aboutsummaryrefslogtreecommitdiff
path: root/block/blk-stat.c
blob: e42c263e53fb995cd7c0b0d6d3de021cae05aae1 (plain)
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
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
// SPDX-License-Identifier: GPL-2.0
/*
 * Block stat tracking code
 *
 * Copyright (C) 2016 Jens Axboe
 */
#include <linux/kernel.h>
#include <linux/rculist.h>

#include "blk-stat.h"
#include "blk-mq.h"
#include "blk.h"

struct blk_queue_stats {
	struct list_head callbacks;
	spinlock_t lock;
	int accounting;
};

void blk_rq_stat_init(struct blk_rq_stat *stat)
{
	stat->min = -1ULL;
	stat->max = stat->nr_samples = stat->mean = 0;
	stat->batch = 0;
}

/* src is a per-cpu stat, mean isn't initialized */
void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
{
	if (dst->nr_samples + src->nr_samples <= dst->nr_samples)
		return;

	dst->min = min(dst->min, src->min);
	dst->max = max(dst->max, src->max);

	dst->mean = div_u64(src->batch + dst->mean * dst->nr_samples,
				dst->nr_samples + src->nr_samples);

	dst->nr_samples += src->nr_samples;
}

void blk_rq_stat_add(struct blk_rq_stat *stat, u64 value)
{
	stat->min = min(stat->min, value);
	stat->max = max(stat->max, value);
	stat->batch += value;
	stat->nr_samples++;
}

void blk_stat_add(struct request *rq, u64 now)
{
	struct request_queue *q = rq->q;
	struct blk_stat_callback *cb;
	struct blk_rq_stat *stat;
	int bucket, cpu;
	u64 value;

	value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0;

	if (req_op(rq) == REQ_OP_READ || req_op(rq) == REQ_OP_WRITE)
		blk_throtl_stat_add(rq, value);

	rcu_read_lock();
	cpu = get_cpu();
	list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
		if (!blk_stat_is_active(cb))
			continue;

		bucket = cb->bucket_fn(rq);
		if (bucket < 0)
			continue;

		stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket];
		blk_rq_stat_add(stat, value);
	}
	put_cpu();
	rcu_read_unlock();
}

static void blk_stat_timer_fn(struct timer_list *t)
{
	struct blk_stat_callback *cb = from_timer(cb, t, timer);
	unsigned int bucket;
	int cpu;

	for (bucket = 0; bucket < cb->buckets; bucket++)
		blk_rq_stat_init(&cb->stat[bucket]);

	for_each_online_cpu(cpu) {
		struct blk_rq_stat *cpu_stat;

		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
		for (bucket = 0; bucket < cb->buckets; bucket++) {
			blk_rq_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]);
			blk_rq_stat_init(&cpu_stat[bucket]);
		}
	}

	cb->timer_fn(cb);
}

struct blk_stat_callback *
blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *),
			int (*bucket_fn)(const struct request *),
			unsigned int buckets, void *data)
{
	struct blk_stat_callback *cb;

	cb = kmalloc(sizeof(*cb), GFP_KERNEL);
	if (!cb)
		return NULL;

	cb->stat = kmalloc_array(buckets, sizeof(struct blk_rq_stat),
				 GFP_KERNEL);
	if (!cb->stat) {
		kfree(cb);
		return NULL;
	}
	cb->cpu_stat = __alloc_percpu(buckets * sizeof(struct blk_rq_stat),
				      __alignof__(struct blk_rq_stat));
	if (!cb->cpu_stat) {
		kfree(cb->stat);
		kfree(cb);
		return NULL;
	}

	cb->timer_fn = timer_fn;
	cb->bucket_fn = bucket_fn;
	cb->data = data;
	cb->buckets = buckets;
	timer_setup(&cb->timer, blk_stat_timer_fn, 0);

	return cb;
}

void blk_stat_add_callback(struct request_queue *q,
			   struct blk_stat_callback *cb)
{
	unsigned int bucket;
	unsigned long flags;
	int cpu;

	for_each_possible_cpu(cpu) {
		struct blk_rq_stat *cpu_stat;

		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
		for (bucket = 0; bucket < cb->buckets; bucket++)
			blk_rq_stat_init(&cpu_stat[bucket]);
	}

	spin_lock_irqsave(&q->stats->lock, flags);
	list_add_tail_rcu(&cb->list, &q->stats->callbacks);
	blk_queue_flag_set(QUEUE_FLAG_STATS, q);
	spin_unlock_irqrestore(&q->stats->lock, flags);
}

void blk_stat_remove_callback(struct request_queue *q,
			      struct blk_stat_callback *cb)
{
	unsigned long flags;

	spin_lock_irqsave(&q->stats->lock, flags);
	list_del_rcu(&cb->list);
	if (list_empty(&q->stats->callbacks) && !q->stats->accounting)
		blk_queue_flag_clear(QUEUE_FLAG_STATS, q);
	spin_unlock_irqrestore(&q->stats->lock, flags);

	del_timer_sync(&cb->timer);
}

static void blk_stat_free_callback_rcu(struct rcu_head *head)
{
	struct blk_stat_callback *cb;

	cb = container_of(head, struct blk_stat_callback, rcu);
	free_percpu(cb->cpu_stat);
	kfree(cb->stat);
	kfree(cb);
}

void blk_stat_free_callback(struct blk_stat_callback *cb)
{
	if (cb)
		call_rcu(&cb->rcu, blk_stat_free_callback_rcu);
}

void blk_stat_disable_accounting(struct request_queue *q)
{
	unsigned long flags;

	spin_lock_irqsave(&q->stats->lock, flags);
	if (!--q->stats->accounting && list_empty(&q->stats->callbacks))
		blk_queue_flag_clear(QUEUE_FLAG_STATS, q);
	spin_unlock_irqrestore(&q->stats->lock, flags);
}
EXPORT_SYMBOL_GPL(blk_stat_disable_accounting);

void blk_stat_enable_accounting(struct request_queue *q)
{
	unsigned long flags;

	spin_lock_irqsave(&q->stats->lock, flags);
	if (!q->stats->accounting++ && list_empty(&q->stats->callbacks))
		blk_queue_flag_set(QUEUE_FLAG_STATS, q);
	spin_unlock_irqrestore(&q->stats->lock, flags);
}
EXPORT_SYMBOL_GPL(blk_stat_enable_accounting);

struct blk_queue_stats *blk_alloc_queue_stats(void)
{
	struct blk_queue_stats *stats;

	stats = kmalloc(sizeof(*stats), GFP_KERNEL);
	if (!stats)
		return NULL;

	INIT_LIST_HEAD(&stats->callbacks);
	spin_lock_init(&stats->lock);
	stats->accounting = 0;

	return stats;
}

void blk_free_queue_stats(struct blk_queue_stats *stats)
{
	if (!stats)
		return;

	WARN_ON(!list_empty(&stats->callbacks));

	kfree(stats);
}