1 // SPDX-License-Identifier: GPL-2.0-or-later
2 /*
3 * Budget Fair Queueing (BFQ) I/O scheduler.
4 *
5 * Based on ideas and code from CFQ:
6 * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
7 *
8 * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
9 * Paolo Valente <paolo.valente@unimore.it>
10 *
11 * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
12 * Arianna Avanzini <avanzini@google.com>
13 *
14 * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
15 *
16 * BFQ is a proportional-share I/O scheduler, with some extra
17 * low-latency capabilities. BFQ also supports full hierarchical
18 * scheduling through cgroups. Next paragraphs provide an introduction
19 * on BFQ inner workings. Details on BFQ benefits, usage and
20 * limitations can be found in Documentation/block/bfq-iosched.rst.
21 *
22 * BFQ is a proportional-share storage-I/O scheduling algorithm based
23 * on the slice-by-slice service scheme of CFQ. But BFQ assigns
24 * budgets, measured in number of sectors, to processes instead of
25 * time slices. The device is not granted to the in-service process
26 * for a given time slice, but until it has exhausted its assigned
27 * budget. This change from the time to the service domain enables BFQ
28 * to distribute the device throughput among processes as desired,
29 * without any distortion due to throughput fluctuations, or to device
30 * internal queueing. BFQ uses an ad hoc internal scheduler, called
31 * B-WF2Q+, to schedule processes according to their budgets. More
32 * precisely, BFQ schedules queues associated with processes. Each
33 * process/queue is assigned a user-configurable weight, and B-WF2Q+
34 * guarantees that each queue receives a fraction of the throughput
35 * proportional to its weight. Thanks to the accurate policy of
36 * B-WF2Q+, BFQ can afford to assign high budgets to I/O-bound
37 * processes issuing sequential requests (to boost the throughput),
38 * and yet guarantee a low latency to interactive and soft real-time
39 * applications.
40 *
41 * In particular, to provide these low-latency guarantees, BFQ
42 * explicitly privileges the I/O of two classes of time-sensitive
43 * applications: interactive and soft real-time. In more detail, BFQ
44 * behaves this way if the low_latency parameter is set (default
45 * configuration). This feature enables BFQ to provide applications in
46 * these classes with a very low latency.
47 *
48 * To implement this feature, BFQ constantly tries to detect whether
49 * the I/O requests in a bfq_queue come from an interactive or a soft
50 * real-time application. For brevity, in these cases, the queue is
51 * said to be interactive or soft real-time. In both cases, BFQ
52 * privileges the service of the queue, over that of non-interactive
53 * and non-soft-real-time queues. This privileging is performed,
54 * mainly, by raising the weight of the queue. So, for brevity, we
55 * call just weight-raising periods the time periods during which a
56 * queue is privileged, because deemed interactive or soft real-time.
57 *
58 * The detection of soft real-time queues/applications is described in
59 * detail in the comments on the function
60 * bfq_bfqq_softrt_next_start. On the other hand, the detection of an
61 * interactive queue works as follows: a queue is deemed interactive
62 * if it is constantly non empty only for a limited time interval,
63 * after which it does become empty. The queue may be deemed
64 * interactive again (for a limited time), if it restarts being
65 * constantly non empty, provided that this happens only after the
66 * queue has remained empty for a given minimum idle time.
67 *
68 * By default, BFQ computes automatically the above maximum time
69 * interval, i.e., the time interval after which a constantly
70 * non-empty queue stops being deemed interactive. Since a queue is
71 * weight-raised while it is deemed interactive, this maximum time
72 * interval happens to coincide with the (maximum) duration of the
73 * weight-raising for interactive queues.
74 *
75 * Finally, BFQ also features additional heuristics for
76 * preserving both a low latency and a high throughput on NCQ-capable,
77 * rotational or flash-based devices, and to get the job done quickly
78 * for applications consisting in many I/O-bound processes.
79 *
80 * NOTE: if the main or only goal, with a given device, is to achieve
81 * the maximum-possible throughput at all times, then do switch off
82 * all low-latency heuristics for that device, by setting low_latency
83 * to 0.
84 *
85 * BFQ is described in [1], where also a reference to the initial,
86 * more theoretical paper on BFQ can be found. The interested reader
87 * can find in the latter paper full details on the main algorithm, as
88 * well as formulas of the guarantees and formal proofs of all the
89 * properties. With respect to the version of BFQ presented in these
90 * papers, this implementation adds a few more heuristics, such as the
91 * ones that guarantee a low latency to interactive and soft real-time
92 * applications, and a hierarchical extension based on H-WF2Q+.
93 *
94 * B-WF2Q+ is based on WF2Q+, which is described in [2], together with
95 * H-WF2Q+, while the augmented tree used here to implement B-WF2Q+
96 * with O(log N) complexity derives from the one introduced with EEVDF
97 * in [3].
98 *
99 * [1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
100 * Scheduler", Proceedings of the First Workshop on Mobile System
101 * Technologies (MST-2015), May 2015.
102 * http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
103 *
104 * [2] Jon C.R. Bennett and H. Zhang, "Hierarchical Packet Fair Queueing
105 * Algorithms", IEEE/ACM Transactions on Networking, 5(5):675-689,
106 * Oct 1997.
107 *
108 * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz
109 *
110 * [3] I. Stoica and H. Abdel-Wahab, "Earliest Eligible Virtual Deadline
111 * First: A Flexible and Accurate Mechanism for Proportional Share
112 * Resource Allocation", technical report.
113 *
114 * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf
115 */
116 #include <linux/module.h>
117 #include <linux/slab.h>
118 #include <linux/blkdev.h>
119 #include <linux/cgroup.h>
120 #include <linux/elevator.h>
121 #include <linux/ktime.h>
122 #include <linux/rbtree.h>
123 #include <linux/ioprio.h>
124 #include <linux/sbitmap.h>
125 #include <linux/delay.h>
126
127 #include "blk.h"
128 #include "blk-mq.h"
129 #include "blk-mq-tag.h"
130 #include "blk-mq-sched.h"
131 #include "bfq-iosched.h"
132 #include "blk-wbt.h"
133
134 #define BFQ_BFQQ_FNS(name) \
135 void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \
136 { \
137 __set_bit(BFQQF_##name, &(bfqq)->flags); \
138 } \
139 void bfq_clear_bfqq_##name(struct bfq_queue *bfqq) \
140 { \
141 __clear_bit(BFQQF_##name, &(bfqq)->flags); \
142 } \
143 int bfq_bfqq_##name(const struct bfq_queue *bfqq) \
144 { \
145 return test_bit(BFQQF_##name, &(bfqq)->flags); \
146 }
147
148 BFQ_BFQQ_FNS(just_created);
149 BFQ_BFQQ_FNS(busy);
150 BFQ_BFQQ_FNS(wait_request);
151 BFQ_BFQQ_FNS(non_blocking_wait_rq);
152 BFQ_BFQQ_FNS(fifo_expire);
153 BFQ_BFQQ_FNS(has_short_ttime);
154 BFQ_BFQQ_FNS(sync);
155 BFQ_BFQQ_FNS(IO_bound);
156 BFQ_BFQQ_FNS(in_large_burst);
157 BFQ_BFQQ_FNS(coop);
158 BFQ_BFQQ_FNS(split_coop);
159 BFQ_BFQQ_FNS(softrt_update);
160 BFQ_BFQQ_FNS(has_waker);
161 #undef BFQ_BFQQ_FNS \
162
163 /* Expiration time of sync (0) and async (1) requests, in ns. */
164 static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
165
166 /* Maximum backwards seek (magic number lifted from CFQ), in KiB. */
167 static const int bfq_back_max = 16 * 1024;
168
169 /* Penalty of a backwards seek, in number of sectors. */
170 static const int bfq_back_penalty = 2;
171
172 /* Idling period duration, in ns. */
173 static u64 bfq_slice_idle = NSEC_PER_SEC / 125;
174
175 /* Minimum number of assigned budgets for which stats are safe to compute. */
176 static const int bfq_stats_min_budgets = 194;
177
178 /* Default maximum budget values, in sectors and number of requests. */
179 static const int bfq_default_max_budget = 16 * 1024;
180
181 /*
182 * When a sync request is dispatched, the queue that contains that
183 * request, and all the ancestor entities of that queue, are charged
184 * with the number of sectors of the request. In contrast, if the
185 * request is async, then the queue and its ancestor entities are
186 * charged with the number of sectors of the request, multiplied by
187 * the factor below. This throttles the bandwidth for async I/O,
188 * w.r.t. to sync I/O, and it is done to counter the tendency of async
189 * writes to steal I/O throughput to reads.
190 *
191 * The current value of this parameter is the result of a tuning with
192 * several hardware and software configurations. We tried to find the
193 * lowest value for which writes do not cause noticeable problems to
194 * reads. In fact, the lower this parameter, the stabler I/O control,
195 * in the following respect. The lower this parameter is, the less
196 * the bandwidth enjoyed by a group decreases
197 * - when the group does writes, w.r.t. to when it does reads;
198 * - when other groups do reads, w.r.t. to when they do writes.
199 */
200 static const int bfq_async_charge_factor = 3;
201
202 /* Default timeout values, in jiffies, approximating CFQ defaults. */
203 const int bfq_timeout = HZ / 8;
204
205 /*
206 * Time limit for merging (see comments in bfq_setup_cooperator). Set
207 * to the slowest value that, in our tests, proved to be effective in
208 * removing false positives, while not causing true positives to miss
209 * queue merging.
210 *
211 * As can be deduced from the low time limit below, queue merging, if
212 * successful, happens at the very beginning of the I/O of the involved
213 * cooperating processes, as a consequence of the arrival of the very
214 * first requests from each cooperator. After that, there is very
215 * little chance to find cooperators.
216 */
217 static const unsigned long bfq_merge_time_limit = HZ/10;
218
219 static struct kmem_cache *bfq_pool;
220
221 /* Below this threshold (in ns), we consider thinktime immediate. */
222 #define BFQ_MIN_TT (2 * NSEC_PER_MSEC)
223
224 /* hw_tag detection: parallel requests threshold and min samples needed. */
225 #define BFQ_HW_QUEUE_THRESHOLD 3
226 #define BFQ_HW_QUEUE_SAMPLES 32
227
228 #define BFQQ_SEEK_THR (sector_t)(8 * 100)
229 #define BFQQ_SECT_THR_NONROT (sector_t)(2 * 32)
230 #define BFQ_RQ_SEEKY(bfqd, last_pos, rq) \
231 (get_sdist(last_pos, rq) > \
232 BFQQ_SEEK_THR && \
233 (!blk_queue_nonrot(bfqd->queue) || \
234 blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT))
235 #define BFQQ_CLOSE_THR (sector_t)(8 * 1024)
236 #define BFQQ_SEEKY(bfqq) (hweight32(bfqq->seek_history) > 19)
237 /*
238 * Sync random I/O is likely to be confused with soft real-time I/O,
239 * because it is characterized by limited throughput and apparently
240 * isochronous arrival pattern. To avoid false positives, queues
241 * containing only random (seeky) I/O are prevented from being tagged
242 * as soft real-time.
243 */
244 #define BFQQ_TOTALLY_SEEKY(bfqq) (bfqq->seek_history == -1)
245
246 /* Min number of samples required to perform peak-rate update */
247 #define BFQ_RATE_MIN_SAMPLES 32
248 /* Min observation time interval required to perform a peak-rate update (ns) */
249 #define BFQ_RATE_MIN_INTERVAL (300*NSEC_PER_MSEC)
250 /* Target observation time interval for a peak-rate update (ns) */
251 #define BFQ_RATE_REF_INTERVAL NSEC_PER_SEC
252
253 /*
254 * Shift used for peak-rate fixed precision calculations.
255 * With
256 * - the current shift: 16 positions
257 * - the current type used to store rate: u32
258 * - the current unit of measure for rate: [sectors/usec], or, more precisely,
259 * [(sectors/usec) / 2^BFQ_RATE_SHIFT] to take into account the shift,
260 * the range of rates that can be stored is
261 * [1 / 2^BFQ_RATE_SHIFT, 2^(32 - BFQ_RATE_SHIFT)] sectors/usec =
262 * [1 / 2^16, 2^16] sectors/usec = [15e-6, 65536] sectors/usec =
263 * [15, 65G] sectors/sec
264 * Which, assuming a sector size of 512B, corresponds to a range of
265 * [7.5K, 33T] B/sec
266 */
267 #define BFQ_RATE_SHIFT 16
268
269 /*
270 * When configured for computing the duration of the weight-raising
271 * for interactive queues automatically (see the comments at the
272 * beginning of this file), BFQ does it using the following formula:
273 * duration = (ref_rate / r) * ref_wr_duration,
274 * where r is the peak rate of the device, and ref_rate and
275 * ref_wr_duration are two reference parameters. In particular,
276 * ref_rate is the peak rate of the reference storage device (see
277 * below), and ref_wr_duration is about the maximum time needed, with
278 * BFQ and while reading two files in parallel, to load typical large
279 * applications on the reference device (see the comments on
280 * max_service_from_wr below, for more details on how ref_wr_duration
281 * is obtained). In practice, the slower/faster the device at hand
282 * is, the more/less it takes to load applications with respect to the
283 * reference device. Accordingly, the longer/shorter BFQ grants
284 * weight raising to interactive applications.
285 *
286 * BFQ uses two different reference pairs (ref_rate, ref_wr_duration),
287 * depending on whether the device is rotational or non-rotational.
288 *
289 * In the following definitions, ref_rate[0] and ref_wr_duration[0]
290 * are the reference values for a rotational device, whereas
291 * ref_rate[1] and ref_wr_duration[1] are the reference values for a
292 * non-rotational device. The reference rates are not the actual peak
293 * rates of the devices used as a reference, but slightly lower
294 * values. The reason for using slightly lower values is that the
295 * peak-rate estimator tends to yield slightly lower values than the
296 * actual peak rate (it can yield the actual peak rate only if there
297 * is only one process doing I/O, and the process does sequential
298 * I/O).
299 *
300 * The reference peak rates are measured in sectors/usec, left-shifted
301 * by BFQ_RATE_SHIFT.
302 */
303 static int ref_rate[2] = {14000, 33000};
304 /*
305 * To improve readability, a conversion function is used to initialize
306 * the following array, which entails that the array can be
307 * initialized only in a function.
308 */
309 static int ref_wr_duration[2];
310
311 /*
312 * BFQ uses the above-detailed, time-based weight-raising mechanism to
313 * privilege interactive tasks. This mechanism is vulnerable to the
314 * following false positives: I/O-bound applications that will go on
315 * doing I/O for much longer than the duration of weight
316 * raising. These applications have basically no benefit from being
317 * weight-raised at the beginning of their I/O. On the opposite end,
318 * while being weight-raised, these applications
319 * a) unjustly steal throughput to applications that may actually need
320 * low latency;
321 * b) make BFQ uselessly perform device idling; device idling results
322 * in loss of device throughput with most flash-based storage, and may
323 * increase latencies when used purposelessly.
324 *
325 * BFQ tries to reduce these problems, by adopting the following
326 * countermeasure. To introduce this countermeasure, we need first to
327 * finish explaining how the duration of weight-raising for
328 * interactive tasks is computed.
329 *
330 * For a bfq_queue deemed as interactive, the duration of weight
331 * raising is dynamically adjusted, as a function of the estimated
332 * peak rate of the device, so as to be equal to the time needed to
333 * execute the 'largest' interactive task we benchmarked so far. By
334 * largest task, we mean the task for which each involved process has
335 * to do more I/O than for any of the other tasks we benchmarked. This
336 * reference interactive task is the start-up of LibreOffice Writer,
337 * and in this task each process/bfq_queue needs to have at most ~110K
338 * sectors transferred.
339 *
340 * This last piece of information enables BFQ to reduce the actual
341 * duration of weight-raising for at least one class of I/O-bound
342 * applications: those doing sequential or quasi-sequential I/O. An
343 * example is file copy. In fact, once started, the main I/O-bound
344 * processes of these applications usually consume the above 110K
345 * sectors in much less time than the processes of an application that
346 * is starting, because these I/O-bound processes will greedily devote
347 * almost all their CPU cycles only to their target,
348 * throughput-friendly I/O operations. This is even more true if BFQ
349 * happens to be underestimating the device peak rate, and thus
350 * overestimating the duration of weight raising. But, according to
351 * our measurements, once transferred 110K sectors, these processes
352 * have no right to be weight-raised any longer.
353 *
354 * Basing on the last consideration, BFQ ends weight-raising for a
355 * bfq_queue if the latter happens to have received an amount of
356 * service at least equal to the following constant. The constant is
357 * set to slightly more than 110K, to have a minimum safety margin.
358 *
359 * This early ending of weight-raising reduces the amount of time
360 * during which interactive false positives cause the two problems
361 * described at the beginning of these comments.
362 */
363 static const unsigned long max_service_from_wr = 120000;
364
365 #define RQ_BIC(rq) icq_to_bic((rq)->elv.priv[0])
366 #define RQ_BFQQ(rq) ((rq)->elv.priv[1])
367
368 struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
369 {
370 return bic->bfqq[is_sync];
371 }
372
373 void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync)
374 {
375 bic->bfqq[is_sync] = bfqq;
376 }
377
378 struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
379 {
380 return bic->icq.q->elevator->elevator_data;
381 }
382
383 /**
384 * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
385 * @icq: the iocontext queue.
386 */
387 static struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
388 {
389 /* bic->icq is the first member, %NULL will convert to %NULL */
390 return container_of(icq, struct bfq_io_cq, icq);
391 }
392
393 /**
394 * bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
395 * @bfqd: the lookup key.
396 * @ioc: the io_context of the process doing I/O.
397 * @q: the request queue.
398 */
399 static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
400 struct io_context *ioc,
401 struct request_queue *q)
402 {
403 if (ioc) {
404 unsigned long flags;
405 struct bfq_io_cq *icq;
406
407 spin_lock_irqsave(&q->queue_lock, flags);
408 icq = icq_to_bic(ioc_lookup_icq(ioc, q));
409 spin_unlock_irqrestore(&q->queue_lock, flags);
410
411 return icq;
412 }
413
414 return NULL;
415 }
416
417 /*
418 * Scheduler run of queue, if there are requests pending and no one in the
419 * driver that will restart queueing.
420 */
421 void bfq_schedule_dispatch(struct bfq_data *bfqd)
422 {
423 if (bfqd->queued != 0) {
424 bfq_log(bfqd, "schedule dispatch");
425 blk_mq_run_hw_queues(bfqd->queue, true);
426 }
427 }
428
429 #define bfq_class_idle(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
430 #define bfq_class_rt(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_RT)
431
432 #define bfq_sample_valid(samples) ((samples) > 80)
433
434 /*
435 * Lifted from AS - choose which of rq1 and rq2 that is best served now.
436 * We choose the request that is closer to the head right now. Distance
437 * behind the head is penalized and only allowed to a certain extent.
438 */
439 static struct request *bfq_choose_req(struct bfq_data *bfqd,
440 struct request *rq1,
441 struct request *rq2,
442 sector_t last)
443 {
444 sector_t s1, s2, d1 = 0, d2 = 0;
445 unsigned long back_max;
446 #define BFQ_RQ1_WRAP 0x01 /* request 1 wraps */
447 #define BFQ_RQ2_WRAP 0x02 /* request 2 wraps */
448 unsigned int wrap = 0; /* bit mask: requests behind the disk head? */
449
450 if (!rq1 || rq1 == rq2)
451 return rq2;
452 if (!rq2)
453 return rq1;
454
455 if (rq_is_sync(rq1) && !rq_is_sync(rq2))
456 return rq1;
457 else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
458 return rq2;
459 if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
460 return rq1;
461 else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META))
462 return rq2;
463
464 s1 = blk_rq_pos(rq1);
465 s2 = blk_rq_pos(rq2);
466
467 /*
468 * By definition, 1KiB is 2 sectors.
469 */
470 back_max = bfqd->bfq_back_max * 2;
471
472 /*
473 * Strict one way elevator _except_ in the case where we allow
474 * short backward seeks which are biased as twice the cost of a
475 * similar forward seek.
476 */
477 if (s1 >= last)
478 d1 = s1 - last;
479 else if (s1 + back_max >= last)
480 d1 = (last - s1) * bfqd->bfq_back_penalty;
481 else
482 wrap |= BFQ_RQ1_WRAP;
483
484 if (s2 >= last)
485 d2 = s2 - last;
486 else if (s2 + back_max >= last)
487 d2 = (last - s2) * bfqd->bfq_back_penalty;
488 else
489 wrap |= BFQ_RQ2_WRAP;
490
491 /* Found required data */
492
493 /*
494 * By doing switch() on the bit mask "wrap" we avoid having to
495 * check two variables for all permutations: --> faster!
496 */
497 switch (wrap) {
498 case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
499 if (d1 < d2)
500 return rq1;
501 else if (d2 < d1)
502 return rq2;
503
504 if (s1 >= s2)
505 return rq1;
506 else
507 return rq2;
508
509 case BFQ_RQ2_WRAP:
510 return rq1;
511 case BFQ_RQ1_WRAP:
512 return rq2;
513 case BFQ_RQ1_WRAP|BFQ_RQ2_WRAP: /* both rqs wrapped */
514 default:
515 /*
516 * Since both rqs are wrapped,
517 * start with the one that's further behind head
518 * (--> only *one* back seek required),
519 * since back seek takes more time than forward.
520 */
521 if (s1 <= s2)
522 return rq1;
523 else
524 return rq2;
525 }
526 }
527
528 /*
529 * Async I/O can easily starve sync I/O (both sync reads and sync
530 * writes), by consuming all tags. Similarly, storms of sync writes,
531 * such as those that sync(2) may trigger, can starve sync reads.
532 * Limit depths of async I/O and sync writes so as to counter both
533 * problems.
534 */
535 static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
536 {
537 struct bfq_data *bfqd = data->q->elevator->elevator_data;
538
539 if (op_is_sync(op) && !op_is_write(op))
540 return;
541
542 data->shallow_depth =
543 bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)];
544
545 bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u",
546 __func__, bfqd->wr_busy_queues, op_is_sync(op),
547 data->shallow_depth);
548 }
549
550 static struct bfq_queue *
551 bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
552 sector_t sector, struct rb_node **ret_parent,
553 struct rb_node ***rb_link)
554 {
555 struct rb_node **p, *parent;
556 struct bfq_queue *bfqq = NULL;
557
558 parent = NULL;
559 p = &root->rb_node;
560 while (*p) {
561 struct rb_node **n;
562
563 parent = *p;
564 bfqq = rb_entry(parent, struct bfq_queue, pos_node);
565
566 /*
567 * Sort strictly based on sector. Smallest to the left,
568 * largest to the right.
569 */
570 if (sector > blk_rq_pos(bfqq->next_rq))
571 n = &(*p)->rb_right;
572 else if (sector < blk_rq_pos(bfqq->next_rq))
573 n = &(*p)->rb_left;
574 else
575 break;
576 p = n;
577 bfqq = NULL;
578 }
579
580 *ret_parent = parent;
581 if (rb_link)
582 *rb_link = p;
583
584 bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
585 (unsigned long long)sector,
586 bfqq ? bfqq->pid : 0);
587
588 return bfqq;
589 }
590
591 static bool bfq_too_late_for_merging(struct bfq_queue *bfqq)
592 {
593 return bfqq->service_from_backlogged > 0 &&
594 time_is_before_jiffies(bfqq->first_IO_time +
595 bfq_merge_time_limit);
596 }
597
598 /*
599 * The following function is not marked as __cold because it is
600 * actually cold, but for the same performance goal described in the
601 * comments on the likely() at the beginning of
602 * bfq_setup_cooperator(). Unexpectedly, to reach an even lower
603 * execution time for the case where this function is not invoked, we
604 * had to add an unlikely() in each involved if().
605 */
606 void __cold
607 bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
608 {
609 struct rb_node **p, *parent;
610 struct bfq_queue *__bfqq;
611
612 if (bfqq->pos_root) {
613 rb_erase(&bfqq->pos_node, bfqq->pos_root);
614 bfqq->pos_root = NULL;
615 }
616
617 /* oom_bfqq does not participate in queue merging */
618 if (bfqq == &bfqd->oom_bfqq)
619 return;
620
621 /*
622 * bfqq cannot be merged any longer (see comments in
623 * bfq_setup_cooperator): no point in adding bfqq into the
624 * position tree.
625 */
626 if (bfq_too_late_for_merging(bfqq))
627 return;
628
629 if (bfq_class_idle(bfqq))
630 return;
631 if (!bfqq->next_rq)
632 return;
633
634 bfqq->pos_root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
635 __bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
636 blk_rq_pos(bfqq->next_rq), &parent, &p);
637 if (!__bfqq) {
638 rb_link_node(&bfqq->pos_node, parent, p);
639 rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
640 } else
641 bfqq->pos_root = NULL;
642 }
643
644 /*
645 * The following function returns false either if every active queue
646 * must receive the same share of the throughput (symmetric scenario),
647 * or, as a special case, if bfqq must receive a share of the
648 * throughput lower than or equal to the share that every other active
649 * queue must receive. If bfqq does sync I/O, then these are the only
650 * two cases where bfqq happens to be guaranteed its share of the
651 * throughput even if I/O dispatching is not plugged when bfqq remains
652 * temporarily empty (for more details, see the comments in the
653 * function bfq_better_to_idle()). For this reason, the return value
654 * of this function is used to check whether I/O-dispatch plugging can
655 * be avoided.
656 *
657 * The above first case (symmetric scenario) occurs when:
658 * 1) all active queues have the same weight,
659 * 2) all active queues belong to the same I/O-priority class,
660 * 3) all active groups at the same level in the groups tree have the same
661 * weight,
662 * 4) all active groups at the same level in the groups tree have the same
663 * number of children.
664 *
665 * Unfortunately, keeping the necessary state for evaluating exactly
666 * the last two symmetry sub-conditions above would be quite complex
667 * and time consuming. Therefore this function evaluates, instead,
668 * only the following stronger three sub-conditions, for which it is
669 * much easier to maintain the needed state:
670 * 1) all active queues have the same weight,
671 * 2) all active queues belong to the same I/O-priority class,
672 * 3) there are no active groups.
673 * In particular, the last condition is always true if hierarchical
674 * support or the cgroups interface are not enabled, thus no state
675 * needs to be maintained in this case.
676 */
677 static bool bfq_asymmetric_scenario(struct bfq_data *bfqd,
678 struct bfq_queue *bfqq)
679 {
680 bool smallest_weight = bfqq &&
681 bfqq->weight_counter &&
682 bfqq->weight_counter ==
683 container_of(
684 rb_first_cached(&bfqd->queue_weights_tree),
685 struct bfq_weight_counter,
686 weights_node);
687
688 /*
689 * For queue weights to differ, queue_weights_tree must contain
690 * at least two nodes.
691 */
692 bool varied_queue_weights = !smallest_weight &&
693 !RB_EMPTY_ROOT(&bfqd->queue_weights_tree.rb_root) &&
694 (bfqd->queue_weights_tree.rb_root.rb_node->rb_left ||
695 bfqd->queue_weights_tree.rb_root.rb_node->rb_right);
696
697 bool multiple_classes_busy =
698 (bfqd->busy_queues[0] && bfqd->busy_queues[1]) ||
699 (bfqd->busy_queues[0] && bfqd->busy_queues[2]) ||
700 (bfqd->busy_queues[1] && bfqd->busy_queues[2]);
701
702 return varied_queue_weights || multiple_classes_busy
703 #ifdef CONFIG_BFQ_GROUP_IOSCHED
704 || bfqd->num_groups_with_pending_reqs > 0
705 #endif
706 ;
707 }
708
709 /*
710 * If the weight-counter tree passed as input contains no counter for
711 * the weight of the input queue, then add that counter; otherwise just
712 * increment the existing counter.
713 *
714 * Note that weight-counter trees contain few nodes in mostly symmetric
715 * scenarios. For example, if all queues have the same weight, then the
716 * weight-counter tree for the queues may contain at most one node.
717 * This holds even if low_latency is on, because weight-raised queues
718 * are not inserted in the tree.
719 * In most scenarios, the rate at which nodes are created/destroyed
720 * should be low too.
721 */
722 void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq,
723 struct rb_root_cached *root)
724 {
725 struct bfq_entity *entity = &bfqq->entity;
726 struct rb_node **new = &(root->rb_root.rb_node), *parent = NULL;
727 bool leftmost = true;
728
729 /*
730 * Do not insert if the queue is already associated with a
731 * counter, which happens if:
732 * 1) a request arrival has caused the queue to become both
733 * non-weight-raised, and hence change its weight, and
734 * backlogged; in this respect, each of the two events
735 * causes an invocation of this function,
736 * 2) this is the invocation of this function caused by the
737 * second event. This second invocation is actually useless,
738 * and we handle this fact by exiting immediately. More
739 * efficient or clearer solutions might possibly be adopted.
740 */
741 if (bfqq->weight_counter)
742 return;
743
744 while (*new) {
745 struct bfq_weight_counter *__counter = container_of(*new,
746 struct bfq_weight_counter,
747 weights_node);
748 parent = *new;
749
750 if (entity->weight == __counter->weight) {
751 bfqq->weight_counter = __counter;
752 goto inc_counter;
753 }
754 if (entity->weight < __counter->weight)
755 new = &((*new)->rb_left);
756 else {
757 new = &((*new)->rb_right);
758 leftmost = false;
759 }
760 }
761
762 bfqq->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
763 GFP_ATOMIC);
764
765 /*
766 * In the unlucky event of an allocation failure, we just
767 * exit. This will cause the weight of queue to not be
768 * considered in bfq_asymmetric_scenario, which, in its turn,
769 * causes the scenario to be deemed wrongly symmetric in case
770 * bfqq's weight would have been the only weight making the
771 * scenario asymmetric. On the bright side, no unbalance will
772 * however occur when bfqq becomes inactive again (the
773 * invocation of this function is triggered by an activation
774 * of queue). In fact, bfq_weights_tree_remove does nothing
775 * if !bfqq->weight_counter.
776 */
777 if (unlikely(!bfqq->weight_counter))
778 return;
779
780 bfqq->weight_counter->weight = entity->weight;
781 rb_link_node(&bfqq->weight_counter->weights_node, parent, new);
782 rb_insert_color_cached(&bfqq->weight_counter->weights_node, root,
783 leftmost);
784
785 inc_counter:
786 bfqq->weight_counter->num_active++;
787 bfqq->ref++;
788 }
789
790 /*
791 * Decrement the weight counter associated with the queue, and, if the
792 * counter reaches 0, remove the counter from the tree.
793 * See the comments to the function bfq_weights_tree_add() for considerations
794 * about overhead.
795 */
796 void __bfq_weights_tree_remove(struct bfq_data *bfqd,
797 struct bfq_queue *bfqq,
798 struct rb_root_cached *root)
799 {
800 if (!bfqq->weight_counter)
801 return;
802
803 bfqq->weight_counter->num_active--;
804 if (bfqq->weight_counter->num_active > 0)
805 goto reset_entity_pointer;
806
807 rb_erase_cached(&bfqq->weight_counter->weights_node, root);
808 kfree(bfqq->weight_counter);
809
810 reset_entity_pointer:
811 bfqq->weight_counter = NULL;
812 bfq_put_queue(bfqq);
813 }
814
815 /*
816 * Invoke __bfq_weights_tree_remove on bfqq and decrement the number
817 * of active groups for each queue's inactive parent entity.
818 */
819 void bfq_weights_tree_remove(struct bfq_data *bfqd,
820 struct bfq_queue *bfqq)
821 {
822 struct bfq_entity *entity = bfqq->entity.parent;
823
824 for_each_entity(entity) {
825 struct bfq_sched_data *sd = entity->my_sched_data;
826
827 if (sd->next_in_service || sd->in_service_entity) {
828 /*
829 * entity is still active, because either
830 * next_in_service or in_service_entity is not
831 * NULL (see the comments on the definition of
832 * next_in_service for details on why
833 * in_service_entity must be checked too).
834 *
835 * As a consequence, its parent entities are
836 * active as well, and thus this loop must
837 * stop here.
838 */
839 break;
840 }
841
842 /*
843 * The decrement of num_groups_with_pending_reqs is
844 * not performed immediately upon the deactivation of
845 * entity, but it is delayed to when it also happens
846 * that the first leaf descendant bfqq of entity gets
847 * all its pending requests completed. The following
848 * instructions perform this delayed decrement, if
849 * needed. See the comments on
850 * num_groups_with_pending_reqs for details.
851 */
852 if (entity->in_groups_with_pending_reqs) {
853 entity->in_groups_with_pending_reqs = false;
854 bfqd->num_groups_with_pending_reqs--;
855 }
856 }
857
858 /*
859 * Next function is invoked last, because it causes bfqq to be
860 * freed if the following holds: bfqq is not in service and
861 * has no dispatched request. DO NOT use bfqq after the next
862 * function invocation.
863 */
864 __bfq_weights_tree_remove(bfqd, bfqq,
865 &bfqd->queue_weights_tree);
866 }
867
868 /*
869 * Return expired entry, or NULL to just start from scratch in rbtree.
870 */
871 static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
872 struct request *last)
873 {
874 struct request *rq;
875
876 if (bfq_bfqq_fifo_expire(bfqq))
877 return NULL;
878
879 bfq_mark_bfqq_fifo_expire(bfqq);
880
881 rq = rq_entry_fifo(bfqq->fifo.next);
882
883 if (rq == last || ktime_get_ns() < rq->fifo_time)
884 return NULL;
885
886 bfq_log_bfqq(bfqq->bfqd, bfqq, "check_fifo: returned %p", rq);
887 return rq;
888 }
889
890 static struct request *bfq_find_next_rq(struct bfq_data *bfqd,
891 struct bfq_queue *bfqq,
892 struct request *last)
893 {
894 struct rb_node *rbnext = rb_next(&last->rb_node);
895 struct rb_node *rbprev = rb_prev(&last->rb_node);
896 struct request *next, *prev = NULL;
897
898 /* Follow expired path, else get first next available. */
899 next = bfq_check_fifo(bfqq, last);
900 if (next)
901 return next;
902
903 if (rbprev)
904 prev = rb_entry_rq(rbprev);
905
906 if (rbnext)
907 next = rb_entry_rq(rbnext);
908 else {
909 rbnext = rb_first(&bfqq->sort_list);
910 if (rbnext && rbnext != &last->rb_node)
911 next = rb_entry_rq(rbnext);
912 }
913
914 return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last));
915 }
916
917 /* see the definition of bfq_async_charge_factor for details */
918 static unsigned long bfq_serv_to_charge(struct request *rq,
919 struct bfq_queue *bfqq)
920 {
921 if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1 ||
922 bfq_asymmetric_scenario(bfqq->bfqd, bfqq))
923 return blk_rq_sectors(rq);
924
925 return blk_rq_sectors(rq) * bfq_async_charge_factor;
926 }
927
928 /**
929 * bfq_updated_next_req - update the queue after a new next_rq selection.
930 * @bfqd: the device data the queue belongs to.
931 * @bfqq: the queue to update.
932 *
933 * If the first request of a queue changes we make sure that the queue
934 * has enough budget to serve at least its first request (if the
935 * request has grown). We do this because if the queue has not enough
936 * budget for its first request, it has to go through two dispatch
937 * rounds to actually get it dispatched.
938 */
939 static void bfq_updated_next_req(struct bfq_data *bfqd,
940 struct bfq_queue *bfqq)
941 {
942 struct bfq_entity *entity = &bfqq->entity;
943 struct request *next_rq = bfqq->next_rq;
944 unsigned long new_budget;
945
946 if (!next_rq)
947 return;
948
949 if (bfqq == bfqd->in_service_queue)
950 /*
951 * In order not to break guarantees, budgets cannot be
952 * changed after an entity has been selected.
953 */
954 return;
955
956 new_budget = max_t(unsigned long,
957 max_t(unsigned long, bfqq->max_budget,
958 bfq_serv_to_charge(next_rq, bfqq)),
959 entity->service);
960 if (entity->budget != new_budget) {
961 entity->budget = new_budget;
962 bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
963 new_budget);
964 bfq_requeue_bfqq(bfqd, bfqq, false);
965 }
966 }
967
968 static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
969 {
970 u64 dur;
971
972 if (bfqd->bfq_wr_max_time > 0)
973 return bfqd->bfq_wr_max_time;
974
975 dur = bfqd->rate_dur_prod;
976 do_div(dur, bfqd->peak_rate);
977
978 /*
979 * Limit duration between 3 and 25 seconds. The upper limit
980 * has been conservatively set after the following worst case:
981 * on a QEMU/KVM virtual machine
982 * - running in a slow PC
983 * - with a virtual disk stacked on a slow low-end 5400rpm HDD
984 * - serving a heavy I/O workload, such as the sequential reading
985 * of several files
986 * mplayer took 23 seconds to start, if constantly weight-raised.
987 *
988 * As for higher values than that accommodating the above bad
989 * scenario, tests show that higher values would often yield
990 * the opposite of the desired result, i.e., would worsen
991 * responsiveness by allowing non-interactive applications to
992 * preserve weight raising for too long.
993 *
994 * On the other end, lower values than 3 seconds make it
995 * difficult for most interactive tasks to complete their jobs
996 * before weight-raising finishes.
997 */
998 return clamp_val(dur, msecs_to_jiffies(3000), msecs_to_jiffies(25000));
999 }
1000
1001 /* switch back from soft real-time to interactive weight raising */
1002 static void switch_back_to_interactive_wr(struct bfq_queue *bfqq,
1003 struct bfq_data *bfqd)
1004 {
1005 bfqq->wr_coeff = bfqd->bfq_wr_coeff;
1006 bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
1007 bfqq->last_wr_start_finish = bfqq->wr_start_at_switch_to_srt;
1008 }
1009
1010 static void
1011 bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
1012 struct bfq_io_cq *bic, bool bfq_already_existing)
1013 {
1014 unsigned int old_wr_coeff = bfqq->wr_coeff;
1015 bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
1016
1017 if (bic->saved_has_short_ttime)
1018 bfq_mark_bfqq_has_short_ttime(bfqq);
1019 else
1020 bfq_clear_bfqq_has_short_ttime(bfqq);
1021
1022 if (bic->saved_IO_bound)
1023 bfq_mark_bfqq_IO_bound(bfqq);
1024 else
1025 bfq_clear_bfqq_IO_bound(bfqq);
1026
1027 bfqq->entity.new_weight = bic->saved_weight;
1028 bfqq->ttime = bic->saved_ttime;
1029 bfqq->wr_coeff = bic->saved_wr_coeff;
1030 bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
1031 bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
1032 bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
1033
1034 if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
1035 time_is_before_jiffies(bfqq->last_wr_start_finish +
1036 bfqq->wr_cur_max_time))) {
1037 if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
1038 !bfq_bfqq_in_large_burst(bfqq) &&
1039 time_is_after_eq_jiffies(bfqq->wr_start_at_switch_to_srt +
1040 bfq_wr_duration(bfqd))) {
1041 switch_back_to_interactive_wr(bfqq, bfqd);
1042 } else {
1043 bfqq->wr_coeff = 1;
1044 bfq_log_bfqq(bfqq->bfqd, bfqq,
1045 "resume state: switching off wr");
1046 }
1047 }
1048
1049 /* make sure weight will be updated, however we got here */
1050 bfqq->entity.prio_changed = 1;
1051
1052 if (likely(!busy))
1053 return;
1054
1055 if (old_wr_coeff == 1 && bfqq->wr_coeff > 1)
1056 bfqd->wr_busy_queues++;
1057 else if (old_wr_coeff > 1 && bfqq->wr_coeff == 1)
1058 bfqd->wr_busy_queues--;
1059 }
1060
1061 static int bfqq_process_refs(struct bfq_queue *bfqq)
1062 {
1063 return bfqq->ref - bfqq->allocated - bfqq->entity.on_st -
1064 (bfqq->weight_counter != NULL);
1065 }
1066
1067 /* Empty burst list and add just bfqq (see comments on bfq_handle_burst) */
1068 static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq)
1069 {
1070 struct bfq_queue *item;
1071 struct hlist_node *n;
1072
1073 hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
1074 hlist_del_init(&item->burst_list_node);
1075
1076 /*
1077 * Start the creation of a new burst list only if there is no
1078 * active queue. See comments on the conditional invocation of
1079 * bfq_handle_burst().
1080 */
1081 if (bfq_tot_busy_queues(bfqd) == 0) {
1082 hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
1083 bfqd->burst_size = 1;
1084 } else
1085 bfqd->burst_size = 0;
1086
1087 bfqd->burst_parent_entity = bfqq->entity.parent;
1088 }
1089
1090 /* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */
1091 static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
1092 {
1093 /* Increment burst size to take into account also bfqq */
1094 bfqd->burst_size++;
1095
1096 if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) {
1097 struct bfq_queue *pos, *bfqq_item;
1098 struct hlist_node *n;
1099
1100 /*
1101 * Enough queues have been activated shortly after each
1102 * other to consider this burst as large.
1103 */
1104 bfqd->large_burst = true;
1105
1106 /*
1107 * We can now mark all queues in the burst list as
1108 * belonging to a large burst.
1109 */
1110 hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
1111 burst_list_node)
1112 bfq_mark_bfqq_in_large_burst(bfqq_item);
1113 bfq_mark_bfqq_in_large_burst(bfqq);
1114
1115 /*
1116 * From now on, and until the current burst finishes, any
1117 * new queue being activated shortly after the last queue
1118 * was inserted in the burst can be immediately marked as
1119 * belonging to a large burst. So the burst list is not
1120 * needed any more. Remove it.
1121 */
1122 hlist_for_each_entry_safe(pos, n, &bfqd->burst_list,
1123 burst_list_node)
1124 hlist_del_init(&pos->burst_list_node);
1125 } else /*
1126 * Burst not yet large: add bfqq to the burst list. Do
1127 * not increment the ref counter for bfqq, because bfqq
1128 * is removed from the burst list before freeing bfqq
1129 * in put_queue.
1130 */
1131 hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
1132 }
1133
1134 /*
1135 * If many queues belonging to the same group happen to be created
1136 * shortly after each other, then the processes associated with these
1137 * queues have typically a common goal. In particular, bursts of queue
1138 * creations are usually caused by services or applications that spawn
1139 * many parallel threads/processes. Examples are systemd during boot,
1140 * or git grep. To help these processes get their job done as soon as
1141 * possible, it is usually better to not grant either weight-raising
1142 * or device idling to their queues, unless these queues must be
1143 * protected from the I/O flowing through other active queues.
1144 *
1145 * In this comment we describe, firstly, the reasons why this fact
1146 * holds, and, secondly, the next function, which implements the main
1147 * steps needed to properly mark these queues so that they can then be
1148 * treated in a different way.
1149 *
1150 * The above services or applications benefit mostly from a high
1151 * throughput: the quicker the requests of the activated queues are
1152 * cumulatively served, the sooner the target job of these queues gets
1153 * completed. As a consequence, weight-raising any of these queues,
1154 * which also implies idling the device for it, is almost always
1155 * counterproductive, unless there are other active queues to isolate
1156 * these new queues from. If there no other active queues, then
1157 * weight-raising these new queues just lowers throughput in most
1158 * cases.
1159 *
1160 * On the other hand, a burst of queue creations may be caused also by
1161 * the start of an application that does not consist of a lot of
1162 * parallel I/O-bound threads. In fact, with a complex application,
1163 * several short processes may need to be executed to start-up the
1164 * application. In this respect, to start an application as quickly as
1165 * possible, the best thing to do is in any case to privilege the I/O
1166 * related to the application with respect to all other
1167 * I/O. Therefore, the best strategy to start as quickly as possible
1168 * an application that causes a burst of queue creations is to
1169 * weight-raise all the queues created during the burst. This is the
1170 * exact opposite of the best strategy for the other type of bursts.
1171 *
1172 * In the end, to take the best action for each of the two cases, the
1173 * two types of bursts need to be distinguished. Fortunately, this
1174 * seems relatively easy, by looking at the sizes of the bursts. In
1175 * particular, we found a threshold such that only bursts with a
1176 * larger size than that threshold are apparently caused by
1177 * services or commands such as systemd or git grep. For brevity,
1178 * hereafter we call just 'large' these bursts. BFQ *does not*
1179 * weight-raise queues whose creation occurs in a large burst. In
1180 * addition, for each of these queues BFQ performs or does not perform
1181 * idling depending on which choice boosts the throughput more. The
1182 * exact choice depends on the device and request pattern at
1183 * hand.
1184 *
1185 * Unfortunately, false positives may occur while an interactive task
1186 * is starting (e.g., an application is being started). The
1187 * consequence is that the queues associated with the task do not
1188 * enjoy weight raising as expected. Fortunately these false positives
1189 * are very rare. They typically occur if some service happens to
1190 * start doing I/O exactly when the interactive task starts.
1191 *
1192 * Turning back to the next function, it is invoked only if there are
1193 * no active queues (apart from active queues that would belong to the
1194 * same, possible burst bfqq would belong to), and it implements all
1195 * the steps needed to detect the occurrence of a large burst and to
1196 * properly mark all the queues belonging to it (so that they can then
1197 * be treated in a different way). This goal is achieved by
1198 * maintaining a "burst list" that holds, temporarily, the queues that
1199 * belong to the burst in progress. The list is then used to mark
1200 * these queues as belonging to a large burst if the burst does become
1201 * large. The main steps are the following.
1202 *
1203 * . when the very first queue is created, the queue is inserted into the
1204 * list (as it could be the first queue in a possible burst)
1205 *
1206 * . if the current burst has not yet become large, and a queue Q that does
1207 * not yet belong to the burst is activated shortly after the last time
1208 * at which a new queue entered the burst list, then the function appends
1209 * Q to the burst list
1210 *
1211 * . if, as a consequence of the previous step, the burst size reaches
1212 * the large-burst threshold, then
1213 *
1214 * . all the queues in the burst list are marked as belonging to a
1215 * large burst
1216 *
1217 * . the burst list is deleted; in fact, the burst list already served
1218 * its purpose (keeping temporarily track of the queues in a burst,
1219 * so as to be able to mark them as belonging to a large burst in the
1220 * previous sub-step), and now is not needed any more
1221 *
1222 * . the device enters a large-burst mode
1223 *
1224 * . if a queue Q that does not belong to the burst is created while
1225 * the device is in large-burst mode and shortly after the last time
1226 * at which a queue either entered the burst list or was marked as
1227 * belonging to the current large burst, then Q is immediately marked
1228 * as belonging to a large burst.
1229 *
1230 * . if a queue Q that does not belong to the burst is created a while
1231 * later, i.e., not shortly after, than the last time at which a queue
1232 * either entered the burst list or was marked as belonging to the
1233 * current large burst, then the current burst is deemed as finished and:
1234 *
1235 * . the large-burst mode is reset if set
1236 *
1237 * . the burst list is emptied
1238 *
1239 * . Q is inserted in the burst list, as Q may be the first queue
1240 * in a possible new burst (then the burst list contains just Q
1241 * after this step).
1242 */
1243 static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
1244 {
1245 /*
1246 * If bfqq is already in the burst list or is part of a large
1247 * burst, or finally has just been split, then there is
1248 * nothing else to do.
1249 */
1250 if (!hlist_unhashed(&bfqq->burst_list_node) ||
1251 bfq_bfqq_in_large_burst(bfqq) ||
1252 time_is_after_eq_jiffies(bfqq->split_time +
1253 msecs_to_jiffies(10)))
1254 return;
1255
1256 /*
1257 * If bfqq's creation happens late enough, or bfqq belongs to
1258 * a different group than the burst group, then the current
1259 * burst is finished, and related data structures must be
1260 * reset.
1261 *
1262 * In this respect, consider the special case where bfqq is
1263 * the very first queue created after BFQ is selected for this
1264 * device. In this case, last_ins_in_burst and
1265 * burst_parent_entity are not yet significant when we get
1266 * here. But it is easy to verify that, whether or not the
1267 * following condition is true, bfqq will end up being
1268 * inserted into the burst list. In particular the list will
1269 * happen to contain only bfqq. And this is exactly what has
1270 * to happen, as bfqq may be the first queue of the first
1271 * burst.
1272 */
1273 if (time_is_before_jiffies(bfqd->last_ins_in_burst +
1274 bfqd->bfq_burst_interval) ||
1275 bfqq->entity.parent != bfqd->burst_parent_entity) {
1276 bfqd->large_burst = false;
1277 bfq_reset_burst_list(bfqd, bfqq);
1278 goto end;
1279 }
1280
1281 /*
1282 * If we get here, then bfqq is being activated shortly after the
1283 * last queue. So, if the current burst is also large, we can mark
1284 * bfqq as belonging to this large burst immediately.
1285 */
1286 if (bfqd->large_burst) {
1287 bfq_mark_bfqq_in_large_burst(bfqq);
1288 goto end;
1289 }
1290
1291 /*
1292 * If we get here, then a large-burst state has not yet been
1293 * reached, but bfqq is being activated shortly after the last
1294 * queue. Then we add bfqq to the burst.
1295 */
1296 bfq_add_to_burst(bfqd, bfqq);
1297 end:
1298 /*
1299 * At this point, bfqq either has been added to the current
1300 * burst or has caused the current burst to terminate and a
1301 * possible new burst to start. In particular, in the second
1302 * case, bfqq has become the first queue in the possible new
1303 * burst. In both cases last_ins_in_burst needs to be moved
1304 * forward.
1305 */
1306 bfqd->last_ins_in_burst = jiffies;
1307 }
1308
1309 static int bfq_bfqq_budget_left(struct bfq_queue *bfqq)
1310 {
1311 struct bfq_entity *entity = &bfqq->entity;
1312
1313 return entity->budget - entity->service;
1314 }
1315
1316 /*
1317 * If enough samples have been computed, return the current max budget
1318 * stored in bfqd, which is dynamically updated according to the
1319 * estimated disk peak rate; otherwise return the default max budget
1320 */
1321 static int bfq_max_budget(struct bfq_data *bfqd)
1322 {
1323 if (bfqd->budgets_assigned < bfq_stats_min_budgets)
1324 return bfq_default_max_budget;
1325 else
1326 return bfqd->bfq_max_budget;
1327 }
1328
1329 /*
1330 * Return min budget, which is a fraction of the current or default
1331 * max budget (trying with 1/32)
1332 */
1333 static int bfq_min_budget(struct bfq_data *bfqd)
1334 {
1335 if (bfqd->budgets_assigned < bfq_stats_min_budgets)
1336 return bfq_default_max_budget / 32;
1337 else
1338 return bfqd->bfq_max_budget / 32;
1339 }
1340
1341 /*
1342 * The next function, invoked after the input queue bfqq switches from
1343 * idle to busy, updates the budget of bfqq. The function also tells
1344 * whether the in-service queue should be expired, by returning
1345 * true. The purpose of expiring the in-service queue is to give bfqq
1346 * the chance to possibly preempt the in-service queue, and the reason
1347 * for preempting the in-service queue is to achieve one of the two
1348 * goals below.
1349 *
1350 * 1. Guarantee to bfqq its reserved bandwidth even if bfqq has
1351 * expired because it has remained idle. In particular, bfqq may have
1352 * expired for one of the following two reasons:
1353 *
1354 * - BFQQE_NO_MORE_REQUESTS bfqq did not enjoy any device idling
1355 * and did not make it to issue a new request before its last
1356 * request was served;
1357 *
1358 * - BFQQE_TOO_IDLE bfqq did enjoy device idling, but did not issue
1359 * a new request before the expiration of the idling-time.
1360 *
1361 * Even if bfqq has expired for one of the above reasons, the process
1362 * associated with the queue may be however issuing requests greedily,
1363 * and thus be sensitive to the bandwidth it receives (bfqq may have
1364 * remained idle for other reasons: CPU high load, bfqq not enjoying
1365 * idling, I/O throttling somewhere in the path from the process to
1366 * the I/O scheduler, ...). But if, after every expiration for one of
1367 * the above two reasons, bfqq has to wait for the service of at least
1368 * one full budget of another queue before being served again, then
1369 * bfqq is likely to get a much lower bandwidth or resource time than
1370 * its reserved ones. To address this issue, two countermeasures need
1371 * to be taken.
1372 *
1373 * First, the budget and the timestamps of bfqq need to be updated in
1374 * a special way on bfqq reactivation: they need to be updated as if
1375 * bfqq did not remain idle and did not expire. In fact, if they are
1376 * computed as if bfqq expired and remained idle until reactivation,
1377 * then the process associated with bfqq is treated as if, instead of
1378 * being greedy, it stopped issuing requests when bfqq remained idle,
1379 * and restarts issuing requests only on this reactivation. In other
1380 * words, the scheduler does not help the process recover the "service
1381 * hole" between bfqq expiration and reactivation. As a consequence,
1382 * the process receives a lower bandwidth than its reserved one. In
1383 * contrast, to recover this hole, the budget must be updated as if
1384 * bfqq was not expired at all before this reactivation, i.e., it must
1385 * be set to the value of the remaining budget when bfqq was
1386 * expired. Along the same line, timestamps need to be assigned the
1387 * value they had the last time bfqq was selected for service, i.e.,
1388 * before last expiration. Thus timestamps need to be back-shifted
1389 * with respect to their normal computation (see [1] for more details
1390 * on this tricky aspect).
1391 *
1392 * Secondly, to allow the process to recover the hole, the in-service
1393 * queue must be expired too, to give bfqq the chance to preempt it
1394 * immediately. In fact, if bfqq has to wait for a full budget of the
1395 * in-service queue to be completed, then it may become impossible to
1396 * let the process recover the hole, even if the back-shifted
1397 * timestamps of bfqq are lower than those of the in-service queue. If
1398 * this happens for most or all of the holes, then the process may not
1399 * receive its reserved bandwidth. In this respect, it is worth noting
1400 * that, being the service of outstanding requests unpreemptible, a
1401 * little fraction of the holes may however be unrecoverable, thereby
1402 * causing a little loss of bandwidth.
1403 *
1404 * The last important point is detecting whether bfqq does need this
1405 * bandwidth recovery. In this respect, the next function deems the
1406 * process associated with bfqq greedy, and thus allows it to recover
1407 * the hole, if: 1) the process is waiting for the arrival of a new
1408 * request (which implies that bfqq expired for one of the above two
1409 * reasons), and 2) such a request has arrived soon. The first
1410 * condition is controlled through the flag non_blocking_wait_rq,
1411 * while the second through the flag arrived_in_time. If both
1412 * conditions hold, then the function computes the budget in the
1413 * above-described special way, and signals that the in-service queue
1414 * should be expired. Timestamp back-shifting is done later in
1415 * __bfq_activate_entity.
1416 *
1417 * 2. Reduce latency. Even if timestamps are not backshifted to let
1418 * the process associated with bfqq recover a service hole, bfqq may
1419 * however happen to have, after being (re)activated, a lower finish
1420 * timestamp than the in-service queue. That is, the next budget of
1421 * bfqq may have to be completed before the one of the in-service
1422 * queue. If this is the case, then preempting the in-service queue
1423 * allows this goal to be achieved, apart from the unpreemptible,
1424 * outstanding requests mentioned above.
1425 *
1426 * Unfortunately, regardless of which of the above two goals one wants
1427 * to achieve, service trees need first to be updated to know whether
1428 * the in-service queue must be preempted. To have service trees
1429 * correctly updated, the in-service queue must be expired and
1430 * rescheduled, and bfqq must be scheduled too. This is one of the
1431 * most costly operations (in future versions, the scheduling
1432 * mechanism may be re-designed in such a way to make it possible to
1433 * know whether preemption is needed without needing to update service
1434 * trees). In addition, queue preemptions almost always cause random
1435 * I/O, which may in turn cause loss of throughput. Finally, there may
1436 * even be no in-service queue when the next function is invoked (so,
1437 * no queue to compare timestamps with). Because of these facts, the
1438 * next function adopts the following simple scheme to avoid costly
1439 * operations, too frequent preemptions and too many dependencies on
1440 * the state of the scheduler: it requests the expiration of the
1441 * in-service queue (unconditionally) only for queues that need to
1442 * recover a hole. Then it delegates to other parts of the code the
1443 * responsibility of handling the above case 2.
1444 */
1445 static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
1446 struct bfq_queue *bfqq,
1447 bool arrived_in_time)
1448 {
1449 struct bfq_entity *entity = &bfqq->entity;
1450
1451 /*
1452 * In the next compound condition, we check also whether there
1453 * is some budget left, because otherwise there is no point in
1454 * trying to go on serving bfqq with this same budget: bfqq
1455 * would be expired immediately after being selected for
1456 * service. This would only cause useless overhead.
1457 */
1458 if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time &&
1459 bfq_bfqq_budget_left(bfqq) > 0) {
1460 /*
1461 * We do not clear the flag non_blocking_wait_rq here, as
1462 * the latter is used in bfq_activate_bfqq to signal
1463 * that timestamps need to be back-shifted (and is
1464 * cleared right after).
1465 */
1466
1467 /*
1468 * In next assignment we rely on that either
1469 * entity->service or entity->budget are not updated
1470 * on expiration if bfqq is empty (see
1471 * __bfq_bfqq_recalc_budget). Thus both quantities
1472 * remain unchanged after such an expiration, and the
1473 * following statement therefore assigns to
1474 * entity->budget the remaining budget on such an
1475 * expiration.
1476 */
1477 entity->budget = min_t(unsigned long,
1478 bfq_bfqq_budget_left(bfqq),
1479 bfqq->max_budget);
1480
1481 /*
1482 * At this point, we have used entity->service to get
1483 * the budget left (needed for updating
1484 * entity->budget). Thus we finally can, and have to,
1485 * reset entity->service. The latter must be reset
1486 * because bfqq would otherwise be charged again for
1487 * the service it has received during its previous
1488 * service slot(s).
1489 */
1490 entity->service = 0;
1491
1492 return true;
1493 }
1494
1495 /*
1496 * We can finally complete expiration, by setting service to 0.
1497 */
1498 entity->service = 0;
1499 entity->budget = max_t(unsigned long, bfqq->max_budget,
1500 bfq_serv_to_charge(bfqq->next_rq, bfqq));
1501 bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
1502 return false;
1503 }
1504
1505 /*
1506 * Return the farthest past time instant according to jiffies
1507 * macros.
1508 */
1509 static unsigned long bfq_smallest_from_now(void)
1510 {
1511 return jiffies - MAX_JIFFY_OFFSET;
1512 }
1513
1514 static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
1515 struct bfq_queue *bfqq,
1516 unsigned int old_wr_coeff,
1517 bool wr_or_deserves_wr,
1518 bool interactive,
1519 bool in_burst,
1520 bool soft_rt)
1521 {
1522 if (old_wr_coeff == 1 && wr_or_deserves_wr) {
1523 /* start a weight-raising period */
1524 if (interactive) {
1525 bfqq->service_from_wr = 0;
1526 bfqq->wr_coeff = bfqd->bfq_wr_coeff;
1527 bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
1528 } else {
1529 /*
1530 * No interactive weight raising in progress
1531 * here: assign minus infinity to
1532 * wr_start_at_switch_to_srt, to make sure
1533 * that, at the end of the soft-real-time
1534 * weight raising periods that is starting
1535 * now, no interactive weight-raising period
1536 * may be wrongly considered as still in
1537 * progress (and thus actually started by
1538 * mistake).
1539 */
1540 bfqq->wr_start_at_switch_to_srt =
1541 bfq_smallest_from_now();
1542 bfqq->wr_coeff = bfqd->bfq_wr_coeff *
1543 BFQ_SOFTRT_WEIGHT_FACTOR;
1544 bfqq->wr_cur_max_time =
1545 bfqd->bfq_wr_rt_max_time;
1546 }
1547
1548 /*
1549 * If needed, further reduce budget to make sure it is
1550 * close to bfqq's backlog, so as to reduce the
1551 * scheduling-error component due to a too large
1552 * budget. Do not care about throughput consequences,
1553 * but only about latency. Finally, do not assign a
1554 * too small budget either, to avoid increasing
1555 * latency by causing too frequent expirations.
1556 */
1557 bfqq->entity.budget = min_t(unsigned long,
1558 bfqq->entity.budget,
1559 2 * bfq_min_budget(bfqd));
1560 } else if (old_wr_coeff > 1) {
1561 if (interactive) { /* update wr coeff and duration */
1562 bfqq->wr_coeff = bfqd->bfq_wr_coeff;
1563 bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
1564 } else if (in_burst)
1565 bfqq->wr_coeff = 1;
1566 else if (soft_rt) {
1567 /*
1568 * The application is now or still meeting the
1569 * requirements for being deemed soft rt. We
1570 * can then correctly and safely (re)charge
1571 * the weight-raising duration for the
1572 * application with the weight-raising
1573 * duration for soft rt applications.
1574 *
1575 * In particular, doing this recharge now, i.e.,
1576 * before the weight-raising period for the
1577 * application finishes, reduces the probability
1578 * of the following negative scenario:
1579 * 1) the weight of a soft rt application is
1580 * raised at startup (as for any newly
1581 * created application),
1582 * 2) since the application is not interactive,
1583 * at a certain time weight-raising is
1584 * stopped for the application,
1585 * 3) at that time the application happens to
1586 * still have pending requests, and hence
1587 * is destined to not have a chance to be
1588 * deemed soft rt before these requests are
1589 * completed (see the comments to the
1590 * function bfq_bfqq_softrt_next_start()
1591 * for details on soft rt detection),
1592 * 4) these pending requests experience a high
1593 * latency because the application is not
1594 * weight-raised while they are pending.
1595 */
1596 if (bfqq->wr_cur_max_time !=
1597 bfqd->bfq_wr_rt_max_time) {
1598 bfqq->wr_start_at_switch_to_srt =
1599 bfqq->last_wr_start_finish;
1600
1601 bfqq->wr_cur_max_time =
1602 bfqd->bfq_wr_rt_max_time;
1603 bfqq->wr_coeff = bfqd->bfq_wr_coeff *
1604 BFQ_SOFTRT_WEIGHT_FACTOR;
1605 }
1606 bfqq->last_wr_start_finish = jiffies;
1607 }
1608 }
1609 }
1610
1611 static bool bfq_bfqq_idle_for_long_time(struct bfq_data *bfqd,
1612 struct bfq_queue *bfqq)
1613 {
1614 return bfqq->dispatched == 0 &&
1615 time_is_before_jiffies(
1616 bfqq->budget_timeout +
1617 bfqd->bfq_wr_min_idle_time);
1618 }
1619
1620
1621 /*
1622 * Return true if bfqq is in a higher priority class, or has a higher
1623 * weight than the in-service queue.
1624 */
1625 static bool bfq_bfqq_higher_class_or_weight(struct bfq_queue *bfqq,
1626 struct bfq_queue *in_serv_bfqq)
1627 {
1628 int bfqq_weight, in_serv_weight;
1629
1630 if (bfqq->ioprio_class < in_serv_bfqq->ioprio_class)
1631 return true;
1632
1633 if (in_serv_bfqq->entity.parent == bfqq->entity.parent) {
1634 bfqq_weight = bfqq->entity.weight;
1635 in_serv_weight = in_serv_bfqq->entity.weight;
1636 } else {
1637 if (bfqq->entity.parent)
1638 bfqq_weight = bfqq->entity.parent->weight;
1639 else
1640 bfqq_weight = bfqq->entity.weight;
1641 if (in_serv_bfqq->entity.parent)
1642 in_serv_weight = in_serv_bfqq->entity.parent->weight;
1643 else
1644 in_serv_weight = in_serv_bfqq->entity.weight;
1645 }
1646
1647 return bfqq_weight > in_serv_weight;
1648 }
1649
1650 static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
1651 struct bfq_queue *bfqq,
1652 int old_wr_coeff,
1653 struct request *rq,
1654 bool *interactive)
1655 {
1656 bool soft_rt, in_burst, wr_or_deserves_wr,
1657 bfqq_wants_to_preempt,
1658 idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq),
1659 /*
1660 * See the comments on
1661 * bfq_bfqq_update_budg_for_activation for
1662 * details on the usage of the next variable.
1663 */
1664 arrived_in_time = ktime_get_ns() <=
1665 bfqq->ttime.last_end_request +
1666 bfqd->bfq_slice_idle * 3;
1667
1668
1669 /*
1670 * bfqq deserves to be weight-raised if:
1671 * - it is sync,
1672 * - it does not belong to a large burst,
1673 * - it has been idle for enough time or is soft real-time,
1674 * - is linked to a bfq_io_cq (it is not shared in any sense).
1675 */
1676 in_burst = bfq_bfqq_in_large_burst(bfqq);
1677 soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
1678 !BFQQ_TOTALLY_SEEKY(bfqq) &&
1679 !in_burst &&
1680 time_is_before_jiffies(bfqq->soft_rt_next_start) &&
1681 bfqq->dispatched == 0;
1682 *interactive = !in_burst && idle_for_long_time;
1683 wr_or_deserves_wr = bfqd->low_latency &&
1684 (bfqq->wr_coeff > 1 ||
1685 (bfq_bfqq_sync(bfqq) &&
1686 bfqq->bic && (*interactive || soft_rt)));
1687
1688 /*
1689 * Using the last flag, update budget and check whether bfqq
1690 * may want to preempt the in-service queue.
1691 */
1692 bfqq_wants_to_preempt =
1693 bfq_bfqq_update_budg_for_activation(bfqd, bfqq,
1694 arrived_in_time);
1695
1696 /*
1697 * If bfqq happened to be activated in a burst, but has been
1698 * idle for much more than an interactive queue, then we
1699 * assume that, in the overall I/O initiated in the burst, the
1700 * I/O associated with bfqq is finished. So bfqq does not need
1701 * to be treated as a queue belonging to a burst
1702 * anymore. Accordingly, we reset bfqq's in_large_burst flag
1703 * if set, and remove bfqq from the burst list if it's
1704 * there. We do not decrement burst_size, because the fact
1705 * that bfqq does not need to belong to the burst list any
1706 * more does not invalidate the fact that bfqq was created in
1707 * a burst.
1708 */
1709 if (likely(!bfq_bfqq_just_created(bfqq)) &&
1710 idle_for_long_time &&
1711 time_is_before_jiffies(
1712 bfqq->budget_timeout +
1713 msecs_to_jiffies(10000))) {
1714 hlist_del_init(&bfqq->burst_list_node);
1715 bfq_clear_bfqq_in_large_burst(bfqq);
1716 }
1717
1718 bfq_clear_bfqq_just_created(bfqq);
1719
1720
1721 if (!bfq_bfqq_IO_bound(bfqq)) {
1722 if (arrived_in_time) {
1723 bfqq->requests_within_timer++;
1724 if (bfqq->requests_within_timer >=
1725 bfqd->bfq_requests_within_timer)
1726 bfq_mark_bfqq_IO_bound(bfqq);
1727 } else
1728 bfqq->requests_within_timer = 0;
1729 }
1730
1731 if (bfqd->low_latency) {
1732 if (unlikely(time_is_after_jiffies(bfqq->split_time)))
1733 /* wraparound */
1734 bfqq->split_time =
1735 jiffies - bfqd->bfq_wr_min_idle_time - 1;
1736
1737 if (time_is_before_jiffies(bfqq->split_time +
1738 bfqd->bfq_wr_min_idle_time)) {
1739 bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq,
1740 old_wr_coeff,
1741 wr_or_deserves_wr,
1742 *interactive,
1743 in_burst,
1744 soft_rt);
1745
1746 if (old_wr_coeff != bfqq->wr_coeff)
1747 bfqq->entity.prio_changed = 1;
1748 }
1749 }
1750
1751 bfqq->last_idle_bklogged = jiffies;
1752 bfqq->service_from_backlogged = 0;
1753 bfq_clear_bfqq_softrt_update(bfqq);
1754
1755 bfq_add_bfqq_busy(bfqd, bfqq);
1756
1757 /*
1758 * Expire in-service queue only if preemption may be needed
1759 * for guarantees. In particular, we care only about two
1760 * cases. The first is that bfqq has to recover a service
1761 * hole, as explained in the comments on
1762 * bfq_bfqq_update_budg_for_activation(), i.e., that
1763 * bfqq_wants_to_preempt is true. However, if bfqq does not
1764 * carry time-critical I/O, then bfqq's bandwidth is less
1765 * important than that of queues that carry time-critical I/O.
1766 * So, as a further constraint, we consider this case only if
1767 * bfqq is at least as weight-raised, i.e., at least as time
1768 * critical, as the in-service queue.
1769 *
1770 * The second case is that bfqq is in a higher priority class,
1771 * or has a higher weight than the in-service queue. If this
1772 * condition does not hold, we don't care because, even if
1773 * bfqq does not start to be served immediately, the resulting
1774 * delay for bfqq's I/O is however lower or much lower than
1775 * the ideal completion time to be guaranteed to bfqq's I/O.
1776 *
1777 * In both cases, preemption is needed only if, according to
1778 * the timestamps of both bfqq and of the in-service queue,
1779 * bfqq actually is the next queue to serve. So, to reduce
1780 * useless preemptions, the return value of
1781 * next_queue_may_preempt() is considered in the next compound
1782 * condition too. Yet next_queue_may_preempt() just checks a
1783 * simple, necessary condition for bfqq to be the next queue
1784 * to serve. In fact, to evaluate a sufficient condition, the
1785 * timestamps of the in-service queue would need to be
1786 * updated, and this operation is quite costly (see the
1787 * comments on bfq_bfqq_update_budg_for_activation()).
1788 */
1789 if (bfqd->in_service_queue &&
1790 ((bfqq_wants_to_preempt &&
1791 bfqq->wr_coeff >= bfqd->in_service_queue->wr_coeff) ||
1792 bfq_bfqq_higher_class_or_weight(bfqq, bfqd->in_service_queue)) &&
1793 next_queue_may_preempt(bfqd))
1794 bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
1795 false, BFQQE_PREEMPTED);
1796 }
1797
1798 static void bfq_reset_inject_limit(struct bfq_data *bfqd,
1799 struct bfq_queue *bfqq)
1800 {
1801 /* invalidate baseline total service time */
1802 bfqq->last_serv_time_ns = 0;
1803
1804 /*
1805 * Reset pointer in case we are waiting for
1806 * some request completion.
1807 */
1808 bfqd->waited_rq = NULL;
1809
1810 /*
1811 * If bfqq has a short think time, then start by setting the
1812 * inject limit to 0 prudentially, because the service time of
1813 * an injected I/O request may be higher than the think time
1814 * of bfqq, and therefore, if one request was injected when
1815 * bfqq remains empty, this injected request might delay the
1816 * service of the next I/O request for bfqq significantly. In
1817 * case bfqq can actually tolerate some injection, then the
1818 * adaptive update will however raise the limit soon. This
1819 * lucky circumstance holds exactly because bfqq has a short
1820 * think time, and thus, after remaining empty, is likely to
1821 * get new I/O enqueued---and then completed---before being
1822 * expired. This is the very pattern that gives the
1823 * limit-update algorithm the chance to measure the effect of
1824 * injection on request service times, and then to update the
1825 * limit accordingly.
1826 *
1827 * However, in the following special case, the inject limit is
1828 * left to 1 even if the think time is short: bfqq's I/O is
1829 * synchronized with that of some other queue, i.e., bfqq may
1830 * receive new I/O only after the I/O of the other queue is
1831 * completed. Keeping the inject limit to 1 allows the
1832 * blocking I/O to be served while bfqq is in service. And
1833 * this is very convenient both for bfqq and for overall
1834 * throughput, as explained in detail in the comments in
1835 * bfq_update_has_short_ttime().
1836 *
1837 * On the opposite end, if bfqq has a long think time, then
1838 * start directly by 1, because:
1839 * a) on the bright side, keeping at most one request in
1840 * service in the drive is unlikely to cause any harm to the
1841 * latency of bfqq's requests, as the service time of a single
1842 * request is likely to be lower than the think time of bfqq;
1843 * b) on the downside, after becoming empty, bfqq is likely to
1844 * expire before getting its next request. With this request
1845 * arrival pattern, it is very hard to sample total service
1846 * times and update the inject limit accordingly (see comments
1847 * on bfq_update_inject_limit()). So the limit is likely to be
1848 * never, or at least seldom, updated. As a consequence, by
1849 * setting the limit to 1, we avoid that no injection ever
1850 * occurs with bfqq. On the downside, this proactive step
1851 * further reduces chances to actually compute the baseline
1852 * total service time. Thus it reduces chances to execute the
1853 * limit-update algorithm and possibly raise the limit to more
1854 * than 1.
1855 */
1856 if (bfq_bfqq_has_short_ttime(bfqq))
1857 bfqq->inject_limit = 0;
1858 else
1859 bfqq->inject_limit = 1;
1860
1861 bfqq->decrease_time_jif = jiffies;
1862 }
1863
1864 static void bfq_add_request(struct request *rq)
1865 {
1866 struct bfq_queue *bfqq = RQ_BFQQ(rq);
1867 struct bfq_data *bfqd = bfqq->bfqd;
1868 struct request *next_rq, *prev;
1869 unsigned int old_wr_coeff = bfqq->wr_coeff;
1870 bool interactive = false;
1871
1872 bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
1873 bfqq->queued[rq_is_sync(rq)]++;
1874 bfqd->queued++;
1875
1876 if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
1877 /*
1878 * Detect whether bfqq's I/O seems synchronized with
1879 * that of some other queue, i.e., whether bfqq, after
1880 * remaining empty, happens to receive new I/O only
1881 * right after some I/O request of the other queue has
1882 * been completed. We call waker queue the other
1883 * queue, and we assume, for simplicity, that bfqq may
1884 * have at most one waker queue.
1885 *
1886 * A remarkable throughput boost can be reached by
1887 * unconditionally injecting the I/O of the waker
1888 * queue, every time a new bfq_dispatch_request
1889 * happens to be invoked while I/O is being plugged
1890 * for bfqq. In addition to boosting throughput, this
1891 * unblocks bfqq's I/O, thereby improving bandwidth
1892 * and latency for bfqq. Note that these same results
1893 * may be achieved with the general injection
1894 * mechanism, but less effectively. For details on
1895 * this aspect, see the comments on the choice of the
1896 * queue for injection in bfq_select_queue().
1897 *
1898 * Turning back to the detection of a waker queue, a
1899 * queue Q is deemed as a waker queue for bfqq if, for
1900 * two consecutive times, bfqq happens to become non
1901 * empty right after a request of Q has been
1902 * completed. In particular, on the first time, Q is
1903 * tentatively set as a candidate waker queue, while
1904 * on the second time, the flag
1905 * bfq_bfqq_has_waker(bfqq) is set to confirm that Q
1906 * is a waker queue for bfqq. These detection steps
1907 * are performed only if bfqq has a long think time,
1908 * so as to make it more likely that bfqq's I/O is
1909 * actually being blocked by a synchronization. This
1910 * last filter, plus the above two-times requirement,
1911 * make false positives less likely.
1912 *
1913 * NOTE
1914 *
1915 * The sooner a waker queue is detected, the sooner
1916 * throughput can be boosted by injecting I/O from the
1917 * waker queue. Fortunately, detection is likely to be
1918 * actually fast, for the following reasons. While
1919 * blocked by synchronization, bfqq has a long think
1920 * time. This implies that bfqq's inject limit is at
1921 * least equal to 1 (see the comments in
1922 * bfq_update_inject_limit()). So, thanks to
1923 * injection, the waker queue is likely to be served
1924 * during the very first I/O-plugging time interval
1925 * for bfqq. This triggers the first step of the
1926 * detection mechanism. Thanks again to injection, the
1927 * candidate waker queue is then likely to be
1928 * confirmed no later than during the next
1929 * I/O-plugging interval for bfqq.
1930 */
1931 if (bfqd->last_completed_rq_bfqq &&
1932 !bfq_bfqq_has_short_ttime(bfqq) &&
1933 ktime_get_ns() - bfqd->last_completion <
1934 200 * NSEC_PER_USEC) {
1935 if (bfqd->last_completed_rq_bfqq != bfqq &&
1936 bfqd->last_completed_rq_bfqq !=
1937 bfqq->waker_bfqq) {
1938 /*
1939 * First synchronization detected with
1940 * a candidate waker queue, or with a
1941 * different candidate waker queue
1942 * from the current one.
1943 */
1944 bfqq->waker_bfqq = bfqd->last_completed_rq_bfqq;
1945
1946 /*
1947 * If the waker queue disappears, then
1948 * bfqq->waker_bfqq must be reset. To
1949 * this goal, we maintain in each
1950 * waker queue a list, woken_list, of
1951 * all the queues that reference the
1952 * waker queue through their
1953 * waker_bfqq pointer. When the waker
1954 * queue exits, the waker_bfqq pointer
1955 * of all the queues in the woken_list
1956 * is reset.
1957 *
1958 * In addition, if bfqq is already in
1959 * the woken_list of a waker queue,
1960 * then, before being inserted into
1961 * the woken_list of a new waker
1962 * queue, bfqq must be removed from
1963 * the woken_list of the old waker
1964 * queue.
1965 */
1966 if (!hlist_unhashed(&bfqq->woken_list_node))
1967 hlist_del_init(&bfqq->woken_list_node);
1968 hlist_add_head(&bfqq->woken_list_node,
1969 &bfqd->last_completed_rq_bfqq->woken_list);
1970
1971 bfq_clear_bfqq_has_waker(bfqq);
1972 } else if (bfqd->last_completed_rq_bfqq ==
1973 bfqq->waker_bfqq &&
1974 !bfq_bfqq_has_waker(bfqq)) {
1975 /*
1976 * synchronization with waker_bfqq
1977 * seen for the second time
1978 */
1979 bfq_mark_bfqq_has_waker(bfqq);
1980 }
1981 }
1982
1983 /*
1984 * Periodically reset inject limit, to make sure that
1985 * the latter eventually drops in case workload
1986 * changes, see step (3) in the comments on
1987 * bfq_update_inject_limit().
1988 */
1989 if (time_is_before_eq_jiffies(bfqq->decrease_time_jif +
1990 msecs_to_jiffies(1000)))
1991 bfq_reset_inject_limit(bfqd, bfqq);
1992
1993 /*
1994 * The following conditions must hold to setup a new
1995 * sampling of total service time, and then a new
1996 * update of the inject limit:
1997 * - bfqq is in service, because the total service
1998 * time is evaluated only for the I/O requests of
1999 * the queues in service;
2000 * - this is the right occasion to compute or to
2001 * lower the baseline total service time, because
2002 * there are actually no requests in the drive,
2003 * or
2004 * the baseline total service time is available, and
2005 * this is the right occasion to compute the other
2006 * quantity needed to update the inject limit, i.e.,
2007 * the total service time caused by the amount of
2008 * injection allowed by the current value of the
2009 * limit. It is the right occasion because injection
2010 * has actually been performed during the service
2011 * hole, and there are still in-flight requests,
2012 * which are very likely to be exactly the injected
2013 * requests, or part of them;
2014 * - the minimum interval for sampling the total
2015 * service time and updating the inject limit has
2016 * elapsed.
2017 */
2018 if (bfqq == bfqd->in_service_queue &&
2019 (bfqd->rq_in_driver == 0 ||
2020 (bfqq->last_serv_time_ns > 0 &&
2021 bfqd->rqs_injected && bfqd->rq_in_driver > 0)) &&
2022 time_is_before_eq_jiffies(bfqq->decrease_time_jif +
2023 msecs_to_jiffies(10))) {
2024 bfqd->last_empty_occupied_ns = ktime_get_ns();
2025 /*
2026 * Start the state machine for measuring the
2027 * total service time of rq: setting
2028 * wait_dispatch will cause bfqd->waited_rq to
2029 * be set when rq will be dispatched.
2030 */
2031 bfqd->wait_dispatch = true;
2032 /*
2033 * If there is no I/O in service in the drive,
2034 * then possible injection occurred before the
2035 * arrival of rq will not affect the total
2036 * service time of rq. So the injection limit
2037 * must not be updated as a function of such
2038 * total service time, unless new injection
2039 * occurs before rq is completed. To have the
2040 * injection limit updated only in the latter
2041 * case, reset rqs_injected here (rqs_injected
2042 * will be set in case injection is performed
2043 * on bfqq before rq is completed).
2044 */
2045 if (bfqd->rq_in_driver == 0)
2046 bfqd->rqs_injected = false;
2047 }
2048 }
2049
2050 elv_rb_add(&bfqq->sort_list, rq);
2051
2052 /*
2053 * Check if this request is a better next-serve candidate.
2054 */
2055 prev = bfqq->next_rq;
2056 next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
2057 bfqq->next_rq = next_rq;
2058
2059 /*
2060 * Adjust priority tree position, if next_rq changes.
2061 * See comments on bfq_pos_tree_add_move() for the unlikely().
2062 */
2063 if (unlikely(!bfqd->nonrot_with_queueing && prev != bfqq->next_rq))
2064 bfq_pos_tree_add_move(bfqd, bfqq);
2065
2066 if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
2067 bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff,
2068 rq, &interactive);
2069 else {
2070 if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) &&
2071 time_is_before_jiffies(
2072 bfqq->last_wr_start_finish +
2073 bfqd->bfq_wr_min_inter_arr_async)) {
2074 bfqq->wr_coeff = bfqd->bfq_wr_coeff;
2075 bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
2076
2077 bfqd->wr_busy_queues++;
2078 bfqq->entity.prio_changed = 1;
2079 }
2080 if (prev != bfqq->next_rq)
2081 bfq_updated_next_req(bfqd, bfqq);
2082 }
2083
2084 /*
2085 * Assign jiffies to last_wr_start_finish in the following
2086 * cases:
2087 *
2088 * . if bfqq is not going to be weight-raised, because, for
2089 * non weight-raised queues, last_wr_start_finish stores the
2090 * arrival time of the last request; as of now, this piece
2091 * of information is used only for deciding whether to
2092 * weight-raise async queues
2093 *
2094 * . if bfqq is not weight-raised, because, if bfqq is now
2095 * switching to weight-raised, then last_wr_start_finish
2096 * stores the time when weight-raising starts
2097 *
2098 * . if bfqq is interactive, because, regardless of whether
2099 * bfqq is currently weight-raised, the weight-raising
2100 * period must start or restart (this case is considered
2101 * separately because it is not detected by the above
2102 * conditions, if bfqq is already weight-raised)
2103 *
2104 * last_wr_start_finish has to be updated also if bfqq is soft
2105 * real-time, because the weight-raising period is constantly
2106 * restarted on idle-to-busy transitions for these queues, but
2107 * this is already done in bfq_bfqq_handle_idle_busy_switch if
2108 * needed.
2109 */
2110 if (bfqd->low_latency &&
2111 (old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive))
2112 bfqq->last_wr_start_finish = jiffies;
2113 }
2114
2115 static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
2116 struct bio *bio,
2117 struct request_queue *q)
2118 {
2119 struct bfq_queue *bfqq = bfqd->bio_bfqq;
2120
2121
2122 if (bfqq)
2123 return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
2124
2125 return NULL;
2126 }
2127
2128 static sector_t get_sdist(sector_t last_pos, struct request *rq)
2129 {
2130 if (last_pos)
2131 return abs(blk_rq_pos(rq) - last_pos);
2132
2133 return 0;
2134 }
2135
2136 #if 0 /* Still not clear if we can do without next two functions */
2137 static void bfq_activate_request(struct request_queue *q, struct request *rq)
2138 {
2139 struct bfq_data *bfqd = q->elevator->elevator_data;
2140
2141 bfqd->rq_in_driver++;
2142 }
2143
2144 static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
2145 {
2146 struct bfq_data *bfqd = q->elevator->elevator_data;
2147
2148 bfqd->rq_in_driver--;
2149 }
2150 #endif
2151
2152 static void bfq_remove_request(struct request_queue *q,
2153 struct request *rq)
2154 {
2155 struct bfq_queue *bfqq = RQ_BFQQ(rq);
2156 struct bfq_data *bfqd = bfqq->bfqd;
2157 const int sync = rq_is_sync(rq);
2158
2159 if (bfqq->next_rq == rq) {
2160 bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq);
2161 bfq_updated_next_req(bfqd, bfqq);
2162 }
2163
2164 if (rq->queuelist.prev != &rq->queuelist)
2165 list_del_init(&rq->queuelist);
2166 bfqq->queued[sync]--;
2167 bfqd->queued--;
2168 elv_rb_del(&bfqq->sort_list, rq);
2169
2170 elv_rqhash_del(q, rq);
2171 if (q->last_merge == rq)
2172 q->last_merge = NULL;
2173
2174 if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
2175 bfqq->next_rq = NULL;
2176
2177 if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) {
2178 bfq_del_bfqq_busy(bfqd, bfqq, false);
2179 /*
2180 * bfqq emptied. In normal operation, when
2181 * bfqq is empty, bfqq->entity.service and
2182 * bfqq->entity.budget must contain,
2183 * respectively, the service received and the
2184 * budget used last time bfqq emptied. These
2185 * facts do not hold in this case, as at least
2186 * this last removal occurred while bfqq is
2187 * not in service. To avoid inconsistencies,
2188 * reset both bfqq->entity.service and
2189 * bfqq->entity.budget, if bfqq has still a
2190 * process that may issue I/O requests to it.
2191 */
2192 bfqq->entity.budget = bfqq->entity.service = 0;
2193 }
2194
2195 /*
2196 * Remove queue from request-position tree as it is empty.
2197 */
2198 if (bfqq->pos_root) {
2199 rb_erase(&bfqq->pos_node, bfqq->pos_root);
2200 bfqq->pos_root = NULL;
2201 }
2202 } else {
2203 /* see comments on bfq_pos_tree_add_move() for the unlikely() */
2204 if (unlikely(!bfqd->nonrot_with_queueing))
2205 bfq_pos_tree_add_move(bfqd, bfqq);
2206 }
2207
2208 if (rq->cmd_flags & REQ_META)
2209 bfqq->meta_pending--;
2210
2211 }
2212
2213 static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio,
2214 unsigned int nr_segs)
2215 {
2216 struct request_queue *q = hctx->queue;
2217 struct bfq_data *bfqd = q->elevator->elevator_data;
2218 struct request *free = NULL;
2219 /*
2220 * bfq_bic_lookup grabs the queue_lock: invoke it now and
2221 * store its return value for later use, to avoid nesting
2222 * queue_lock inside the bfqd->lock. We assume that the bic
2223 * returned by bfq_bic_lookup does not go away before
2224 * bfqd->lock is taken.
2225 */
2226 struct bfq_io_cq *bic = bfq_bic_lookup(bfqd, current->io_context, q);
2227 bool ret;
2228
2229 spin_lock_irq(&bfqd->lock);
2230
2231 if (bic)
2232 bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
2233 else
2234 bfqd->bio_bfqq = NULL;
2235 bfqd->bio_bic = bic;
2236
2237 ret = blk_mq_sched_try_merge(q, bio, nr_segs, &free);
2238
2239 if (free)
2240 blk_mq_free_request(free);
2241 spin_unlock_irq(&bfqd->lock);
2242
2243 return ret;
2244 }
2245
2246 static int bfq_request_merge(struct request_queue *q, struct request **req,
2247 struct bio *bio)
2248 {
2249 struct bfq_data *bfqd = q->elevator->elevator_data;
2250 struct request *__rq;
2251
2252 __rq = bfq_find_rq_fmerge(bfqd, bio, q);
2253 if (__rq && elv_bio_merge_ok(__rq, bio)) {
2254 *req = __rq;
2255 return ELEVATOR_FRONT_MERGE;
2256 }
2257
2258 return ELEVATOR_NO_MERGE;
2259 }
2260
2261 static struct bfq_queue *bfq_init_rq(struct request *rq);
2262
2263 static void bfq_request_merged(struct request_queue *q, struct request *req,
2264 enum elv_merge type)
2265 {
2266 if (type == ELEVATOR_FRONT_MERGE &&
2267 rb_prev(&req->rb_node) &&
2268 blk_rq_pos(req) <
2269 blk_rq_pos(container_of(rb_prev(&req->rb_node),
2270 struct request, rb_node))) {
2271 struct bfq_queue *bfqq = bfq_init_rq(req);
2272 struct bfq_data *bfqd;
2273 struct request *prev, *next_rq;
2274
2275 if (!bfqq)
2276 return;
2277
2278 bfqd = bfqq->bfqd;
2279
2280 /* Reposition request in its sort_list */
2281 elv_rb_del(&bfqq->sort_list, req);
2282 elv_rb_add(&bfqq->sort_list, req);
2283
2284 /* Choose next request to be served for bfqq */
2285 prev = bfqq->next_rq;
2286 next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req,
2287 bfqd->last_position);
2288 bfqq->next_rq = next_rq;
2289 /*
2290 * If next_rq changes, update both the queue's budget to
2291 * fit the new request and the queue's position in its
2292 * rq_pos_tree.
2293 */
2294 if (prev != bfqq->next_rq) {
2295 bfq_updated_next_req(bfqd, bfqq);
2296 /*
2297 * See comments on bfq_pos_tree_add_move() for
2298 * the unlikely().
2299 */
2300 if (unlikely(!bfqd->nonrot_with_queueing))
2301 bfq_pos_tree_add_move(bfqd, bfqq);
2302 }
2303 }
2304 }
2305
2306 /*
2307 * This function is called to notify the scheduler that the requests
2308 * rq and 'next' have been merged, with 'next' going away. BFQ
2309 * exploits this hook to address the following issue: if 'next' has a
2310 * fifo_time lower that rq, then the fifo_time of rq must be set to
2311 * the value of 'next', to not forget the greater age of 'next'.
2312 *
2313 * NOTE: in this function we assume that rq is in a bfq_queue, basing
2314 * on that rq is picked from the hash table q->elevator->hash, which,
2315 * in its turn, is filled only with I/O requests present in
2316 * bfq_queues, while BFQ is in use for the request queue q. In fact,
2317 * the function that fills this hash table (elv_rqhash_add) is called
2318 * only by bfq_insert_request.
2319 */
2320 static void bfq_requests_merged(struct request_queue *q, struct request *rq,
2321 struct request *next)
2322 {
2323 struct bfq_queue *bfqq = bfq_init_rq(rq),
2324 *next_bfqq = bfq_init_rq(next);
2325
2326 if (!bfqq)
2327 return;
2328
2329 /*
2330 * If next and rq belong to the same bfq_queue and next is older
2331 * than rq, then reposition rq in the fifo (by substituting next
2332 * with rq). Otherwise, if next and rq belong to different
2333 * bfq_queues, never reposition rq: in fact, we would have to
2334 * reposition it with respect to next's position in its own fifo,
2335 * which would most certainly be too expensive with respect to
2336 * the benefits.
2337 */
2338 if (bfqq == next_bfqq &&
2339 !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
2340 next->fifo_time < rq->fifo_time) {
2341 list_del_init(&rq->queuelist);
2342 list_replace_init(&next->queuelist, &rq->queuelist);
2343 rq->fifo_time = next->fifo_time;
2344 }
2345
2346 if (bfqq->next_rq == next)
2347 bfqq->next_rq = rq;
2348
2349 bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
2350 }
2351
2352 /* Must be called with bfqq != NULL */
2353 static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
2354 {
2355 if (bfq_bfqq_busy(bfqq))
2356 bfqq->bfqd->wr_busy_queues--;
2357 bfqq->wr_coeff = 1;
2358 bfqq->wr_cur_max_time = 0;
2359 bfqq->last_wr_start_finish = jiffies;
2360 /*
2361 * Trigger a weight change on the next invocation of
2362 * __bfq_entity_update_weight_prio.
2363 */
2364 bfqq->entity.prio_changed = 1;
2365 }
2366
2367 void bfq_end_wr_async_queues(struct bfq_data *bfqd,
2368 struct bfq_group *bfqg)
2369 {
2370 int i, j;
2371
2372 for (i = 0; i < 2; i++)
2373 for (j = 0; j < IOPRIO_BE_NR; j++)
2374 if (bfqg->async_bfqq[i][j])
2375 bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]);
2376 if (bfqg->async_idle_bfqq)
2377 bfq_bfqq_end_wr(bfqg->async_idle_bfqq);
2378 }
2379
2380 static void bfq_end_wr(struct bfq_data *bfqd)
2381 {
2382 struct bfq_queue *bfqq;
2383
2384 spin_lock_irq(&bfqd->lock);
2385
2386 list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
2387 bfq_bfqq_end_wr(bfqq);
2388 list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
2389 bfq_bfqq_end_wr(bfqq);
2390 bfq_end_wr_async(bfqd);
2391
2392 spin_unlock_irq(&bfqd->lock);
2393 }
2394
2395 static sector_t bfq_io_struct_pos(void *io_struct, bool request)
2396 {
2397 if (request)
2398 return blk_rq_pos(io_struct);
2399 else
2400 return ((struct bio *)io_struct)->bi_iter.bi_sector;
2401 }
2402
2403 static int bfq_rq_close_to_sector(void *io_struct, bool request,
2404 sector_t sector)
2405 {
2406 return abs(bfq_io_struct_pos(io_struct, request) - sector) <=
2407 BFQQ_CLOSE_THR;
2408 }
2409
2410 static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd,
2411 struct bfq_queue *bfqq,
2412 sector_t sector)
2413 {
2414 struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
2415 struct rb_node *parent, *node;
2416 struct bfq_queue *__bfqq;
2417
2418 if (RB_EMPTY_ROOT(root))
2419 return NULL;
2420
2421 /*
2422 * First, if we find a request starting at the end of the last
2423 * request, choose it.
2424 */
2425 __bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL);
2426 if (__bfqq)
2427 return __bfqq;
2428
2429 /*
2430 * If the exact sector wasn't found, the parent of the NULL leaf
2431 * will contain the closest sector (rq_pos_tree sorted by
2432 * next_request position).
2433 */
2434 __bfqq = rb_entry(parent, struct bfq_queue, pos_node);
2435 if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
2436 return __bfqq;
2437
2438 if (blk_rq_pos(__bfqq->next_rq) < sector)
2439 node = rb_next(&__bfqq->pos_node);
2440 else
2441 node = rb_prev(&__bfqq->pos_node);
2442 if (!node)
2443 return NULL;
2444
2445 __bfqq = rb_entry(node, struct bfq_queue, pos_node);
2446 if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
2447 return __bfqq;
2448
2449 return NULL;
2450 }
2451
2452 static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd,
2453 struct bfq_queue *cur_bfqq,
2454 sector_t sector)
2455 {
2456 struct bfq_queue *bfqq;
2457
2458 /*
2459 * We shall notice if some of the queues are cooperating,
2460 * e.g., working closely on the same area of the device. In
2461 * that case, we can group them together and: 1) don't waste
2462 * time idling, and 2) serve the union of their requests in
2463 * the best possible order for throughput.
2464 */
2465 bfqq = bfqq_find_close(bfqd, cur_bfqq, sector);
2466 if (!bfqq || bfqq == cur_bfqq)
2467 return NULL;
2468
2469 return bfqq;
2470 }
2471
2472 static struct bfq_queue *
2473 bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
2474 {
2475 int process_refs, new_process_refs;
2476 struct bfq_queue *__bfqq;
2477
2478 /*
2479 * If there are no process references on the new_bfqq, then it is
2480 * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
2481 * may have dropped their last reference (not just their last process
2482 * reference).
2483 */
2484 if (!bfqq_process_refs(new_bfqq))
2485 return NULL;
2486
2487 /* Avoid a circular list and skip interim queue merges. */
2488 while ((__bfqq = new_bfqq->new_bfqq)) {
2489 if (__bfqq == bfqq)
2490 return NULL;
2491 new_bfqq = __bfqq;
2492 }
2493
2494 process_refs = bfqq_process_refs(bfqq);
2495 new_process_refs = bfqq_process_refs(new_bfqq);
2496 /*
2497 * If the process for the bfqq has gone away, there is no
2498 * sense in merging the queues.
2499 */
2500 if (process_refs == 0 || new_process_refs == 0)
2501 return NULL;
2502
2503 bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
2504 new_bfqq->pid);
2505
2506 /*
2507 * Merging is just a redirection: the requests of the process
2508 * owning one of the two queues are redirected to the other queue.
2509 * The latter queue, in its turn, is set as shared if this is the
2510 * first time that the requests of some process are redirected to
2511 * it.
2512 *
2513 * We redirect bfqq to new_bfqq and not the opposite, because
2514 * we are in the context of the process owning bfqq, thus we
2515 * have the io_cq of this process. So we can immediately
2516 * configure this io_cq to redirect the requests of the
2517 * process to new_bfqq. In contrast, the io_cq of new_bfqq is
2518 * not available any more (new_bfqq->bic == NULL).
2519 *
2520 * Anyway, even in case new_bfqq coincides with the in-service
2521 * queue, redirecting requests the in-service queue is the
2522 * best option, as we feed the in-service queue with new
2523 * requests close to the last request served and, by doing so,
2524 * are likely to increase the throughput.
2525 */
2526 bfqq->new_bfqq = new_bfqq;
2527 new_bfqq->ref += process_refs;
2528 return new_bfqq;
2529 }
2530
2531 static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
2532 struct bfq_queue *new_bfqq)
2533 {
2534 if (bfq_too_late_for_merging(new_bfqq))
2535 return false;
2536
2537 if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) ||
2538 (bfqq->ioprio_class != new_bfqq->ioprio_class))
2539 return false;
2540
2541 /*
2542 * If either of the queues has already been detected as seeky,
2543 * then merging it with the other queue is unlikely to lead to
2544 * sequential I/O.
2545 */
2546 if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq))
2547 return false;
2548
2549 /*
2550 * Interleaved I/O is known to be done by (some) applications
2551 * only for reads, so it does not make sense to merge async
2552 * queues.
2553 */
2554 if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq))
2555 return false;
2556
2557 return true;
2558 }
2559
2560 /*
2561 * Attempt to schedule a merge of bfqq with the currently in-service
2562 * queue or with a close queue among the scheduled queues. Return
2563 * NULL if no merge was scheduled, a pointer to the shared bfq_queue
2564 * structure otherwise.
2565 *
2566 * The OOM queue is not allowed to participate to cooperation: in fact, since
2567 * the requests temporarily redirected to the OOM queue could be redirected
2568 * again to dedicated queues at any time, the state needed to correctly
2569 * handle merging with the OOM queue would be quite complex and expensive
2570 * to maintain. Besides, in such a critical condition as an out of memory,
2571 * the benefits of queue merging may be little relevant, or even negligible.
2572 *
2573 * WARNING: queue merging may impair fairness among non-weight raised
2574 * queues, for at least two reasons: 1) the original weight of a
2575 * merged queue may change during the merged state, 2) even being the
2576 * weight the same, a merged queue may be bloated with many more
2577 * requests than the ones produced by its originally-associated
2578 * process.
2579 */
2580 static struct bfq_queue *
2581 bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
2582 void *io_struct, bool request)
2583 {
2584 struct bfq_queue *in_service_bfqq, *new_bfqq;
2585
2586 /*
2587 * Do not perform queue merging if the device is non
2588 * rotational and performs internal queueing. In fact, such a
2589 * device reaches a high speed through internal parallelism
2590 * and pipelining. This means that, to reach a high
2591 * throughput, it must have many requests enqueued at the same
2592 * time. But, in this configuration, the internal scheduling
2593 * algorithm of the device does exactly the job of queue
2594 * merging: it reorders requests so as to obtain as much as
2595 * possible a sequential I/O pattern. As a consequence, with
2596 * the workload generated by processes doing interleaved I/O,
2597 * the throughput reached by the device is likely to be the
2598 * same, with and without queue merging.
2599 *
2600 * Disabling merging also provides a remarkable benefit in
2601 * terms of throughput. Merging tends to make many workloads
2602 * artificially more uneven, because of shared queues
2603 * remaining non empty for incomparably more time than
2604 * non-merged queues. This may accentuate workload
2605 * asymmetries. For example, if one of the queues in a set of
2606 * merged queues has a higher weight than a normal queue, then
2607 * the shared queue may inherit such a high weight and, by
2608 * staying almost always active, may force BFQ to perform I/O
2609 * plugging most of the time. This evidently makes it harder
2610 * for BFQ to let the device reach a high throughput.
2611 *
2612 * Finally, the likely() macro below is not used because one
2613 * of the two branches is more likely than the other, but to
2614 * have the code path after the following if() executed as
2615 * fast as possible for the case of a non rotational device
2616 * with queueing. We want it because this is the fastest kind
2617 * of device. On the opposite end, the likely() may lengthen
2618 * the execution time of BFQ for the case of slower devices
2619 * (rotational or at least without queueing). But in this case
2620 * the execution time of BFQ matters very little, if not at
2621 * all.
2622 */
2623 if (likely(bfqd->nonrot_with_queueing))
2624 return NULL;
2625
2626 /*
2627 * Prevent bfqq from being merged if it has been created too
2628 * long ago. The idea is that true cooperating processes, and
2629 * thus their associated bfq_queues, are supposed to be
2630 * created shortly after each other. This is the case, e.g.,
2631 * for KVM/QEMU and dump I/O threads. Basing on this
2632 * assumption, the following filtering greatly reduces the
2633 * probability that two non-cooperating processes, which just
2634 * happen to do close I/O for some short time interval, have
2635 * their queues merged by mistake.
2636 */
2637 if (bfq_too_late_for_merging(bfqq))
2638 return NULL;
2639
2640 if (bfqq->new_bfqq)
2641 return bfqq->new_bfqq;
2642
2643 if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq))
2644 return NULL;
2645
2646 /* If there is only one backlogged queue, don't search. */
2647 if (bfq_tot_busy_queues(bfqd) == 1)
2648 return NULL;
2649
2650 in_service_bfqq = bfqd->in_service_queue;
2651
2652 if (in_service_bfqq && in_service_bfqq != bfqq &&
2653 likely(in_service_bfqq != &bfqd->oom_bfqq) &&
2654 bfq_rq_close_to_sector(io_struct, request,
2655 bfqd->in_serv_last_pos) &&
2656 bfqq->entity.parent == in_service_bfqq->entity.parent &&
2657 bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) {
2658 new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
2659 if (new_bfqq)
2660 return new_bfqq;
2661 }
2662 /*
2663 * Check whether there is a cooperator among currently scheduled
2664 * queues. The only thing we need is that the bio/request is not
2665 * NULL, as we need it to establish whether a cooperator exists.
2666 */
2667 new_bfqq = bfq_find_close_cooperator(bfqd, bfqq,
2668 bfq_io_struct_pos(io_struct, request));
2669
2670 if (new_bfqq && likely(new_bfqq != &bfqd->oom_bfqq) &&
2671 bfq_may_be_close_cooperator(bfqq, new_bfqq))
2672 return bfq_setup_merge(bfqq, new_bfqq);
2673
2674 return NULL;
2675 }
2676
2677 static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
2678 {
2679 struct bfq_io_cq *bic = bfqq->bic;
2680
2681 /*
2682 * If !bfqq->bic, the queue is already shared or its requests
2683 * have already been redirected to a shared queue; both idle window
2684 * and weight raising state have already been saved. Do nothing.
2685 */
2686 if (!bic)
2687 return;
2688
2689 bic->saved_weight = bfqq->entity.orig_weight;
2690 bic->saved_ttime = bfqq->ttime;
2691 bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq);
2692 bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
2693 bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
2694 bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
2695 if (unlikely(bfq_bfqq_just_created(bfqq) &&
2696 !bfq_bfqq_in_large_burst(bfqq) &&
2697 bfqq->bfqd->low_latency)) {
2698 /*
2699 * bfqq being merged right after being created: bfqq
2700 * would have deserved interactive weight raising, but
2701 * did not make it to be set in a weight-raised state,
2702 * because of this early merge. Store directly the
2703 * weight-raising state that would have been assigned
2704 * to bfqq, so that to avoid that bfqq unjustly fails
2705 * to enjoy weight raising if split soon.
2706 */
2707 bic->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff;
2708 bic->saved_wr_start_at_switch_to_srt = bfq_smallest_from_now();
2709 bic->saved_wr_cur_max_time = bfq_wr_duration(bfqq->bfqd);
2710 bic->saved_last_wr_start_finish = jiffies;
2711 } else {
2712 bic->saved_wr_coeff = bfqq->wr_coeff;
2713 bic->saved_wr_start_at_switch_to_srt =
2714 bfqq->wr_start_at_switch_to_srt;
2715 bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
2716 bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
2717 }
2718 }
2719
2720 void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
2721 {
2722 /*
2723 * To prevent bfqq's service guarantees from being violated,
2724 * bfqq may be left busy, i.e., queued for service, even if
2725 * empty (see comments in __bfq_bfqq_expire() for
2726 * details). But, if no process will send requests to bfqq any
2727 * longer, then there is no point in keeping bfqq queued for
2728 * service. In addition, keeping bfqq queued for service, but
2729 * with no process ref any longer, may have caused bfqq to be
2730 * freed when dequeued from service. But this is assumed to
2731 * never happen.
2732 */
2733 if (bfq_bfqq_busy(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list) &&
2734 bfqq != bfqd->in_service_queue)
2735 bfq_del_bfqq_busy(bfqd, bfqq, false);
2736
2737 bfq_put_queue(bfqq);
2738 }
2739
2740 static void
2741 bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
2742 struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
2743 {
2744 bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
2745 (unsigned long)new_bfqq->pid);
2746 /* Save weight raising and idle window of the merged queues */
2747 bfq_bfqq_save_state(bfqq);
2748 bfq_bfqq_save_state(new_bfqq);
2749 if (bfq_bfqq_IO_bound(bfqq))
2750 bfq_mark_bfqq_IO_bound(new_bfqq);
2751 bfq_clear_bfqq_IO_bound(bfqq);
2752
2753 /*
2754 * If bfqq is weight-raised, then let new_bfqq inherit
2755 * weight-raising. To reduce false positives, neglect the case
2756 * where bfqq has just been created, but has not yet made it
2757 * to be weight-raised (which may happen because EQM may merge
2758 * bfqq even before bfq_add_request is executed for the first
2759 * time for bfqq). Handling this case would however be very
2760 * easy, thanks to the flag just_created.
2761 */
2762 if (new_bfqq->wr_coeff == 1 && bfqq->wr_coeff > 1) {
2763 new_bfqq->wr_coeff = bfqq->wr_coeff;
2764 new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time;
2765 new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish;
2766 new_bfqq->wr_start_at_switch_to_srt =
2767 bfqq->wr_start_at_switch_to_srt;
2768 if (bfq_bfqq_busy(new_bfqq))
2769 bfqd->wr_busy_queues++;
2770 new_bfqq->entity.prio_changed = 1;
2771 }
2772
2773 if (bfqq->wr_coeff > 1) { /* bfqq has given its wr to new_bfqq */
2774 bfqq->wr_coeff = 1;
2775 bfqq->entity.prio_changed = 1;
2776 if (bfq_bfqq_busy(bfqq))
2777 bfqd->wr_busy_queues--;
2778 }
2779
2780 bfq_log_bfqq(bfqd, new_bfqq, "merge_bfqqs: wr_busy %d",
2781 bfqd->wr_busy_queues);
2782
2783 /*
2784 * Merge queues (that is, let bic redirect its requests to new_bfqq)
2785 */
2786 bic_set_bfqq(bic, new_bfqq, 1);
2787 bfq_mark_bfqq_coop(new_bfqq);
2788 /*
2789 * new_bfqq now belongs to at least two bics (it is a shared queue):
2790 * set new_bfqq->bic to NULL. bfqq either:
2791 * - does not belong to any bic any more, and hence bfqq->bic must
2792 * be set to NULL, or
2793 * - is a queue whose owning bics have already been redirected to a
2794 * different queue, hence the queue is destined to not belong to
2795 * any bic soon and bfqq->bic is already NULL (therefore the next
2796 * assignment causes no harm).
2797 */
2798 new_bfqq->bic = NULL;
2799 /*
2800 * If the queue is shared, the pid is the pid of one of the associated
2801 * processes. Which pid depends on the exact sequence of merge events
2802 * the queue underwent. So printing such a pid is useless and confusing
2803 * because it reports a random pid between those of the associated
2804 * processes.
2805 * We mark such a queue with a pid -1, and then print SHARED instead of
2806 * a pid in logging messages.
2807 */
2808 new_bfqq->pid = -1;
2809 bfqq->bic = NULL;
2810 bfq_release_process_ref(bfqd, bfqq);
2811 }
2812
2813 static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
2814 struct bio *bio)
2815 {
2816 struct bfq_data *bfqd = q->elevator->elevator_data;
2817 bool is_sync = op_is_sync(bio->bi_opf);
2818 struct bfq_queue *bfqq = bfqd->bio_bfqq, *new_bfqq;
2819
2820 /*
2821 * Disallow merge of a sync bio into an async request.
2822 */
2823 if (is_sync && !rq_is_sync(rq))
2824 return false;
2825
2826 /*
2827 * Lookup the bfqq that this bio will be queued with. Allow
2828 * merge only if rq is queued there.
2829 */
2830 if (!bfqq)
2831 return false;
2832
2833 /*
2834 * We take advantage of this function to perform an early merge
2835 * of the queues of possible cooperating processes.
2836 */
2837 new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
2838 if (new_bfqq) {
2839 /*
2840 * bic still points to bfqq, then it has not yet been
2841 * redirected to some other bfq_queue, and a queue
2842 * merge between bfqq and new_bfqq can be safely
2843 * fulfilled, i.e., bic can be redirected to new_bfqq
2844 * and bfqq can be put.
2845 */
2846 bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq,
2847 new_bfqq);
2848 /*
2849 * If we get here, bio will be queued into new_queue,
2850 * so use new_bfqq to decide whether bio and rq can be
2851 * merged.
2852 */
2853 bfqq = new_bfqq;
2854
2855 /*
2856 * Change also bqfd->bio_bfqq, as
2857 * bfqd->bio_bic now points to new_bfqq, and
2858 * this function may be invoked again (and then may
2859 * use again bqfd->bio_bfqq).
2860 */
2861 bfqd->bio_bfqq = bfqq;
2862 }
2863
2864 return bfqq == RQ_BFQQ(rq);
2865 }
2866
2867 /*
2868 * Set the maximum time for the in-service queue to consume its
2869 * budget. This prevents seeky processes from lowering the throughput.
2870 * In practice, a time-slice service scheme is used with seeky
2871 * processes.
2872 */
2873 static void bfq_set_budget_timeout(struct bfq_data *bfqd,
2874 struct bfq_queue *bfqq)
2875 {
2876 unsigned int timeout_coeff;
2877
2878 if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time)
2879 timeout_coeff = 1;
2880 else
2881 timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
2882
2883 bfqd->last_budget_start = ktime_get();
2884
2885 bfqq->budget_timeout = jiffies +
2886 bfqd->bfq_timeout * timeout_coeff;
2887 }
2888
2889 static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
2890 struct bfq_queue *bfqq)
2891 {
2892 if (bfqq) {
2893 bfq_clear_bfqq_fifo_expire(bfqq);
2894
2895 bfqd->budgets_assigned = (bfqd->budgets_assigned * 7 + 256) / 8;
2896
2897 if (time_is_before_jiffies(bfqq->last_wr_start_finish) &&
2898 bfqq->wr_coeff > 1 &&
2899 bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
2900 time_is_before_jiffies(bfqq->budget_timeout)) {
2901 /*
2902 * For soft real-time queues, move the start
2903 * of the weight-raising period forward by the
2904 * time the queue has not received any
2905 * service. Otherwise, a relatively long
2906 * service delay is likely to cause the
2907 * weight-raising period of the queue to end,
2908 * because of the short duration of the
2909 * weight-raising period of a soft real-time
2910 * queue. It is worth noting that this move
2911 * is not so dangerous for the other queues,
2912 * because soft real-time queues are not
2913 * greedy.
2914 *
2915 * To not add a further variable, we use the
2916 * overloaded field budget_timeout to
2917 * determine for how long the queue has not
2918 * received service, i.e., how much time has
2919 * elapsed since the queue expired. However,
2920 * this is a little imprecise, because
2921 * budget_timeout is set to jiffies if bfqq
2922 * not only expires, but also remains with no
2923 * request.
2924 */
2925 if (time_after(bfqq->budget_timeout,
2926 bfqq->last_wr_start_finish))
2927 bfqq->last_wr_start_finish +=
2928 jiffies - bfqq->budget_timeout;
2929 else
2930 bfqq->last_wr_start_finish = jiffies;
2931 }
2932
2933 bfq_set_budget_timeout(bfqd, bfqq);
2934 bfq_log_bfqq(bfqd, bfqq,
2935 "set_in_service_queue, cur-budget = %d",
2936 bfqq->entity.budget);
2937 }
2938
2939 bfqd->in_service_queue = bfqq;
2940 }
2941
2942 /*
2943 * Get and set a new queue for service.
2944 */
2945 static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd)
2946 {
2947 struct bfq_queue *bfqq = bfq_get_next_queue(bfqd);
2948
2949 __bfq_set_in_service_queue(bfqd, bfqq);
2950 return bfqq;
2951 }
2952
2953 static void bfq_arm_slice_timer(struct bfq_data *bfqd)
2954 {
2955 struct bfq_queue *bfqq = bfqd->in_service_queue;
2956 u32 sl;
2957
2958 bfq_mark_bfqq_wait_request(bfqq);
2959
2960 /*
2961 * We don't want to idle for seeks, but we do want to allow
2962 * fair distribution of slice time for a process doing back-to-back
2963 * seeks. So allow a little bit of time for him to submit a new rq.
2964 */
2965 sl = bfqd->bfq_slice_idle;
2966 /*
2967 * Unless the queue is being weight-raised or the scenario is
2968 * asymmetric, grant only minimum idle time if the queue
2969 * is seeky. A long idling is preserved for a weight-raised
2970 * queue, or, more in general, in an asymmetric scenario,
2971 * because a long idling is needed for guaranteeing to a queue
2972 * its reserved share of the throughput (in particular, it is
2973 * needed if the queue has a higher weight than some other
2974 * queue).
2975 */
2976 if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
2977 !bfq_asymmetric_scenario(bfqd, bfqq))
2978 sl = min_t(u64, sl, BFQ_MIN_TT);
2979 else if (bfqq->wr_coeff > 1)
2980 sl = max_t(u32, sl, 20ULL * NSEC_PER_MSEC);
2981
2982 bfqd->last_idling_start = ktime_get();
2983 bfqd->last_idling_start_jiffies = jiffies;
2984
2985 hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
2986 HRTIMER_MODE_REL);
2987 bfqg_stats_set_start_idle_time(bfqq_group(bfqq));
2988 }
2989
2990 /*
2991 * In autotuning mode, max_budget is dynamically recomputed as the
2992 * amount of sectors transferred in timeout at the estimated peak
2993 * rate. This enables BFQ to utilize a full timeslice with a full
2994 * budget, even if the in-service queue is served at peak rate. And
2995 * this maximises throughput with sequential workloads.
2996 */
2997 static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
2998 {
2999 return (u64)bfqd->peak_rate * USEC_PER_MSEC *
3000 jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT;
3001 }
3002
3003 /*
3004 * Update parameters related to throughput and responsiveness, as a
3005 * function of the estimated peak rate. See comments on
3006 * bfq_calc_max_budget(), and on the ref_wr_duration array.
3007 */
3008 static void update_thr_responsiveness_params(struct bfq_data *bfqd)
3009 {
3010 if (bfqd->bfq_user_max_budget == 0) {
3011 bfqd->bfq_max_budget =
3012 bfq_calc_max_budget(bfqd);
3013 bfq_log(bfqd, "new max_budget = %d", bfqd->bfq_max_budget);
3014 }
3015 }
3016
3017 static void bfq_reset_rate_computation(struct bfq_data *bfqd,
3018 struct request *rq)
3019 {
3020 if (rq != NULL) { /* new rq dispatch now, reset accordingly */
3021 bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns();
3022 bfqd->peak_rate_samples = 1;
3023 bfqd->sequential_samples = 0;
3024 bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size =
3025 blk_rq_sectors(rq);
3026 } else /* no new rq dispatched, just reset the number of samples */
3027 bfqd->peak_rate_samples = 0; /* full re-init on next disp. */
3028
3029 bfq_log(bfqd,
3030 "reset_rate_computation at end, sample %u/%u tot_sects %llu",
3031 bfqd->peak_rate_samples, bfqd->sequential_samples,
3032 bfqd->tot_sectors_dispatched);
3033 }
3034
3035 static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq)
3036 {
3037 u32 rate, weight, divisor;
3038
3039 /*
3040 * For the convergence property to hold (see comments on
3041 * bfq_update_peak_rate()) and for the assessment to be
3042 * reliable, a minimum number of samples must be present, and
3043 * a minimum amount of time must have elapsed. If not so, do
3044 * not compute new rate. Just reset parameters, to get ready
3045 * for a new evaluation attempt.
3046 */
3047 if (bfqd->peak_rate_samples < BFQ_RATE_MIN_SAMPLES ||
3048 bfqd->delta_from_first < BFQ_RATE_MIN_INTERVAL)
3049 goto reset_computation;
3050
3051 /*
3052 * If a new request completion has occurred after last
3053 * dispatch, then, to approximate the rate at which requests
3054 * have been served by the device, it is more precise to
3055 * extend the observation interval to the last completion.
3056 */
3057 bfqd->delta_from_first =
3058 max_t(u64, bfqd->delta_from_first,
3059 bfqd->last_completion - bfqd->first_dispatch);
3060
3061 /*
3062 * Rate computed in sects/usec, and not sects/nsec, for
3063 * precision issues.
3064 */
3065 rate = div64_ul(bfqd->tot_sectors_dispatched<<BFQ_RATE_SHIFT,
3066 div_u64(bfqd->delta_from_first, NSEC_PER_USEC));
3067
3068 /*
3069 * Peak rate not updated if:
3070 * - the percentage of sequential dispatches is below 3/4 of the
3071 * total, and rate is below the current estimated peak rate
3072 * - rate is unreasonably high (> 20M sectors/sec)
3073 */
3074 if ((bfqd->sequential_samples < (3 * bfqd->peak_rate_samples)>>2 &&
3075 rate <= bfqd->peak_rate) ||
3076 rate > 20<<BFQ_RATE_SHIFT)
3077 goto reset_computation;
3078
3079 /*
3080 * We have to update the peak rate, at last! To this purpose,
3081 * we use a low-pass filter. We compute the smoothing constant
3082 * of the filter as a function of the 'weight' of the new
3083 * measured rate.
3084 *
3085 * As can be seen in next formulas, we define this weight as a
3086 * quantity proportional to how sequential the workload is,
3087 * and to how long the observation time interval is.
3088 *
3089 * The weight runs from 0 to 8. The maximum value of the
3090 * weight, 8, yields the minimum value for the smoothing
3091 * constant. At this minimum value for the smoothing constant,
3092 * the measured rate contributes for half of the next value of
3093 * the estimated peak rate.
3094 *
3095 * So, the first step is to compute the weight as a function
3096 * of how sequential the workload is. Note that the weight
3097 * cannot reach 9, because bfqd->sequential_samples cannot
3098 * become equal to bfqd->peak_rate_samples, which, in its
3099 * turn, holds true because bfqd->sequential_samples is not
3100 * incremented for the first sample.
3101 */
3102 weight = (9 * bfqd->sequential_samples) / bfqd->peak_rate_samples;
3103
3104 /*
3105 * Second step: further refine the weight as a function of the
3106 * duration of the observation interval.
3107 */
3108 weight = min_t(u32, 8,
3109 div_u64(weight * bfqd->delta_from_first,
3110 BFQ_RATE_REF_INTERVAL));
3111
3112 /*
3113 * Divisor ranging from 10, for minimum weight, to 2, for
3114 * maximum weight.
3115 */
3116 divisor = 10 - weight;
3117
3118 /*
3119 * Finally, update peak rate:
3120 *
3121 * peak_rate = peak_rate * (divisor-1) / divisor + rate / divisor
3122 */
3123 bfqd->peak_rate *= divisor-1;
3124 bfqd->peak_rate /= divisor;
3125 rate /= divisor; /* smoothing constant alpha = 1/divisor */
3126
3127 bfqd->peak_rate += rate;
3128
3129 /*
3130 * For a very slow device, bfqd->peak_rate can reach 0 (see
3131 * the minimum representable values reported in the comments
3132 * on BFQ_RATE_SHIFT). Push to 1 if this happens, to avoid
3133 * divisions by zero where bfqd->peak_rate is used as a
3134 * divisor.
3135 */
3136 bfqd->peak_rate = max_t(u32, 1, bfqd->peak_rate);
3137
3138 update_thr_responsiveness_params(bfqd);
3139
3140 reset_computation:
3141 bfq_reset_rate_computation(bfqd, rq);
3142 }
3143
3144 /*
3145 * Update the read/write peak rate (the main quantity used for
3146 * auto-tuning, see update_thr_responsiveness_params()).
3147 *
3148 * It is not trivial to estimate the peak rate (correctly): because of
3149 * the presence of sw and hw queues between the scheduler and the
3150 * device components that finally serve I/O requests, it is hard to
3151 * say exactly when a given dispatched request is served inside the
3152 * device, and for how long. As a consequence, it is hard to know
3153 * precisely at what rate a given set of requests is actually served
3154 * by the device.
3155 *
3156 * On the opposite end, the dispatch time of any request is trivially
3157 * available, and, from this piece of information, the "dispatch rate"
3158 * of requests can be immediately computed. So, the idea in the next
3159 * function is to use what is known, namely request dispatch times
3160 * (plus, when useful, request completion times), to estimate what is
3161 * unknown, namely in-device request service rate.
3162 *
3163 * The main issue is that, because of the above facts, the rate at
3164 * which a certain set of requests is dispatched over a certain time
3165 * interval can vary greatly with respect to the rate at which the
3166 * same requests are then served. But, since the size of any
3167 * intermediate queue is limited, and the service scheme is lossless
3168 * (no request is silently dropped), the following obvious convergence
3169 * property holds: the number of requests dispatched MUST become
3170 * closer and closer to the number of requests completed as the
3171 * observation interval grows. This is the key property used in
3172 * the next function to estimate the peak service rate as a function
3173 * of the observed dispatch rate. The function assumes to be invoked
3174 * on every request dispatch.
3175 */
3176 static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
3177 {
3178 u64 now_ns = ktime_get_ns();
3179
3180 if (bfqd->peak_rate_samples == 0) { /* first dispatch */
3181 bfq_log(bfqd, "update_peak_rate: goto reset, samples %d",
3182 bfqd->peak_rate_samples);
3183 bfq_reset_rate_computation(bfqd, rq);
3184 goto update_last_values; /* will add one sample */
3185 }
3186
3187 /*
3188 * Device idle for very long: the observation interval lasting
3189 * up to this dispatch cannot be a valid observation interval
3190 * for computing a new peak rate (similarly to the late-
3191 * completion event in bfq_completed_request()). Go to
3192 * update_rate_and_reset to have the following three steps
3193 * taken:
3194 * - close the observation interval at the last (previous)
3195 * request dispatch or completion
3196 * - compute rate, if possible, for that observation interval
3197 * - start a new observation interval with this dispatch
3198 */
3199 if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC &&
3200 bfqd->rq_in_driver == 0)
3201 goto update_rate_and_reset;
3202
3203 /* Update sampling information */
3204 bfqd->peak_rate_samples++;
3205
3206 if ((bfqd->rq_in_driver > 0 ||
3207 now_ns - bfqd->last_completion < BFQ_MIN_TT)
3208 && !BFQ_RQ_SEEKY(bfqd, bfqd->last_position, rq))
3209 bfqd->sequential_samples++;
3210
3211 bfqd->tot_sectors_dispatched += blk_rq_sectors(rq);
3212
3213 /* Reset max observed rq size every 32 dispatches */
3214 if (likely(bfqd->peak_rate_samples % 32))
3215 bfqd->last_rq_max_size =
3216 max_t(u32, blk_rq_sectors(rq), bfqd->last_rq_max_size);
3217 else
3218 bfqd->last_rq_max_size = blk_rq_sectors(rq);
3219
3220 bfqd->delta_from_first = now_ns - bfqd->first_dispatch;
3221
3222 /* Target observation interval not yet reached, go on sampling */
3223 if (bfqd->delta_from_first < BFQ_RATE_REF_INTERVAL)
3224 goto update_last_values;
3225
3226 update_rate_and_reset:
3227 bfq_update_rate_reset(bfqd, rq);
3228 update_last_values:
3229 bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
3230 if (RQ_BFQQ(rq) == bfqd->in_service_queue)
3231 bfqd->in_serv_last_pos = bfqd->last_position;
3232 bfqd->last_dispatch = now_ns;
3233 }
3234
3235 /*
3236 * Remove request from internal lists.
3237 */
3238 static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
3239 {
3240 struct bfq_queue *bfqq = RQ_BFQQ(rq);
3241
3242 /*
3243 * For consistency, the next instruction should have been
3244 * executed after removing the request from the queue and
3245 * dispatching it. We execute instead this instruction before
3246 * bfq_remove_request() (and hence introduce a temporary
3247 * inconsistency), for efficiency. In fact, should this
3248 * dispatch occur for a non in-service bfqq, this anticipated
3249 * increment prevents two counters related to bfqq->dispatched
3250 * from risking to be, first, uselessly decremented, and then
3251 * incremented again when the (new) value of bfqq->dispatched
3252 * happens to be taken into account.
3253 */
3254 bfqq->dispatched++;
3255 bfq_update_peak_rate(q->elevator->elevator_data, rq);
3256
3257 bfq_remove_request(q, rq);
3258 }
3259
3260 /*
3261 * There is a case where idling does not have to be performed for
3262 * throughput concerns, but to preserve the throughput share of
3263 * the process associated with bfqq.
3264 *
3265 * To introduce this case, we can note that allowing the drive
3266 * to enqueue more than one request at a time, and hence
3267 * delegating de facto final scheduling decisions to the
3268 * drive's internal scheduler, entails loss of control on the
3269 * actual request service order. In particular, the critical
3270 * situation is when requests from different processes happen
3271 * to be present, at the same time, in the internal queue(s)
3272 * of the drive. In such a situation, the drive, by deciding
3273 * the service order of the internally-queued requests, does
3274 * determine also the actual throughput distribution among
3275 * these processes. But the drive typically has no notion or
3276 * concern about per-process throughput distribution, and
3277 * makes its decisions only on a per-request basis. Therefore,
3278 * the service distribution enforced by the drive's internal
3279 * scheduler is likely to coincide with the desired throughput
3280 * distribution only in a completely symmetric, or favorably
3281 * skewed scenario where:
3282 * (i-a) each of these processes must get the same throughput as
3283 * the others,
3284 * (i-b) in case (i-a) does not hold, it holds that the process
3285 * associated with bfqq must receive a lower or equal
3286 * throughput than any of the other processes;
3287 * (ii) the I/O of each process has the same properties, in
3288 * terms of locality (sequential or random), direction
3289 * (reads or writes), request sizes, greediness
3290 * (from I/O-bound to sporadic), and so on;
3291
3292 * In fact, in such a scenario, the drive tends to treat the requests
3293 * of each process in about the same way as the requests of the
3294 * others, and thus to provide each of these processes with about the
3295 * same throughput. This is exactly the desired throughput
3296 * distribution if (i-a) holds, or, if (i-b) holds instead, this is an
3297 * even more convenient distribution for (the process associated with)
3298 * bfqq.
3299 *
3300 * In contrast, in any asymmetric or unfavorable scenario, device
3301 * idling (I/O-dispatch plugging) is certainly needed to guarantee
3302 * that bfqq receives its assigned fraction of the device throughput
3303 * (see [1] for details).
3304 *
3305 * The problem is that idling may significantly reduce throughput with
3306 * certain combinations of types of I/O and devices. An important
3307 * example is sync random I/O on flash storage with command
3308 * queueing. So, unless bfqq falls in cases where idling also boosts
3309 * throughput, it is important to check conditions (i-a), i(-b) and
3310 * (ii) accurately, so as to avoid idling when not strictly needed for
3311 * service guarantees.
3312 *
3313 * Unfortunately, it is extremely difficult to thoroughly check
3314 * condition (ii). And, in case there are active groups, it becomes
3315 * very difficult to check conditions (i-a) and (i-b) too. In fact,
3316 * if there are active groups, then, for conditions (i-a) or (i-b) to
3317 * become false 'indirectly', it is enough that an active group
3318 * contains more active processes or sub-groups than some other active
3319 * group. More precisely, for conditions (i-a) or (i-b) to become
3320 * false because of such a group, it is not even necessary that the
3321 * group is (still) active: it is sufficient that, even if the group
3322 * has become inactive, some of its descendant processes still have
3323 * some request already dispatched but still waiting for
3324 * completion. In fact, requests have still to be guaranteed their
3325 * share of the throughput even after being dispatched. In this
3326 * respect, it is easy to show that, if a group frequently becomes
3327 * inactive while still having in-flight requests, and if, when this
3328 * happens, the group is not considered in the calculation of whether
3329 * the scenario is asymmetric, then the group may fail to be
3330 * guaranteed its fair share of the throughput (basically because
3331 * idling may not be performed for the descendant processes of the
3332 * group, but it had to be). We address this issue with the following
3333 * bi-modal behavior, implemented in the function
3334 * bfq_asymmetric_scenario().
3335 *
3336 * If there are groups with requests waiting for completion
3337 * (as commented above, some of these groups may even be
3338 * already inactive), then the scenario is tagged as
3339 * asymmetric, conservatively, without checking any of the
3340 * conditions (i-a), (i-b) or (ii). So the device is idled for bfqq.
3341 * This behavior matches also the fact that groups are created
3342 * exactly if controlling I/O is a primary concern (to
3343 * preserve bandwidth and latency guarantees).
3344 *
3345 * On the opposite end, if there are no groups with requests waiting
3346 * for completion, then only conditions (i-a) and (i-b) are actually
3347 * controlled, i.e., provided that conditions (i-a) or (i-b) holds,
3348 * idling is not performed, regardless of whether condition (ii)
3349 * holds. In other words, only if conditions (i-a) and (i-b) do not
3350 * hold, then idling is allowed, and the device tends to be prevented
3351 * from queueing many requests, possibly of several processes. Since
3352 * there are no groups with requests waiting for completion, then, to
3353 * control conditions (i-a) and (i-b) it is enough to check just
3354 * whether all the queues with requests waiting for completion also
3355 * have the same weight.
3356 *
3357 * Not checking condition (ii) evidently exposes bfqq to the
3358 * risk of getting less throughput than its fair share.
3359 * However, for queues with the same weight, a further
3360 * mechanism, preemption, mitigates or even eliminates this
3361 * problem. And it does so without consequences on overall
3362 * throughput. This mechanism and its benefits are explained
3363 * in the next three paragraphs.
3364 *
3365 * Even if a queue, say Q, is expired when it remains idle, Q
3366 * can still preempt the new in-service queue if the next
3367 * request of Q arrives soon (see the comments on
3368 * bfq_bfqq_update_budg_for_activation). If all queues and
3369 * groups have the same weight, this form of preemption,
3370 * combined with the hole-recovery heuristic described in the
3371 * comments on function bfq_bfqq_update_budg_for_activation,
3372 * are enough to preserve a correct bandwidth distribution in
3373 * the mid term, even without idling. In fact, even if not
3374 * idling allows the internal queues of the device to contain
3375 * many requests, and thus to reorder requests, we can rather
3376 * safely assume that the internal scheduler still preserves a
3377 * minimum of mid-term fairness.
3378 *
3379 * More precisely, this preemption-based, idleless approach
3380 * provides fairness in terms of IOPS, and not sectors per
3381 * second. This can be seen with a simple example. Suppose
3382 * that there are two queues with the same weight, but that
3383 * the first queue receives requests of 8 sectors, while the
3384 * second queue receives requests of 1024 sectors. In
3385 * addition, suppose that each of the two queues contains at
3386 * most one request at a time, which implies that each queue
3387 * always remains idle after it is served. Finally, after
3388 * remaining idle, each queue receives very quickly a new
3389 * request. It follows that the two queues are served
3390 * alternatively, preempting each other if needed. This
3391 * implies that, although both queues have the same weight,
3392 * the queue with large requests receives a service that is
3393 * 1024/8 times as high as the service received by the other
3394 * queue.
3395 *
3396 * The motivation for using preemption instead of idling (for
3397 * queues with the same weight) is that, by not idling,
3398 * service guarantees are preserved (completely or at least in
3399 * part) without minimally sacrificing throughput. And, if
3400 * there is no active group, then the primary expectation for
3401 * this device is probably a high throughput.
3402 *
3403 * We are now left only with explaining the two sub-conditions in the
3404 * additional compound condition that is checked below for deciding
3405 * whether the scenario is asymmetric. To explain the first
3406 * sub-condition, we need to add that the function
3407 * bfq_asymmetric_scenario checks the weights of only
3408 * non-weight-raised queues, for efficiency reasons (see comments on
3409 * bfq_weights_tree_add()). Then the fact that bfqq is weight-raised
3410 * is checked explicitly here. More precisely, the compound condition
3411 * below takes into account also the fact that, even if bfqq is being
3412 * weight-raised, the scenario is still symmetric if all queues with
3413 * requests waiting for completion happen to be
3414 * weight-raised. Actually, we should be even more precise here, and
3415 * differentiate between interactive weight raising and soft real-time
3416 * weight raising.
3417 *
3418 * The second sub-condition checked in the compound condition is
3419 * whether there is a fair amount of already in-flight I/O not
3420 * belonging to bfqq. If so, I/O dispatching is to be plugged, for the
3421 * following reason. The drive may decide to serve in-flight
3422 * non-bfqq's I/O requests before bfqq's ones, thereby delaying the
3423 * arrival of new I/O requests for bfqq (recall that bfqq is sync). If
3424 * I/O-dispatching is not plugged, then, while bfqq remains empty, a
3425 * basically uncontrolled amount of I/O from other queues may be
3426 * dispatched too, possibly causing the service of bfqq's I/O to be
3427 * delayed even longer in the drive. This problem gets more and more
3428 * serious as the speed and the queue depth of the drive grow,
3429 * because, as these two quantities grow, the probability to find no
3430 * queue busy but many requests in flight grows too. By contrast,
3431 * plugging I/O dispatching minimizes the delay induced by already
3432 * in-flight I/O, and enables bfqq to recover the bandwidth it may
3433 * lose because of this delay.
3434 *
3435 * As a side note, it is worth considering that the above
3436 * device-idling countermeasures may however fail in the following
3437 * unlucky scenario: if I/O-dispatch plugging is (correctly) disabled
3438 * in a time period during which all symmetry sub-conditions hold, and
3439 * therefore the device is allowed to enqueue many requests, but at
3440 * some later point in time some sub-condition stops to hold, then it
3441 * may become impossible to make requests be served in the desired
3442 * order until all the requests already queued in the device have been
3443 * served. The last sub-condition commented above somewhat mitigates
3444 * this problem for weight-raised queues.
3445 */
3446 static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd,
3447 struct bfq_queue *bfqq)
3448 {
3449 /* No point in idling for bfqq if it won't get requests any longer */
3450 if (unlikely(!bfqq_process_refs(bfqq)))
3451 return false;
3452
3453 return (bfqq->wr_coeff > 1 &&
3454 (bfqd->wr_busy_queues <
3455 bfq_tot_busy_queues(bfqd) ||
3456 bfqd->rq_in_driver >=
3457 bfqq->dispatched + 4)) ||
3458 bfq_asymmetric_scenario(bfqd, bfqq);
3459 }
3460
3461 static bool __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
3462 enum bfqq_expiration reason)
3463 {
3464 /*
3465 * If this bfqq is shared between multiple processes, check
3466 * to make sure that those processes are still issuing I/Os
3467 * within the mean seek distance. If not, it may be time to
3468 * break the queues apart again.
3469 */
3470 if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq))
3471 bfq_mark_bfqq_split_coop(bfqq);
3472
3473 /*
3474 * Consider queues with a higher finish virtual time than
3475 * bfqq. If idling_needed_for_service_guarantees(bfqq) returns
3476 * true, then bfqq's bandwidth would be violated if an
3477 * uncontrolled amount of I/O from these queues were
3478 * dispatched while bfqq is waiting for its new I/O to
3479 * arrive. This is exactly what may happen if this is a forced
3480 * expiration caused by a preemption attempt, and if bfqq is
3481 * not re-scheduled. To prevent this from happening, re-queue
3482 * bfqq if it needs I/O-dispatch plugging, even if it is
3483 * empty. By doing so, bfqq is granted to be served before the
3484 * above queues (provided that bfqq is of course eligible).
3485 */
3486 if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
3487 !(reason == BFQQE_PREEMPTED &&
3488 idling_needed_for_service_guarantees(bfqd, bfqq))) {
3489 if (bfqq->dispatched == 0)
3490 /*
3491 * Overloading budget_timeout field to store
3492 * the time at which the queue remains with no
3493 * backlog and no outstanding request; used by
3494 * the weight-raising mechanism.
3495 */
3496 bfqq->budget_timeout = jiffies;
3497
3498 bfq_del_bfqq_busy(bfqd, bfqq, true);
3499 } else {
3500 bfq_requeue_bfqq(bfqd, bfqq, true);
3501 /*
3502 * Resort priority tree of potential close cooperators.
3503 * See comments on bfq_pos_tree_add_move() for the unlikely().
3504 */
3505 if (unlikely(!bfqd->nonrot_with_queueing &&
3506 !RB_EMPTY_ROOT(&bfqq->sort_list)))
3507 bfq_pos_tree_add_move(bfqd, bfqq);
3508 }
3509
3510 /*
3511 * All in-service entities must have been properly deactivated
3512 * or requeued before executing the next function, which
3513 * resets all in-service entities as no more in service. This
3514 * may cause bfqq to be freed. If this happens, the next
3515 * function returns true.
3516 */
3517 return __bfq_bfqd_reset_in_service(bfqd);
3518 }
3519
3520 /**
3521 * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior.
3522 * @bfqd: device data.
3523 * @bfqq: queue to update.
3524 * @reason: reason for expiration.
3525 *
3526 * Handle the feedback on @bfqq budget at queue expiration.
3527 * See the body for detailed comments.
3528 */
3529 static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
3530 struct bfq_queue *bfqq,
3531 enum bfqq_expiration reason)
3532 {
3533 struct request *next_rq;
3534 int budget, min_budget;
3535
3536 min_budget = bfq_min_budget(bfqd);
3537
3538 if (bfqq->wr_coeff == 1)
3539 budget = bfqq->max_budget;
3540 else /*
3541 * Use a constant, low budget for weight-raised queues,
3542 * to help achieve a low latency. Keep it slightly higher
3543 * than the minimum possible budget, to cause a little
3544 * bit fewer expirations.
3545 */
3546 budget = 2 * min_budget;
3547
3548 bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %d, budg left %d",
3549 bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
3550 bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %d, min budg %d",
3551 budget, bfq_min_budget(bfqd));
3552 bfq_log_bfqq(bfqd, bfqq, "recalc_budg: sync %d, seeky %d",
3553 bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue));
3554
3555 if (bfq_bfqq_sync(bfqq) && bfqq->wr_coeff == 1) {
3556 switch (reason) {
3557 /*
3558 * Caveat: in all the following cases we trade latency
3559 * for throughput.
3560 */
3561 case BFQQE_TOO_IDLE:
3562 /*
3563 * This is the only case where we may reduce
3564 * the budget: if there is no request of the
3565 * process still waiting for completion, then
3566 * we assume (tentatively) that the timer has
3567 * expired because the batch of requests of
3568 * the process could have been served with a
3569 * smaller budget. Hence, betting that
3570 * process will behave in the same way when it
3571 * becomes backlogged again, we reduce its
3572 * next budget. As long as we guess right,
3573 * this budget cut reduces the latency
3574 * experienced by the process.
3575 *
3576 * However, if there are still outstanding
3577 * requests, then the process may have not yet
3578 * issued its next request just because it is
3579 * still waiting for the completion of some of
3580 * the still outstanding ones. So in this
3581 * subcase we do not reduce its budget, on the
3582 * contrary we increase it to possibly boost
3583 * the throughput, as discussed in the
3584 * comments to the BUDGET_TIMEOUT case.
3585 */
3586 if (bfqq->dispatched > 0) /* still outstanding reqs */
3587 budget = min(budget * 2, bfqd->bfq_max_budget);
3588 else {
3589 if (budget > 5 * min_budget)
3590 budget -= 4 * min_budget;
3591 else
3592 budget = min_budget;
3593 }
3594 break;
3595 case BFQQE_BUDGET_TIMEOUT:
3596 /*
3597 * We double the budget here because it gives
3598 * the chance to boost the throughput if this
3599 * is not a seeky process (and has bumped into
3600 * this timeout because of, e.g., ZBR).
3601 */
3602 budget = min(budget * 2, bfqd->bfq_max_budget);
3603 break;
3604 case BFQQE_BUDGET_EXHAUSTED:
3605 /*
3606 * The process still has backlog, and did not
3607 * let either the budget timeout or the disk
3608 * idling timeout expire. Hence it is not
3609 * seeky, has a short thinktime and may be
3610 * happy with a higher budget too. So
3611 * definitely increase the budget of this good
3612 * candidate to boost the disk throughput.
3613 */
3614 budget = min(budget * 4, bfqd->bfq_max_budget);
3615 break;
3616 case BFQQE_NO_MORE_REQUESTS:
3617 /*
3618 * For queues that expire for this reason, it
3619 * is particularly important to keep the
3620 * budget close to the actual service they
3621 * need. Doing so reduces the timestamp
3622 * misalignment problem described in the
3623 * comments in the body of
3624 * __bfq_activate_entity. In fact, suppose
3625 * that a queue systematically expires for
3626 * BFQQE_NO_MORE_REQUESTS and presents a
3627 * new request in time to enjoy timestamp
3628 * back-shifting. The larger the budget of the
3629 * queue is with respect to the service the
3630 * queue actually requests in each service
3631 * slot, the more times the queue can be
3632 * reactivated with the same virtual finish
3633 * time. It follows that, even if this finish
3634 * time is pushed to the system virtual time
3635 * to reduce the consequent timestamp
3636 * misalignment, the queue unjustly enjoys for
3637 * many re-activations a lower finish time
3638 * than all newly activated queues.
3639 *
3640 * The service needed by bfqq is measured
3641 * quite precisely by bfqq->entity.service.
3642 * Since bfqq does not enjoy device idling,
3643 * bfqq->entity.service is equal to the number
3644 * of sectors that the process associated with
3645 * bfqq requested to read/write before waiting
3646 * for request completions, or blocking for
3647 * other reasons.
3648 */
3649 budget = max_t(int, bfqq->entity.service, min_budget);
3650 break;
3651 default:
3652 return;
3653 }
3654 } else if (!bfq_bfqq_sync(bfqq)) {
3655 /*
3656 * Async queues get always the maximum possible
3657 * budget, as for them we do not care about latency
3658 * (in addition, their ability to dispatch is limited
3659 * by the charging factor).
3660 */
3661 budget = bfqd->bfq_max_budget;
3662 }
3663
3664 bfqq->max_budget = budget;
3665
3666 if (bfqd->budgets_assigned >= bfq_stats_min_budgets &&
3667 !bfqd->bfq_user_max_budget)
3668 bfqq->max_budget = min(bfqq->max_budget, bfqd->bfq_max_budget);
3669
3670 /*
3671 * If there is still backlog, then assign a new budget, making
3672 * sure that it is large enough for the next request. Since
3673 * the finish time of bfqq must be kept in sync with the
3674 * budget, be sure to call __bfq_bfqq_expire() *after* this
3675 * update.
3676 *
3677 * If there is no backlog, then no need to update the budget;
3678 * it will be updated on the arrival of a new request.
3679 */
3680 next_rq = bfqq->next_rq;
3681 if (next_rq)
3682 bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
3683 bfq_serv_to_charge(next_rq, bfqq));
3684
3685 bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d",
3686 next_rq ? blk_rq_sectors(next_rq) : 0,
3687 bfqq->entity.budget);
3688 }
3689
3690 /*
3691 * Return true if the process associated with bfqq is "slow". The slow
3692 * flag is used, in addition to the budget timeout, to reduce the
3693 * amount of service provided to seeky processes, and thus reduce
3694 * their chances to lower the throughput. More details in the comments
3695 * on the function bfq_bfqq_expire().
3696 *
3697 * An important observation is in order: as discussed in the comments
3698 * on the function bfq_update_peak_rate(), with devices with internal
3699 * queues, it is hard if ever possible to know when and for how long
3700 * an I/O request is processed by the device (apart from the trivial
3701 * I/O pattern where a new request is dispatched only after the
3702 * previous one has been completed). This makes it hard to evaluate
3703 * the real rate at which the I/O requests of each bfq_queue are
3704 * served. In fact, for an I/O scheduler like BFQ, serving a
3705 * bfq_queue means just dispatching its requests during its service
3706 * slot (i.e., until the budget of the queue is exhausted, or the
3707 * queue remains idle, or, finally, a timeout fires). But, during the
3708 * service slot of a bfq_queue, around 100 ms at most, the device may
3709 * be even still processing requests of bfq_queues served in previous
3710 * service slots. On the opposite end, the requests of the in-service
3711 * bfq_queue may be completed after the service slot of the queue
3712 * finishes.
3713 *
3714 * Anyway, unless more sophisticated solutions are used
3715 * (where possible), the sum of the sizes of the requests dispatched
3716 * during the service slot of a bfq_queue is probably the only
3717 * approximation available for the service received by the bfq_queue
3718 * during its service slot. And this sum is the quantity used in this
3719 * function to evaluate the I/O speed of a process.
3720 */
3721 static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
3722 bool compensate, enum bfqq_expiration reason,
3723 unsigned long *delta_ms)
3724 {
3725 ktime_t delta_ktime;
3726 u32 delta_usecs;
3727 bool slow = BFQQ_SEEKY(bfqq); /* if delta too short, use seekyness */
3728
3729 if (!bfq_bfqq_sync(bfqq))
3730 return false;
3731
3732 if (compensate)
3733 delta_ktime = bfqd->last_idling_start;
3734 else
3735 delta_ktime = ktime_get();
3736 delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start);
3737 delta_usecs = ktime_to_us(delta_ktime);
3738
3739 /* don't use too short time intervals */
3740 if (delta_usecs < 1000) {
3741 if (blk_queue_nonrot(bfqd->queue))
3742 /*
3743 * give same worst-case guarantees as idling
3744 * for seeky
3745 */
3746 *delta_ms = BFQ_MIN_TT / NSEC_PER_MSEC;
3747 else /* charge at least one seek */
3748 *delta_ms = bfq_slice_idle / NSEC_PER_MSEC;
3749
3750 return slow;
3751 }
3752
3753 *delta_ms = delta_usecs / USEC_PER_MSEC;
3754
3755 /*
3756 * Use only long (> 20ms) intervals to filter out excessive
3757 * spikes in service rate estimation.
3758 */
3759 if (delta_usecs > 20000) {
3760 /*
3761 * Caveat for rotational devices: processes doing I/O
3762 * in the slower disk zones tend to be slow(er) even
3763 * if not seeky. In this respect, the estimated peak
3764 * rate is likely to be an average over the disk
3765 * surface. Accordingly, to not be too harsh with
3766 * unlucky processes, a process is deemed slow only if
3767 * its rate has been lower than half of the estimated
3768 * peak rate.
3769 */
3770 slow = bfqq->entity.service < bfqd->bfq_max_budget / 2;
3771 }
3772
3773 bfq_log_bfqq(bfqd, bfqq, "bfq_bfqq_is_slow: slow %d", slow);
3774
3775 return slow;
3776 }
3777
3778 /*
3779 * To be deemed as soft real-time, an application must meet two
3780 * requirements. First, the application must not require an average
3781 * bandwidth higher than the approximate bandwidth required to playback or
3782 * record a compressed high-definition video.
3783 * The next function is invoked on the completion of the last request of a
3784 * batch, to compute the next-start time instant, soft_rt_next_start, such
3785 * that, if the next request of the application does not arrive before
3786 * soft_rt_next_start, then the above requirement on the bandwidth is met.
3787 *
3788 * The second requirement is that the request pattern of the application is
3789 * isochronous, i.e., that, after issuing a request or a batch of requests,
3790 * the application stops issuing new requests until all its pending requests
3791 * have been completed. After that, the application may issue a new batch,
3792 * and so on.
3793 * For this reason the next function is invoked to compute
3794 * soft_rt_next_start only for applications that meet this requirement,
3795 * whereas soft_rt_next_start is set to infinity for applications that do
3796 * not.
3797 *
3798 * Unfortunately, even a greedy (i.e., I/O-bound) application may
3799 * happen to meet, occasionally or systematically, both the above
3800 * bandwidth and isochrony requirements. This may happen at least in
3801 * the following circumstances. First, if the CPU load is high. The
3802 * application may stop issuing requests while the CPUs are busy
3803 * serving other processes, then restart, then stop again for a while,
3804 * and so on. The other circumstances are related to the storage
3805 * device: the storage device is highly loaded or reaches a low-enough
3806 * throughput with the I/O of the application (e.g., because the I/O
3807 * is random and/or the device is slow). In all these cases, the
3808 * I/O of the application may be simply slowed down enough to meet
3809 * the bandwidth and isochrony requirements. To reduce the probability
3810 * that greedy applications are deemed as soft real-time in these
3811 * corner cases, a further rule is used in the computation of
3812 * soft_rt_next_start: the return value of this function is forced to
3813 * be higher than the maximum between the following two quantities.
3814 *
3815 * (a) Current time plus: (1) the maximum time for which the arrival
3816 * of a request is waited for when a sync queue becomes idle,
3817 * namely bfqd->bfq_slice_idle, and (2) a few extra jiffies. We
3818 * postpone for a moment the reason for adding a few extra
3819 * jiffies; we get back to it after next item (b). Lower-bounding
3820 * the return value of this function with the current time plus
3821 * bfqd->bfq_slice_idle tends to filter out greedy applications,
3822 * because the latter issue their next request as soon as possible
3823 * after the last one has been completed. In contrast, a soft
3824 * real-time application spends some time processing data, after a
3825 * batch of its requests has been completed.
3826 *
3827 * (b) Current value of bfqq->soft_rt_next_start. As pointed out
3828 * above, greedy applications may happen to meet both the
3829 * bandwidth and isochrony requirements under heavy CPU or
3830 * storage-device load. In more detail, in these scenarios, these
3831 * applications happen, only for limited time periods, to do I/O
3832 * slowly enough to meet all the requirements described so far,
3833 * including the filtering in above item (a). These slow-speed
3834 * time intervals are usually interspersed between other time
3835 * intervals during which these applications do I/O at a very high
3836 * speed. Fortunately, exactly because of the high speed of the
3837 * I/O in the high-speed intervals, the values returned by this
3838 * function happen to be so high, near the end of any such
3839 * high-speed interval, to be likely to fall *after* the end of
3840 * the low-speed time interval that follows. These high values are
3841 * stored in bfqq->soft_rt_next_start after each invocation of
3842 * this function. As a consequence, if the last value of
3843 * bfqq->soft_rt_next_start is constantly used to lower-bound the
3844 * next value that this function may return, then, from the very
3845 * beginning of a low-speed interval, bfqq->soft_rt_next_start is
3846 * likely to be constantly kept so high that any I/O request
3847 * issued during the low-speed interval is considered as arriving
3848 * to soon for the application to be deemed as soft
3849 * real-time. Then, in the high-speed interval that follows, the
3850 * application will not be deemed as soft real-time, just because
3851 * it will do I/O at a high speed. And so on.
3852 *
3853 * Getting back to the filtering in item (a), in the following two
3854 * cases this filtering might be easily passed by a greedy
3855 * application, if the reference quantity was just
3856 * bfqd->bfq_slice_idle:
3857 * 1) HZ is so low that the duration of a jiffy is comparable to or
3858 * higher than bfqd->bfq_slice_idle. This happens, e.g., on slow
3859 * devices with HZ=100. The time granularity may be so coarse
3860 * that the approximation, in jiffies, of bfqd->bfq_slice_idle
3861 * is rather lower than the exact value.
3862 * 2) jiffies, instead of increasing at a constant rate, may stop increasing
3863 * for a while, then suddenly 'jump' by several units to recover the lost
3864 * increments. This seems to happen, e.g., inside virtual machines.
3865 * To address this issue, in the filtering in (a) we do not use as a
3866 * reference time interval just bfqd->bfq_slice_idle, but
3867 * bfqd->bfq_slice_idle plus a few jiffies. In particular, we add the
3868 * minimum number of jiffies for which the filter seems to be quite
3869 * precise also in embedded systems and KVM/QEMU virtual machines.
3870 */
3871 static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
3872 struct bfq_queue *bfqq)
3873 {
3874 return max3(bfqq->soft_rt_next_start,
3875 bfqq->last_idle_bklogged +
3876 HZ * bfqq->service_from_backlogged /
3877 bfqd->bfq_wr_max_softrt_rate,
3878 jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
3879 }
3880
3881 /**
3882 * bfq_bfqq_expire - expire a queue.
3883 * @bfqd: device owning the queue.
3884 * @bfqq: the queue to expire.
3885 * @compensate: if true, compensate for the time spent idling.
3886 * @reason: the reason causing the expiration.
3887 *
3888 * If the process associated with bfqq does slow I/O (e.g., because it
3889 * issues random requests), we charge bfqq with the time it has been
3890 * in service instead of the service it has received (see
3891 * bfq_bfqq_charge_time for details on how this goal is achieved). As
3892 * a consequence, bfqq will typically get higher timestamps upon
3893 * reactivation, and hence it will be rescheduled as if it had
3894 * received more service than what it has actually received. In the
3895 * end, bfqq receives less service in proportion to how slowly its
3896 * associated process consumes its budgets (and hence how seriously it
3897 * tends to lower the throughput). In addition, this time-charging
3898 * strategy guarantees time fairness among slow processes. In
3899 * contrast, if the process associated with bfqq is not slow, we
3900 * charge bfqq exactly with the service it has received.
3901 *
3902 * Charging time to the first type of queues and the exact service to
3903 * the other has the effect of using the WF2Q+ policy to schedule the
3904 * former on a timeslice basis, without violating service domain
3905 * guarantees among the latter.
3906 */
3907 void bfq_bfqq_expire(struct bfq_data *bfqd,
3908 struct bfq_queue *bfqq,
3909 bool compensate,
3910 enum bfqq_expiration reason)
3911 {
3912 bool slow;
3913 unsigned long delta = 0;
3914 struct bfq_entity *entity = &bfqq->entity;
3915
3916 /*
3917 * Check whether the process is slow (see bfq_bfqq_is_slow).
3918 */
3919 slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta);
3920
3921 /*
3922 * As above explained, charge slow (typically seeky) and
3923 * timed-out queues with the time and not the service
3924 * received, to favor sequential workloads.
3925 *
3926 * Processes doing I/O in the slower disk zones will tend to
3927 * be slow(er) even if not seeky. Therefore, since the
3928 * estimated peak rate is actually an average over the disk
3929 * surface, these processes may timeout just for bad luck. To
3930 * avoid punishing them, do not charge time to processes that
3931 * succeeded in consuming at least 2/3 of their budget. This
3932 * allows BFQ to preserve enough elasticity to still perform
3933 * bandwidth, and not time, distribution with little unlucky
3934 * or quasi-sequential processes.
3935 */
3936 if (bfqq->wr_coeff == 1 &&
3937 (slow ||
3938 (reason == BFQQE_BUDGET_TIMEOUT &&
3939 bfq_bfqq_budget_left(bfqq) >= entity->budget / 3)))
3940 bfq_bfqq_charge_time(bfqd, bfqq, delta);
3941
3942 if (reason == BFQQE_TOO_IDLE &&
3943 entity->service <= 2 * entity->budget / 10)
3944 bfq_clear_bfqq_IO_bound(bfqq);
3945
3946 if (bfqd->low_latency && bfqq->wr_coeff == 1)
3947 bfqq->last_wr_start_finish = jiffies;
3948
3949 if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 &&
3950 RB_EMPTY_ROOT(&bfqq->sort_list)) {
3951 /*
3952 * If we get here, and there are no outstanding
3953 * requests, then the request pattern is isochronous
3954 * (see the comments on the function
3955 * bfq_bfqq_softrt_next_start()). Thus we can compute
3956 * soft_rt_next_start. And we do it, unless bfqq is in
3957 * interactive weight raising. We do not do it in the
3958 * latter subcase, for the following reason. bfqq may
3959 * be conveying the I/O needed to load a soft
3960 * real-time application. Such an application will
3961 * actually exhibit a soft real-time I/O pattern after
3962 * it finally starts doing its job. But, if
3963 * soft_rt_next_start is computed here for an
3964 * interactive bfqq, and bfqq had received a lot of
3965 * service before remaining with no outstanding
3966 * request (likely to happen on a fast device), then
3967 * soft_rt_next_start would be assigned such a high
3968 * value that, for a very long time, bfqq would be
3969 * prevented from being possibly considered as soft
3970 * real time.
3971 *
3972 * If, instead, the queue still has outstanding
3973 * requests, then we have to wait for the completion
3974 * of all the outstanding requests to discover whether
3975 * the request pattern is actually isochronous.
3976 */
3977 if (bfqq->dispatched == 0 &&
3978 bfqq->wr_coeff != bfqd->bfq_wr_coeff)
3979 bfqq->soft_rt_next_start =
3980 bfq_bfqq_softrt_next_start(bfqd, bfqq);
3981 else if (bfqq->dispatched > 0) {
3982 /*
3983 * Schedule an update of soft_rt_next_start to when
3984 * the task may be discovered to be isochronous.
3985 */
3986 bfq_mark_bfqq_softrt_update(bfqq);
3987 }
3988 }
3989
3990 bfq_log_bfqq(bfqd, bfqq,
3991 "expire (%d, slow %d, num_disp %d, short_ttime %d)", reason,
3992 slow, bfqq->dispatched, bfq_bfqq_has_short_ttime(bfqq));
3993
3994 /*
3995 * bfqq expired, so no total service time needs to be computed
3996 * any longer: reset state machine for measuring total service
3997 * times.
3998 */
3999 bfqd->rqs_injected = bfqd->wait_dispatch = false;
4000 bfqd->waited_rq = NULL;
4001
4002 /*
4003 * Increase, decrease or leave budget unchanged according to
4004 * reason.
4005 */
4006 __bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
4007 if (__bfq_bfqq_expire(bfqd, bfqq, reason))
4008 /* bfqq is gone, no more actions on it */
4009 return;
4010
4011 /* mark bfqq as waiting a request only if a bic still points to it */
4012 if (!bfq_bfqq_busy(bfqq) &&
4013 reason != BFQQE_BUDGET_TIMEOUT &&
4014 reason != BFQQE_BUDGET_EXHAUSTED) {
4015 bfq_mark_bfqq_non_blocking_wait_rq(bfqq);
4016 /*
4017 * Not setting service to 0, because, if the next rq
4018 * arrives in time, the queue will go on receiving
4019 * service with this same budget (as if it never expired)
4020 */
4021 } else
4022 entity->service = 0;
4023
4024 /*
4025 * Reset the received-service counter for every parent entity.
4026 * Differently from what happens with bfqq->entity.service,
4027 * the resetting of this counter never needs to be postponed
4028 * for parent entities. In fact, in case bfqq may have a
4029 * chance to go on being served using the last, partially
4030 * consumed budget, bfqq->entity.service needs to be kept,
4031 * because if bfqq then actually goes on being served using
4032 * the same budget, the last value of bfqq->entity.service is
4033 * needed to properly decrement bfqq->entity.budget by the
4034 * portion already consumed. In contrast, it is not necessary
4035 * to keep entity->service for parent entities too, because
4036 * the bubble up of the new value of bfqq->entity.budget will
4037 * make sure that the budgets of parent entities are correct,
4038 * even in case bfqq and thus parent entities go on receiving
4039 * service with the same budget.
4040 */
4041 entity = entity->parent;
4042 for_each_entity(entity)
4043 entity->service = 0;
4044 }
4045
4046 /*
4047 * Budget timeout is not implemented through a dedicated timer, but
4048 * just checked on request arrivals and completions, as well as on
4049 * idle timer expirations.
4050 */
4051 static bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq)
4052 {
4053 return time_is_before_eq_jiffies(bfqq->budget_timeout);
4054 }
4055
4056 /*
4057 * If we expire a queue that is actively waiting (i.e., with the
4058 * device idled) for the arrival of a new request, then we may incur
4059 * the timestamp misalignment problem described in the body of the
4060 * function __bfq_activate_entity. Hence we return true only if this
4061 * condition does not hold, or if the queue is slow enough to deserve
4062 * only to be kicked off for preserving a high throughput.
4063 */
4064 static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
4065 {
4066 bfq_log_bfqq(bfqq->bfqd, bfqq,
4067 "may_budget_timeout: wait_request %d left %d timeout %d",
4068 bfq_bfqq_wait_request(bfqq),
4069 bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3,
4070 bfq_bfqq_budget_timeout(bfqq));
4071
4072 return (!bfq_bfqq_wait_request(bfqq) ||
4073 bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3)
4074 &&
4075 bfq_bfqq_budget_timeout(bfqq);
4076 }
4077
4078 static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd,
4079 struct bfq_queue *bfqq)
4080 {
4081 bool rot_without_queueing =
4082 !blk_queue_nonrot(bfqd->queue) && !bfqd->hw_tag,
4083 bfqq_sequential_and_IO_bound,
4084 idling_boosts_thr;
4085
4086 /* No point in idling for bfqq if it won't get requests any longer */
4087 if (unlikely(!bfqq_process_refs(bfqq)))
4088 return false;
4089
4090 bfqq_sequential_and_IO_bound = !BFQQ_SEEKY(bfqq) &&
4091 bfq_bfqq_IO_bound(bfqq) && bfq_bfqq_has_short_ttime(bfqq);
4092
4093 /*
4094 * The next variable takes into account the cases where idling
4095 * boosts the throughput.
4096 *
4097 * The value of the variable is computed considering, first, that
4098 * idling is virtually always beneficial for the throughput if:
4099 * (a) the device is not NCQ-capable and rotational, or
4100 * (b) regardless of the presence of NCQ, the device is rotational and
4101 * the request pattern for bfqq is I/O-bound and sequential, or
4102 * (c) regardless of whether it is rotational, the device is
4103 * not NCQ-capable and the request pattern for bfqq is
4104 * I/O-bound and sequential.
4105 *
4106 * Secondly, and in contrast to the above item (b), idling an
4107 * NCQ-capable flash-based device would not boost the
4108 * throughput even with sequential I/O; rather it would lower
4109 * the throughput in proportion to how fast the device
4110 * is. Accordingly, the next variable is true if any of the
4111 * above conditions (a), (b) or (c) is true, and, in
4112 * particular, happens to be false if bfqd is an NCQ-capable
4113 * flash-based device.
4114 */
4115 idling_boosts_thr = rot_without_queueing ||
4116 ((!blk_queue_nonrot(bfqd->queue) || !bfqd->hw_tag) &&
4117 bfqq_sequential_and_IO_bound);
4118
4119 /*
4120 * The return value of this function is equal to that of
4121 * idling_boosts_thr, unless a special case holds. In this
4122 * special case, described below, idling may cause problems to
4123 * weight-raised queues.
4124 *
4125 * When the request pool is saturated (e.g., in the presence
4126 * of write hogs), if the processes associated with
4127 * non-weight-raised queues ask for requests at a lower rate,
4128 * then processes associated with weight-raised queues have a
4129 * higher probability to get a request from the pool
4130 * immediately (or at least soon) when they need one. Thus
4131 * they have a higher probability to actually get a fraction
4132 * of the device throughput proportional to their high
4133 * weight. This is especially true with NCQ-capable drives,
4134 * which enqueue several requests in advance, and further
4135 * reorder internally-queued requests.
4136 *
4137 * For this reason, we force to false the return value if
4138 * there are weight-raised busy queues. In this case, and if
4139 * bfqq is not weight-raised, this guarantees that the device
4140 * is not idled for bfqq (if, instead, bfqq is weight-raised,
4141 * then idling will be guaranteed by another variable, see
4142 * below). Combined with the timestamping rules of BFQ (see
4143 * [1] for details), this behavior causes bfqq, and hence any
4144 * sync non-weight-raised queue, to get a lower number of
4145 * requests served, and thus to ask for a lower number of
4146 * requests from the request pool, before the busy
4147 * weight-raised queues get served again. This often mitigates
4148 * starvation problems in the presence of heavy write
4149 * workloads and NCQ, thereby guaranteeing a higher
4150 * application and system responsiveness in these hostile
4151 * scenarios.
4152 */
4153 return idling_boosts_thr &&
4154 bfqd->wr_busy_queues == 0;
4155 }
4156
4157 /*
4158 * For a queue that becomes empty, device idling is allowed only if
4159 * this function returns true for that queue. As a consequence, since
4160 * device idling plays a critical role for both throughput boosting
4161 * and service guarantees, the return value of this function plays a
4162 * critical role as well.
4163 *
4164 * In a nutshell, this function returns true only if idling is
4165 * beneficial for throughput or, even if detrimental for throughput,
4166 * idling is however necessary to preserve service guarantees (low
4167 * latency, desired throughput distribution, ...). In particular, on
4168 * NCQ-capable devices, this function tries to return false, so as to
4169 * help keep the drives' internal queues full, whenever this helps the
4170 * device boost the throughput without causing any service-guarantee
4171 * issue.
4172 *
4173 * Most of the issues taken into account to get the return value of
4174 * this function are not trivial. We discuss these issues in the two
4175 * functions providing the main pieces of information needed by this
4176 * function.
4177 */
4178 static bool bfq_better_to_idle(struct bfq_queue *bfqq)
4179 {
4180 struct bfq_data *bfqd = bfqq->bfqd;
4181 bool idling_boosts_thr_with_no_issue, idling_needed_for_service_guar;
4182
4183 /* No point in idling for bfqq if it won't get requests any longer */
4184 if (unlikely(!bfqq_process_refs(bfqq)))
4185 return false;
4186
4187 if (unlikely(bfqd->strict_guarantees))
4188 return true;
4189
4190 /*
4191 * Idling is performed only if slice_idle > 0. In addition, we
4192 * do not idle if
4193 * (a) bfqq is async
4194 * (b) bfqq is in the idle io prio class: in this case we do
4195 * not idle because we want to minimize the bandwidth that
4196 * queues in this class can steal to higher-priority queues
4197 */
4198 if (bfqd->bfq_slice_idle == 0 || !bfq_bfqq_sync(bfqq) ||
4199 bfq_class_idle(bfqq))
4200 return false;
4201
4202 idling_boosts_thr_with_no_issue =
4203 idling_boosts_thr_without_issues(bfqd, bfqq);
4204
4205 idling_needed_for_service_guar =
4206 idling_needed_for_service_guarantees(bfqd, bfqq);
4207
4208 /*
4209 * We have now the two components we need to compute the
4210 * return value of the function, which is true only if idling
4211 * either boosts the throughput (without issues), or is
4212 * necessary to preserve service guarantees.
4213 */
4214 return idling_boosts_thr_with_no_issue ||
4215 idling_needed_for_service_guar;
4216 }
4217
4218 /*
4219 * If the in-service queue is empty but the function bfq_better_to_idle
4220 * returns true, then:
4221 * 1) the queue must remain in service and cannot be expired, and
4222 * 2) the device must be idled to wait for the possible arrival of a new
4223 * request for the queue.
4224 * See the comments on the function bfq_better_to_idle for the reasons
4225 * why performing device idling is the best choice to boost the throughput
4226 * and preserve service guarantees when bfq_better_to_idle itself
4227 * returns true.
4228 */
4229 static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
4230 {
4231 return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_better_to_idle(bfqq);
4232 }
4233
4234 /*
4235 * This function chooses the queue from which to pick the next extra
4236 * I/O request to inject, if it finds a compatible queue. See the
4237 * comments on bfq_update_inject_limit() for details on the injection
4238 * mechanism, and for the definitions of the quantities mentioned
4239 * below.
4240 */
4241 static struct bfq_queue *
4242 bfq_choose_bfqq_for_injection(struct bfq_data *bfqd)
4243 {
4244 struct bfq_queue *bfqq, *in_serv_bfqq = bfqd->in_service_queue;
4245 unsigned int limit = in_serv_bfqq->inject_limit;
4246 /*
4247 * If
4248 * - bfqq is not weight-raised and therefore does not carry
4249 * time-critical I/O,
4250 * or
4251 * - regardless of whether bfqq is weight-raised, bfqq has
4252 * however a long think time, during which it can absorb the
4253 * effect of an appropriate number of extra I/O requests
4254 * from other queues (see bfq_update_inject_limit for
4255 * details on the computation of this number);
4256 * then injection can be performed without restrictions.
4257 */
4258 bool in_serv_always_inject = in_serv_bfqq->wr_coeff == 1 ||
4259 !bfq_bfqq_has_short_ttime(in_serv_bfqq);
4260
4261 /*
4262 * If
4263 * - the baseline total service time could not be sampled yet,
4264 * so the inject limit happens to be still 0, and
4265 * - a lot of time has elapsed since the plugging of I/O
4266 * dispatching started, so drive speed is being wasted
4267 * significantly;
4268 * then temporarily raise inject limit to one request.
4269 */
4270 if (limit == 0 && in_serv_bfqq->last_serv_time_ns == 0 &&
4271 bfq_bfqq_wait_request(in_serv_bfqq) &&
4272 time_is_before_eq_jiffies(bfqd->last_idling_start_jiffies +
4273 bfqd->bfq_slice_idle)
4274 )
4275 limit = 1;
4276
4277 if (bfqd->rq_in_driver >= limit)
4278 return NULL;
4279
4280 /*
4281 * Linear search of the source queue for injection; but, with
4282 * a high probability, very few steps are needed to find a
4283 * candidate queue, i.e., a queue with enough budget left for
4284 * its next request. In fact:
4285 * - BFQ dynamically updates the budget of every queue so as
4286 * to accommodate the expected backlog of the queue;
4287 * - if a queue gets all its requests dispatched as injected
4288 * service, then the queue is removed from the active list
4289 * (and re-added only if it gets new requests, but then it
4290 * is assigned again enough budget for its new backlog).
4291 */
4292 list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
4293 if (!RB_EMPTY_ROOT(&bfqq->sort_list) &&
4294 (in_serv_always_inject || bfqq->wr_coeff > 1) &&
4295 bfq_serv_to_charge(bfqq->next_rq, bfqq) <=
4296 bfq_bfqq_budget_left(bfqq)) {
4297 /*
4298 * Allow for only one large in-flight request
4299 * on non-rotational devices, for the
4300 * following reason. On non-rotationl drives,
4301 * large requests take much longer than
4302 * smaller requests to be served. In addition,
4303 * the drive prefers to serve large requests
4304 * w.r.t. to small ones, if it can choose. So,
4305 * having more than one large requests queued
4306 * in the drive may easily make the next first
4307 * request of the in-service queue wait for so
4308 * long to break bfqq's service guarantees. On
4309 * the bright side, large requests let the
4310 * drive reach a very high throughput, even if
4311 * there is only one in-flight large request
4312 * at a time.
4313 */
4314 if (blk_queue_nonrot(bfqd->queue) &&
4315 blk_rq_sectors(bfqq->next_rq) >=
4316 BFQQ_SECT_THR_NONROT)
4317 limit = min_t(unsigned int, 1, limit);
4318 else
4319 limit = in_serv_bfqq->inject_limit;
4320
4321 if (bfqd->rq_in_driver < limit) {
4322 bfqd->rqs_injected = true;
4323 return bfqq;
4324 }
4325 }
4326
4327 return NULL;
4328 }
4329
4330 /*
4331 * Select a queue for service. If we have a current queue in service,
4332 * check whether to continue servicing it, or retrieve and set a new one.
4333 */
4334 static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
4335 {
4336 struct bfq_queue *bfqq;
4337 struct request *next_rq;
4338 enum bfqq_expiration reason = BFQQE_BUDGET_TIMEOUT;
4339
4340 bfqq = bfqd->in_service_queue;
4341 if (!bfqq)
4342 goto new_queue;
4343
4344 bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
4345
4346 /*
4347 * Do not expire bfqq for budget timeout if bfqq may be about
4348 * to enjoy device idling. The reason why, in this case, we
4349 * prevent bfqq from expiring is the same as in the comments
4350 * on the case where bfq_bfqq_must_idle() returns true, in
4351 * bfq_completed_request().
4352 */
4353 if (bfq_may_expire_for_budg_timeout(bfqq) &&
4354 !bfq_bfqq_must_idle(bfqq))
4355 goto expire;
4356
4357 check_queue:
4358 /*
4359 * This loop is rarely executed more than once. Even when it
4360 * happens, it is much more convenient to re-execute this loop
4361 * than to return NULL and trigger a new dispatch to get a
4362 * request served.
4363 */
4364 next_rq = bfqq->next_rq;
4365 /*
4366 * If bfqq has requests queued and it has enough budget left to
4367 * serve them, keep the queue, otherwise expire it.
4368 */
4369 if (next_rq) {
4370 if (bfq_serv_to_charge(next_rq, bfqq) >
4371 bfq_bfqq_budget_left(bfqq)) {
4372 /*
4373 * Expire the queue for budget exhaustion,
4374 * which makes sure that the next budget is
4375 * enough to serve the next request, even if
4376 * it comes from the fifo expired path.
4377 */
4378 reason = BFQQE_BUDGET_EXHAUSTED;
4379 goto expire;
4380 } else {
4381 /*
4382 * The idle timer may be pending because we may
4383 * not disable disk idling even when a new request
4384 * arrives.
4385 */
4386 if (bfq_bfqq_wait_request(bfqq)) {
4387 /*
4388 * If we get here: 1) at least a new request
4389 * has arrived but we have not disabled the
4390 * timer because the request was too small,
4391 * 2) then the block layer has unplugged
4392 * the device, causing the dispatch to be
4393 * invoked.
4394 *
4395 * Since the device is unplugged, now the
4396 * requests are probably large enough to
4397 * provide a reasonable throughput.
4398 * So we disable idling.
4399 */
4400 bfq_clear_bfqq_wait_request(bfqq);
4401 hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
4402 }
4403 goto keep_queue;
4404 }
4405 }
4406
4407 /*
4408 * No requests pending. However, if the in-service queue is idling
4409 * for a new request, or has requests waiting for a completion and
4410 * may idle after their completion, then keep it anyway.
4411 *
4412 * Yet, inject service from other queues if it boosts
4413 * throughput and is possible.
4414 */
4415 if (bfq_bfqq_wait_request(bfqq) ||
4416 (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) {
4417 struct bfq_queue *async_bfqq =
4418 bfqq->bic && bfqq->bic->bfqq[0] &&
4419 bfq_bfqq_busy(bfqq->bic->bfqq[0]) &&
4420 bfqq->bic->bfqq[0]->next_rq ?
4421 bfqq->bic->bfqq[0] : NULL;
4422
4423 /*
4424 * The next three mutually-exclusive ifs decide
4425 * whether to try injection, and choose the queue to
4426 * pick an I/O request from.
4427 *
4428 * The first if checks whether the process associated
4429 * with bfqq has also async I/O pending. If so, it
4430 * injects such I/O unconditionally. Injecting async
4431 * I/O from the same process can cause no harm to the
4432 * process. On the contrary, it can only increase
4433 * bandwidth and reduce latency for the process.
4434 *
4435 * The second if checks whether there happens to be a
4436 * non-empty waker queue for bfqq, i.e., a queue whose
4437 * I/O needs to be completed for bfqq to receive new
4438 * I/O. This happens, e.g., if bfqq is associated with
4439 * a process that does some sync. A sync generates
4440 * extra blocking I/O, which must be completed before
4441 * the process associated with bfqq can go on with its
4442 * I/O. If the I/O of the waker queue is not served,
4443 * then bfqq remains empty, and no I/O is dispatched,
4444 * until the idle timeout fires for bfqq. This is
4445 * likely to result in lower bandwidth and higher
4446 * latencies for bfqq, and in a severe loss of total
4447 * throughput. The best action to take is therefore to
4448 * serve the waker queue as soon as possible. So do it
4449 * (without relying on the third alternative below for
4450 * eventually serving waker_bfqq's I/O; see the last
4451 * paragraph for further details). This systematic
4452 * injection of I/O from the waker queue does not
4453 * cause any delay to bfqq's I/O. On the contrary,
4454 * next bfqq's I/O is brought forward dramatically,
4455 * for it is not blocked for milliseconds.
4456 *
4457 * The third if checks whether bfqq is a queue for
4458 * which it is better to avoid injection. It is so if
4459 * bfqq delivers more throughput when served without
4460 * any further I/O from other queues in the middle, or
4461 * if the service times of bfqq's I/O requests both
4462 * count more than overall throughput, and may be
4463 * easily increased by injection (this happens if bfqq
4464 * has a short think time). If none of these
4465 * conditions holds, then a candidate queue for
4466 * injection is looked for through
4467 * bfq_choose_bfqq_for_injection(). Note that the
4468 * latter may return NULL (for example if the inject
4469 * limit for bfqq is currently 0).
4470 *
4471 * NOTE: motivation for the second alternative
4472 *
4473 * Thanks to the way the inject limit is updated in
4474 * bfq_update_has_short_ttime(), it is rather likely
4475 * that, if I/O is being plugged for bfqq and the
4476 * waker queue has pending I/O requests that are
4477 * blocking bfqq's I/O, then the third alternative
4478 * above lets the waker queue get served before the
4479 * I/O-plugging timeout fires. So one may deem the
4480 * second alternative superfluous. It is not, because
4481 * the third alternative may be way less effective in
4482 * case of a synchronization. For two main
4483 * reasons. First, throughput may be low because the
4484 * inject limit may be too low to guarantee the same
4485 * amount of injected I/O, from the waker queue or
4486 * other queues, that the second alternative
4487 * guarantees (the second alternative unconditionally
4488 * injects a pending I/O request of the waker queue
4489 * for each bfq_dispatch_request()). Second, with the
4490 * third alternative, the duration of the plugging,
4491 * i.e., the time before bfqq finally receives new I/O,
4492 * may not be minimized, because the waker queue may
4493 * happen to be served only after other queues.
4494 */
4495 if (async_bfqq &&
4496 icq_to_bic(async_bfqq->next_rq->elv.icq) == bfqq->bic &&
4497 bfq_serv_to_charge(async_bfqq->next_rq, async_bfqq) <=
4498 bfq_bfqq_budget_left(async_bfqq))
4499 bfqq = bfqq->bic->bfqq[0];
4500 else if (bfq_bfqq_has_waker(bfqq) &&
4501 bfq_bfqq_busy(bfqq->waker_bfqq) &&
4502 bfqq->next_rq &&
4503 bfq_serv_to_charge(bfqq->waker_bfqq->next_rq,
4504 bfqq->waker_bfqq) <=
4505 bfq_bfqq_budget_left(bfqq->waker_bfqq)
4506 )
4507 bfqq = bfqq->waker_bfqq;
4508 else if (!idling_boosts_thr_without_issues(bfqd, bfqq) &&
4509 (bfqq->wr_coeff == 1 || bfqd->wr_busy_queues > 1 ||
4510 !bfq_bfqq_has_short_ttime(bfqq)))
4511 bfqq = bfq_choose_bfqq_for_injection(bfqd);
4512 else
4513 bfqq = NULL;
4514
4515 goto keep_queue;
4516 }
4517
4518 reason = BFQQE_NO_MORE_REQUESTS;
4519 expire:
4520 bfq_bfqq_expire(bfqd, bfqq, false, reason);
4521 new_queue:
4522 bfqq = bfq_set_in_service_queue(bfqd);
4523 if (bfqq) {
4524 bfq_log_bfqq(bfqd, bfqq, "select_queue: checking new queue");
4525 goto check_queue;
4526 }
4527 keep_queue:
4528 if (bfqq)
4529 bfq_log_bfqq(bfqd, bfqq, "select_queue: returned this queue");
4530 else
4531 bfq_log(bfqd, "select_queue: no queue returned");
4532
4533 return bfqq;
4534 }
4535
4536 static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
4537 {
4538 struct bfq_entity *entity = &bfqq->entity;
4539
4540 if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */
4541 bfq_log_bfqq(bfqd, bfqq,
4542 "raising period dur %u/%u msec, old coeff %u, w %d(%d)",
4543 jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
4544 jiffies_to_msecs(bfqq->wr_cur_max_time),
4545 bfqq->wr_coeff,
4546 bfqq->entity.weight, bfqq->entity.orig_weight);
4547
4548 if (entity->prio_changed)
4549 bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change");
4550
4551 /*
4552 * If the queue was activated in a burst, or too much
4553 * time has elapsed from the beginning of this
4554 * weight-raising period, then end weight raising.
4555 */
4556 if (bfq_bfqq_in_large_burst(bfqq))
4557 bfq_bfqq_end_wr(bfqq);
4558 else if (time_is_before_jiffies(bfqq->last_wr_start_finish +
4559 bfqq->wr_cur_max_time)) {
4560 if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time ||
4561 time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
4562 bfq_wr_duration(bfqd)))
4563 bfq_bfqq_end_wr(bfqq);
4564 else {
4565 switch_back_to_interactive_wr(bfqq, bfqd);
4566 bfqq->entity.prio_changed = 1;
4567 }
4568 }
4569 if (bfqq->wr_coeff > 1 &&
4570 bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time &&
4571 bfqq->service_from_wr > max_service_from_wr) {
4572 /* see comments on max_service_from_wr */
4573 bfq_bfqq_end_wr(bfqq);
4574 }
4575 }
4576 /*
4577 * To improve latency (for this or other queues), immediately
4578 * update weight both if it must be raised and if it must be
4579 * lowered. Since, entity may be on some active tree here, and
4580 * might have a pending change of its ioprio class, invoke
4581 * next function with the last parameter unset (see the
4582 * comments on the function).
4583 */
4584 if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1))
4585 __bfq_entity_update_weight_prio(bfq_entity_service_tree(entity),
4586 entity, false);
4587 }
4588
4589 /*
4590 * Dispatch next request from bfqq.
4591 */
4592 static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
4593 struct bfq_queue *bfqq)
4594 {
4595 struct request *rq = bfqq->next_rq;
4596 unsigned long service_to_charge;
4597
4598 service_to_charge = bfq_serv_to_charge(rq, bfqq);
4599
4600 bfq_bfqq_served(bfqq, service_to_charge);
4601
4602 if (bfqq == bfqd->in_service_queue && bfqd->wait_dispatch) {
4603 bfqd->wait_dispatch = false;
4604 bfqd->waited_rq = rq;
4605 }
4606
4607 bfq_dispatch_remove(bfqd->queue, rq);
4608
4609 if (bfqq != bfqd->in_service_queue)
4610 goto return_rq;
4611
4612 /*
4613 * If weight raising has to terminate for bfqq, then next
4614 * function causes an immediate update of bfqq's weight,
4615 * without waiting for next activation. As a consequence, on
4616 * expiration, bfqq will be timestamped as if has never been
4617 * weight-raised during this service slot, even if it has
4618 * received part or even most of the service as a
4619 * weight-raised queue. This inflates bfqq's timestamps, which
4620 * is beneficial, as bfqq is then more willing to leave the
4621 * device immediately to possible other weight-raised queues.
4622 */
4623 bfq_update_wr_data(bfqd, bfqq);
4624
4625 /*
4626 * Expire bfqq, pretending that its budget expired, if bfqq
4627 * belongs to CLASS_IDLE and other queues are waiting for
4628 * service.
4629 */
4630 if (!(bfq_tot_busy_queues(bfqd) > 1 && bfq_class_idle(bfqq)))
4631 goto return_rq;
4632
4633 bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_BUDGET_EXHAUSTED);
4634
4635 return_rq:
4636 return rq;
4637 }
4638
4639 static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
4640 {
4641 struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
4642
4643 /*
4644 * Avoiding lock: a race on bfqd->busy_queues should cause at
4645 * most a call to dispatch for nothing
4646 */
4647 return !list_empty_careful(&bfqd->dispatch) ||
4648 bfq_tot_busy_queues(bfqd) > 0;
4649 }
4650
4651 static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
4652 {
4653 struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
4654 struct request *rq = NULL;
4655 struct bfq_queue *bfqq = NULL;
4656
4657 if (!list_empty(&bfqd->dispatch)) {
4658 rq = list_first_entry(&bfqd->dispatch, struct request,
4659 queuelist);
4660 list_del_init(&rq->queuelist);
4661
4662 bfqq = RQ_BFQQ(rq);
4663
4664 if (bfqq) {
4665 /*
4666 * Increment counters here, because this
4667 * dispatch does not follow the standard
4668 * dispatch flow (where counters are
4669 * incremented)
4670 */
4671 bfqq->dispatched++;
4672
4673 goto inc_in_driver_start_rq;
4674 }
4675
4676 /*
4677 * We exploit the bfq_finish_requeue_request hook to
4678 * decrement rq_in_driver, but
4679 * bfq_finish_requeue_request will not be invoked on
4680 * this request. So, to avoid unbalance, just start
4681 * this request, without incrementing rq_in_driver. As
4682 * a negative consequence, rq_in_driver is deceptively
4683 * lower than it should be while this request is in
4684 * service. This may cause bfq_schedule_dispatch to be
4685 * invoked uselessly.
4686 *
4687 * As for implementing an exact solution, the
4688 * bfq_finish_requeue_request hook, if defined, is
4689 * probably invoked also on this request. So, by
4690 * exploiting this hook, we could 1) increment
4691 * rq_in_driver here, and 2) decrement it in
4692 * bfq_finish_requeue_request. Such a solution would
4693 * let the value of the counter be always accurate,
4694 * but it would entail using an extra interface
4695 * function. This cost seems higher than the benefit,
4696 * being the frequency of non-elevator-private
4697 * requests very low.
4698 */
4699 goto start_rq;
4700 }
4701
4702 bfq_log(bfqd, "dispatch requests: %d busy queues",
4703 bfq_tot_busy_queues(bfqd));
4704
4705 if (bfq_tot_busy_queues(bfqd) == 0)
4706 goto exit;
4707
4708 /*
4709 * Force device to serve one request at a time if
4710 * strict_guarantees is true. Forcing this service scheme is
4711 * currently the ONLY way to guarantee that the request
4712 * service order enforced by the scheduler is respected by a
4713 * queueing device. Otherwise the device is free even to make
4714 * some unlucky request wait for as long as the device
4715 * wishes.
4716 *
4717 * Of course, serving one request at at time may cause loss of
4718 * throughput.
4719 */
4720 if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0)
4721 goto exit;
4722
4723 bfqq = bfq_select_queue(bfqd);
4724 if (!bfqq)
4725 goto exit;
4726
4727 rq = bfq_dispatch_rq_from_bfqq(bfqd, bfqq);
4728
4729 if (rq) {
4730 inc_in_driver_start_rq:
4731 bfqd->rq_in_driver++;
4732 start_rq:
4733 rq->rq_flags |= RQF_STARTED;
4734 }
4735 exit:
4736 return rq;
4737 }
4738
4739 #ifdef CONFIG_BFQ_CGROUP_DEBUG
4740 static void bfq_update_dispatch_stats(struct request_queue *q,
4741 struct request *rq,
4742 struct bfq_queue *in_serv_queue,
4743 bool idle_timer_disabled)
4744 {
4745 struct bfq_queue *bfqq = rq ? RQ_BFQQ(rq) : NULL;
4746
4747 if (!idle_timer_disabled && !bfqq)
4748 return;
4749
4750 /*
4751 * rq and bfqq are guaranteed to exist until this function
4752 * ends, for the following reasons. First, rq can be
4753 * dispatched to the device, and then can be completed and
4754 * freed, only after this function ends. Second, rq cannot be
4755 * merged (and thus freed because of a merge) any longer,
4756 * because it has already started. Thus rq cannot be freed
4757 * before this function ends, and, since rq has a reference to
4758 * bfqq, the same guarantee holds for bfqq too.
4759 *
4760 * In addition, the following queue lock guarantees that
4761 * bfqq_group(bfqq) exists as well.
4762 */
4763 spin_lock_irq(&q->queue_lock);
4764 if (idle_timer_disabled)
4765 /*
4766 * Since the idle timer has been disabled,
4767 * in_serv_queue contained some request when
4768 * __bfq_dispatch_request was invoked above, which
4769 * implies that rq was picked exactly from
4770 * in_serv_queue. Thus in_serv_queue == bfqq, and is
4771 * therefore guaranteed to exist because of the above
4772 * arguments.
4773 */
4774 bfqg_stats_update_idle_time(bfqq_group(in_serv_queue));
4775 if (bfqq) {
4776 struct bfq_group *bfqg = bfqq_group(bfqq);
4777
4778 bfqg_stats_update_avg_queue_size(bfqg);
4779 bfqg_stats_set_start_empty_time(bfqg);
4780 bfqg_stats_update_io_remove(bfqg, rq->cmd_flags);
4781 }
4782 spin_unlock_irq(&q->queue_lock);
4783 }
4784 #else
4785 static inline void bfq_update_dispatch_stats(struct request_queue *q,
4786 struct request *rq,
4787 struct bfq_queue *in_serv_queue,
4788 bool idle_timer_disabled) {}
4789 #endif /* CONFIG_BFQ_CGROUP_DEBUG */
4790
4791 static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
4792 {
4793 struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
4794 struct request *rq;
4795 struct bfq_queue *in_serv_queue;
4796 bool waiting_rq, idle_timer_disabled;
4797
4798 spin_lock_irq(&bfqd->lock);
4799
4800 in_serv_queue = bfqd->in_service_queue;
4801 waiting_rq = in_serv_queue && bfq_bfqq_wait_request(in_serv_queue);
4802
4803 rq = __bfq_dispatch_request(hctx);
4804
4805 idle_timer_disabled =
4806 waiting_rq && !bfq_bfqq_wait_request(in_serv_queue);
4807
4808 spin_unlock_irq(&bfqd->lock);
4809
4810 bfq_update_dispatch_stats(hctx->queue, rq, in_serv_queue,
4811 idle_timer_disabled);
4812
4813 return rq;
4814 }
4815
4816 /*
4817 * Task holds one reference to the queue, dropped when task exits. Each rq
4818 * in-flight on this queue also holds a reference, dropped when rq is freed.
4819 *
4820 * Scheduler lock must be held here. Recall not to use bfqq after calling
4821 * this function on it.
4822 */
4823 void bfq_put_queue(struct bfq_queue *bfqq)
4824 {
4825 struct bfq_queue *item;
4826 struct hlist_node *n;
4827 struct bfq_group *bfqg = bfqq_group(bfqq);
4828
4829 if (bfqq->bfqd)
4830 bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d",
4831 bfqq, bfqq->ref);
4832
4833 bfqq->ref--;
4834 if (bfqq->ref)
4835 return;
4836
4837 if (!hlist_unhashed(&bfqq->burst_list_node)) {
4838 hlist_del_init(&bfqq->burst_list_node);
4839 /*
4840 * Decrement also burst size after the removal, if the
4841 * process associated with bfqq is exiting, and thus
4842 * does not contribute to the burst any longer. This
4843 * decrement helps filter out false positives of large
4844 * bursts, when some short-lived process (often due to
4845 * the execution of commands by some service) happens
4846 * to start and exit while a complex application is
4847 * starting, and thus spawning several processes that
4848 * do I/O (and that *must not* be treated as a large
4849 * burst, see comments on bfq_handle_burst).
4850 *
4851 * In particular, the decrement is performed only if:
4852 * 1) bfqq is not a merged queue, because, if it is,
4853 * then this free of bfqq is not triggered by the exit
4854 * of the process bfqq is associated with, but exactly
4855 * by the fact that bfqq has just been merged.
4856 * 2) burst_size is greater than 0, to handle
4857 * unbalanced decrements. Unbalanced decrements may
4858 * happen in te following case: bfqq is inserted into
4859 * the current burst list--without incrementing
4860 * bust_size--because of a split, but the current
4861 * burst list is not the burst list bfqq belonged to
4862 * (see comments on the case of a split in
4863 * bfq_set_request).
4864 */
4865 if (bfqq->bic && bfqq->bfqd->burst_size > 0)
4866 bfqq->bfqd->burst_size--;
4867 }
4868
4869 /*
4870 * bfqq does not exist any longer, so it cannot be woken by
4871 * any other queue, and cannot wake any other queue. Then bfqq
4872 * must be removed from the woken list of its possible waker
4873 * queue, and all queues in the woken list of bfqq must stop
4874 * having a waker queue. Strictly speaking, these updates
4875 * should be performed when bfqq remains with no I/O source
4876 * attached to it, which happens before bfqq gets freed. In
4877 * particular, this happens when the last process associated
4878 * with bfqq exits or gets associated with a different
4879 * queue. However, both events lead to bfqq being freed soon,
4880 * and dangling references would come out only after bfqq gets
4881 * freed. So these updates are done here, as a simple and safe
4882 * way to handle all cases.
4883 */
4884 /* remove bfqq from woken list */
4885 if (!hlist_unhashed(&bfqq->woken_list_node))
4886 hlist_del_init(&bfqq->woken_list_node);
4887
4888 /* reset waker for all queues in woken list */
4889 hlist_for_each_entry_safe(item, n, &bfqq->woken_list,
4890 woken_list_node) {
4891 item->waker_bfqq = NULL;
4892 bfq_clear_bfqq_has_waker(item);
4893 hlist_del_init(&item->woken_list_node);
4894 }
4895
4896 if (bfqq->bfqd && bfqq->bfqd->last_completed_rq_bfqq == bfqq)
4897 bfqq->bfqd->last_completed_rq_bfqq = NULL;
4898
4899 kmem_cache_free(bfq_pool, bfqq);
4900 bfqg_and_blkg_put(bfqg);
4901 }
4902
4903 static void bfq_put_cooperator(struct bfq_queue *bfqq)
4904 {
4905 struct bfq_queue *__bfqq, *next;
4906
4907 /*
4908 * If this queue was scheduled to merge with another queue, be
4909 * sure to drop the reference taken on that queue (and others in
4910 * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs.
4911 */
4912 __bfqq = bfqq->new_bfqq;
4913 while (__bfqq) {
4914 if (__bfqq == bfqq)
4915 break;
4916 next = __bfqq->new_bfqq;
4917 bfq_put_queue(__bfqq);
4918 __bfqq = next;
4919 }
4920 }
4921
4922 static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
4923 {
4924 if (bfqq == bfqd->in_service_queue) {
4925 __bfq_bfqq_expire(bfqd, bfqq, BFQQE_BUDGET_TIMEOUT);
4926 bfq_schedule_dispatch(bfqd);
4927 }
4928
4929 bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq, bfqq->ref);
4930
4931 bfq_put_cooperator(bfqq);
4932
4933 bfq_release_process_ref(bfqd, bfqq);
4934 }
4935
4936 static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
4937 {
4938 struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
4939 struct bfq_data *bfqd;
4940
4941 if (bfqq)
4942 bfqd = bfqq->bfqd; /* NULL if scheduler already exited */
4943
4944 if (bfqq && bfqd) {
4945 unsigned long flags;
4946
4947 spin_lock_irqsave(&bfqd->lock, flags);
4948 bfqq->bic = NULL;
4949 bfq_exit_bfqq(bfqd, bfqq);
4950 bic_set_bfqq(bic, NULL, is_sync);
4951 spin_unlock_irqrestore(&bfqd->lock, flags);
4952 }
4953 }
4954
4955 static void bfq_exit_icq(struct io_cq *icq)
4956 {
4957 struct bfq_io_cq *bic = icq_to_bic(icq);
4958
4959 bfq_exit_icq_bfqq(bic, true);
4960 bfq_exit_icq_bfqq(bic, false);
4961 }
4962
4963 /*
4964 * Update the entity prio values; note that the new values will not
4965 * be used until the next (re)activation.
4966 */
4967 static void
4968 bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
4969 {
4970 struct task_struct *tsk = current;
4971 int ioprio_class;
4972 struct bfq_data *bfqd = bfqq->bfqd;
4973
4974 if (!bfqd)
4975 return;
4976
4977 ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
4978 switch (ioprio_class) {
4979 default:
4980 dev_err(bfqq->bfqd->queue->backing_dev_info->dev,
4981 "bfq: bad prio class %d\n", ioprio_class);
4982 /* fall through */
4983 case IOPRIO_CLASS_NONE:
4984 /*
4985 * No prio set, inherit CPU scheduling settings.
4986 */
4987 bfqq->new_ioprio = task_nice_ioprio(tsk);
4988 bfqq->new_ioprio_class = task_nice_ioclass(tsk);
4989 break;
4990 case IOPRIO_CLASS_RT:
4991 bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
4992 bfqq->new_ioprio_class = IOPRIO_CLASS_RT;
4993 break;
4994 case IOPRIO_CLASS_BE:
4995 bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
4996 bfqq->new_ioprio_class = IOPRIO_CLASS_BE;
4997 break;
4998 case IOPRIO_CLASS_IDLE:
4999 bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE;
5000 bfqq->new_ioprio = 7;
5001 break;
5002 }
5003
5004 if (bfqq->new_ioprio >= IOPRIO_BE_NR) {
5005 pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n",
5006 bfqq->new_ioprio);
5007 bfqq->new_ioprio = IOPRIO_BE_NR;
5008 }
5009
5010 bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio);
5011 bfqq->entity.prio_changed = 1;
5012 }
5013
5014 static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
5015 struct bio *bio, bool is_sync,
5016 struct bfq_io_cq *bic);
5017
5018 static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
5019 {
5020 struct bfq_data *bfqd = bic_to_bfqd(bic);
5021 struct bfq_queue *bfqq;
5022 int ioprio = bic->icq.ioc->ioprio;
5023
5024 /*
5025 * This condition may trigger on a newly created bic, be sure to
5026 * drop the lock before returning.
5027 */
5028 if (unlikely(!bfqd) || likely(bic->ioprio == ioprio))
5029 return;
5030
5031 bic->ioprio = ioprio;
5032
5033 bfqq = bic_to_bfqq(bic, false);
5034 if (bfqq) {
5035 bfq_release_process_ref(bfqd, bfqq);
5036 bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic);
5037 bic_set_bfqq(bic, bfqq, false);
5038 }
5039
5040 bfqq = bic_to_bfqq(bic, true);
5041 if (bfqq)
5042 bfq_set_next_ioprio_data(bfqq, bic);
5043 }
5044
5045 static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
5046 struct bfq_io_cq *bic, pid_t pid, int is_sync)
5047 {
5048 RB_CLEAR_NODE(&bfqq->entity.rb_node);
5049 INIT_LIST_HEAD(&bfqq->fifo);
5050 INIT_HLIST_NODE(&bfqq->burst_list_node);
5051 INIT_HLIST_NODE(&bfqq->woken_list_node);
5052 INIT_HLIST_HEAD(&bfqq->woken_list);
5053
5054 bfqq->ref = 0;
5055 bfqq->bfqd = bfqd;
5056
5057 if (bic)
5058 bfq_set_next_ioprio_data(bfqq, bic);
5059
5060 if (is_sync) {
5061 /*
5062 * No need to mark as has_short_ttime if in
5063 * idle_class, because no device idling is performed
5064 * for queues in idle class
5065 */
5066 if (!bfq_class_idle(bfqq))
5067 /* tentatively mark as has_short_ttime */
5068 bfq_mark_bfqq_has_short_ttime(bfqq);
5069 bfq_mark_bfqq_sync(bfqq);
5070 bfq_mark_bfqq_just_created(bfqq);
5071 } else
5072 bfq_clear_bfqq_sync(bfqq);
5073
5074 /* set end request to minus infinity from now */
5075 bfqq->ttime.last_end_request = ktime_get_ns() + 1;
5076
5077 bfq_mark_bfqq_IO_bound(bfqq);
5078
5079 bfqq->pid = pid;
5080
5081 /* Tentative initial value to trade off between thr and lat */
5082 bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
5083 bfqq->budget_timeout = bfq_smallest_from_now();
5084
5085 bfqq->wr_coeff = 1;
5086 bfqq->last_wr_start_finish = jiffies;
5087 bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now();
5088 bfqq->split_time = bfq_smallest_from_now();
5089
5090 /*
5091 * To not forget the possibly high bandwidth consumed by a
5092 * process/queue in the recent past,
5093 * bfq_bfqq_softrt_next_start() returns a value at least equal
5094 * to the current value of bfqq->soft_rt_next_start (see
5095 * comments on bfq_bfqq_softrt_next_start). Set
5096 * soft_rt_next_start to now, to mean that bfqq has consumed
5097 * no bandwidth so far.
5098 */
5099 bfqq->soft_rt_next_start = jiffies;
5100
5101 /* first request is almost certainly seeky */
5102 bfqq->seek_history = 1;
5103 }
5104
5105 static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
5106 struct bfq_group *bfqg,
5107 int ioprio_class, int ioprio)
5108 {
5109 switch (ioprio_class) {
5110 case IOPRIO_CLASS_RT:
5111 return &bfqg->async_bfqq[0][ioprio];
5112 case IOPRIO_CLASS_NONE:
5113 ioprio = IOPRIO_NORM;
5114 /* fall through */
5115 case IOPRIO_CLASS_BE:
5116 return &bfqg->async_bfqq[1][ioprio];
5117 case IOPRIO_CLASS_IDLE:
5118 return &bfqg->async_idle_bfqq;
5119 default:
5120 return NULL;
5121 }
5122 }
5123
5124 static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
5125 struct bio *bio, bool is_sync,
5126 struct bfq_io_cq *bic)
5127 {
5128 const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
5129 const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
5130 struct bfq_queue **async_bfqq = NULL;
5131 struct bfq_queue *bfqq;
5132 struct bfq_group *bfqg;
5133
5134 rcu_read_lock();
5135
5136 bfqg = bfq_find_set_group(bfqd, __bio_blkcg(bio));
5137 if (!bfqg) {
5138 bfqq = &bfqd->oom_bfqq;
5139 goto out;
5140 }
5141
5142 if (!is_sync) {
5143 async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class,
5144 ioprio);
5145 bfqq = *async_bfqq;
5146 if (bfqq)
5147 goto out;
5148 }
5149
5150 bfqq = kmem_cache_alloc_node(bfq_pool,
5151 GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN,
5152 bfqd->queue->node);
5153
5154 if (bfqq) {
5155 bfq_init_bfqq(bfqd, bfqq, bic, current->pid,
5156 is_sync);
5157 bfq_init_entity(&bfqq->entity, bfqg);
5158 bfq_log_bfqq(bfqd, bfqq, "allocated");
5159 } else {
5160 bfqq = &bfqd->oom_bfqq;
5161 bfq_log_bfqq(bfqd, bfqq, "using oom bfqq");
5162 goto out;
5163 }
5164
5165 /*
5166 * Pin the queue now that it's allocated, scheduler exit will
5167 * prune it.
5168 */
5169 if (async_bfqq) {
5170 bfqq->ref++; /*
5171 * Extra group reference, w.r.t. sync
5172 * queue. This extra reference is removed
5173 * only if bfqq->bfqg disappears, to
5174 * guarantee that this queue is not freed
5175 * until its group goes away.
5176 */
5177 bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d",
5178 bfqq, bfqq->ref);
5179 *async_bfqq = bfqq;
5180 }
5181
5182 out:
5183 bfqq->ref++; /* get a process reference to this queue */
5184 bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq, bfqq->ref);
5185 rcu_read_unlock();
5186 return bfqq;
5187 }
5188
5189 static void bfq_update_io_thinktime(struct bfq_data *bfqd,
5190 struct bfq_queue *bfqq)
5191 {
5192 struct bfq_ttime *ttime = &bfqq->ttime;
5193 u64 elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;
5194
5195 elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);
5196
5197 ttime->ttime_samples = (7*bfqq->ttime.ttime_samples + 256) / 8;
5198 ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed, 8);
5199 ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
5200 ttime->ttime_samples);
5201 }
5202
5203 static void
5204 bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
5205 struct request *rq)
5206 {
5207 bfqq->seek_history <<= 1;
5208 bfqq->seek_history |= BFQ_RQ_SEEKY(bfqd, bfqq->last_request_pos, rq);
5209
5210 if (bfqq->wr_coeff > 1 &&
5211 bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
5212 BFQQ_TOTALLY_SEEKY(bfqq))
5213 bfq_bfqq_end_wr(bfqq);
5214 }
5215
5216 static void bfq_update_has_short_ttime(struct bfq_data *bfqd,
5217 struct bfq_queue *bfqq,
5218 struct bfq_io_cq *bic)
5219 {
5220 bool has_short_ttime = true, state_changed;
5221
5222 /*
5223 * No need to update has_short_ttime if bfqq is async or in
5224 * idle io prio class, or if bfq_slice_idle is zero, because
5225 * no device idling is performed for bfqq in this case.
5226 */
5227 if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq) ||
5228 bfqd->bfq_slice_idle == 0)
5229 return;
5230
5231 /* Idle window just restored, statistics are meaningless. */
5232 if (time_is_after_eq_jiffies(bfqq->split_time +
5233 bfqd->bfq_wr_min_idle_time))
5234 return;
5235
5236 /* Think time is infinite if no process is linked to
5237 * bfqq. Otherwise check average think time to
5238 * decide whether to mark as has_short_ttime
5239 */
5240 if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
5241 (bfq_sample_valid(bfqq->ttime.ttime_samples) &&
5242 bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle))
5243 has_short_ttime = false;
5244
5245 state_changed = has_short_ttime != bfq_bfqq_has_short_ttime(bfqq);
5246
5247 if (has_short_ttime)
5248 bfq_mark_bfqq_has_short_ttime(bfqq);
5249 else
5250 bfq_clear_bfqq_has_short_ttime(bfqq);
5251
5252 /*
5253 * Until the base value for the total service time gets
5254 * finally computed for bfqq, the inject limit does depend on
5255 * the think-time state (short|long). In particular, the limit
5256 * is 0 or 1 if the think time is deemed, respectively, as
5257 * short or long (details in the comments in
5258 * bfq_update_inject_limit()). Accordingly, the next
5259 * instructions reset the inject limit if the think-time state
5260 * has changed and the above base value is still to be
5261 * computed.
5262 *
5263 * However, the reset is performed only if more than 100 ms
5264 * have elapsed since the last update of the inject limit, or
5265 * (inclusive) if the change is from short to long think
5266 * time. The reason for this waiting is as follows.
5267 *
5268 * bfqq may have a long think time because of a
5269 * synchronization with some other queue, i.e., because the
5270 * I/O of some other queue may need to be completed for bfqq
5271 * to receive new I/O. Details in the comments on the choice
5272 * of the queue for injection in bfq_select_queue().
5273 *
5274 * As stressed in those comments, if such a synchronization is
5275 * actually in place, then, without injection on bfqq, the
5276 * blocking I/O cannot happen to served while bfqq is in
5277 * service. As a consequence, if bfqq is granted
5278 * I/O-dispatch-plugging, then bfqq remains empty, and no I/O
5279 * is dispatched, until the idle timeout fires. This is likely
5280 * to result in lower bandwidth and higher latencies for bfqq,
5281 * and in a severe loss of total throughput.
5282 *
5283 * On the opposite end, a non-zero inject limit may allow the
5284 * I/O that blocks bfqq to be executed soon, and therefore
5285 * bfqq to receive new I/O soon.
5286 *
5287 * But, if the blocking gets actually eliminated, then the
5288 * next think-time sample for bfqq may be very low. This in
5289 * turn may cause bfqq's think time to be deemed
5290 * short. Without the 100 ms barrier, this new state change
5291 * would cause the body of the next if to be executed
5292 * immediately. But this would set to 0 the inject
5293 * limit. Without injection, the blocking I/O would cause the
5294 * think time of bfqq to become long again, and therefore the
5295 * inject limit to be raised again, and so on. The only effect
5296 * of such a steady oscillation between the two think-time
5297 * states would be to prevent effective injection on bfqq.
5298 *
5299 * In contrast, if the inject limit is not reset during such a
5300 * long time interval as 100 ms, then the number of short
5301 * think time samples can grow significantly before the reset
5302 * is performed. As a consequence, the think time state can
5303 * become stable before the reset. Therefore there will be no
5304 * state change when the 100 ms elapse, and no reset of the
5305 * inject limit. The inject limit remains steadily equal to 1
5306 * both during and after the 100 ms. So injection can be
5307 * performed at all times, and throughput gets boosted.
5308 *
5309 * An inject limit equal to 1 is however in conflict, in
5310 * general, with the fact that the think time of bfqq is
5311 * short, because injection may be likely to delay bfqq's I/O
5312 * (as explained in the comments in
5313 * bfq_update_inject_limit()). But this does not happen in
5314 * this special case, because bfqq's low think time is due to
5315 * an effective handling of a synchronization, through
5316 * injection. In this special case, bfqq's I/O does not get
5317 * delayed by injection; on the contrary, bfqq's I/O is
5318 * brought forward, because it is not blocked for
5319 * milliseconds.
5320 *
5321 * In addition, serving the blocking I/O much sooner, and much
5322 * more frequently than once per I/O-plugging timeout, makes
5323 * it much quicker to detect a waker queue (the concept of
5324 * waker queue is defined in the comments in
5325 * bfq_add_request()). This makes it possible to start sooner
5326 * to boost throughput more effectively, by injecting the I/O
5327 * of the waker queue unconditionally on every
5328 * bfq_dispatch_request().
5329 *
5330 * One last, important benefit of not resetting the inject
5331 * limit before 100 ms is that, during this time interval, the
5332 * base value for the total service time is likely to get
5333 * finally computed for bfqq, freeing the inject limit from
5334 * its relation with the think time.
5335 */
5336 if (state_changed && bfqq->last_serv_time_ns == 0 &&
5337 (time_is_before_eq_jiffies(bfqq->decrease_time_jif +
5338 msecs_to_jiffies(100)) ||
5339 !has_short_ttime))
5340 bfq_reset_inject_limit(bfqd, bfqq);
5341 }
5342
5343 /*
5344 * Called when a new fs request (rq) is added to bfqq. Check if there's
5345 * something we should do about it.
5346 */
5347 static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
5348 struct request *rq)
5349 {
5350 if (rq->cmd_flags & REQ_META)
5351 bfqq->meta_pending++;
5352
5353 bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
5354
5355 if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) {
5356 bool small_req = bfqq->queued[rq_is_sync(rq)] == 1 &&
5357 blk_rq_sectors(rq) < 32;
5358 bool budget_timeout = bfq_bfqq_budget_timeout(bfqq);
5359
5360 /*
5361 * There is just this request queued: if
5362 * - the request is small, and
5363 * - we are idling to boost throughput, and
5364 * - the queue is not to be expired,
5365 * then just exit.
5366 *
5367 * In this way, if the device is being idled to wait
5368 * for a new request from the in-service queue, we
5369 * avoid unplugging the device and committing the
5370 * device to serve just a small request. In contrast
5371 * we wait for the block layer to decide when to
5372 * unplug the device: hopefully, new requests will be
5373 * merged to this one quickly, then the device will be
5374 * unplugged and larger requests will be dispatched.
5375 */
5376 if (small_req && idling_boosts_thr_without_issues(bfqd, bfqq) &&
5377 !budget_timeout)
5378 return;
5379
5380 /*
5381 * A large enough request arrived, or idling is being
5382 * performed to preserve service guarantees, or
5383 * finally the queue is to be expired: in all these
5384 * cases disk idling is to be stopped, so clear
5385 * wait_request flag and reset timer.
5386 */
5387 bfq_clear_bfqq_wait_request(bfqq);
5388 hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
5389
5390 /*
5391 * The queue is not empty, because a new request just
5392 * arrived. Hence we can safely expire the queue, in
5393 * case of budget timeout, without risking that the
5394 * timestamps of the queue are not updated correctly.
5395 * See [1] for more details.
5396 */
5397 if (budget_timeout)
5398 bfq_bfqq_expire(bfqd, bfqq, false,
5399 BFQQE_BUDGET_TIMEOUT);
5400 }
5401 }
5402
5403 /* returns true if it causes the idle timer to be disabled */
5404 static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
5405 {
5406 struct bfq_queue *bfqq = RQ_BFQQ(rq),
5407 *new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
5408 bool waiting, idle_timer_disabled = false;
5409
5410 if (new_bfqq) {
5411 /*
5412 * Release the request's reference to the old bfqq
5413 * and make sure one is taken to the shared queue.
5414 */
5415 new_bfqq->allocated++;
5416 bfqq->allocated--;
5417 new_bfqq->ref++;
5418 /*
5419 * If the bic associated with the process
5420 * issuing this request still points to bfqq
5421 * (and thus has not been already redirected
5422 * to new_bfqq or even some other bfq_queue),
5423 * then complete the merge and redirect it to
5424 * new_bfqq.
5425 */
5426 if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
5427 bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
5428 bfqq, new_bfqq);
5429
5430 bfq_clear_bfqq_just_created(bfqq);
5431 /*
5432 * rq is about to be enqueued into new_bfqq,
5433 * release rq reference on bfqq
5434 */
5435 bfq_put_queue(bfqq);
5436 rq->elv.priv[1] = new_bfqq;
5437 bfqq = new_bfqq;
5438 }
5439
5440 bfq_update_io_thinktime(bfqd, bfqq);
5441 bfq_update_has_short_ttime(bfqd, bfqq, RQ_BIC(rq));
5442 bfq_update_io_seektime(bfqd, bfqq, rq);
5443
5444 waiting = bfqq && bfq_bfqq_wait_request(bfqq);
5445 bfq_add_request(rq);
5446 idle_timer_disabled = waiting && !bfq_bfqq_wait_request(bfqq);
5447
5448 rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
5449 list_add_tail(&rq->queuelist, &bfqq->fifo);
5450
5451 bfq_rq_enqueued(bfqd, bfqq, rq);
5452
5453 return idle_timer_disabled;
5454 }
5455
5456 #ifdef CONFIG_BFQ_CGROUP_DEBUG
5457 static void bfq_update_insert_stats(struct request_queue *q,
5458 struct bfq_queue *bfqq,
5459 bool idle_timer_disabled,
5460 unsigned int cmd_flags)
5461 {
5462 if (!bfqq)
5463 return;
5464
5465 /*
5466 * bfqq still exists, because it can disappear only after
5467 * either it is merged with another queue, or the process it
5468 * is associated with exits. But both actions must be taken by
5469 * the same process currently executing this flow of
5470 * instructions.
5471 *
5472 * In addition, the following queue lock guarantees that
5473 * bfqq_group(bfqq) exists as well.
5474 */
5475 spin_lock_irq(&q->queue_lock);
5476 bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, cmd_flags);
5477 if (idle_timer_disabled)
5478 bfqg_stats_update_idle_time(bfqq_group(bfqq));
5479 spin_unlock_irq(&q->queue_lock);
5480 }
5481 #else
5482 static inline void bfq_update_insert_stats(struct request_queue *q,
5483 struct bfq_queue *bfqq,
5484 bool idle_timer_disabled,
5485 unsigned int cmd_flags) {}
5486 #endif /* CONFIG_BFQ_CGROUP_DEBUG */
5487
5488 static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
5489 bool at_head)
5490 {
5491 struct request_queue *q = hctx->queue;
5492 struct bfq_data *bfqd = q->elevator->elevator_data;
5493 struct bfq_queue *bfqq;
5494 bool idle_timer_disabled = false;
5495 unsigned int cmd_flags;
5496
5497 spin_lock_irq(&bfqd->lock);
5498 if (blk_mq_sched_try_insert_merge(q, rq)) {
5499 spin_unlock_irq(&bfqd->lock);
5500 return;
5501 }
5502
5503 spin_unlock_irq(&bfqd->lock);
5504
5505 blk_mq_sched_request_inserted(rq);
5506
5507 spin_lock_irq(&bfqd->lock);
5508 bfqq = bfq_init_rq(rq);
5509 if (!bfqq || at_head || blk_rq_is_passthrough(rq)) {
5510 if (at_head)
5511 list_add(&rq->queuelist, &bfqd->dispatch);
5512 else
5513 list_add_tail(&rq->queuelist, &bfqd->dispatch);
5514 } else {
5515 idle_timer_disabled = __bfq_insert_request(bfqd, rq);
5516 /*
5517 * Update bfqq, because, if a queue merge has occurred
5518 * in __bfq_insert_request, then rq has been
5519 * redirected into a new queue.
5520 */
5521 bfqq = RQ_BFQQ(rq);
5522
5523 if (rq_mergeable(rq)) {
5524 elv_rqhash_add(q, rq);
5525 if (!q->last_merge)
5526 q->last_merge = rq;
5527 }
5528 }
5529
5530 /*
5531 * Cache cmd_flags before releasing scheduler lock, because rq
5532 * may disappear afterwards (for example, because of a request
5533 * merge).
5534 */
5535 cmd_flags = rq->cmd_flags;
5536
5537 spin_unlock_irq(&bfqd->lock);
5538
5539 bfq_update_insert_stats(q, bfqq, idle_timer_disabled,
5540 cmd_flags);
5541 }
5542
5543 static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
5544 struct list_head *list, bool at_head)
5545 {
5546 while (!list_empty(list)) {
5547 struct request *rq;
5548
5549 rq = list_first_entry(list, struct request, queuelist);
5550 list_del_init(&rq->queuelist);
5551 bfq_insert_request(hctx, rq, at_head);
5552 }
5553 }
5554
5555 static void bfq_update_hw_tag(struct bfq_data *bfqd)
5556 {
5557 struct bfq_queue *bfqq = bfqd->in_service_queue;
5558
5559 bfqd->max_rq_in_driver = max_t(int, bfqd->max_rq_in_driver,
5560 bfqd->rq_in_driver);
5561
5562 if (bfqd->hw_tag == 1)
5563 return;
5564
5565 /*
5566 * This sample is valid if the number of outstanding requests
5567 * is large enough to allow a queueing behavior. Note that the
5568 * sum is not exact, as it's not taking into account deactivated
5569 * requests.
5570 */
5571 if (bfqd->rq_in_driver + bfqd->queued <= BFQ_HW_QUEUE_THRESHOLD)
5572 return;
5573
5574 /*
5575 * If active queue hasn't enough requests and can idle, bfq might not
5576 * dispatch sufficient requests to hardware. Don't zero hw_tag in this
5577 * case
5578 */
5579 if (bfqq && bfq_bfqq_has_short_ttime(bfqq) &&
5580 bfqq->dispatched + bfqq->queued[0] + bfqq->queued[1] <
5581 BFQ_HW_QUEUE_THRESHOLD &&
5582 bfqd->rq_in_driver < BFQ_HW_QUEUE_THRESHOLD)
5583 return;
5584
5585 if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES)
5586 return;
5587
5588 bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD;
5589 bfqd->max_rq_in_driver = 0;
5590 bfqd->hw_tag_samples = 0;
5591
5592 bfqd->nonrot_with_queueing =
5593 blk_queue_nonrot(bfqd->queue) && bfqd->hw_tag;
5594 }
5595
5596 static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
5597 {
5598 u64 now_ns;
5599 u32 delta_us;
5600
5601 bfq_update_hw_tag(bfqd);
5602
5603 bfqd->rq_in_driver--;
5604 bfqq->dispatched--;
5605
5606 if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
5607 /*
5608 * Set budget_timeout (which we overload to store the
5609 * time at which the queue remains with no backlog and
5610 * no outstanding request; used by the weight-raising
5611 * mechanism).
5612 */
5613 bfqq->budget_timeout = jiffies;
5614
5615 bfq_weights_tree_remove(bfqd, bfqq);
5616 }
5617
5618 now_ns = ktime_get_ns();
5619
5620 bfqq->ttime.last_end_request = now_ns;
5621
5622 /*
5623 * Using us instead of ns, to get a reasonable precision in
5624 * computing rate in next check.
5625 */
5626 delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC);
5627
5628 /*
5629 * If the request took rather long to complete, and, according
5630 * to the maximum request size recorded, this completion latency
5631 * implies that the request was certainly served at a very low
5632 * rate (less than 1M sectors/sec), then the whole observation
5633 * interval that lasts up to this time instant cannot be a
5634 * valid time interval for computing a new peak rate. Invoke
5635 * bfq_update_rate_reset to have the following three steps
5636 * taken:
5637 * - close the observation interval at the last (previous)
5638 * request dispatch or completion
5639 * - compute rate, if possible, for that observation interval
5640 * - reset to zero samples, which will trigger a proper
5641 * re-initialization of the observation interval on next
5642 * dispatch
5643 */
5644 if (delta_us > BFQ_MIN_TT/NSEC_PER_USEC &&
5645 (bfqd->last_rq_max_size<<BFQ_RATE_SHIFT)/delta_us <
5646 1UL<<(BFQ_RATE_SHIFT - 10))
5647 bfq_update_rate_reset(bfqd, NULL);
5648 bfqd->last_completion = now_ns;
5649 bfqd->last_completed_rq_bfqq = bfqq;
5650
5651 /*
5652 * If we are waiting to discover whether the request pattern
5653 * of the task associated with the queue is actually
5654 * isochronous, and both requisites for this condition to hold
5655 * are now satisfied, then compute soft_rt_next_start (see the
5656 * comments on the function bfq_bfqq_softrt_next_start()). We
5657 * do not compute soft_rt_next_start if bfqq is in interactive
5658 * weight raising (see the comments in bfq_bfqq_expire() for
5659 * an explanation). We schedule this delayed update when bfqq
5660 * expires, if it still has in-flight requests.
5661 */
5662 if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 &&
5663 RB_EMPTY_ROOT(&bfqq->sort_list) &&
5664 bfqq->wr_coeff != bfqd->bfq_wr_coeff)
5665 bfqq->soft_rt_next_start =
5666 bfq_bfqq_softrt_next_start(bfqd, bfqq);
5667
5668 /*
5669 * If this is the in-service queue, check if it needs to be expired,
5670 * or if we want to idle in case it has no pending requests.
5671 */
5672 if (bfqd->in_service_queue == bfqq) {
5673 if (bfq_bfqq_must_idle(bfqq)) {
5674 if (bfqq->dispatched == 0)
5675 bfq_arm_slice_timer(bfqd);
5676 /*
5677 * If we get here, we do not expire bfqq, even
5678 * if bfqq was in budget timeout or had no
5679 * more requests (as controlled in the next
5680 * conditional instructions). The reason for
5681 * not expiring bfqq is as follows.
5682 *
5683 * Here bfqq->dispatched > 0 holds, but
5684 * bfq_bfqq_must_idle() returned true. This
5685 * implies that, even if no request arrives
5686 * for bfqq before bfqq->dispatched reaches 0,
5687 * bfqq will, however, not be expired on the
5688 * completion event that causes bfqq->dispatch
5689 * to reach zero. In contrast, on this event,
5690 * bfqq will start enjoying device idling
5691 * (I/O-dispatch plugging).
5692 *
5693 * But, if we expired bfqq here, bfqq would
5694 * not have the chance to enjoy device idling
5695 * when bfqq->dispatched finally reaches
5696 * zero. This would expose bfqq to violation
5697 * of its reserved service guarantees.
5698 */
5699 return;
5700 } else if (bfq_may_expire_for_budg_timeout(bfqq))
5701 bfq_bfqq_expire(bfqd, bfqq, false,
5702 BFQQE_BUDGET_TIMEOUT);
5703 else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
5704 (bfqq->dispatched == 0 ||
5705 !bfq_better_to_idle(bfqq)))
5706 bfq_bfqq_expire(bfqd, bfqq, false,
5707 BFQQE_NO_MORE_REQUESTS);
5708 }
5709
5710 if (!bfqd->rq_in_driver)
5711 bfq_schedule_dispatch(bfqd);
5712 }
5713
5714 static void bfq_finish_requeue_request_body(struct bfq_queue *bfqq)
5715 {
5716 bfqq->allocated--;
5717
5718 bfq_put_queue(bfqq);
5719 }
5720
5721 /*
5722 * The processes associated with bfqq may happen to generate their
5723 * cumulative I/O at a lower rate than the rate at which the device
5724 * could serve the same I/O. This is rather probable, e.g., if only
5725 * one process is associated with bfqq and the device is an SSD. It
5726 * results in bfqq becoming often empty while in service. In this
5727 * respect, if BFQ is allowed to switch to another queue when bfqq
5728 * remains empty, then the device goes on being fed with I/O requests,
5729 * and the throughput is not affected. In contrast, if BFQ is not
5730 * allowed to switch to another queue---because bfqq is sync and
5731 * I/O-dispatch needs to be plugged while bfqq is temporarily
5732 * empty---then, during the service of bfqq, there will be frequent
5733 * "service holes", i.e., time intervals during which bfqq gets empty
5734 * and the device can only consume the I/O already queued in its
5735 * hardware queues. During service holes, the device may even get to
5736 * remaining idle. In the end, during the service of bfqq, the device
5737 * is driven at a lower speed than the one it can reach with the kind
5738 * of I/O flowing through bfqq.
5739 *
5740 * To counter this loss of throughput, BFQ implements a "request
5741 * injection mechanism", which tries to fill the above service holes
5742 * with I/O requests taken from other queues. The hard part in this
5743 * mechanism is finding the right amount of I/O to inject, so as to
5744 * both boost throughput and not break bfqq's bandwidth and latency
5745 * guarantees. In this respect, the mechanism maintains a per-queue
5746 * inject limit, computed as below. While bfqq is empty, the injection
5747 * mechanism dispatches extra I/O requests only until the total number
5748 * of I/O requests in flight---i.e., already dispatched but not yet
5749 * completed---remains lower than this limit.
5750 *
5751 * A first definition comes in handy to introduce the algorithm by
5752 * which the inject limit is computed. We define as first request for
5753 * bfqq, an I/O request for bfqq that arrives while bfqq is in
5754 * service, and causes bfqq to switch from empty to non-empty. The
5755 * algorithm updates the limit as a function of the effect of
5756 * injection on the service times of only the first requests of
5757 * bfqq. The reason for this restriction is that these are the
5758 * requests whose service time is affected most, because they are the
5759 * first to arrive after injection possibly occurred.
5760 *
5761 * To evaluate the effect of injection, the algorithm measures the
5762 * "total service time" of first requests. We define as total service
5763 * time of an I/O request, the time that elapses since when the
5764 * request is enqueued into bfqq, to when it is completed. This
5765 * quantity allows the whole effect of injection to be measured. It is
5766 * easy to see why. Suppose that some requests of other queues are
5767 * actually injected while bfqq is empty, and that a new request R
5768 * then arrives for bfqq. If the device does start to serve all or
5769 * part of the injected requests during the service hole, then,
5770 * because of this extra service, it may delay the next invocation of
5771 * the dispatch hook of BFQ. Then, even after R gets eventually
5772 * dispatched, the device may delay the actual service of R if it is
5773 * still busy serving the extra requests, or if it decides to serve,
5774 * before R, some extra request still present in its queues. As a
5775 * conclusion, the cumulative extra delay caused by injection can be
5776 * easily evaluated by just comparing the total service time of first
5777 * requests with and without injection.
5778 *
5779 * The limit-update algorithm works as follows. On the arrival of a
5780 * first request of bfqq, the algorithm measures the total time of the
5781 * request only if one of the three cases below holds, and, for each
5782 * case, it updates the limit as described below:
5783 *
5784 * (1) If there is no in-flight request. This gives a baseline for the
5785 * total service time of the requests of bfqq. If the baseline has
5786 * not been computed yet, then, after computing it, the limit is
5787 * set to 1, to start boosting throughput, and to prepare the
5788 * ground for the next case. If the baseline has already been
5789 * computed, then it is updated, in case it results to be lower
5790 * than the previous value.
5791 *
5792 * (2) If the limit is higher than 0 and there are in-flight
5793 * requests. By comparing the total service time in this case with
5794 * the above baseline, it is possible to know at which extent the
5795 * current value of the limit is inflating the total service
5796 * time. If the inflation is below a certain threshold, then bfqq
5797 * is assumed to be suffering from no perceivable loss of its
5798 * service guarantees, and the limit is even tentatively
5799 * increased. If the inflation is above the threshold, then the
5800 * limit is decreased. Due to the lack of any hysteresis, this
5801 * logic makes the limit oscillate even in steady workload
5802 * conditions. Yet we opted for it, because it is fast in reaching
5803 * the best value for the limit, as a function of the current I/O
5804 * workload. To reduce oscillations, this step is disabled for a
5805 * short time interval after the limit happens to be decreased.
5806 *
5807 * (3) Periodically, after resetting the limit, to make sure that the
5808 * limit eventually drops in case the workload changes. This is
5809 * needed because, after the limit has gone safely up for a
5810 * certain workload, it is impossible to guess whether the
5811 * baseline total service time may have changed, without measuring
5812 * it again without injection. A more effective version of this
5813 * step might be to just sample the baseline, by interrupting
5814 * injection only once, and then to reset/lower the limit only if
5815 * the total service time with the current limit does happen to be
5816 * too large.
5817 *
5818 * More details on each step are provided in the comments on the
5819 * pieces of code that implement these steps: the branch handling the
5820 * transition from empty to non empty in bfq_add_request(), the branch
5821 * handling injection in bfq_select_queue(), and the function
5822 * bfq_choose_bfqq_for_injection(). These comments also explain some
5823 * exceptions, made by the injection mechanism in some special cases.
5824 */
5825 static void bfq_update_inject_limit(struct bfq_data *bfqd,
5826 struct bfq_queue *bfqq)
5827 {
5828 u64 tot_time_ns = ktime_get_ns() - bfqd->last_empty_occupied_ns;
5829 unsigned int old_limit = bfqq->inject_limit;
5830
5831 if (bfqq->last_serv_time_ns > 0 && bfqd->rqs_injected) {
5832 u64 threshold = (bfqq->last_serv_time_ns * 3)>>1;
5833
5834 if (tot_time_ns >= threshold && old_limit > 0) {
5835 bfqq->inject_limit--;
5836 bfqq->decrease_time_jif = jiffies;
5837 } else if (tot_time_ns < threshold &&
5838 old_limit <= bfqd->max_rq_in_driver)
5839 bfqq->inject_limit++;
5840 }
5841
5842 /*
5843 * Either we still have to compute the base value for the
5844 * total service time, and there seem to be the right
5845 * conditions to do it, or we can lower the last base value
5846 * computed.
5847 *
5848 * NOTE: (bfqd->rq_in_driver == 1) means that there is no I/O
5849 * request in flight, because this function is in the code
5850 * path that handles the completion of a request of bfqq, and,
5851 * in particular, this function is executed before
5852 * bfqd->rq_in_driver is decremented in such a code path.
5853 */
5854 if ((bfqq->last_serv_time_ns == 0 && bfqd->rq_in_driver == 1) ||
5855 tot_time_ns < bfqq->last_serv_time_ns) {
5856 if (bfqq->last_serv_time_ns == 0) {
5857 /*
5858 * Now we certainly have a base value: make sure we
5859 * start trying injection.
5860 */
5861 bfqq->inject_limit = max_t(unsigned int, 1, old_limit);
5862 }
5863 bfqq->last_serv_time_ns = tot_time_ns;
5864 } else if (!bfqd->rqs_injected && bfqd->rq_in_driver == 1)
5865 /*
5866 * No I/O injected and no request still in service in
5867 * the drive: these are the exact conditions for
5868 * computing the base value of the total service time
5869 * for bfqq. So let's update this value, because it is
5870 * rather variable. For example, it varies if the size
5871 * or the spatial locality of the I/O requests in bfqq
5872 * change.
5873 */
5874 bfqq->last_serv_time_ns = tot_time_ns;
5875
5876
5877 /* update complete, not waiting for any request completion any longer */
5878 bfqd->waited_rq = NULL;
5879 bfqd->rqs_injected = false;
5880 }
5881
5882 /*
5883 * Handle either a requeue or a finish for rq. The things to do are
5884 * the same in both cases: all references to rq are to be dropped. In
5885 * particular, rq is considered completed from the point of view of
5886 * the scheduler.
5887 */
5888 static void bfq_finish_requeue_request(struct request *rq)
5889 {
5890 struct bfq_queue *bfqq = RQ_BFQQ(rq);
5891 struct bfq_data *bfqd;
5892
5893 /*
5894 * Requeue and finish hooks are invoked in blk-mq without
5895 * checking whether the involved request is actually still
5896 * referenced in the scheduler. To handle this fact, the
5897 * following two checks make this function exit in case of
5898 * spurious invocations, for which there is nothing to do.
5899 *
5900 * First, check whether rq has nothing to do with an elevator.
5901 */
5902 if (unlikely(!(rq->rq_flags & RQF_ELVPRIV)))
5903 return;
5904
5905 /*
5906 * rq either is not associated with any icq, or is an already
5907 * requeued request that has not (yet) been re-inserted into
5908 * a bfq_queue.
5909 */
5910 if (!rq->elv.icq || !bfqq)
5911 return;
5912
5913 bfqd = bfqq->bfqd;
5914
5915 if (rq->rq_flags & RQF_STARTED)
5916 bfqg_stats_update_completion(bfqq_group(bfqq),
5917 rq->start_time_ns,
5918 rq->io_start_time_ns,
5919 rq->cmd_flags);
5920
5921 if (likely(rq->rq_flags & RQF_STARTED)) {
5922 unsigned long flags;
5923
5924 spin_lock_irqsave(&bfqd->lock, flags);
5925
5926 if (rq == bfqd->waited_rq)
5927 bfq_update_inject_limit(bfqd, bfqq);
5928
5929 bfq_completed_request(bfqq, bfqd);
5930 bfq_finish_requeue_request_body(bfqq);
5931
5932 spin_unlock_irqrestore(&bfqd->lock, flags);
5933 } else {
5934 /*
5935 * Request rq may be still/already in the scheduler,
5936 * in which case we need to remove it (this should
5937 * never happen in case of requeue). And we cannot
5938 * defer such a check and removal, to avoid
5939 * inconsistencies in the time interval from the end
5940 * of this function to the start of the deferred work.
5941 * This situation seems to occur only in process
5942 * context, as a consequence of a merge. In the
5943 * current version of the code, this implies that the
5944 * lock is held.
5945 */
5946
5947 if (!RB_EMPTY_NODE(&rq->rb_node)) {
5948 bfq_remove_request(rq->q, rq);
5949 bfqg_stats_update_io_remove(bfqq_group(bfqq),
5950 rq->cmd_flags);
5951 }
5952 bfq_finish_requeue_request_body(bfqq);
5953 }
5954
5955 /*
5956 * Reset private fields. In case of a requeue, this allows
5957 * this function to correctly do nothing if it is spuriously
5958 * invoked again on this same request (see the check at the
5959 * beginning of the function). Probably, a better general
5960 * design would be to prevent blk-mq from invoking the requeue
5961 * or finish hooks of an elevator, for a request that is not
5962 * referred by that elevator.
5963 *
5964 * Resetting the following fields would break the
5965 * request-insertion logic if rq is re-inserted into a bfq
5966 * internal queue, without a re-preparation. Here we assume
5967 * that re-insertions of requeued requests, without
5968 * re-preparation, can happen only for pass_through or at_head
5969 * requests (which are not re-inserted into bfq internal
5970 * queues).
5971 */
5972 rq->elv.priv[0] = NULL;
5973 rq->elv.priv[1] = NULL;
5974 }
5975
5976 /*
5977 * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
5978 * was the last process referring to that bfqq.
5979 */
5980 static struct bfq_queue *
5981 bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
5982 {
5983 bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
5984
5985 if (bfqq_process_refs(bfqq) == 1) {
5986 bfqq->pid = current->pid;
5987 bfq_clear_bfqq_coop(bfqq);
5988 bfq_clear_bfqq_split_coop(bfqq);
5989 return bfqq;
5990 }
5991
5992 bic_set_bfqq(bic, NULL, 1);
5993
5994 bfq_put_cooperator(bfqq);
5995
5996 bfq_release_process_ref(bfqq->bfqd, bfqq);
5997 return NULL;
5998 }
5999
6000 static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
6001 struct bfq_io_cq *bic,
6002 struct bio *bio,
6003 bool split, bool is_sync,
6004 bool *new_queue)
6005 {
6006 struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
6007
6008 if (likely(bfqq && bfqq != &bfqd->oom_bfqq))
6009 return bfqq;
6010
6011 if (new_queue)
6012 *new_queue = true;
6013
6014 if (bfqq)
6015 bfq_put_queue(bfqq);
6016 bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
6017
6018 bic_set_bfqq(bic, bfqq, is_sync);
6019 if (split && is_sync) {
6020 if ((bic->was_in_burst_list && bfqd->large_burst) ||
6021 bic->saved_in_large_burst)
6022 bfq_mark_bfqq_in_large_burst(bfqq);
6023 else {
6024 bfq_clear_bfqq_in_large_burst(bfqq);
6025 if (bic->was_in_burst_list)
6026 /*
6027 * If bfqq was in the current
6028 * burst list before being
6029 * merged, then we have to add
6030 * it back. And we do not need
6031 * to increase burst_size, as
6032 * we did not decrement
6033 * burst_size when we removed
6034 * bfqq from the burst list as
6035 * a consequence of a merge
6036 * (see comments in
6037 * bfq_put_queue). In this
6038 * respect, it would be rather
6039 * costly to know whether the
6040 * current burst list is still
6041 * the same burst list from
6042 * which bfqq was removed on
6043 * the merge. To avoid this
6044 * cost, if bfqq was in a
6045 * burst list, then we add
6046 * bfqq to the current burst
6047 * list without any further
6048 * check. This can cause
6049 * inappropriate insertions,
6050 * but rarely enough to not
6051 * harm the detection of large
6052 * bursts significantly.
6053 */
6054 hlist_add_head(&bfqq->burst_list_node,
6055 &bfqd->burst_list);
6056 }
6057 bfqq->split_time = jiffies;
6058 }
6059
6060 return bfqq;
6061 }
6062
6063 /*
6064 * Only reset private fields. The actual request preparation will be
6065 * performed by bfq_init_rq, when rq is either inserted or merged. See
6066 * comments on bfq_init_rq for the reason behind this delayed
6067 * preparation.
6068 */
6069 static void bfq_prepare_request(struct request *rq, struct bio *bio)
6070 {
6071 /*
6072 * Regardless of whether we have an icq attached, we have to
6073 * clear the scheduler pointers, as they might point to
6074 * previously allocated bic/bfqq structs.
6075 */
6076 rq->elv.priv[0] = rq->elv.priv[1] = NULL;
6077 }
6078
6079 /*
6080 * If needed, init rq, allocate bfq data structures associated with
6081 * rq, and increment reference counters in the destination bfq_queue
6082 * for rq. Return the destination bfq_queue for rq, or NULL is rq is
6083 * not associated with any bfq_queue.
6084 *
6085 * This function is invoked by the functions that perform rq insertion
6086 * or merging. One may have expected the above preparation operations
6087 * to be performed in bfq_prepare_request, and not delayed to when rq
6088 * is inserted or merged. The rationale behind this delayed
6089 * preparation is that, after the prepare_request hook is invoked for
6090 * rq, rq may still be transformed into a request with no icq, i.e., a
6091 * request not associated with any queue. No bfq hook is invoked to
6092 * signal this transformation. As a consequence, should these
6093 * preparation operations be performed when the prepare_request hook
6094 * is invoked, and should rq be transformed one moment later, bfq
6095 * would end up in an inconsistent state, because it would have
6096 * incremented some queue counters for an rq destined to
6097 * transformation, without any chance to correctly lower these
6098 * counters back. In contrast, no transformation can still happen for
6099 * rq after rq has been inserted or merged. So, it is safe to execute
6100 * these preparation operations when rq is finally inserted or merged.
6101 */
6102 static struct bfq_queue *bfq_init_rq(struct request *rq)
6103 {
6104 struct request_queue *q = rq->q;
6105 struct bio *bio = rq->bio;
6106 struct bfq_data *bfqd = q->elevator->elevator_data;
6107 struct bfq_io_cq *bic;
6108 const int is_sync = rq_is_sync(rq);
6109 struct bfq_queue *bfqq;
6110 bool new_queue = false;
6111 bool bfqq_already_existing = false, split = false;
6112
6113 if (unlikely(!rq->elv.icq))
6114 return NULL;
6115
6116 /*
6117 * Assuming that elv.priv[1] is set only if everything is set
6118 * for this rq. This holds true, because this function is
6119 * invoked only for insertion or merging, and, after such
6120 * events, a request cannot be manipulated any longer before
6121 * being removed from bfq.
6122 */
6123 if (rq->elv.priv[1])
6124 return rq->elv.priv[1];
6125
6126 bic = icq_to_bic(rq->elv.icq);
6127
6128 bfq_check_ioprio_change(bic, bio);
6129
6130 bfq_bic_update_cgroup(bic, bio);
6131
6132 bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
6133 &new_queue);
6134
6135 if (likely(!new_queue)) {
6136 /* If the queue was seeky for too long, break it apart. */
6137 if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
6138 bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
6139
6140 /* Update bic before losing reference to bfqq */
6141 if (bfq_bfqq_in_large_burst(bfqq))
6142 bic->saved_in_large_burst = true;
6143
6144 bfqq = bfq_split_bfqq(bic, bfqq);
6145 split = true;
6146
6147 if (!bfqq)
6148 bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
6149 true, is_sync,
6150 NULL);
6151 else
6152 bfqq_already_existing = true;
6153 }
6154 }
6155
6156 bfqq->allocated++;
6157 bfqq->ref++;
6158 bfq_log_bfqq(bfqd, bfqq, "get_request %p: bfqq %p, %d",
6159 rq, bfqq, bfqq->ref);
6160
6161 rq->elv.priv[0] = bic;
6162 rq->elv.priv[1] = bfqq;
6163
6164 /*
6165 * If a bfq_queue has only one process reference, it is owned
6166 * by only this bic: we can then set bfqq->bic = bic. in
6167 * addition, if the queue has also just been split, we have to
6168 * resume its state.
6169 */
6170 if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
6171 bfqq->bic = bic;
6172 if (split) {
6173 /*
6174 * The queue has just been split from a shared
6175 * queue: restore the idle window and the
6176 * possible weight raising period.
6177 */
6178 bfq_bfqq_resume_state(bfqq, bfqd, bic,
6179 bfqq_already_existing);
6180 }
6181 }
6182
6183 /*
6184 * Consider bfqq as possibly belonging to a burst of newly
6185 * created queues only if:
6186 * 1) A burst is actually happening (bfqd->burst_size > 0)
6187 * or
6188 * 2) There is no other active queue. In fact, if, in
6189 * contrast, there are active queues not belonging to the
6190 * possible burst bfqq may belong to, then there is no gain
6191 * in considering bfqq as belonging to a burst, and
6192 * therefore in not weight-raising bfqq. See comments on
6193 * bfq_handle_burst().
6194 *
6195 * This filtering also helps eliminating false positives,
6196 * occurring when bfqq does not belong to an actual large
6197 * burst, but some background task (e.g., a service) happens
6198 * to trigger the creation of new queues very close to when
6199 * bfqq and its possible companion queues are created. See
6200 * comments on bfq_handle_burst() for further details also on
6201 * this issue.
6202 */
6203 if (unlikely(bfq_bfqq_just_created(bfqq) &&
6204 (bfqd->burst_size > 0 ||
6205 bfq_tot_busy_queues(bfqd) == 0)))
6206 bfq_handle_burst(bfqd, bfqq);
6207
6208 return bfqq;
6209 }
6210
6211 static void
6212 bfq_idle_slice_timer_body(struct bfq_data *bfqd, struct bfq_queue *bfqq)
6213 {
6214 enum bfqq_expiration reason;
6215 unsigned long flags;
6216
6217 spin_lock_irqsave(&bfqd->lock, flags);
6218
6219 /*
6220 * Considering that bfqq may be in race, we should firstly check
6221 * whether bfqq is in service before doing something on it. If
6222 * the bfqq in race is not in service, it has already been expired
6223 * through __bfq_bfqq_expire func and its wait_request flags has
6224 * been cleared in __bfq_bfqd_reset_in_service func.
6225 */
6226 if (bfqq != bfqd->in_service_queue) {
6227 spin_unlock_irqrestore(&bfqd->lock, flags);
6228 return;
6229 }
6230
6231 bfq_clear_bfqq_wait_request(bfqq);
6232
6233 if (bfq_bfqq_budget_timeout(bfqq))
6234 /*
6235 * Also here the queue can be safely expired
6236 * for budget timeout without wasting
6237 * guarantees
6238 */
6239 reason = BFQQE_BUDGET_TIMEOUT;
6240 else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0)
6241 /*
6242 * The queue may not be empty upon timer expiration,
6243 * because we may not disable the timer when the
6244 * first request of the in-service queue arrives
6245 * during disk idling.
6246 */
6247 reason = BFQQE_TOO_IDLE;
6248 else
6249 goto schedule_dispatch;
6250
6251 bfq_bfqq_expire(bfqd, bfqq, true, reason);
6252
6253 schedule_dispatch:
6254 spin_unlock_irqrestore(&bfqd->lock, flags);
6255 bfq_schedule_dispatch(bfqd);
6256 }
6257
6258 /*
6259 * Handler of the expiration of the timer running if the in-service queue
6260 * is idling inside its time slice.
6261 */
6262 static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
6263 {
6264 struct bfq_data *bfqd = container_of(timer, struct bfq_data,
6265 idle_slice_timer);
6266 struct bfq_queue *bfqq = bfqd->in_service_queue;
6267
6268 /*
6269 * Theoretical race here: the in-service queue can be NULL or
6270 * different from the queue that was idling if a new request
6271 * arrives for the current queue and there is a full dispatch
6272 * cycle that changes the in-service queue. This can hardly
6273 * happen, but in the worst case we just expire a queue too
6274 * early.
6275 */
6276 if (bfqq)
6277 bfq_idle_slice_timer_body(bfqd, bfqq);
6278
6279 return HRTIMER_NORESTART;
6280 }
6281
6282 static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
6283 struct bfq_queue **bfqq_ptr)
6284 {
6285 struct bfq_queue *bfqq = *bfqq_ptr;
6286
6287 bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
6288 if (bfqq) {
6289 bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
6290
6291 bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
6292 bfqq, bfqq->ref);
6293 bfq_put_queue(bfqq);
6294 *bfqq_ptr = NULL;
6295 }
6296 }
6297
6298 /*
6299 * Release all the bfqg references to its async queues. If we are
6300 * deallocating the group these queues may still contain requests, so
6301 * we reparent them to the root cgroup (i.e., the only one that will
6302 * exist for sure until all the requests on a device are gone).
6303 */
6304 void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
6305 {
6306 int i, j;
6307
6308 for (i = 0; i < 2; i++)
6309 for (j = 0; j < IOPRIO_BE_NR; j++)
6310 __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]);
6311
6312 __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
6313 }
6314
6315 /*
6316 * See the comments on bfq_limit_depth for the purpose of
6317 * the depths set in the function. Return minimum shallow depth we'll use.
6318 */
6319 static unsigned int bfq_update_depths(struct bfq_data *bfqd,
6320 struct sbitmap_queue *bt)
6321 {
6322 unsigned int i, j, min_shallow = UINT_MAX;
6323
6324 /*
6325 * In-word depths if no bfq_queue is being weight-raised:
6326 * leaving 25% of tags only for sync reads.
6327 *
6328 * In next formulas, right-shift the value
6329 * (1U<<bt->sb.shift), instead of computing directly
6330 * (1U<<(bt->sb.shift - something)), to be robust against
6331 * any possible value of bt->sb.shift, without having to
6332 * limit 'something'.
6333 */
6334 /* no more than 50% of tags for async I/O */
6335 bfqd->word_depths[0][0] = max((1U << bt->sb.shift) >> 1, 1U);
6336 /*
6337 * no more than 75% of tags for sync writes (25% extra tags
6338 * w.r.t. async I/O, to prevent async I/O from starving sync
6339 * writes)
6340 */
6341 bfqd->word_depths[0][1] = max(((1U << bt->sb.shift) * 3) >> 2, 1U);
6342
6343 /*
6344 * In-word depths in case some bfq_queue is being weight-
6345 * raised: leaving ~63% of tags for sync reads. This is the
6346 * highest percentage for which, in our tests, application
6347 * start-up times didn't suffer from any regression due to tag
6348 * shortage.
6349 */
6350 /* no more than ~18% of tags for async I/O */
6351 bfqd->word_depths[1][0] = max(((1U << bt->sb.shift) * 3) >> 4, 1U);
6352 /* no more than ~37% of tags for sync writes (~20% extra tags) */
6353 bfqd->word_depths[1][1] = max(((1U << bt->sb.shift) * 6) >> 4, 1U);
6354
6355 for (i = 0; i < 2; i++)
6356 for (j = 0; j < 2; j++)
6357 min_shallow = min(min_shallow, bfqd->word_depths[i][j]);
6358
6359 return min_shallow;
6360 }
6361
6362 static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)
6363 {
6364 struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
6365 struct blk_mq_tags *tags = hctx->sched_tags;
6366 unsigned int min_shallow;
6367
6368 min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags);
6369 sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow);
6370 }
6371
6372 static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
6373 {
6374 bfq_depth_updated(hctx);
6375 return 0;
6376 }
6377
6378 static void bfq_exit_queue(struct elevator_queue *e)
6379 {
6380 struct bfq_data *bfqd = e->elevator_data;
6381 struct bfq_queue *bfqq, *n;
6382
6383 hrtimer_cancel(&bfqd->idle_slice_timer);
6384
6385 spin_lock_irq(&bfqd->lock);
6386 list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
6387 bfq_deactivate_bfqq(bfqd, bfqq, false, false);
6388 spin_unlock_irq(&bfqd->lock);
6389
6390 hrtimer_cancel(&bfqd->idle_slice_timer);
6391
6392 /* release oom-queue reference to root group */
6393 bfqg_and_blkg_put(bfqd->root_group);
6394
6395 #ifdef CONFIG_BFQ_GROUP_IOSCHED
6396 blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq);
6397 #else
6398 spin_lock_irq(&bfqd->lock);
6399 bfq_put_async_queues(bfqd, bfqd->root_group);
6400 kfree(bfqd->root_group);
6401 spin_unlock_irq(&bfqd->lock);
6402 #endif
6403
6404 kfree(bfqd);
6405 }
6406
6407 static void bfq_init_root_group(struct bfq_group *root_group,
6408 struct bfq_data *bfqd)
6409 {
6410 int i;
6411
6412 #ifdef CONFIG_BFQ_GROUP_IOSCHED
6413 root_group->entity.parent = NULL;
6414 root_group->my_entity = NULL;
6415 root_group->bfqd = bfqd;
6416 #endif
6417 root_group->rq_pos_tree = RB_ROOT;
6418 for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
6419 root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
6420 root_group->sched_data.bfq_class_idle_last_service = jiffies;
6421 }
6422
6423 static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
6424 {
6425 struct bfq_data *bfqd;
6426 struct elevator_queue *eq;
6427
6428 eq = elevator_alloc(q, e);
6429 if (!eq)
6430 return -ENOMEM;
6431
6432 bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
6433 if (!bfqd) {
6434 kobject_put(&eq->kobj);
6435 return -ENOMEM;
6436 }
6437 eq->elevator_data = bfqd;
6438
6439 spin_lock_irq(&q->queue_lock);
6440 q->elevator = eq;
6441 spin_unlock_irq(&q->queue_lock);
6442
6443 /*
6444 * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
6445 * Grab a permanent reference to it, so that the normal code flow
6446 * will not attempt to free it.
6447 */
6448 bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0);
6449 bfqd->oom_bfqq.ref++;
6450 bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO;
6451 bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE;
6452 bfqd->oom_bfqq.entity.new_weight =
6453 bfq_ioprio_to_weight(bfqd->oom_bfqq.new_ioprio);
6454
6455 /* oom_bfqq does not participate to bursts */
6456 bfq_clear_bfqq_just_created(&bfqd->oom_bfqq);
6457
6458 /*
6459 * Trigger weight initialization, according to ioprio, at the
6460 * oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio
6461 * class won't be changed any more.
6462 */
6463 bfqd->oom_bfqq.entity.prio_changed = 1;
6464
6465 bfqd->queue = q;
6466
6467 INIT_LIST_HEAD(&bfqd->dispatch);
6468
6469 hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
6470 HRTIMER_MODE_REL);
6471 bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
6472
6473 bfqd->queue_weights_tree = RB_ROOT_CACHED;
6474 bfqd->num_groups_with_pending_reqs = 0;
6475
6476 INIT_LIST_HEAD(&bfqd->active_list);
6477 INIT_LIST_HEAD(&bfqd->idle_list);
6478 INIT_HLIST_HEAD(&bfqd->burst_list);
6479
6480 bfqd->hw_tag = -1;
6481 bfqd->nonrot_with_queueing = blk_queue_nonrot(bfqd->queue);
6482
6483 bfqd->bfq_max_budget = bfq_default_max_budget;
6484
6485 bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0];
6486 bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1];
6487 bfqd->bfq_back_max = bfq_back_max;
6488 bfqd->bfq_back_penalty = bfq_back_penalty;
6489 bfqd->bfq_slice_idle = bfq_slice_idle;
6490 bfqd->bfq_timeout = bfq_timeout;
6491
6492 bfqd->bfq_requests_within_timer = 120;
6493
6494 bfqd->bfq_large_burst_thresh = 8;
6495 bfqd->bfq_burst_interval = msecs_to_jiffies(180);
6496
6497 bfqd->low_latency = true;
6498
6499 /*
6500 * Trade-off between responsiveness and fairness.
6501 */
6502 bfqd->bfq_wr_coeff = 30;
6503 bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300);
6504 bfqd->bfq_wr_max_time = 0;
6505 bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000);
6506 bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500);
6507 bfqd->bfq_wr_max_softrt_rate = 7000; /*
6508 * Approximate rate required
6509 * to playback or record a
6510 * high-definition compressed
6511 * video.
6512 */
6513 bfqd->wr_busy_queues = 0;
6514
6515 /*
6516 * Begin by assuming, optimistically, that the device peak
6517 * rate is equal to 2/3 of the highest reference rate.
6518 */
6519 bfqd->rate_dur_prod = ref_rate[blk_queue_nonrot(bfqd->queue)] *
6520 ref_wr_duration[blk_queue_nonrot(bfqd->queue)];
6521 bfqd->peak_rate = ref_rate[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
6522
6523 spin_lock_init(&bfqd->lock);
6524
6525 /*
6526 * The invocation of the next bfq_create_group_hierarchy
6527 * function is the head of a chain of function calls
6528 * (bfq_create_group_hierarchy->blkcg_activate_policy->
6529 * blk_mq_freeze_queue) that may lead to the invocation of the
6530 * has_work hook function. For this reason,
6531 * bfq_create_group_hierarchy is invoked only after all
6532 * scheduler data has been initialized, apart from the fields
6533 * that can be initialized only after invoking
6534 * bfq_create_group_hierarchy. This, in particular, enables
6535 * has_work to correctly return false. Of course, to avoid
6536 * other inconsistencies, the blk-mq stack must then refrain
6537 * from invoking further scheduler hooks before this init
6538 * function is finished.
6539 */
6540 bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node);
6541 if (!bfqd->root_group)
6542 goto out_free;
6543 bfq_init_root_group(bfqd->root_group, bfqd);
6544 bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);
6545
6546 wbt_disable_default(q);
6547 return 0;
6548
6549 out_free:
6550 kfree(bfqd);
6551 kobject_put(&eq->kobj);
6552 return -ENOMEM;
6553 }
6554
6555 static void bfq_slab_kill(void)
6556 {
6557 kmem_cache_destroy(bfq_pool);
6558 }
6559
6560 static int __init bfq_slab_setup(void)
6561 {
6562 bfq_pool = KMEM_CACHE(bfq_queue, 0);
6563 if (!bfq_pool)
6564 return -ENOMEM;
6565 return 0;
6566 }
6567
6568 static ssize_t bfq_var_show(unsigned int var, char *page)
6569 {
6570 return sprintf(page, "%u\n", var);
6571 }
6572
6573 static int bfq_var_store(unsigned long *var, const char *page)
6574 {
6575 unsigned long new_val;
6576 int ret = kstrtoul(page, 10, &new_val);
6577
6578 if (ret)
6579 return ret;
6580 *var = new_val;
6581 return 0;
6582 }
6583
6584 #define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \
6585 static ssize_t __FUNC(struct elevator_queue *e, char *page) \
6586 { \
6587 struct bfq_data *bfqd = e->elevator_data; \
6588 u64 __data = __VAR; \
6589 if (__CONV == 1) \
6590 __data = jiffies_to_msecs(__data); \
6591 else if (__CONV == 2) \
6592 __data = div_u64(__data, NSEC_PER_MSEC); \
6593 return bfq_var_show(__data, (page)); \
6594 }
6595 SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2);
6596 SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2);
6597 SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0);
6598 SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0);
6599 SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 2);
6600 SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
6601 SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1);
6602 SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0);
6603 SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
6604 #undef SHOW_FUNCTION
6605
6606 #define USEC_SHOW_FUNCTION(__FUNC, __VAR) \
6607 static ssize_t __FUNC(struct elevator_queue *e, char *page) \
6608 { \
6609 struct bfq_data *bfqd = e->elevator_data; \
6610 u64 __data = __VAR; \
6611 __data = div_u64(__data, NSEC_PER_USEC); \
6612 return bfq_var_show(__data, (page)); \
6613 }
6614 USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle);
6615 #undef USEC_SHOW_FUNCTION
6616
6617 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \
6618 static ssize_t \
6619 __FUNC(struct elevator_queue *e, const char *page, size_t count) \
6620 { \
6621 struct bfq_data *bfqd = e->elevator_data; \
6622 unsigned long __data, __min = (MIN), __max = (MAX); \
6623 int ret; \
6624 \
6625 ret = bfq_var_store(&__data, (page)); \
6626 if (ret) \
6627 return ret; \
6628 if (__data < __min) \
6629 __data = __min; \
6630 else if (__data > __max) \
6631 __data = __max; \
6632 if (__CONV == 1) \
6633 *(__PTR) = msecs_to_jiffies(__data); \
6634 else if (__CONV == 2) \
6635 *(__PTR) = (u64)__data * NSEC_PER_MSEC; \
6636 else \
6637 *(__PTR) = __data; \
6638 return count; \
6639 }
6640 STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
6641 INT_MAX, 2);
6642 STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
6643 INT_MAX, 2);
6644 STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0);
6645 STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1,
6646 INT_MAX, 0);
6647 STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2);
6648 #undef STORE_FUNCTION
6649
6650 #define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX) \
6651 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\
6652 { \
6653 struct bfq_data *bfqd = e->elevator_data; \
6654 unsigned long __data, __min = (MIN), __max = (MAX); \
6655 int ret; \
6656 \
6657 ret = bfq_var_store(&__data, (page)); \
6658 if (ret) \
6659 return ret; \
6660 if (__data < __min) \
6661 __data = __min; \
6662 else if (__data > __max) \
6663 __data = __max; \
6664 *(__PTR) = (u64)__data * NSEC_PER_USEC; \
6665 return count; \
6666 }
6667 USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0,
6668 UINT_MAX);
6669 #undef USEC_STORE_FUNCTION
6670
6671 static ssize_t bfq_max_budget_store(struct elevator_queue *e,
6672 const char *page, size_t count)
6673 {
6674 struct bfq_data *bfqd = e->elevator_data;
6675 unsigned long __data;
6676 int ret;
6677
6678 ret = bfq_var_store(&__data, (page));
6679 if (ret)
6680 return ret;
6681
6682 if (__data == 0)
6683 bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
6684 else {
6685 if (__data > INT_MAX)
6686 __data = INT_MAX;
6687 bfqd->bfq_max_budget = __data;
6688 }
6689
6690 bfqd->bfq_user_max_budget = __data;
6691
6692 return count;
6693 }
6694
6695 /*
6696 * Leaving this name to preserve name compatibility with cfq
6697 * parameters, but this timeout is used for both sync and async.
6698 */
6699 static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
6700 const char *page, size_t count)
6701 {
6702 struct bfq_data *bfqd = e->elevator_data;
6703 unsigned long __data;
6704 int ret;
6705
6706 ret = bfq_var_store(&__data, (page));
6707 if (ret)
6708 return ret;
6709
6710 if (__data < 1)
6711 __data = 1;
6712 else if (__data > INT_MAX)
6713 __data = INT_MAX;
6714
6715 bfqd->bfq_timeout = msecs_to_jiffies(__data);
6716 if (bfqd->bfq_user_max_budget == 0)
6717 bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
6718
6719 return count;
6720 }
6721
6722 static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e,
6723 const char *page, size_t count)
6724 {
6725 struct bfq_data *bfqd = e->elevator_data;
6726 unsigned long __data;
6727 int ret;
6728
6729 ret = bfq_var_store(&__data, (page));
6730 if (ret)
6731 return ret;
6732
6733 if (__data > 1)
6734 __data = 1;
6735 if (!bfqd->strict_guarantees && __data == 1
6736 && bfqd->bfq_slice_idle < 8 * NSEC_PER_MSEC)
6737 bfqd->bfq_slice_idle = 8 * NSEC_PER_MSEC;
6738
6739 bfqd->strict_guarantees = __data;
6740
6741 return count;
6742 }
6743
6744 static ssize_t bfq_low_latency_store(struct elevator_queue *e,
6745 const char *page, size_t count)
6746 {
6747 struct bfq_data *bfqd = e->elevator_data;
6748 unsigned long __data;
6749 int ret;
6750
6751 ret = bfq_var_store(&__data, (page));
6752 if (ret)
6753 return ret;
6754
6755 if (__data > 1)
6756 __data = 1;
6757 if (__data == 0 && bfqd->low_latency != 0)
6758 bfq_end_wr(bfqd);
6759 bfqd->low_latency = __data;
6760
6761 return count;
6762 }
6763
6764 #define BFQ_ATTR(name) \
6765 __ATTR(name, 0644, bfq_##name##_show, bfq_##name##_store)
6766
6767 static struct elv_fs_entry bfq_attrs[] = {
6768 BFQ_ATTR(fifo_expire_sync),
6769 BFQ_ATTR(fifo_expire_async),
6770 BFQ_ATTR(back_seek_max),
6771 BFQ_ATTR(back_seek_penalty),
6772 BFQ_ATTR(slice_idle),
6773 BFQ_ATTR(slice_idle_us),
6774 BFQ_ATTR(max_budget),
6775 BFQ_ATTR(timeout_sync),
6776 BFQ_ATTR(strict_guarantees),
6777 BFQ_ATTR(low_latency),
6778 __ATTR_NULL
6779 };
6780
6781 static struct elevator_type iosched_bfq_mq = {
6782 .ops = {
6783 .limit_depth = bfq_limit_depth,
6784 .prepare_request = bfq_prepare_request,
6785 .requeue_request = bfq_finish_requeue_request,
6786 .finish_request = bfq_finish_requeue_request,
6787 .exit_icq = bfq_exit_icq,
6788 .insert_requests = bfq_insert_requests,
6789 .dispatch_request = bfq_dispatch_request,
6790 .next_request = elv_rb_latter_request,
6791 .former_request = elv_rb_former_request,
6792 .allow_merge = bfq_allow_bio_merge,
6793 .bio_merge = bfq_bio_merge,
6794 .request_merge = bfq_request_merge,
6795 .requests_merged = bfq_requests_merged,
6796 .request_merged = bfq_request_merged,
6797 .has_work = bfq_has_work,
6798 .depth_updated = bfq_depth_updated,
6799 .init_hctx = bfq_init_hctx,
6800 .init_sched = bfq_init_queue,
6801 .exit_sched = bfq_exit_queue,
6802 },
6803
6804 .icq_size = sizeof(struct bfq_io_cq),
6805 .icq_align = __alignof__(struct bfq_io_cq),
6806 .elevator_attrs = bfq_attrs,
6807 .elevator_name = "bfq",
6808 .elevator_owner = THIS_MODULE,
6809 };
6810 MODULE_ALIAS("bfq-iosched");
6811
6812 static int __init bfq_init(void)
6813 {
6814 int ret;
6815
6816 #ifdef CONFIG_BFQ_GROUP_IOSCHED
6817 ret = blkcg_policy_register(&blkcg_policy_bfq);
6818 if (ret)
6819 return ret;
6820 #endif
6821
6822 ret = -ENOMEM;
6823 if (bfq_slab_setup())
6824 goto err_pol_unreg;
6825
6826 /*
6827 * Times to load large popular applications for the typical
6828 * systems installed on the reference devices (see the
6829 * comments before the definition of the next
6830 * array). Actually, we use slightly lower values, as the
6831 * estimated peak rate tends to be smaller than the actual
6832 * peak rate. The reason for this last fact is that estimates
6833 * are computed over much shorter time intervals than the long
6834 * intervals typically used for benchmarking. Why? First, to
6835 * adapt more quickly to variations. Second, because an I/O
6836 * scheduler cannot rely on a peak-rate-evaluation workload to
6837 * be run for a long time.
6838 */
6839 ref_wr_duration[0] = msecs_to_jiffies(7000); /* actually 8 sec */
6840 ref_wr_duration[1] = msecs_to_jiffies(2500); /* actually 3 sec */
6841
6842 ret = elv_register(&iosched_bfq_mq);
6843 if (ret)
6844 goto slab_kill;
6845
6846 return 0;
6847
6848 slab_kill:
6849 bfq_slab_kill();
6850 err_pol_unreg:
6851 #ifdef CONFIG_BFQ_GROUP_IOSCHED
6852 blkcg_policy_unregister(&blkcg_policy_bfq);
6853 #endif
6854 return ret;
6855 }
6856
6857 static void __exit bfq_exit(void)
6858 {
6859 elv_unregister(&iosched_bfq_mq);
6860 #ifdef CONFIG_BFQ_GROUP_IOSCHED
6861 blkcg_policy_unregister(&blkcg_policy_bfq);
6862 #endif
6863 bfq_slab_kill();
6864 }
6865
6866 module_init(bfq_init);
6867 module_exit(bfq_exit);
6868
6869 MODULE_AUTHOR("Paolo Valente");
6870 MODULE_LICENSE("GPL");
6871 MODULE_DESCRIPTION("MQ Budget Fair Queueing I/O Scheduler");