summaryrefslogtreecommitdiff
path: root/block/blk-mq.h
blob: e1bb420dc5d6cdcea146d381e7d9f823b3d0b542 (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
233
234
235
236
237
238
239
240
241
242
243
244
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef INT_BLK_MQ_H
#define INT_BLK_MQ_H

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

struct blk_mq_tag_set;

/**
 * struct blk_mq_ctx - State for a software queue facing the submitting CPUs
 */
struct blk_mq_ctx {
	struct {
		spinlock_t		lock;
		struct list_head	rq_list;
	}  ____cacheline_aligned_in_smp;

	unsigned int		cpu;
	unsigned int		index_hw;

	/* incremented at dispatch time */
	unsigned long		rq_dispatched[2];
	unsigned long		rq_merged;

	/* incremented at completion time */
	unsigned long		____cacheline_aligned_in_smp rq_completed[2];

	struct request_queue	*queue;
	struct kobject		kobj;
} ____cacheline_aligned_in_smp;

/*
 * Bits for request->gstate.  The lower two bits carry MQ_RQ_* state value
 * and the upper bits the generation number.
 */
enum mq_rq_state {
	MQ_RQ_IDLE		= 0,
	MQ_RQ_IN_FLIGHT		= 1,
	MQ_RQ_COMPLETE		= 2,

	MQ_RQ_STATE_BITS	= 2,
	MQ_RQ_STATE_MASK	= (1 << MQ_RQ_STATE_BITS) - 1,
	MQ_RQ_GEN_INC		= 1 << MQ_RQ_STATE_BITS,
};

void blk_mq_freeze_queue(struct request_queue *q);
void blk_mq_free_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
void blk_mq_wake_waiters(struct request_queue *q);
bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
				bool wait);
struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
					struct blk_mq_ctx *start);

/*
 * Internal helpers for allocating/freeing the request map
 */
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
		     unsigned int hctx_idx);
void blk_mq_free_rq_map(struct blk_mq_tags *tags);
struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
					unsigned int hctx_idx,
					unsigned int nr_tags,
					unsigned int reserved_tags);
int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
		     unsigned int hctx_idx, unsigned int depth);

/*
 * Internal helpers for request insertion into sw queues
 */
void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
				bool at_head);
void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
				struct list_head *list);

/* Used by blk_insert_cloned_request() to issue request directly */
blk_status_t blk_mq_request_issue_directly(struct request *rq);

/*
 * CPU -> queue mappings
 */
extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);

static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
		int cpu)
{
	return q->queue_hw_ctx[q->mq_map[cpu]];
}

/*
 * sysfs helpers
 */
extern void blk_mq_sysfs_init(struct request_queue *q);
extern void blk_mq_sysfs_deinit(struct request_queue *q);
extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q);
extern int blk_mq_sysfs_register(struct request_queue *q);
extern void blk_mq_sysfs_unregister(struct request_queue *q);
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);

void blk_mq_release(struct request_queue *q);

/**
 * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
 * @rq: target request.
 */
static inline int blk_mq_rq_state(struct request *rq)
{
	return READ_ONCE(rq->gstate) & MQ_RQ_STATE_MASK;
}

/**
 * blk_mq_rq_update_state() - set the current MQ_RQ_* state of a request
 * @rq: target request.
 * @state: new state to set.
 *
 * Set @rq's state to @state.  The caller is responsible for ensuring that
 * there are no other updaters.  A request can transition into IN_FLIGHT
 * only from IDLE and doing so increments the generation number.
 */
static inline void blk_mq_rq_update_state(struct request *rq,
					  enum mq_rq_state state)
{
	u64 old_val = READ_ONCE(rq->gstate);
	u64 new_val = (old_val & ~MQ_RQ_STATE_MASK) | state;

	if (state == MQ_RQ_IN_FLIGHT) {
		WARN_ON_ONCE((old_val & MQ_RQ_STATE_MASK) != MQ_RQ_IDLE);
		new_val += MQ_RQ_GEN_INC;
	}

	/* avoid exposing interim values */
	WRITE_ONCE(rq->gstate, new_val);
}

static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
					   unsigned int cpu)
{
	return per_cpu_ptr(q->queue_ctx, cpu);
}

/*
 * This assumes per-cpu software queueing queues. They could be per-node
 * as well, for instance. For now this is hardcoded as-is. Note that we don't
 * care about preemption, since we know the ctx's are persistent. This does
 * mean that we can't rely on ctx always matching the currently running CPU.
 */
static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
{
	return __blk_mq_get_ctx(q, get_cpu());
}

static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
{
	put_cpu();
}

struct blk_mq_alloc_data {
	/* input parameter */
	struct request_queue *q;
	blk_mq_req_flags_t flags;
	unsigned int shallow_depth;

	/* input & output parameter */
	struct blk_mq_ctx *ctx;
	struct blk_mq_hw_ctx *hctx;
};

static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
{
	if (data->flags & BLK_MQ_REQ_INTERNAL)
		return data->hctx->sched_tags;

	return data->hctx->tags;
}

static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
{
	return test_bit(BLK_MQ_S_STOPPED, &hctx->state);
}

static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
{
	return hctx->nr_ctx && hctx->tags;
}

void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
		      unsigned int inflight[2]);
void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
			 unsigned int inflight[2]);

static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx)
{
	struct request_queue *q = hctx->queue;

	if (q->mq_ops->put_budget)
		q->mq_ops->put_budget(hctx);
}

static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx)
{
	struct request_queue *q = hctx->queue;

	if (q->mq_ops->get_budget)
		return q->mq_ops->get_budget(hctx);
	return true;
}

static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
					   struct request *rq)
{
	blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
	rq->tag = -1;

	if (rq->rq_flags & RQF_MQ_INFLIGHT) {
		rq->rq_flags &= ~RQF_MQ_INFLIGHT;
		atomic_dec(&hctx->nr_active);
	}
}

static inline void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx,
				       struct request *rq)
{
	if (rq->tag == -1 || rq->internal_tag == -1)
		return;

	__blk_mq_put_driver_tag(hctx, rq);
}

static inline void blk_mq_put_driver_tag(struct request *rq)
{
	struct blk_mq_hw_ctx *hctx;

	if (rq->tag == -1 || rq->internal_tag == -1)
		return;

	hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
	__blk_mq_put_driver_tag(hctx, rq);
}

#endif