Blame view

block/blk-wbt.c 17.7 KB
e34cbd307   Jens Axboe   blk-wbt: add gene...
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
  /*
   * buffered writeback throttling. loosely based on CoDel. We can't drop
   * packets for IO scheduling, so the logic is something like this:
   *
   * - Monitor latencies in a defined window of time.
   * - If the minimum latency in the above window exceeds some target, increment
   *   scaling step and scale down queue depth by a factor of 2x. The monitoring
   *   window is then shrunk to 100 / sqrt(scaling step + 1).
   * - For any window where we don't have solid data on what the latencies
   *   look like, retain status quo.
   * - If latencies look good, decrement scaling step.
   * - If we're only doing writes, allow the scaling step to go negative. This
   *   will temporarily boost write performance, snapping back to a stable
   *   scaling step of 0 if reads show up or the heavy writers finish. Unlike
   *   positive scaling steps where we shrink the monitoring window, a negative
   *   scaling step retains the default step==0 window size.
   *
   * Copyright (C) 2016 Jens Axboe
   *
   */
  #include <linux/kernel.h>
  #include <linux/blk_types.h>
  #include <linux/slab.h>
  #include <linux/backing-dev.h>
  #include <linux/swap.h>
  
  #include "blk-wbt.h"
  
  #define CREATE_TRACE_POINTS
  #include <trace/events/wbt.h>
  
  enum {
  	/*
  	 * Default setting, we'll scale up (to 75% of QD max) or down (min 1)
  	 * from here depending on device stats
  	 */
  	RWB_DEF_DEPTH	= 16,
  
  	/*
  	 * 100msec window
  	 */
  	RWB_WINDOW_NSEC		= 100 * 1000 * 1000ULL,
  
  	/*
  	 * Disregard stats, if we don't meet this minimum
  	 */
  	RWB_MIN_WRITE_SAMPLES	= 3,
  
  	/*
  	 * If we have this number of consecutive windows with not enough
  	 * information to scale up or down, scale up.
  	 */
  	RWB_UNKNOWN_BUMP	= 5,
  };
  
  static inline bool rwb_enabled(struct rq_wb *rwb)
  {
  	return rwb && rwb->wb_normal != 0;
  }
  
  /*
   * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
   * false if 'v' + 1 would be bigger than 'below'.
   */
  static bool atomic_inc_below(atomic_t *v, int below)
  {
  	int cur = atomic_read(v);
  
  	for (;;) {
  		int old;
  
  		if (cur >= below)
  			return false;
  		old = atomic_cmpxchg(v, cur, cur + 1);
  		if (old == cur)
  			break;
  		cur = old;
  	}
  
  	return true;
  }
  
  static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  {
  	if (rwb_enabled(rwb)) {
  		const unsigned long cur = jiffies;
  
  		if (cur != *var)
  			*var = cur;
  	}
  }
  
  /*
   * If a task was rate throttled in balance_dirty_pages() within the last
   * second or so, use that to indicate a higher cleaning rate.
   */
  static bool wb_recent_wait(struct rq_wb *rwb)
  {
dc3b17cc8   Jan Kara   block: Use pointe...
99
  	struct bdi_writeback *wb = &rwb->queue->backing_dev_info->wb;
e34cbd307   Jens Axboe   blk-wbt: add gene...
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
  
  	return time_before(jiffies, wb->dirty_sleep + HZ);
  }
  
  static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, bool is_kswapd)
  {
  	return &rwb->rq_wait[is_kswapd];
  }
  
  static void rwb_wake_all(struct rq_wb *rwb)
  {
  	int i;
  
  	for (i = 0; i < WBT_NUM_RWQ; i++) {
  		struct rq_wait *rqw = &rwb->rq_wait[i];
  
  		if (waitqueue_active(&rqw->wait))
  			wake_up_all(&rqw->wait);
  	}
  }
  
  void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
  {
  	struct rq_wait *rqw;
  	int inflight, limit;
  
  	if (!(wb_acct & WBT_TRACKED))
  		return;
  
  	rqw = get_rq_wait(rwb, wb_acct & WBT_KSWAPD);
  	inflight = atomic_dec_return(&rqw->inflight);
  
  	/*
  	 * wbt got disabled with IO in flight. Wake up any potential
  	 * waiters, we don't have to do more than that.
  	 */
  	if (unlikely(!rwb_enabled(rwb))) {
  		rwb_wake_all(rwb);
  		return;
  	}
  
  	/*
  	 * If the device does write back caching, drop further down
  	 * before we wake people up.
  	 */
  	if (rwb->wc && !wb_recent_wait(rwb))
  		limit = 0;
  	else
  		limit = rwb->wb_normal;
  
  	/*
  	 * Don't wake anyone up if we are above the normal limit.
  	 */
  	if (inflight && inflight >= limit)
  		return;
  
  	if (waitqueue_active(&rqw->wait)) {
  		int diff = limit - inflight;
  
  		if (!inflight || diff >= rwb->wb_background / 2)
  			wake_up_all(&rqw->wait);
  	}
  }
  
  /*
   * Called on completion of a request. Note that it's also called when
   * a request is merged, when the request gets freed.
   */
  void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat)
  {
  	if (!rwb)
  		return;
  
  	if (!wbt_is_tracked(stat)) {
  		if (rwb->sync_cookie == stat) {
  			rwb->sync_issue = 0;
  			rwb->sync_cookie = NULL;
  		}
  
  		if (wbt_is_read(stat))
  			wb_timestamp(rwb, &rwb->last_comp);
  		wbt_clear_state(stat);
  	} else {
  		WARN_ON_ONCE(stat == rwb->sync_cookie);
  		__wbt_done(rwb, wbt_stat_to_mask(stat));
  		wbt_clear_state(stat);
  	}
  }
  
  /*
   * Return true, if we can't increase the depth further by scaling
   */
  static bool calc_wb_limits(struct rq_wb *rwb)
  {
  	unsigned int depth;
  	bool ret = false;
  
  	if (!rwb->min_lat_nsec) {
  		rwb->wb_max = rwb->wb_normal = rwb->wb_background = 0;
  		return false;
  	}
  
  	/*
  	 * For QD=1 devices, this is a special case. It's important for those
  	 * to have one request ready when one completes, so force a depth of
  	 * 2 for those devices. On the backend, it'll be a depth of 1 anyway,
  	 * since the device can't have more than that in flight. If we're
  	 * scaling down, then keep a setting of 1/1/1.
  	 */
  	if (rwb->queue_depth == 1) {
  		if (rwb->scale_step > 0)
  			rwb->wb_max = rwb->wb_normal = 1;
  		else {
  			rwb->wb_max = rwb->wb_normal = 2;
  			ret = true;
  		}
  		rwb->wb_background = 1;
  	} else {
  		/*
  		 * scale_step == 0 is our default state. If we have suffered
  		 * latency spikes, step will be > 0, and we shrink the
  		 * allowed write depths. If step is < 0, we're only doing
  		 * writes, and we allow a temporarily higher depth to
  		 * increase performance.
  		 */
  		depth = min_t(unsigned int, RWB_DEF_DEPTH, rwb->queue_depth);
  		if (rwb->scale_step > 0)
  			depth = 1 + ((depth - 1) >> min(31, rwb->scale_step));
  		else if (rwb->scale_step < 0) {
  			unsigned int maxd = 3 * rwb->queue_depth / 4;
  
  			depth = 1 + ((depth - 1) << -rwb->scale_step);
  			if (depth > maxd) {
  				depth = maxd;
  				ret = true;
  			}
  		}
  
  		/*
  		 * Set our max/normal/bg queue depths based on how far
  		 * we have scaled down (->scale_step).
  		 */
  		rwb->wb_max = depth;
  		rwb->wb_normal = (rwb->wb_max + 1) / 2;
  		rwb->wb_background = (rwb->wb_max + 3) / 4;
  	}
  
  	return ret;
  }
4121d385f   Arnd Bergmann   blk-wbt: fix old-...
249
  static inline bool stat_sample_valid(struct blk_rq_stat *stat)
e34cbd307   Jens Axboe   blk-wbt: add gene...
250
251
252
253
254
255
256
  {
  	/*
  	 * We need at least one read sample, and a minimum of
  	 * RWB_MIN_WRITE_SAMPLES. We require some write samples to know
  	 * that it's writes impacting us, and not just some sole read on
  	 * a device that is in a lower power state.
  	 */
fa2e39cb9   Omar Sandoval   blk-stat: use REA...
257
258
  	return (stat[READ].nr_samples >= 1 &&
  		stat[WRITE].nr_samples >= RWB_MIN_WRITE_SAMPLES);
e34cbd307   Jens Axboe   blk-wbt: add gene...
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
  }
  
  static u64 rwb_sync_issue_lat(struct rq_wb *rwb)
  {
  	u64 now, issue = ACCESS_ONCE(rwb->sync_issue);
  
  	if (!issue || !rwb->sync_cookie)
  		return 0;
  
  	now = ktime_to_ns(ktime_get());
  	return now - issue;
  }
  
  enum {
  	LAT_OK = 1,
  	LAT_UNKNOWN,
  	LAT_UNKNOWN_WRITES,
  	LAT_EXCEEDED,
  };
34dbad5d2   Omar Sandoval   blk-stat: convert...
278
  static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
e34cbd307   Jens Axboe   blk-wbt: add gene...
279
  {
dc3b17cc8   Jan Kara   block: Use pointe...
280
  	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
e34cbd307   Jens Axboe   blk-wbt: add gene...
281
282
283
284
285
286
287
288
289
290
291
292
293
  	u64 thislat;
  
  	/*
  	 * If our stored sync issue exceeds the window size, or it
  	 * exceeds our min target AND we haven't logged any entries,
  	 * flag the latency as exceeded. wbt works off completion latencies,
  	 * but for a flooded device, a single sync IO can take a long time
  	 * to complete after being issued. If this time exceeds our
  	 * monitoring window AND we didn't see any other completions in that
  	 * window, then count that sync IO as a violation of the latency.
  	 */
  	thislat = rwb_sync_issue_lat(rwb);
  	if (thislat > rwb->cur_win_nsec ||
fa2e39cb9   Omar Sandoval   blk-stat: use REA...
294
  	    (thislat > rwb->min_lat_nsec && !stat[READ].nr_samples)) {
d8a0cbfd7   Jens Axboe   blk-wbt: store qu...
295
  		trace_wbt_lat(bdi, thislat);
e34cbd307   Jens Axboe   blk-wbt: add gene...
296
297
298
299
300
301
302
303
304
305
306
307
308
  		return LAT_EXCEEDED;
  	}
  
  	/*
  	 * No read/write mix, if stat isn't valid
  	 */
  	if (!stat_sample_valid(stat)) {
  		/*
  		 * If we had writes in this stat window and the window is
  		 * current, we're only doing writes. If a task recently
  		 * waited or still has writes in flights, consider us doing
  		 * just writes as well.
  		 */
34dbad5d2   Omar Sandoval   blk-stat: convert...
309
310
  		if (stat[WRITE].nr_samples || wb_recent_wait(rwb) ||
  		    wbt_inflight(rwb))
e34cbd307   Jens Axboe   blk-wbt: add gene...
311
312
313
314
315
316
317
  			return LAT_UNKNOWN_WRITES;
  		return LAT_UNKNOWN;
  	}
  
  	/*
  	 * If the 'min' latency exceeds our target, step down.
  	 */
fa2e39cb9   Omar Sandoval   blk-stat: use REA...
318
319
  	if (stat[READ].min > rwb->min_lat_nsec) {
  		trace_wbt_lat(bdi, stat[READ].min);
d8a0cbfd7   Jens Axboe   blk-wbt: store qu...
320
  		trace_wbt_stat(bdi, stat);
e34cbd307   Jens Axboe   blk-wbt: add gene...
321
322
323
324
  		return LAT_EXCEEDED;
  	}
  
  	if (rwb->scale_step)
d8a0cbfd7   Jens Axboe   blk-wbt: store qu...
325
  		trace_wbt_stat(bdi, stat);
e34cbd307   Jens Axboe   blk-wbt: add gene...
326
327
328
  
  	return LAT_OK;
  }
e34cbd307   Jens Axboe   blk-wbt: add gene...
329
330
  static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
  {
dc3b17cc8   Jan Kara   block: Use pointe...
331
  	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
d8a0cbfd7   Jens Axboe   blk-wbt: store qu...
332
333
  
  	trace_wbt_step(bdi, msg, rwb->scale_step, rwb->cur_win_nsec,
e34cbd307   Jens Axboe   blk-wbt: add gene...
334
335
336
337
338
339
340
341
342
343
344
345
346
  			rwb->wb_background, rwb->wb_normal, rwb->wb_max);
  }
  
  static void scale_up(struct rq_wb *rwb)
  {
  	/*
  	 * Hit max in previous round, stop here
  	 */
  	if (rwb->scaled_max)
  		return;
  
  	rwb->scale_step--;
  	rwb->unknown_cnt = 0;
e34cbd307   Jens Axboe   blk-wbt: add gene...
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
  
  	rwb->scaled_max = calc_wb_limits(rwb);
  
  	rwb_wake_all(rwb);
  
  	rwb_trace_step(rwb, "step up");
  }
  
  /*
   * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
   * had a latency violation.
   */
  static void scale_down(struct rq_wb *rwb, bool hard_throttle)
  {
  	/*
  	 * Stop scaling down when we've hit the limit. This also prevents
  	 * ->scale_step from going to crazy values, if the device can't
  	 * keep up.
  	 */
  	if (rwb->wb_max == 1)
  		return;
  
  	if (rwb->scale_step < 0 && hard_throttle)
  		rwb->scale_step = 0;
  	else
  		rwb->scale_step++;
  
  	rwb->scaled_max = false;
  	rwb->unknown_cnt = 0;
e34cbd307   Jens Axboe   blk-wbt: add gene...
376
377
378
379
380
381
  	calc_wb_limits(rwb);
  	rwb_trace_step(rwb, "step down");
  }
  
  static void rwb_arm_timer(struct rq_wb *rwb)
  {
e34cbd307   Jens Axboe   blk-wbt: add gene...
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
  	if (rwb->scale_step > 0) {
  		/*
  		 * We should speed this up, using some variant of a fast
  		 * integer inverse square root calculation. Since we only do
  		 * this for every window expiration, it's not a huge deal,
  		 * though.
  		 */
  		rwb->cur_win_nsec = div_u64(rwb->win_nsec << 4,
  					int_sqrt((rwb->scale_step + 1) << 8));
  	} else {
  		/*
  		 * For step < 0, we don't want to increase/decrease the
  		 * window size.
  		 */
  		rwb->cur_win_nsec = rwb->win_nsec;
  	}
34dbad5d2   Omar Sandoval   blk-stat: convert...
398
  	blk_stat_activate_nsecs(rwb->cb, rwb->cur_win_nsec);
e34cbd307   Jens Axboe   blk-wbt: add gene...
399
  }
34dbad5d2   Omar Sandoval   blk-stat: convert...
400
  static void wb_timer_fn(struct blk_stat_callback *cb)
e34cbd307   Jens Axboe   blk-wbt: add gene...
401
  {
34dbad5d2   Omar Sandoval   blk-stat: convert...
402
  	struct rq_wb *rwb = cb->data;
e34cbd307   Jens Axboe   blk-wbt: add gene...
403
404
  	unsigned int inflight = wbt_inflight(rwb);
  	int status;
34dbad5d2   Omar Sandoval   blk-stat: convert...
405
  	status = latency_exceeded(rwb, cb->stat);
e34cbd307   Jens Axboe   blk-wbt: add gene...
406

dc3b17cc8   Jan Kara   block: Use pointe...
407
  	trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step,
d8a0cbfd7   Jens Axboe   blk-wbt: store qu...
408
  			inflight);
e34cbd307   Jens Axboe   blk-wbt: add gene...
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
  
  	/*
  	 * If we exceeded the latency target, step down. If we did not,
  	 * step one level up. If we don't know enough to say either exceeded
  	 * or ok, then don't do anything.
  	 */
  	switch (status) {
  	case LAT_EXCEEDED:
  		scale_down(rwb, true);
  		break;
  	case LAT_OK:
  		scale_up(rwb);
  		break;
  	case LAT_UNKNOWN_WRITES:
  		/*
  		 * We started a the center step, but don't have a valid
  		 * read/write sample, but we do have writes going on.
  		 * Allow step to go negative, to increase write perf.
  		 */
  		scale_up(rwb);
  		break;
  	case LAT_UNKNOWN:
  		if (++rwb->unknown_cnt < RWB_UNKNOWN_BUMP)
  			break;
  		/*
  		 * We get here when previously scaled reduced depth, and we
  		 * currently don't have a valid read/write sample. For that
  		 * case, slowly return to center state (step == 0).
  		 */
  		if (rwb->scale_step > 0)
  			scale_up(rwb);
  		else if (rwb->scale_step < 0)
  			scale_down(rwb, false);
  		break;
  	default:
  		break;
  	}
  
  	/*
  	 * Re-arm timer, if we have IO in flight
  	 */
  	if (rwb->scale_step || inflight)
  		rwb_arm_timer(rwb);
  }
  
  void wbt_update_limits(struct rq_wb *rwb)
  {
  	rwb->scale_step = 0;
  	rwb->scaled_max = false;
  	calc_wb_limits(rwb);
  
  	rwb_wake_all(rwb);
  }
  
  static bool close_io(struct rq_wb *rwb)
  {
  	const unsigned long now = jiffies;
  
  	return time_before(now, rwb->last_issue + HZ / 10) ||
  		time_before(now, rwb->last_comp + HZ / 10);
  }
  
  #define REQ_HIPRIO	(REQ_SYNC | REQ_META | REQ_PRIO)
  
  static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
  {
  	unsigned int limit;
  
  	/*
  	 * At this point we know it's a buffered write. If this is
  	 * kswapd trying to free memory, or REQ_SYNC is set, set, then
  	 * it's WB_SYNC_ALL writeback, and we'll use the max limit for
  	 * that. If the write is marked as a background write, then use
  	 * the idle limit, or go to normal if we haven't had competing
  	 * IO for a bit.
  	 */
  	if ((rw & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd())
  		limit = rwb->wb_max;
  	else if ((rw & REQ_BACKGROUND) || close_io(rwb)) {
  		/*
  		 * If less than 100ms since we completed unrelated IO,
  		 * limit us to half the depth for background writeback.
  		 */
  		limit = rwb->wb_background;
  	} else
  		limit = rwb->wb_normal;
  
  	return limit;
  }
  
  static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
ac6424b98   Ingo Molnar   sched/wait: Renam...
500
  			     wait_queue_entry_t *wait, unsigned long rw)
e34cbd307   Jens Axboe   blk-wbt: add gene...
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
  {
  	/*
  	 * inc it here even if disabled, since we'll dec it at completion.
  	 * this only happens if the task was sleeping in __wbt_wait(),
  	 * and someone turned it off at the same time.
  	 */
  	if (!rwb_enabled(rwb)) {
  		atomic_inc(&rqw->inflight);
  		return true;
  	}
  
  	/*
  	 * If the waitqueue is already active and we are not the next
  	 * in line to be woken up, wait for our turn.
  	 */
  	if (waitqueue_active(&rqw->wait) &&
2055da973   Ingo Molnar   sched/wait: Disam...
517
  	    rqw->wait.head.next != &wait->entry)
e34cbd307   Jens Axboe   blk-wbt: add gene...
518
519
520
521
522
523
524
525
526
527
  		return false;
  
  	return atomic_inc_below(&rqw->inflight, get_limit(rwb, rw));
  }
  
  /*
   * Block if we will exceed our limit, or if we are currently waiting for
   * the timer to kick off queuing again.
   */
  static void __wbt_wait(struct rq_wb *rwb, unsigned long rw, spinlock_t *lock)
9eca53508   Bart Van Assche   block: Avoid that...
528
529
  	__releases(lock)
  	__acquires(lock)
e34cbd307   Jens Axboe   blk-wbt: add gene...
530
531
532
533
534
535
536
537
538
539
540
541
542
  {
  	struct rq_wait *rqw = get_rq_wait(rwb, current_is_kswapd());
  	DEFINE_WAIT(wait);
  
  	if (may_queue(rwb, rqw, &wait, rw))
  		return;
  
  	do {
  		prepare_to_wait_exclusive(&rqw->wait, &wait,
  						TASK_UNINTERRUPTIBLE);
  
  		if (may_queue(rwb, rqw, &wait, rw))
  			break;
9eca53508   Bart Van Assche   block: Avoid that...
543
  		if (lock) {
e34cbd307   Jens Axboe   blk-wbt: add gene...
544
  			spin_unlock_irq(lock);
9eca53508   Bart Van Assche   block: Avoid that...
545
  			io_schedule();
e34cbd307   Jens Axboe   blk-wbt: add gene...
546
  			spin_lock_irq(lock);
9eca53508   Bart Van Assche   block: Avoid that...
547
548
  		} else
  			io_schedule();
e34cbd307   Jens Axboe   blk-wbt: add gene...
549
550
551
552
553
554
555
556
557
558
  	} while (1);
  
  	finish_wait(&rqw->wait, &wait);
  }
  
  static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
  {
  	const int op = bio_op(bio);
  
  	/*
be07e14f9   Christoph Hellwig   blk-wbt: don't th...
559
  	 * If not a WRITE, do nothing
e34cbd307   Jens Axboe   blk-wbt: add gene...
560
  	 */
be07e14f9   Christoph Hellwig   blk-wbt: don't th...
561
  	if (op != REQ_OP_WRITE)
e34cbd307   Jens Axboe   blk-wbt: add gene...
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
  		return false;
  
  	/*
  	 * Don't throttle WRITE_ODIRECT
  	 */
  	if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) == (REQ_SYNC | REQ_IDLE))
  		return false;
  
  	return true;
  }
  
  /*
   * Returns true if the IO request should be accounted, false if not.
   * May sleep, if we have exceeded the writeback limits. Caller can pass
   * in an irq held spinlock, if it holds one when calling this function.
   * If we do sleep, we'll release and re-grab it.
   */
f2e0a0b29   Bart Van Assche   block: Make wbt_w...
579
  enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
e34cbd307   Jens Axboe   blk-wbt: add gene...
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
  {
  	unsigned int ret = 0;
  
  	if (!rwb_enabled(rwb))
  		return 0;
  
  	if (bio_op(bio) == REQ_OP_READ)
  		ret = WBT_READ;
  
  	if (!wbt_should_throttle(rwb, bio)) {
  		if (ret & WBT_READ)
  			wb_timestamp(rwb, &rwb->last_issue);
  		return ret;
  	}
  
  	__wbt_wait(rwb, bio->bi_opf, lock);
34dbad5d2   Omar Sandoval   blk-stat: convert...
596
  	if (!blk_stat_is_active(rwb->cb))
e34cbd307   Jens Axboe   blk-wbt: add gene...
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
  		rwb_arm_timer(rwb);
  
  	if (current_is_kswapd())
  		ret |= WBT_KSWAPD;
  
  	return ret | WBT_TRACKED;
  }
  
  void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat)
  {
  	if (!rwb_enabled(rwb))
  		return;
  
  	/*
  	 * Track sync issue, in case it takes a long time to complete. Allows
  	 * us to react quicker, if a sync IO takes a long time to complete.
  	 * Note that this is just a hint. 'stat' can go away when the
  	 * request completes, so it's important we never dereference it. We
  	 * only use the address to compare with, which is why we store the
  	 * sync_issue time locally.
  	 */
  	if (wbt_is_read(stat) && !rwb->sync_issue) {
  		rwb->sync_cookie = stat;
  		rwb->sync_issue = blk_stat_time(stat);
  	}
  }
  
  void wbt_requeue(struct rq_wb *rwb, struct blk_issue_stat *stat)
  {
  	if (!rwb_enabled(rwb))
  		return;
  	if (stat == rwb->sync_cookie) {
  		rwb->sync_issue = 0;
  		rwb->sync_cookie = NULL;
  	}
  }
  
  void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
  {
  	if (rwb) {
  		rwb->queue_depth = depth;
  		wbt_update_limits(rwb);
  	}
  }
  
  void wbt_set_write_cache(struct rq_wb *rwb, bool write_cache_on)
  {
  	if (rwb)
  		rwb->wc = write_cache_on;
  }
3f19cd23f   Jan Kara   block: Fix list c...
647
  /*
7535afccf   Luca Miccio   block,bfq: Disabl...
648
   * Disable wbt, if enabled by default.
fa224eed2   Jens Axboe   blk-wbt: cleanup ...
649
650
   */
  void wbt_disable_default(struct request_queue *q)
e34cbd307   Jens Axboe   blk-wbt: add gene...
651
  {
fa224eed2   Jens Axboe   blk-wbt: cleanup ...
652
  	struct rq_wb *rwb = q->rq_wb;
3f19cd23f   Jan Kara   block: Fix list c...
653
654
  	if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT)
  		wbt_exit(q);
e34cbd307   Jens Axboe   blk-wbt: add gene...
655
  }
fa224eed2   Jens Axboe   blk-wbt: cleanup ...
656
  EXPORT_SYMBOL_GPL(wbt_disable_default);
e34cbd307   Jens Axboe   blk-wbt: add gene...
657

8330cdb0f   Jan Kara   block: Make write...
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
  /*
   * Enable wbt if defaults are configured that way
   */
  void wbt_enable_default(struct request_queue *q)
  {
  	/* Throttling already enabled? */
  	if (q->rq_wb)
  		return;
  
  	/* Queue not registered? Maybe shutting down... */
  	if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
  		return;
  
  	if ((q->mq_ops && IS_ENABLED(CONFIG_BLK_WBT_MQ)) ||
  	    (q->request_fn && IS_ENABLED(CONFIG_BLK_WBT_SQ)))
  		wbt_init(q);
  }
  EXPORT_SYMBOL_GPL(wbt_enable_default);
80e091d10   Jens Axboe   blk-wbt: allow re...
676
677
678
679
680
681
682
683
684
685
686
  u64 wbt_default_latency_nsec(struct request_queue *q)
  {
  	/*
  	 * We default to 2msec for non-rotational storage, and 75msec
  	 * for rotational storage.
  	 */
  	if (blk_queue_nonrot(q))
  		return 2000000ULL;
  	else
  		return 75000000ULL;
  }
99c749a4c   Jens Axboe   blk-stat: kill bl...
687
688
  static int wbt_data_dir(const struct request *rq)
  {
0528a533f   Jens Axboe   blk-wbt: account ...
689
690
691
692
693
694
695
696
697
  	const int op = req_op(rq);
  
  	if (op == REQ_OP_READ)
  		return READ;
  	else if (op == REQ_OP_WRITE || op == REQ_OP_FLUSH)
  		return WRITE;
  
  	/* don't account */
  	return -1;
99c749a4c   Jens Axboe   blk-stat: kill bl...
698
  }
8054b89f8   Jens Axboe   blk-wbt: remove s...
699
  int wbt_init(struct request_queue *q)
e34cbd307   Jens Axboe   blk-wbt: add gene...
700
701
702
  {
  	struct rq_wb *rwb;
  	int i;
e34cbd307   Jens Axboe   blk-wbt: add gene...
703
  	BUILD_BUG_ON(WBT_NR_BITS > BLK_STAT_RES_BITS);
e34cbd307   Jens Axboe   blk-wbt: add gene...
704
705
706
  	rwb = kzalloc(sizeof(*rwb), GFP_KERNEL);
  	if (!rwb)
  		return -ENOMEM;
99c749a4c   Jens Axboe   blk-stat: kill bl...
707
  	rwb->cb = blk_stat_alloc_callback(wb_timer_fn, wbt_data_dir, 2, rwb);
34dbad5d2   Omar Sandoval   blk-stat: convert...
708
709
710
711
  	if (!rwb->cb) {
  		kfree(rwb);
  		return -ENOMEM;
  	}
e34cbd307   Jens Axboe   blk-wbt: add gene...
712
713
714
715
  	for (i = 0; i < WBT_NUM_RWQ; i++) {
  		atomic_set(&rwb->rq_wait[i].inflight, 0);
  		init_waitqueue_head(&rwb->rq_wait[i].wait);
  	}
e34cbd307   Jens Axboe   blk-wbt: add gene...
716
717
718
  	rwb->wc = 1;
  	rwb->queue_depth = RWB_DEF_DEPTH;
  	rwb->last_comp = rwb->last_issue = jiffies;
d8a0cbfd7   Jens Axboe   blk-wbt: store qu...
719
  	rwb->queue = q;
e34cbd307   Jens Axboe   blk-wbt: add gene...
720
  	rwb->win_nsec = RWB_WINDOW_NSEC;
d62118b6d   Jens Axboe   blk-wbt: allow wb...
721
  	rwb->enable_state = WBT_STATE_ON_DEFAULT;
e34cbd307   Jens Axboe   blk-wbt: add gene...
722
723
724
  	wbt_update_limits(rwb);
  
  	/*
34dbad5d2   Omar Sandoval   blk-stat: convert...
725
  	 * Assign rwb and add the stats callback.
e34cbd307   Jens Axboe   blk-wbt: add gene...
726
727
  	 */
  	q->rq_wb = rwb;
34dbad5d2   Omar Sandoval   blk-stat: convert...
728
  	blk_stat_add_callback(q, rwb->cb);
e34cbd307   Jens Axboe   blk-wbt: add gene...
729

80e091d10   Jens Axboe   blk-wbt: allow re...
730
  	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
e34cbd307   Jens Axboe   blk-wbt: add gene...
731
732
733
734
735
736
737
738
739
740
741
742
  
  	wbt_set_queue_depth(rwb, blk_queue_depth(q));
  	wbt_set_write_cache(rwb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
  
  	return 0;
  }
  
  void wbt_exit(struct request_queue *q)
  {
  	struct rq_wb *rwb = q->rq_wb;
  
  	if (rwb) {
34dbad5d2   Omar Sandoval   blk-stat: convert...
743
744
  		blk_stat_remove_callback(q, rwb->cb);
  		blk_stat_free_callback(rwb->cb);
e34cbd307   Jens Axboe   blk-wbt: add gene...
745
746
747
748
  		q->rq_wb = NULL;
  		kfree(rwb);
  	}
  }