bfqq(bfqd, bfqq, "select_queue: checking new queue");
		goto check_queue;
	}
keep_queue:
	if (bfqq)
		bfq_log_bfqq(bfqd, bfqq, "select_queue: returned this queue");
	else
		bfq_log(bfqd, "select_queue: no queue returned");

	return bfqq;
}

3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730
static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
	struct bfq_entity *entity = &bfqq->entity;

	if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */
		bfq_log_bfqq(bfqd, bfqq,
			"raising period dur %u/%u msec, old coeff %u, w %d(%d)",
			jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
			jiffies_to_msecs(bfqq->wr_cur_max_time),
			bfqq->wr_coeff,
			bfqq->entity.weight, bfqq->entity.orig_weight);

		if (entity->prio_changed)
			bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change");

		/*
3731 3732 3733
		 * If the queue was activated in a burst, or too much
		 * time has elapsed from the beginning of this
		 * weight-raising period, then end weight raising.
3734
		 */
3735 3736 3737 3738
		if (bfq_bfqq_in_large_burst(bfqq))
			bfq_bfqq_end_wr(bfqq);
		else if (time_is_before_jiffies(bfqq->last_wr_start_finish +
						bfqq->wr_cur_max_time)) {
3739 3740
			if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time ||
			time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
3741
					       bfq_wr_duration(bfqd)))
3742 3743
				bfq_bfqq_end_wr(bfqq);
			else {
3744
				switch_back_to_interactive_wr(bfqq, bfqd);
3745 3746
				bfqq->entity.prio_changed = 1;
			}
3747
		}
3748 3749 3750 3751 3752 3753
		if (bfqq->wr_coeff > 1 &&
		    bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time &&
		    bfqq->service_from_wr > max_service_from_wr) {
			/* see comments on max_service_from_wr */
			bfq_bfqq_end_wr(bfqq);
		}
3754
	}
3755 3756 3757 3758 3759 3760 3761 3762
	/*
	 * To improve latency (for this or other queues), immediately
	 * update weight both if it must be raised and if it must be
	 * lowered. Since, entity may be on some active tree here, and
	 * might have a pending change of its ioprio class, invoke
	 * next function with the last parameter unset (see the
	 * comments on the function).
	 */
3763
	if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1))
3764 3765
		__bfq_entity_update_weight_prio(bfq_entity_service_tree(entity),
						entity, false);
3766 3767
}

3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782
/*
 * Dispatch next request from bfqq.
 */
static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
						 struct bfq_queue *bfqq)
{
	struct request *rq = bfqq->next_rq;
	unsigned long service_to_charge;

	service_to_charge = bfq_serv_to_charge(rq, bfqq);

	bfq_bfqq_served(bfqq, service_to_charge);

	bfq_dispatch_remove(bfqd->queue, rq);

3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795
	/*
	 * If weight raising has to terminate for bfqq, then next
	 * function causes an immediate update of bfqq's weight,
	 * without waiting for next activation. As a consequence, on
	 * expiration, bfqq will be timestamped as if has never been
	 * weight-raised during this service slot, even if it has
	 * received part or even most of the service as a
	 * weight-raised queue. This inflates bfqq's timestamps, which
	 * is beneficial, as bfqq is then more willing to leave the
	 * device immediately to possible other weight-raised queues.
	 */
	bfq_update_wr_data(bfqd, bfqq);

3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848
	/*
	 * Expire bfqq, pretending that its budget expired, if bfqq
	 * belongs to CLASS_IDLE and other queues are waiting for
	 * service.
	 */
	if (bfqd->busy_queues > 1 && bfq_class_idle(bfqq))
		goto expire;

	return rq;

expire:
	bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_BUDGET_EXHAUSTED);
	return rq;
}

static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
{
	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;

	/*
	 * Avoiding lock: a race on bfqd->busy_queues should cause at
	 * most a call to dispatch for nothing
	 */
	return !list_empty_careful(&bfqd->dispatch) ||
		bfqd->busy_queues > 0;
}

static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
{
	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
	struct request *rq = NULL;
	struct bfq_queue *bfqq = NULL;

	if (!list_empty(&bfqd->dispatch)) {
		rq = list_first_entry(&bfqd->dispatch, struct request,
				      queuelist);
		list_del_init(&rq->queuelist);

		bfqq = RQ_BFQQ(rq);

		if (bfqq) {
			/*
			 * Increment counters here, because this
			 * dispatch does not follow the standard
			 * dispatch flow (where counters are
			 * incremented)
			 */
			bfqq->dispatched++;

			goto inc_in_driver_start_rq;
		}

		/*
3849 3850 3851 3852 3853 3854 3855 3856 3857
		 * We exploit the bfq_finish_requeue_request hook to
		 * decrement rq_in_driver, but
		 * bfq_finish_requeue_request will not be invoked on
		 * this request. So, to avoid unbalance, just start
		 * this request, without incrementing rq_in_driver. As
		 * a negative consequence, rq_in_driver is deceptively
		 * lower than it should be while this request is in
		 * service. This may cause bfq_schedule_dispatch to be
		 * invoked uselessly.
3858 3859
		 *
		 * As for implementing an exact solution, the
3860 3861 3862 3863 3864 3865 3866 3867 3868
		 * bfq_finish_requeue_request hook, if defined, is
		 * probably invoked also on this request. So, by
		 * exploiting this hook, we could 1) increment
		 * rq_in_driver here, and 2) decrement it in
		 * bfq_finish_requeue_request. Such a solution would
		 * let the value of the counter be always accurate,
		 * but it would entail using an extra interface
		 * function. This cost seems higher than the benefit,
		 * being the frequency of non-elevator-private
3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909
		 * requests very low.
		 */
		goto start_rq;
	}

	bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);

	if (bfqd->busy_queues == 0)
		goto exit;

	/*
	 * Force device to serve one request at a time if
	 * strict_guarantees is true. Forcing this service scheme is
	 * currently the ONLY way to guarantee that the request
	 * service order enforced by the scheduler is respected by a
	 * queueing device. Otherwise the device is free even to make
	 * some unlucky request wait for as long as the device
	 * wishes.
	 *
	 * Of course, serving one request at at time may cause loss of
	 * throughput.
	 */
	if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0)
		goto exit;

	bfqq = bfq_select_queue(bfqd);
	if (!bfqq)
		goto exit;

	rq = bfq_dispatch_rq_from_bfqq(bfqd, bfqq);

	if (rq) {
inc_in_driver_start_rq:
		bfqd->rq_in_driver++;
start_rq:
		rq->rq_flags |= RQF_STARTED;
	}
exit:
	return rq;
}

3910
#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
3911 3912 3913 3914 3915 3916
static void bfq_update_dispatch_stats(struct request_queue *q,
				      struct request *rq,
				      struct bfq_queue *in_serv_queue,
				      bool idle_timer_disabled)
{
	struct bfq_queue *bfqq = rq ? RQ_BFQQ(rq) : NULL;
3917

3918
	if (!idle_timer_disabled && !bfqq)
3919
		return;
3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933

	/*
	 * rq and bfqq are guaranteed to exist until this function
	 * ends, for the following reasons. First, rq can be
	 * dispatched to the device, and then can be completed and
	 * freed, only after this function ends. Second, rq cannot be
	 * merged (and thus freed because of a merge) any longer,
	 * because it has already started. Thus rq cannot be freed
	 * before this function ends, and, since rq has a reference to
	 * bfqq, the same guarantee holds for bfqq too.
	 *
	 * In addition, the following queue lock guarantees that
	 * bfqq_group(bfqq) exists as well.
	 */
3934
	spin_lock_irq(q->queue_lock);
3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952
	if (idle_timer_disabled)
		/*
		 * Since the idle timer has been disabled,
		 * in_serv_queue contained some request when
		 * __bfq_dispatch_request was invoked above, which
		 * implies that rq was picked exactly from
		 * in_serv_queue. Thus in_serv_queue == bfqq, and is
		 * therefore guaranteed to exist because of the above
		 * arguments.
		 */
		bfqg_stats_update_idle_time(bfqq_group(in_serv_queue));
	if (bfqq) {
		struct bfq_group *bfqg = bfqq_group(bfqq);

		bfqg_stats_update_avg_queue_size(bfqg);
		bfqg_stats_set_start_empty_time(bfqg);
		bfqg_stats_update_io_remove(bfqg, rq->cmd_flags);
	}
3953 3954 3955 3956 3957 3958 3959
	spin_unlock_irq(q->queue_lock);
}
#else
static inline void bfq_update_dispatch_stats(struct request_queue *q,
					     struct request *rq,
					     struct bfq_queue *in_serv_queue,
					     bool idle_timer_disabled) {}
3960 3961
#endif

3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983
static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
{
	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
	struct request *rq;
	struct bfq_queue *in_serv_queue;
	bool waiting_rq, idle_timer_disabled;

	spin_lock_irq(&bfqd->lock);

	in_serv_queue = bfqd->in_service_queue;
	waiting_rq = in_serv_queue && bfq_bfqq_wait_request(in_serv_queue);

	rq = __bfq_dispatch_request(hctx);

	idle_timer_disabled =
		waiting_rq && !bfq_bfqq_wait_request(in_serv_queue);

	spin_unlock_irq(&bfqd->lock);

	bfq_update_dispatch_stats(hctx->queue, rq, in_serv_queue,
				  idle_timer_disabled);

3984 3985 3986 3987 3988 3989 3990 3991 3992 3993
	return rq;
}

/*
 * Task holds one reference to the queue, dropped when task exits.  Each rq
 * in-flight on this queue also holds a reference, dropped when rq is freed.
 *
 * Scheduler lock must be held here. Recall not to use bfqq after calling
 * this function on it.
 */
3994
void bfq_put_queue(struct bfq_queue *bfqq)
3995
{
3996 3997 3998 3999
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	struct bfq_group *bfqg = bfqq_group(bfqq);
#endif

4000 4001 4002 4003 4004 4005 4006 4007
	if (bfqq->bfqd)
		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d",
			     bfqq, bfqq->ref);

	bfqq->ref--;
	if (bfqq->ref)
		return;

4008
	if (!hlist_unhashed(&bfqq->burst_list_node)) {
4009
		hlist_del_init(&bfqq->burst_list_node);
4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037
		/*
		 * Decrement also burst size after the removal, if the
		 * process associated with bfqq is exiting, and thus
		 * does not contribute to the burst any longer. This
		 * decrement helps filter out false positives of large
		 * bursts, when some short-lived process (often due to
		 * the execution of commands by some service) happens
		 * to start and exit while a complex application is
		 * starting, and thus spawning several processes that
		 * do I/O (and that *must not* be treated as a large
		 * burst, see comments on bfq_handle_burst).
		 *
		 * In particular, the decrement is performed only if:
		 * 1) bfqq is not a merged queue, because, if it is,
		 * then this free of bfqq is not triggered by the exit
		 * of the process bfqq is associated with, but exactly
		 * by the fact that bfqq has just been merged.
		 * 2) burst_size is greater than 0, to handle
		 * unbalanced decrements. Unbalanced decrements may
		 * happen in te following case: bfqq is inserted into
		 * the current burst list--without incrementing
		 * bust_size--because of a split, but the current
		 * burst list is not the burst list bfqq belonged to
		 * (see comments on the case of a split in
		 * bfq_set_request).
		 */
		if (bfqq->bic && bfqq->bfqd->burst_size > 0)
			bfqq->bfqd->burst_size--;
4038
	}
4039

4040
	kmem_cache_free(bfq_pool, bfqq);
4041
#ifdef CONFIG_BFQ_GROUP_IOSCHED
4042
	bfqg_and_blkg_put(bfqg);
4043
#endif
4044 4045
}

4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064
static void bfq_put_cooperator(struct bfq_queue *bfqq)
{
	struct bfq_queue *__bfqq, *next;

	/*
	 * If this queue was scheduled to merge with another queue, be
	 * sure to drop the reference taken on that queue (and others in
	 * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs.
	 */
	__bfqq = bfqq->new_bfqq;
	while (__bfqq) {
		if (__bfqq == bfqq)
			break;
		next = __bfqq->new_bfqq;
		bfq_put_queue(__bfqq);
		__bfqq = next;
	}
}

4065 4066 4067 4068 4069 4070 4071 4072 4073
static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
	if (bfqq == bfqd->in_service_queue) {
		__bfq_bfqq_expire(bfqd, bfqq);
		bfq_schedule_dispatch(bfqd);
	}

	bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq, bfqq->ref);

4074 4075
	bfq_put_cooperator(bfqq);

4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092
	bfq_put_queue(bfqq); /* release process reference */
}

static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
{
	struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
	struct bfq_data *bfqd;

	if (bfqq)
		bfqd = bfqq->bfqd; /* NULL if scheduler already exited */

	if (bfqq && bfqd) {
		unsigned long flags;

		spin_lock_irqsave(&bfqd->lock, flags);
		bfq_exit_bfqq(bfqd, bfqq);
		bic_set_bfqq(bic, NULL, is_sync);
4093
		spin_unlock_irqrestore(&bfqd->lock, flags);
4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123
	}
}

static void bfq_exit_icq(struct io_cq *icq)
{
	struct bfq_io_cq *bic = icq_to_bic(icq);

	bfq_exit_icq_bfqq(bic, true);
	bfq_exit_icq_bfqq(bic, false);
}

/*
 * Update the entity prio values; note that the new values will not
 * be used until the next (re)activation.
 */
static void
bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
{
	struct task_struct *tsk = current;
	int ioprio_class;
	struct bfq_data *bfqd = bfqq->bfqd;

	if (!bfqd)
		return;

	ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
	switch (ioprio_class) {
	default:
		dev_err(bfqq->bfqd->queue->backing_dev_info->dev,
			"bfq: bad prio class %d\n", ioprio_class);
4124
		/* fall through */
4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155
	case IOPRIO_CLASS_NONE:
		/*
		 * No prio set, inherit CPU scheduling settings.
		 */
		bfqq->new_ioprio = task_nice_ioprio(tsk);
		bfqq->new_ioprio_class = task_nice_ioclass(tsk);
		break;
	case IOPRIO_CLASS_RT:
		bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
		bfqq->new_ioprio_class = IOPRIO_CLASS_RT;
		break;
	case IOPRIO_CLASS_BE:
		bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
		bfqq->new_ioprio_class = IOPRIO_CLASS_BE;
		break;
	case IOPRIO_CLASS_IDLE:
		bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE;
		bfqq->new_ioprio = 7;
		break;
	}

	if (bfqq->new_ioprio >= IOPRIO_BE_NR) {
		pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n",
			bfqq->new_ioprio);
		bfqq->new_ioprio = IOPRIO_BE_NR;
	}

	bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio);
	bfqq->entity.prio_changed = 1;
}

4156 4157 4158 4159
static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
				       struct bio *bio, bool is_sync,
				       struct bfq_io_cq *bic);

4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192
static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
{
	struct bfq_data *bfqd = bic_to_bfqd(bic);
	struct bfq_queue *bfqq;
	int ioprio = bic->icq.ioc->ioprio;

	/*
	 * This condition may trigger on a newly created bic, be sure to
	 * drop the lock before returning.
	 */
	if (unlikely(!bfqd) || likely(bic->ioprio == ioprio))
		return;

	bic->ioprio = ioprio;

	bfqq = bic_to_bfqq(bic, false);
	if (bfqq) {
		/* release process reference on this queue */
		bfq_put_queue(bfqq);
		bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic);
		bic_set_bfqq(bic, bfqq, false);
	}

	bfqq = bic_to_bfqq(bic, true);
	if (bfqq)
		bfq_set_next_ioprio_data(bfqq, bic);
}

static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
			  struct bfq_io_cq *bic, pid_t pid, int is_sync)
{
	RB_CLEAR_NODE(&bfqq->entity.rb_node);
	INIT_LIST_HEAD(&bfqq->fifo);
4193
	INIT_HLIST_NODE(&bfqq->burst_list_node);
4194 4195 4196 4197 4198 4199 4200 4201

	bfqq->ref = 0;
	bfqq->bfqd = bfqd;

	if (bic)
		bfq_set_next_ioprio_data(bfqq, bic);

	if (is_sync) {
4202 4203 4204 4205 4206
		/*
		 * No need to mark as has_short_ttime if in
		 * idle_class, because no device idling is performed
		 * for queues in idle class
		 */
4207
		if (!bfq_class_idle(bfqq))
4208 4209
			/* tentatively mark as has_short_ttime */
			bfq_mark_bfqq_has_short_ttime(bfqq);
4210
		bfq_mark_bfqq_sync(bfqq);
4211
		bfq_mark_bfqq_just_created(bfqq);
4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222
	} else
		bfq_clear_bfqq_sync(bfqq);

	/* set end request to minus infinity from now */
	bfqq->ttime.last_end_request = ktime_get_ns() + 1;

	bfq_mark_bfqq_IO_bound(bfqq);

	bfqq->pid = pid;

	/* Tentative initial value to trade off between thr and lat */
4223
	bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
4224 4225
	bfqq->budget_timeout = bfq_smallest_from_now();

4226
	bfqq->wr_coeff = 1;
4227
	bfqq->last_wr_start_finish = jiffies;
4228
	bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now();
4229
	bfqq->split_time = bfq_smallest_from_now();
4230 4231

	/*
4232 4233 4234 4235 4236 4237 4238
	 * To not forget the possibly high bandwidth consumed by a
	 * process/queue in the recent past,
	 * bfq_bfqq_softrt_next_start() returns a value at least equal
	 * to the current value of bfqq->soft_rt_next_start (see
	 * comments on bfq_bfqq_softrt_next_start).  Set
	 * soft_rt_next_start to now, to mean that bfqq has consumed
	 * no bandwidth so far.
4239
	 */
4240
	bfqq->soft_rt_next_start = jiffies;
4241

4242 4243 4244 4245 4246
	/* first request is almost certainly seeky */
	bfqq->seek_history = 1;
}

static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
4247
					       struct bfq_group *bfqg,
4248 4249 4250 4251
					       int ioprio_class, int ioprio)
{
	switch (ioprio_class) {
	case IOPRIO_CLASS_RT:
4252
		return &bfqg->async_bfqq[0][ioprio];
4253 4254 4255 4256
	case IOPRIO_CLASS_NONE:
		ioprio = IOPRIO_NORM;
		/* fall through */
	case IOPRIO_CLASS_BE:
4257
		return &bfqg->async_bfqq[1][ioprio];
4258
	case IOPRIO_CLASS_IDLE:
4259
		return &bfqg->async_idle_bfqq;
4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272
	default:
		return NULL;
	}
}

static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
				       struct bio *bio, bool is_sync,
				       struct bfq_io_cq *bic)
{
	const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
	const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
	struct bfq_queue **async_bfqq = NULL;
	struct bfq_queue *bfqq;
4273
	struct bfq_group *bfqg;
4274 4275 4276

	rcu_read_lock();

4277 4278 4279 4280 4281 4282
	bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio));
	if (!bfqg) {
		bfqq = &bfqd->oom_bfqq;
		goto out;
	}

4283
	if (!is_sync) {
4284
		async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class,
4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297
						  ioprio);
		bfqq = *async_bfqq;
		if (bfqq)
			goto out;
	}

	bfqq = kmem_cache_alloc_node(bfq_pool,
				     GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN,
				     bfqd->queue->node);

	if (bfqq) {
		bfq_init_bfqq(bfqd, bfqq, bic, current->pid,
			      is_sync);
4298
		bfq_init_entity(&bfqq->entity, bfqg);
4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310
		bfq_log_bfqq(bfqd, bfqq, "allocated");
	} else {
		bfqq = &bfqd->oom_bfqq;
		bfq_log_bfqq(bfqd, bfqq, "using oom bfqq");
		goto out;
	}

	/*
	 * Pin the queue now that it's allocated, scheduler exit will
	 * prune it.
	 */
	if (async_bfqq) {
4311 4312 4313 4314 4315 4316 4317 4318
		bfqq->ref++; /*
			      * Extra group reference, w.r.t. sync
			      * queue. This extra reference is removed
			      * only if bfqq->bfqg disappears, to
			      * guarantee that this queue is not freed
			      * until its group goes away.
			      */
		bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d",
4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348
			     bfqq, bfqq->ref);
		*async_bfqq = bfqq;
	}

out:
	bfqq->ref++; /* get a process reference to this queue */
	bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq, bfqq->ref);
	rcu_read_unlock();
	return bfqq;
}

static void bfq_update_io_thinktime(struct bfq_data *bfqd,
				    struct bfq_queue *bfqq)
{
	struct bfq_ttime *ttime = &bfqq->ttime;
	u64 elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;

	elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);

	ttime->ttime_samples = (7*bfqq->ttime.ttime_samples + 256) / 8;
	ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed,  8);
	ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
				     ttime->ttime_samples);
}

static void
bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
		       struct request *rq)
{
	bfqq->seek_history <<= 1;
4349 4350
	bfqq->seek_history |=
		get_sdist(bfqq->last_request_pos, rq) > BFQQ_SEEK_THR &&
4351 4352 4353 4354
		(!blk_queue_nonrot(bfqd->queue) ||
		 blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT);
}

4355 4356 4357
static void bfq_update_has_short_ttime(struct bfq_data *bfqd,
				       struct bfq_queue *bfqq,
				       struct bfq_io_cq *bic)
4358
{
4359
	bool has_short_ttime = true;
4360

4361 4362 4363 4364 4365 4366 4367
	/*
	 * No need to update has_short_ttime if bfqq is async or in
	 * idle io prio class, or if bfq_slice_idle is zero, because
	 * no device idling is performed for bfqq in this case.
	 */
	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq) ||
	    bfqd->bfq_slice_idle == 0)
4368 4369
		return;

4370 4371 4372 4373 4374
	/* Idle window just restored, statistics are meaningless. */
	if (time_is_after_eq_jiffies(bfqq->split_time +
				     bfqd->bfq_wr_min_idle_time))
		return;

4375 4376 4377 4378
	/* Think time is infinite if no process is linked to
	 * bfqq. Otherwise check average think time to
	 * decide whether to mark as has_short_ttime
	 */
4379
	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
4380 4381 4382 4383 4384 4385
	    (bfq_sample_valid(bfqq->ttime.ttime_samples) &&
	     bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle))
		has_short_ttime = false;

	bfq_log_bfqq(bfqd, bfqq, "update_has_short_ttime: has_short_ttime %d",
		     has_short_ttime);
4386

4387 4388
	if (has_short_ttime)
		bfq_mark_bfqq_has_short_ttime(bfqq);
4389
	else
4390
		bfq_clear_bfqq_has_short_ttime(bfqq);
4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405
}

/*
 * Called when a new fs request (rq) is added to bfqq.  Check if there's
 * something we should do about it.
 */
static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
			    struct request *rq)
{
	struct bfq_io_cq *bic = RQ_BIC(rq);

	if (rq->cmd_flags & REQ_META)
		bfqq->meta_pending++;

	bfq_update_io_thinktime(bfqd, bfqq);
4406
	bfq_update_has_short_ttime(bfqd, bfqq, bic);
4407 4408 4409
	bfq_update_io_seektime(bfqd, bfqq, rq);

	bfq_log_bfqq(bfqd, bfqq,
4410 4411
		     "rq_enqueued: has_short_ttime=%d (seeky %d)",
		     bfq_bfqq_has_short_ttime(bfqq), BFQQ_SEEKY(bfqq));
4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459

	bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);

	if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) {
		bool small_req = bfqq->queued[rq_is_sync(rq)] == 1 &&
				 blk_rq_sectors(rq) < 32;
		bool budget_timeout = bfq_bfqq_budget_timeout(bfqq);

		/*
		 * There is just this request queued: if the request
		 * is small and the queue is not to be expired, then
		 * just exit.
		 *
		 * In this way, if the device is being idled to wait
		 * for a new request from the in-service queue, we
		 * avoid unplugging the device and committing the
		 * device to serve just a small request. On the
		 * contrary, we wait for the block layer to decide
		 * when to unplug the device: hopefully, new requests
		 * will be merged to this one quickly, then the device
		 * will be unplugged and larger requests will be
		 * dispatched.
		 */
		if (small_req && !budget_timeout)
			return;

		/*
		 * A large enough request arrived, or the queue is to
		 * be expired: in both cases disk idling is to be
		 * stopped, so clear wait_request flag and reset
		 * timer.
		 */
		bfq_clear_bfqq_wait_request(bfqq);
		hrtimer_try_to_cancel(&bfqd->idle_slice_timer);

		/*
		 * The queue is not empty, because a new request just
		 * arrived. Hence we can safely expire the queue, in
		 * case of budget timeout, without risking that the
		 * timestamps of the queue are not updated correctly.
		 * See [1] for more details.
		 */
		if (budget_timeout)
			bfq_bfqq_expire(bfqd, bfqq, false,
					BFQQE_BUDGET_TIMEOUT);
	}
}

4460 4461
/* returns true if it causes the idle timer to be disabled */
static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
4462
{
4463 4464
	struct bfq_queue *bfqq = RQ_BFQQ(rq),
		*new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
4465
	bool waiting, idle_timer_disabled = false;
4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487

	if (new_bfqq) {
		if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq)
			new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1);
		/*
		 * Release the request's reference to the old bfqq
		 * and make sure one is taken to the shared queue.
		 */
		new_bfqq->allocated++;
		bfqq->allocated--;
		new_bfqq->ref++;
		/*
		 * If the bic associated with the process
		 * issuing this request still points to bfqq
		 * (and thus has not been already redirected
		 * to new_bfqq or even some other bfq_queue),
		 * then complete the merge and redirect it to
		 * new_bfqq.
		 */
		if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
			bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
					bfqq, new_bfqq);
4488 4489

		bfq_clear_bfqq_just_created(bfqq);
4490 4491 4492 4493 4494 4495 4496 4497
		/*
		 * rq is about to be enqueued into new_bfqq,
		 * release rq reference on bfqq
		 */
		bfq_put_queue(bfqq);
		rq->elv.priv[1] = new_bfqq;
		bfqq = new_bfqq;
	}
4498

4499
	waiting = bfqq && bfq_bfqq_wait_request(bfqq);
4500
	bfq_add_request(rq);
4501
	idle_timer_disabled = waiting && !bfq_bfqq_wait_request(bfqq);
4502 4503 4504 4505 4506

	rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
	list_add_tail(&rq->queuelist, &bfqq->fifo);

	bfq_rq_enqueued(bfqd, bfqq, rq);
4507 4508

	return idle_timer_disabled;
4509 4510
}

4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542
#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
static void bfq_update_insert_stats(struct request_queue *q,
				    struct bfq_queue *bfqq,
				    bool idle_timer_disabled,
				    unsigned int cmd_flags)
{
	if (!bfqq)
		return;

	/*
	 * bfqq still exists, because it can disappear only after
	 * either it is merged with another queue, or the process it
	 * is associated with exits. But both actions must be taken by
	 * the same process currently executing this flow of
	 * instructions.
	 *
	 * In addition, the following queue lock guarantees that
	 * bfqq_group(bfqq) exists as well.
	 */
	spin_lock_irq(q->queue_lock);
	bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, cmd_flags);
	if (idle_timer_disabled)
		bfqg_stats_update_idle_time(bfqq_group(bfqq));
	spin_unlock_irq(q->queue_lock);
}
#else
static inline void bfq_update_insert_stats(struct request_queue *q,
					   struct bfq_queue *bfqq,
					   bool idle_timer_disabled,
					   unsigned int cmd_flags) {}
#endif

4543 4544
static void bfq_prepare_request(struct request *rq, struct bio *bio);

4545 4546 4547 4548 4549
static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
			       bool at_head)
{
	struct request_queue *q = hctx->queue;
	struct bfq_data *bfqd = q->elevator->elevator_data;
4550
	struct bfq_queue *bfqq = RQ_BFQQ(rq);
4551 4552
	bool idle_timer_disabled = false;
	unsigned int cmd_flags;
4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570

	spin_lock_irq(&bfqd->lock);
	if (blk_mq_sched_try_insert_merge(q, rq)) {
		spin_unlock_irq(&bfqd->lock);
		return;
	}

	spin_unlock_irq(&bfqd->lock);

	blk_mq_sched_request_inserted(rq);

	spin_lock_irq(&bfqd->lock);
	if (at_head || blk_rq_is_passthrough(rq)) {
		if (at_head)
			list_add(&rq->queuelist, &bfqd->dispatch);
		else
			list_add_tail(&rq->queuelist, &bfqd->dispatch);
	} else {
4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582
		if (WARN_ON_ONCE(!bfqq)) {
			/*
			 * This should never happen. Most likely rq is
			 * a requeued regular request, being
			 * re-inserted without being first
			 * re-prepared. Do a prepare, to avoid
			 * failure.
			 */
			bfq_prepare_request(rq, rq->bio);
			bfqq = RQ_BFQQ(rq);
		}

4583
		idle_timer_disabled = __bfq_insert_request(bfqd, rq);
4584 4585 4586 4587 4588 4589
		/*
		 * Update bfqq, because, if a queue merge has occurred
		 * in __bfq_insert_request, then rq has been
		 * redirected into a new queue.
		 */
		bfqq = RQ_BFQQ(rq);
4590 4591 4592 4593 4594 4595 4596 4597

		if (rq_mergeable(rq)) {
			elv_rqhash_add(q, rq);
			if (!q->last_merge)
				q->last_merge = rq;
		}
	}

4598 4599 4600 4601 4602 4603
	/*
	 * Cache cmd_flags before releasing scheduler lock, because rq
	 * may disappear afterwards (for example, because of a request
	 * merge).
	 */
	cmd_flags = rq->cmd_flags;
4604

4605
	spin_unlock_irq(&bfqd->lock);
4606

4607 4608
	bfq_update_insert_stats(q, bfqq, idle_timer_disabled,
				cmd_flags);
4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649
}

static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
				struct list_head *list, bool at_head)
{
	while (!list_empty(list)) {
		struct request *rq;

		rq = list_first_entry(list, struct request, queuelist);
		list_del_init(&rq->queuelist);
		bfq_insert_request(hctx, rq, at_head);
	}
}

static void bfq_update_hw_tag(struct bfq_data *bfqd)
{
	bfqd->max_rq_in_driver = max_t(int, bfqd->max_rq_in_driver,
				       bfqd->rq_in_driver);

	if (bfqd->hw_tag == 1)
		return;

	/*
	 * This sample is valid if the number of outstanding requests
	 * is large enough to allow a queueing behavior.  Note that the
	 * sum is not exact, as it's not taking into account deactivated
	 * requests.
	 */
	if (bfqd->rq_in_driver + bfqd->queued < BFQ_HW_QUEUE_THRESHOLD)
		return;

	if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES)
		return;

	bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD;
	bfqd->max_rq_in_driver = 0;
	bfqd->hw_tag_samples = 0;
}

static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
{
4650 4651 4652
	u64 now_ns;
	u32 delta_us;

4653 4654 4655 4656 4657
	bfq_update_hw_tag(bfqd);

	bfqd->rq_in_driver--;
	bfqq->dispatched--;

4658 4659 4660 4661 4662 4663 4664 4665
	if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
		/*
		 * Set budget_timeout (which we overload to store the
		 * time at which the queue remains with no backlog and
		 * no outstanding request; used by the weight-raising
		 * mechanism).
		 */
		bfqq->budget_timeout = jiffies;
4666 4667 4668

		bfq_weights_tree_remove(bfqd, &bfqq->entity,
					&bfqd->queue_weights_tree);
4669 4670
	}

4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701
	now_ns = ktime_get_ns();

	bfqq->ttime.last_end_request = now_ns;

	/*
	 * Using us instead of ns, to get a reasonable precision in
	 * computing rate in next check.
	 */
	delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC);

	/*
	 * If the request took rather long to complete, and, according
	 * to the maximum request size recorded, this completion latency
	 * implies that the request was certainly served at a very low
	 * rate (less than 1M sectors/sec), then the whole observation
	 * interval that lasts up to this time instant cannot be a
	 * valid time interval for computing a new peak rate.  Invoke
	 * bfq_update_rate_reset to have the following three steps
	 * taken:
	 * - close the observation interval at the last (previous)
	 *   request dispatch or completion
	 * - compute rate, if possible, for that observation interval
	 * - reset to zero samples, which will trigger a proper
	 *   re-initialization of the observation interval on next
	 *   dispatch
	 */
	if (delta_us > BFQ_MIN_TT/NSEC_PER_USEC &&
	   (bfqd->last_rq_max_size<<BFQ_RATE_SHIFT)/delta_us <
			1UL<<(BFQ_RATE_SHIFT - 10))
		bfq_update_rate_reset(bfqd, NULL);
	bfqd->last_completion = now_ns;
4702

4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716
	/*
	 * If we are waiting to discover whether the request pattern
	 * of the task associated with the queue is actually
	 * isochronous, and both requisites for this condition to hold
	 * are now satisfied, then compute soft_rt_next_start (see the
	 * comments on the function bfq_bfqq_softrt_next_start()). We
	 * schedule this delayed check when bfqq expires, if it still
	 * has in-flight requests.
	 */
	if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 &&
	    RB_EMPTY_ROOT(&bfqq->sort_list))
		bfqq->soft_rt_next_start =
			bfq_bfqq_softrt_next_start(bfqd, bfqq);

4717 4718 4719 4720 4721
	/*
	 * If this is the in-service queue, check if it needs to be expired,
	 * or if we want to idle in case it has no pending requests.
	 */
	if (bfqd->in_service_queue == bfqq) {
4722
		if (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) {
4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733
			bfq_arm_slice_timer(bfqd);
			return;
		} else if (bfq_may_expire_for_budg_timeout(bfqq))
			bfq_bfqq_expire(bfqd, bfqq, false,
					BFQQE_BUDGET_TIMEOUT);
		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
			 (bfqq->dispatched == 0 ||
			  !bfq_bfqq_may_idle(bfqq)))
			bfq_bfqq_expire(bfqd, bfqq, false,
					BFQQE_NO_MORE_REQUESTS);
	}
4734 4735 4736

	if (!bfqd->rq_in_driver)
		bfq_schedule_dispatch(bfqd);
4737 4738
}

4739
static void bfq_finish_requeue_request_body(struct bfq_queue *bfqq)
4740 4741 4742 4743 4744 4745
{
	bfqq->allocated--;

	bfq_put_queue(bfqq);
}

4746 4747 4748 4749 4750 4751 4752
/*
 * Handle either a requeue or a finish for rq. The things to do are
 * the same in both cases: all references to rq are to be dropped. In
 * particular, rq is considered completed from the point of view of
 * the scheduler.
 */
static void bfq_finish_requeue_request(struct request *rq)
4753
{
4754
	struct bfq_queue *bfqq = RQ_BFQQ(rq);
4755 4756
	struct bfq_data *bfqd;

4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774
	/*
	 * Requeue and finish hooks are invoked in blk-mq without
	 * checking whether the involved request is actually still
	 * referenced in the scheduler. To handle this fact, the
	 * following two checks make this function exit in case of
	 * spurious invocations, for which there is nothing to do.
	 *
	 * First, check whether rq has nothing to do with an elevator.
	 */
	if (unlikely(!(rq->rq_flags & RQF_ELVPRIV)))
		return;

	/*
	 * rq either is not associated with any icq, or is an already
	 * requeued request that has not (yet) been re-inserted into
	 * a bfq_queue.
	 */
	if (!rq->elv.icq || !bfqq)
4775 4776 4777
		return;

	bfqd = bfqq->bfqd;
4778

4779 4780 4781 4782 4783
	if (rq->rq_flags & RQF_STARTED)
		bfqg_stats_update_completion(bfqq_group(bfqq),
					     rq_start_time_ns(rq),
					     rq_io_start_time_ns(rq),
					     rq->cmd_flags);
4784 4785 4786 4787 4788 4789 4790

	if (likely(rq->rq_flags & RQF_STARTED)) {
		unsigned long flags;

		spin_lock_irqsave(&bfqd->lock, flags);

		bfq_completed_request(bfqq, bfqd);
4791
		bfq_finish_requeue_request_body(bfqq);
4792

4793
		spin_unlock_irqrestore(&bfqd->lock, flags);
4794 4795 4796
	} else {
		/*
		 * Request rq may be still/already in the scheduler,
4797 4798
		 * in which case we need to remove it (this should
		 * never happen in case of requeue). And we cannot
4799 4800 4801 4802 4803 4804 4805 4806 4807
		 * defer such a check and removal, to avoid
		 * inconsistencies in the time interval from the end
		 * of this function to the start of the deferred work.
		 * This situation seems to occur only in process
		 * context, as a consequence of a merge. In the
		 * current version of the code, this implies that the
		 * lock is held.
		 */

4808
		if (!RB_EMPTY_NODE(&rq->rb_node)) {
4809
			bfq_remove_request(rq->q, rq);
4810 4811 4812
			bfqg_stats_update_io_remove(bfqq_group(bfqq),
						    rq->cmd_flags);
		}
4813
		bfq_finish_requeue_request_body(bfqq);
4814 4815
	}

4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832
	/*
	 * Reset private fields. In case of a requeue, this allows
	 * this function to correctly do nothing if it is spuriously
	 * invoked again on this same request (see the check at the
	 * beginning of the function). Probably, a better general
	 * design would be to prevent blk-mq from invoking the requeue
	 * or finish hooks of an elevator, for a request that is not
	 * referred by that elevator.
	 *
	 * Resetting the following fields would break the
	 * request-insertion logic if rq is re-inserted into a bfq
	 * internal queue, without a re-preparation. Here we assume
	 * that re-insertions of requeued requests, without
	 * re-preparation, can happen only for pass_through or at_head
	 * requests (which are not re-inserted into bfq internal
	 * queues).
	 */
4833 4834 4835 4836
	rq->elv.priv[0] = NULL;
	rq->elv.priv[1] = NULL;
}

4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879
/*
 * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
 * was the last process referring to that bfqq.
 */
static struct bfq_queue *
bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
{
	bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");

	if (bfqq_process_refs(bfqq) == 1) {
		bfqq->pid = current->pid;
		bfq_clear_bfqq_coop(bfqq);
		bfq_clear_bfqq_split_coop(bfqq);
		return bfqq;
	}

	bic_set_bfqq(bic, NULL, 1);

	bfq_put_cooperator(bfqq);

	bfq_put_queue(bfqq);
	return NULL;
}

static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
						   struct bfq_io_cq *bic,
						   struct bio *bio,
						   bool split, bool is_sync,
						   bool *new_queue)
{
	struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);

	if (likely(bfqq && bfqq != &bfqd->oom_bfqq))
		return bfqq;

	if (new_queue)
		*new_queue = true;

	if (bfqq)
		bfq_put_queue(bfqq);
	bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);

	bic_set_bfqq(bic, bfqq, is_sync);
4880 4881 4882 4883 4884 4885 4886
	if (split && is_sync) {
		if ((bic->was_in_burst_list && bfqd->large_burst) ||
		    bic->saved_in_large_burst)
			bfq_mark_bfqq_in_large_burst(bfqq);
		else {
			bfq_clear_bfqq_in_large_burst(bfqq);
			if (bic->was_in_burst_list)
4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914
				/*
				 * If bfqq was in the current
				 * burst list before being
				 * merged, then we have to add
				 * it back. And we do not need
				 * to increase burst_size, as
				 * we did not decrement
				 * burst_size when we removed
				 * bfqq from the burst list as
				 * a consequence of a merge
				 * (see comments in
				 * bfq_put_queue). In this
				 * respect, it would be rather
				 * costly to know whether the
				 * current burst list is still
				 * the same burst list from
				 * which bfqq was removed on
				 * the merge. To avoid this
				 * cost, if bfqq was in a
				 * burst list, then we add
				 * bfqq to the current burst
				 * list without any further
				 * check. This can cause
				 * inappropriate insertions,
				 * but rarely enough to not
				 * harm the detection of large
				 * bursts significantly.
				 */
4915 4916 4917
				hlist_add_head(&bfqq->burst_list_node,
					       &bfqd->burst_list);
		}
4918
		bfqq->split_time = jiffies;
4919
	}
4920 4921 4922 4923

	return bfqq;
}

4924 4925 4926
/*
 * Allocate bfq data structures associated with this request.
 */
4927
static void bfq_prepare_request(struct request *rq, struct bio *bio)
4928
{
4929
	struct request_queue *q = rq->q;
4930
	struct bfq_data *bfqd = q->elevator->elevator_data;
4931
	struct bfq_io_cq *bic;
4932 4933
	const int is_sync = rq_is_sync(rq);
	struct bfq_queue *bfqq;
4934
	bool new_queue = false;
4935
	bool bfqq_already_existing = false, split = false;
4936

4937 4938 4939 4940 4941 4942 4943
	/*
	 * Even if we don't have an icq attached, we should still clear
	 * the scheduler pointers, as they might point to previously
	 * allocated bic/bfqq structs.
	 */
	if (!rq->elv.icq) {
		rq->elv.priv[0] = rq->elv.priv[1] = NULL;
4944
		return;
4945 4946
	}

4947
	bic = icq_to_bic(rq->elv.icq);
4948

4949
	spin_lock_irq(&bfqd->lock);
4950

4951 4952
	bfq_check_ioprio_change(bic, bio);

4953 4954
	bfq_bic_update_cgroup(bic, bio);

4955 4956 4957 4958 4959 4960 4961
	bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
					 &new_queue);

	if (likely(!new_queue)) {
		/* If the queue was seeky for too long, break it apart. */
		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
4962 4963 4964 4965 4966

			/* Update bic before losing reference to bfqq */
			if (bfq_bfqq_in_large_burst(bfqq))
				bic->saved_in_large_burst = true;

4967
			bfqq = bfq_split_bfqq(bic, bfqq);
4968
			split = true;
4969 4970 4971 4972 4973

			if (!bfqq)
				bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
								 true, is_sync,
								 NULL);
4974 4975
			else
				bfqq_already_existing = true;
4976
		}
4977 4978 4979 4980 4981 4982 4983 4984 4985 4986
	}

	bfqq->allocated++;
	bfqq->ref++;
	bfq_log_bfqq(bfqd, bfqq, "get_request %p: bfqq %p, %d",
		     rq, bfqq, bfqq->ref);

	rq->elv.priv[0] = bic;
	rq->elv.priv[1] = bfqq;

4987 4988 4989 4990 4991 4992 4993 4994
	/*
	 * If a bfq_queue has only one process reference, it is owned
	 * by only this bic: we can then set bfqq->bic = bic. in
	 * addition, if the queue has also just been split, we have to
	 * resume its state.
	 */
	if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
		bfqq->bic = bic;
4995
		if (split) {
4996 4997 4998 4999 5000
			/*
			 * The queue has just been split from a shared
			 * queue: restore the idle window and the
			 * possible weight raising period.
			 */
5001 5002
			bfq_bfqq_resume_state(bfqq, bfqd, bic,
					      bfqq_already_existing);
5003 5004 5005
		}
	}

5006 5007 5008
	if (unlikely(bfq_bfqq_just_created(bfqq)))
		bfq_handle_burst(bfqd, bfqq);

5009
	spin_unlock_irq(&bfqd->lock);
5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046
}

static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
{
	struct bfq_data *bfqd = bfqq->bfqd;
	enum bfqq_expiration reason;
	unsigned long flags;

	spin_lock_irqsave(&bfqd->lock, flags);
	bfq_clear_bfqq_wait_request(bfqq);

	if (bfqq != bfqd->in_service_queue) {
		spin_unlock_irqrestore(&bfqd->lock, flags);
		return;
	}

	if (bfq_bfqq_budget_timeout(bfqq))
		/*
		 * Also here the queue can be safely expired
		 * for budget timeout without wasting
		 * guarantees
		 */
		reason = BFQQE_BUDGET_TIMEOUT;
	else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0)
		/*
		 * The queue may not be empty upon timer expiration,
		 * because we may not disable the timer when the
		 * first request of the in-service queue arrives
		 * during disk idling.
		 */
		reason = BFQQE_TOO_IDLE;
	else
		goto schedule_dispatch;

	bfq_bfqq_expire(bfqd, bfqq, true, reason);

schedule_dispatch:
5047
	spin_unlock_irqrestore(&bfqd->lock, flags);
5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081
	bfq_schedule_dispatch(bfqd);
}

/*
 * Handler of the expiration of the timer running if the in-service queue
 * is idling inside its time slice.
 */
static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
{
	struct bfq_data *bfqd = container_of(timer, struct bfq_data,
					     idle_slice_timer);
	struct bfq_queue *bfqq = bfqd->in_service_queue;

	/*
	 * Theoretical race here: the in-service queue can be NULL or
	 * different from the queue that was idling if a new request
	 * arrives for the current queue and there is a full dispatch
	 * cycle that changes the in-service queue.  This can hardly
	 * happen, but in the worst case we just expire a queue too
	 * early.
	 */
	if (bfqq)
		bfq_idle_slice_timer_body(bfqq);

	return HRTIMER_NORESTART;
}

static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
				 struct bfq_queue **bfqq_ptr)
{
	struct bfq_queue *bfqq = *bfqq_ptr;

	bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
	if (bfqq) {
5082 5083
		bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);

5084 5085 5086 5087 5088 5089 5090 5091
		bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
			     bfqq, bfqq->ref);
		bfq_put_queue(bfqq);
		*bfqq_ptr = NULL;
	}
}

/*
5092 5093 5094 5095
 * Release all the bfqg references to its async queues.  If we are
 * deallocating the group these queues may still contain requests, so
 * we reparent them to the root cgroup (i.e., the only one that will
 * exist for sure until all the requests on a device are gone).
5096
 */
5097
void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
5098 5099 5100 5101 5102
{
	int i, j;

	for (i = 0; i < 2; i++)
		for (j = 0; j < IOPRIO_BE_NR; j++)
5103
			__bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]);
5104

5105
	__bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116
}

static void bfq_exit_queue(struct elevator_queue *e)
{
	struct bfq_data *bfqd = e->elevator_data;
	struct bfq_queue *bfqq, *n;

	hrtimer_cancel(&bfqd->idle_slice_timer);

	spin_lock_irq(&bfqd->lock);
	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
5117
		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
5118 5119 5120 5121
	spin_unlock_irq(&bfqd->lock);

	hrtimer_cancel(&bfqd->idle_slice_timer);

5122
#ifdef CONFIG_BFQ_GROUP_IOSCHED
5123 5124 5125
	/* release oom-queue reference to root group */
	bfqg_and_blkg_put(bfqd->root_group);

5126 5127 5128 5129 5130 5131 5132 5133
	blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq);
#else
	spin_lock_irq(&bfqd->lock);
	bfq_put_async_queues(bfqd, bfqd->root_group);
	kfree(bfqd->root_group);
	spin_unlock_irq(&bfqd->lock);
#endif

5134 5135 5136
	kfree(bfqd);
}

5137 5138 5139 5140 5141 5142 5143 5144 5145 5146
static void bfq_init_root_group(struct bfq_group *root_group,
				struct bfq_data *bfqd)
{
	int i;

#ifdef CONFIG_BFQ_GROUP_IOSCHED
	root_group->entity.parent = NULL;
	root_group->my_entity = NULL;
	root_group->bfqd = bfqd;
#endif
5147
	root_group->rq_pos_tree = RB_ROOT;
5148 5149 5150 5151 5152
	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
		root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
	root_group->sched_data.bfq_class_idle_last_service = jiffies;
}

5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168
static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
{
	struct bfq_data *bfqd;
	struct elevator_queue *eq;

	eq = elevator_alloc(q, e);
	if (!eq)
		return -ENOMEM;

	bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
	if (!bfqd) {
		kobject_put(&eq->kobj);
		return -ENOMEM;
	}
	eq->elevator_data = bfqd;

5169 5170 5171 5172
	spin_lock_irq(q->queue_lock);
	q->elevator = eq;
	spin_unlock_irq(q->queue_lock);

5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183
	/*
	 * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
	 * Grab a permanent reference to it, so that the normal code flow
	 * will not attempt to free it.
	 */
	bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0);
	bfqd->oom_bfqq.ref++;
	bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO;
	bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE;
	bfqd->oom_bfqq.entity.new_weight =
		bfq_ioprio_to_weight(bfqd->oom_bfqq.new_ioprio);
5184 5185 5186 5187

	/* oom_bfqq does not participate to bursts */
	bfq_clear_bfqq_just_created(&bfqd->oom_bfqq);

5188 5189 5190 5191 5192 5193 5194 5195 5196
	/*
	 * Trigger weight initialization, according to ioprio, at the
	 * oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio
	 * class won't be changed any more.
	 */
	bfqd->oom_bfqq.entity.prio_changed = 1;

	bfqd->queue = q;

5197
	INIT_LIST_HEAD(&bfqd->dispatch);
5198 5199 5200 5201 5202

	hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
		     HRTIMER_MODE_REL);
	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;

5203 5204 5205
	bfqd->queue_weights_tree = RB_ROOT;
	bfqd->group_weights_tree = RB_ROOT;

5206 5207
	INIT_LIST_HEAD(&bfqd->active_list);
	INIT_LIST_HEAD(&bfqd->idle_list);
5208
	INIT_HLIST_HEAD(&bfqd->burst_list);
5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222

	bfqd->hw_tag = -1;

	bfqd->bfq_max_budget = bfq_default_max_budget;

	bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0];
	bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1];
	bfqd->bfq_back_max = bfq_back_max;
	bfqd->bfq_back_penalty = bfq_back_penalty;
	bfqd->bfq_slice_idle = bfq_slice_idle;
	bfqd->bfq_timeout = bfq_timeout;

	bfqd->bfq_requests_within_timer = 120;

5223 5224 5225
	bfqd->bfq_large_burst_thresh = 8;
	bfqd->bfq_burst_interval = msecs_to_jiffies(180);

5226 5227 5228 5229 5230 5231
	bfqd->low_latency = true;

	/*
	 * Trade-off between responsiveness and fairness.
	 */
	bfqd->bfq_wr_coeff = 30;
5232
	bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300);
5233 5234 5235
	bfqd->bfq_wr_max_time = 0;
	bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000);
	bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500);
5236 5237 5238 5239 5240 5241
	bfqd->bfq_wr_max_softrt_rate = 7000; /*
					      * Approximate rate required
					      * to playback or record a
					      * high-definition compressed
					      * video.
					      */
5242
	bfqd->wr_busy_queues = 0;
5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253

	/*
	 * Begin by assuming, optimistically, that the device is a
	 * high-speed one, and that its peak rate is equal to 2/3 of
	 * the highest reference rate.
	 */
	bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] *
			T_fast[blk_queue_nonrot(bfqd->queue)];
	bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
	bfqd->device_speed = BFQ_BFQD_FAST;

5254 5255
	spin_lock_init(&bfqd->lock);

5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276
	/*
	 * The invocation of the next bfq_create_group_hierarchy
	 * function is the head of a chain of function calls
	 * (bfq_create_group_hierarchy->blkcg_activate_policy->
	 * blk_mq_freeze_queue) that may lead to the invocation of the
	 * has_work hook function. For this reason,
	 * bfq_create_group_hierarchy is invoked only after all
	 * scheduler data has been initialized, apart from the fields
	 * that can be initialized only after invoking
	 * bfq_create_group_hierarchy. This, in particular, enables
	 * has_work to correctly return false. Of course, to avoid
	 * other inconsistencies, the blk-mq stack must then refrain
	 * from invoking further scheduler hooks before this init
	 * function is finished.
	 */
	bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node);
	if (!bfqd->root_group)
		goto out_free;
	bfq_init_root_group(bfqd->root_group, bfqd);
	bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);

5277
	wbt_disable_default(q);
5278
	return 0;
5279 5280 5281 5282 5283

out_free:
	kfree(bfqd);
	kobject_put(&eq->kobj);
	return -ENOMEM;
5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303
}

static void bfq_slab_kill(void)
{
	kmem_cache_destroy(bfq_pool);
}

static int __init bfq_slab_setup(void)
{
	bfq_pool = KMEM_CACHE(bfq_queue, 0);
	if (!bfq_pool)
		return -ENOMEM;
	return 0;
}

static ssize_t bfq_var_show(unsigned int var, char *page)
{
	return sprintf(page, "%u\n", var);
}

5304
static int bfq_var_store(unsigned long *var, const char *page)
5305 5306 5307 5308
{
	unsigned long new_val;
	int ret = kstrtoul(page, 10, &new_val);

5309 5310 5311 5312
	if (ret)
		return ret;
	*var = new_val;
	return 0;
5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333
}

#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
{									\
	struct bfq_data *bfqd = e->elevator_data;			\
	u64 __data = __VAR;						\
	if (__CONV == 1)						\
		__data = jiffies_to_msecs(__data);			\
	else if (__CONV == 2)						\
		__data = div_u64(__data, NSEC_PER_MSEC);		\
	return bfq_var_show(__data, (page));				\
}
SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2);
SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2);
SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0);
SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0);
SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 2);
SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1);
SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0);
5334
SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352
#undef SHOW_FUNCTION

#define USEC_SHOW_FUNCTION(__FUNC, __VAR)				\
static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
{									\
	struct bfq_data *bfqd = e->elevator_data;			\
	u64 __data = __VAR;						\
	__data = div_u64(__data, NSEC_PER_USEC);			\
	return bfq_var_show(__data, (page));				\
}
USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle);
#undef USEC_SHOW_FUNCTION

#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
static ssize_t								\
__FUNC(struct elevator_queue *e, const char *page, size_t count)	\
{									\
	struct bfq_data *bfqd = e->elevator_data;			\
5353
	unsigned long __data, __min = (MIN), __max = (MAX);		\
5354 5355 5356 5357 5358
	int ret;							\
									\
	ret = bfq_var_store(&__data, (page));				\
	if (ret)							\
		return ret;						\
5359 5360 5361 5362
	if (__data < __min)						\
		__data = __min;						\
	else if (__data > __max)					\
		__data = __max;						\
5363 5364 5365 5366 5367 5368
	if (__CONV == 1)						\
		*(__PTR) = msecs_to_jiffies(__data);			\
	else if (__CONV == 2)						\
		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
	else								\
		*(__PTR) = __data;					\
5369
	return count;							\
5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384
}
STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
		INT_MAX, 2);
STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
		INT_MAX, 2);
STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0);
STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1,
		INT_MAX, 0);
STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2);
#undef STORE_FUNCTION

#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)			\
static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\
{									\
	struct bfq_data *bfqd = e->elevator_data;			\
5385
	unsigned long __data, __min = (MIN), __max = (MAX);		\
5386 5387 5388 5389 5390
	int ret;							\
									\
	ret = bfq_var_store(&__data, (page));				\
	if (ret)							\
		return ret;						\
5391 5392 5393 5394
	if (__data < __min)						\
		__data = __min;						\
	else if (__data > __max)					\
		__data = __max;						\
5395
	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
5396
	return count;							\
5397 5398 5399 5400 5401 5402 5403 5404 5405
}
USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0,
		    UINT_MAX);
#undef USEC_STORE_FUNCTION

static ssize_t bfq_max_budget_store(struct elevator_queue *e,
				    const char *page, size_t count)
{
	struct bfq_data *bfqd = e->elevator_data;
5406 5407
	unsigned long __data;
	int ret;
5408

5409 5410 5411
	ret = bfq_var_store(&__data, (page));
	if (ret)
		return ret;
5412 5413

	if (__data == 0)
5414
		bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
5415 5416 5417 5418 5419 5420 5421 5422
	else {
		if (__data > INT_MAX)
			__data = INT_MAX;
		bfqd->bfq_max_budget = __data;
	}

	bfqd->bfq_user_max_budget = __data;

5423
	return count;
5424 5425 5426 5427 5428 5429 5430 5431 5432 5433
}

/*
 * Leaving this name to preserve name compatibility with cfq
 * parameters, but this timeout is used for both sync and async.
 */
static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
				      const char *page, size_t count)
{
	struct bfq_data *bfqd = e->elevator_data;
5434 5435
	unsigned long __data;
	int ret;
5436

5437 5438 5439
	ret = bfq_var_store(&__data, (page));
	if (ret)
		return ret;
5440 5441 5442 5443 5444 5445 5446 5447

	if (__data < 1)
		__data = 1;
	else if (__data > INT_MAX)
		__data = INT_MAX;

	bfqd->bfq_timeout = msecs_to_jiffies(__data);
	if (bfqd->bfq_user_max_budget == 0)
5448
		bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
5449

5450
	return count;
5451 5452 5453 5454 5455 5456
}

static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e,
				     const char *page, size_t count)
{
	struct bfq_data *bfqd = e->elevator_data;
5457 5458
	unsigned long __data;
	int ret;
5459

5460 5461 5462
	ret = bfq_var_store(&__data, (page));
	if (ret)
		return ret;
5463 5464 5465 5466 5467 5468 5469 5470 5471

	if (__data > 1)
		__data = 1;
	if (!bfqd->strict_guarantees && __data == 1
	    && bfqd->bfq_slice_idle < 8 * NSEC_PER_MSEC)
		bfqd->bfq_slice_idle = 8 * NSEC_PER_MSEC;

	bfqd->strict_guarantees = __data;

5472
	return count;
5473 5474
}

5475 5476 5477 5478
static ssize_t bfq_low_latency_store(struct elevator_queue *e,
				     const char *page, size_t count)
{
	struct bfq_data *bfqd = e->elevator_data;
5479 5480
	unsigned long __data;
	int ret;
5481

5482 5483 5484
	ret = bfq_var_store(&__data, (page));
	if (ret)
		return ret;
5485 5486 5487 5488 5489 5490 5491

	if (__data > 1)
		__data = 1;
	if (__data == 0 && bfqd->low_latency != 0)
		bfq_end_wr(bfqd);
	bfqd->low_latency = __data;

5492
	return count;
5493 5494
}

5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507
#define BFQ_ATTR(name) \
	__ATTR(name, 0644, bfq_##name##_show, bfq_##name##_store)

static struct elv_fs_entry bfq_attrs[] = {
	BFQ_ATTR(fifo_expire_sync),
	BFQ_ATTR(fifo_expire_async),
	BFQ_ATTR(back_seek_max),
	BFQ_ATTR(back_seek_penalty),
	BFQ_ATTR(slice_idle),
	BFQ_ATTR(slice_idle_us),
	BFQ_ATTR(max_budget),
	BFQ_ATTR(timeout_sync),
	BFQ_ATTR(strict_guarantees),
5508
	BFQ_ATTR(low_latency),
5509 5510 5511 5512 5513
	__ATTR_NULL
};

static struct elevator_type iosched_bfq_mq = {
	.ops.mq = {
5514
		.limit_depth		= bfq_limit_depth,
5515
		.prepare_request	= bfq_prepare_request,
5516 5517
		.requeue_request        = bfq_finish_requeue_request,
		.finish_request		= bfq_finish_requeue_request,
5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539
		.exit_icq		= bfq_exit_icq,
		.insert_requests	= bfq_insert_requests,
		.dispatch_request	= bfq_dispatch_request,
		.next_request		= elv_rb_latter_request,
		.former_request		= elv_rb_former_request,
		.allow_merge		= bfq_allow_bio_merge,
		.bio_merge		= bfq_bio_merge,
		.request_merge		= bfq_request_merge,
		.requests_merged	= bfq_requests_merged,
		.request_merged		= bfq_request_merged,
		.has_work		= bfq_has_work,
		.init_sched		= bfq_init_queue,
		.exit_sched		= bfq_exit_queue,
	},

	.uses_mq =		true,
	.icq_size =		sizeof(struct bfq_io_cq),
	.icq_align =		__alignof__(struct bfq_io_cq),
	.elevator_attrs =	bfq_attrs,
	.elevator_name =	"bfq",
	.elevator_owner =	THIS_MODULE,
};
5540
MODULE_ALIAS("bfq-iosched");
5541 5542 5543 5544 5545

static int __init bfq_init(void)
{
	int ret;

5546 5547 5548 5549 5550 5551
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	ret = blkcg_policy_register(&blkcg_policy_bfq);
	if (ret)
		return ret;
#endif

5552 5553 5554 5555
	ret = -ENOMEM;
	if (bfq_slab_setup())
		goto err_pol_unreg;

5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588
	/*
	 * Times to load large popular applications for the typical
	 * systems installed on the reference devices (see the
	 * comments before the definitions of the next two
	 * arrays). Actually, we use slightly slower values, as the
	 * estimated peak rate tends to be smaller than the actual
	 * peak rate.  The reason for this last fact is that estimates
	 * are computed over much shorter time intervals than the long
	 * intervals typically used for benchmarking. Why? First, to
	 * adapt more quickly to variations. Second, because an I/O
	 * scheduler cannot rely on a peak-rate-evaluation workload to
	 * be run for a long time.
	 */
	T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */
	T_slow[1] = msecs_to_jiffies(6000); /* actually 6.5 sec */
	T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */
	T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */

	/*
	 * Thresholds that determine the switch between speed classes
	 * (see the comments before the definition of the array
	 * device_speed_thresh). These thresholds are biased towards
	 * transitions to the fast class. This is safer than the
	 * opposite bias. In fact, a wrong transition to the slow
	 * class results in short weight-raising periods, because the
	 * speed of the device then tends to be higher that the
	 * reference peak rate. On the opposite end, a wrong
	 * transition to the fast class tends to increase
	 * weight-raising periods, because of the opposite reason.
	 */
	device_speed_thresh[0] = (4 * R_slow[0]) / 3;
	device_speed_thresh[1] = (4 * R_slow[1]) / 3;

5589 5590
	ret = elv_register(&iosched_bfq_mq);
	if (ret)
5591
		goto slab_kill;
5592 5593 5594

	return 0;

5595 5596
slab_kill:
	bfq_slab_kill();
5597
err_pol_unreg:
5598 5599 5600
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	blkcg_policy_unregister(&blkcg_policy_bfq);
#endif
5601 5602 5603 5604 5605 5606
	return ret;
}

static void __exit bfq_exit(void)
{
	elv_unregister(&iosched_bfq_mq);
5607 5608 5609
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	blkcg_policy_unregister(&blkcg_policy_bfq);
#endif
5610 5611 5612 5613 5614 5615 5616 5617 5618
	bfq_slab_kill();
}

module_init(bfq_init);
module_exit(bfq_exit);

MODULE_AUTHOR("Paolo Valente");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MQ Budget Fair Queueing I/O Scheduler");