summaryrefslogtreecommitdiff
path: root/block/blk-mq-tag.c
blob: 83ae96c51a2762cf7386f096e348eace58525e37 (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
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/percpu_ida.h>

#include <linux/blk-mq.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"

/*
 * Per tagged queue (tag address space) map
 */
struct blk_mq_tags {
	unsigned int nr_tags;
	unsigned int nr_reserved_tags;
	unsigned int nr_batch_move;
	unsigned int nr_max_cache;

	struct percpu_ida free_tags;
	struct percpu_ida reserved_tags;
};

void blk_mq_wait_for_tags(struct blk_mq_tags *tags)
{
	int tag = blk_mq_get_tag(tags, __GFP_WAIT, false);
	blk_mq_put_tag(tags, tag);
}

bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
{
	return !tags ||
		percpu_ida_free_tags(&tags->free_tags, nr_cpu_ids) != 0;
}

static unsigned int __blk_mq_get_tag(struct blk_mq_tags *tags, gfp_t gfp)
{
	int tag;

	tag = percpu_ida_alloc(&tags->free_tags, (gfp & __GFP_WAIT) ?
			       TASK_UNINTERRUPTIBLE : TASK_RUNNING);
	if (tag < 0)
		return BLK_MQ_TAG_FAIL;
	return tag + tags->nr_reserved_tags;
}

static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_tags *tags,
					      gfp_t gfp)
{
	int tag;

	if (unlikely(!tags->nr_reserved_tags)) {
		WARN_ON_ONCE(1);
		return BLK_MQ_TAG_FAIL;
	}

	tag = percpu_ida_alloc(&tags->reserved_tags, (gfp & __GFP_WAIT) ?
			       TASK_UNINTERRUPTIBLE : TASK_RUNNING);
	if (tag < 0)
		return BLK_MQ_TAG_FAIL;
	return tag;
}

unsigned int blk_mq_get_tag(struct blk_mq_tags *tags, gfp_t gfp, bool reserved)
{
	if (!reserved)
		return __blk_mq_get_tag(tags, gfp);

	return __blk_mq_get_reserved_tag(tags, gfp);
}

static void __blk_mq_put_tag(struct blk_mq_tags *tags, unsigned int tag)
{
	BUG_ON(tag >= tags->nr_tags);

	percpu_ida_free(&tags->free_tags, tag - tags->nr_reserved_tags);
}

static void __blk_mq_put_reserved_tag(struct blk_mq_tags *tags,
				      unsigned int tag)
{
	BUG_ON(tag >= tags->nr_reserved_tags);

	percpu_ida_free(&tags->reserved_tags, tag);
}

void blk_mq_put_tag(struct blk_mq_tags *tags, unsigned int tag)
{
	if (tag >= tags->nr_reserved_tags)
		__blk_mq_put_tag(tags, tag);
	else
		__blk_mq_put_reserved_tag(tags, tag);
}

static int __blk_mq_tag_iter(unsigned id, void *data)
{
	unsigned long *tag_map = data;
	__set_bit(id, tag_map);
	return 0;
}

void blk_mq_tag_busy_iter(struct blk_mq_tags *tags,
			  void (*fn)(void *, unsigned long *), void *data)
{
	unsigned long *tag_map;
	size_t map_size;

	map_size = ALIGN(tags->nr_tags, BITS_PER_LONG) / BITS_PER_LONG;
	tag_map = kzalloc(map_size * sizeof(unsigned long), GFP_ATOMIC);
	if (!tag_map)
		return;

	percpu_ida_for_each_free(&tags->free_tags, __blk_mq_tag_iter, tag_map);
	if (tags->nr_reserved_tags)
		percpu_ida_for_each_free(&tags->reserved_tags, __blk_mq_tag_iter,
			tag_map);

	fn(data, tag_map);
	kfree(tag_map);
}

struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
				     unsigned int reserved_tags, int node)
{
	unsigned int nr_tags, nr_cache;
	struct blk_mq_tags *tags;
	int ret;

	if (total_tags > BLK_MQ_TAG_MAX) {
		pr_err("blk-mq: tag depth too large\n");
		return NULL;
	}

	tags = kzalloc_node(sizeof(*tags), GFP_KERNEL, node);
	if (!tags)
		return NULL;

	nr_tags = total_tags - reserved_tags;
	nr_cache = nr_tags / num_possible_cpus();

	if (nr_cache < BLK_MQ_TAG_CACHE_MIN)
		nr_cache = BLK_MQ_TAG_CACHE_MIN;
	else if (nr_cache > BLK_MQ_TAG_CACHE_MAX)
		nr_cache = BLK_MQ_TAG_CACHE_MAX;

	tags->nr_tags = total_tags;
	tags->nr_reserved_tags = reserved_tags;
	tags->nr_max_cache = nr_cache;
	tags->nr_batch_move = max(1u, nr_cache / 2);

	ret = __percpu_ida_init(&tags->free_tags, tags->nr_tags -
				tags->nr_reserved_tags,
				tags->nr_max_cache,
				tags->nr_batch_move);
	if (ret)
		goto err_free_tags;

	if (reserved_tags) {
		/*
		 * With max_cahe and batch set to 1, the allocator fallbacks to
		 * no cached. It's fine reserved tags allocation is slow.
		 */
		ret = __percpu_ida_init(&tags->reserved_tags, reserved_tags,
				1, 1);
		if (ret)
			goto err_reserved_tags;
	}

	return tags;

err_reserved_tags:
	percpu_ida_destroy(&tags->free_tags);
err_free_tags:
	kfree(tags);
	return NULL;
}

void blk_mq_free_tags(struct blk_mq_tags *tags)
{
	percpu_ida_destroy(&tags->free_tags);
	percpu_ida_destroy(&tags->reserved_tags);
	kfree(tags);
}

ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
{
	char *orig_page = page;
	unsigned int cpu;

	if (!tags)
		return 0;

	page += sprintf(page, "nr_tags=%u, reserved_tags=%u, batch_move=%u,"
			" max_cache=%u\n", tags->nr_tags, tags->nr_reserved_tags,
			tags->nr_batch_move, tags->nr_max_cache);

	page += sprintf(page, "nr_free=%u, nr_reserved=%u\n",
			percpu_ida_free_tags(&tags->free_tags, nr_cpu_ids),
			percpu_ida_free_tags(&tags->reserved_tags, nr_cpu_ids));

	for_each_possible_cpu(cpu) {
		page += sprintf(page, "  cpu%02u: nr_free=%u\n", cpu,
				percpu_ida_free_tags(&tags->free_tags, cpu));
	}

	return page - orig_page;
}