summaryrefslogtreecommitdiffstats
path: root/block/blk-ioc.c
blob: b13ed96776c2995bf818b1c01a4033bad1be7baf (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
/*
 * Functions related to io context handling
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
#include <linux/slab.h>

#include "blk.h"

/*
 * For io context allocations
 */
static struct kmem_cache *iocontext_cachep;

/**
 * get_io_context - increment reference count to io_context
 * @ioc: io_context to get
 *
 * Increment reference count to @ioc.
 */
void get_io_context(struct io_context *ioc)
{
	BUG_ON(atomic_long_read(&ioc->refcount) <= 0);
	atomic_long_inc(&ioc->refcount);
}
EXPORT_SYMBOL(get_io_context);

static void cfq_dtor(struct io_context *ioc)
{
	if (!hlist_empty(&ioc->cic_list)) {
		struct cfq_io_context *cic;

		cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
								cic_list);
		cic->dtor(ioc);
	}
}

/**
 * put_io_context - put a reference of io_context
 * @ioc: io_context to put
 *
 * Decrement reference count of @ioc and release it if the count reaches
 * zero.
 */
void put_io_context(struct io_context *ioc)
{
	if (ioc == NULL)
		return;

	BUG_ON(atomic_long_read(&ioc->refcount) <= 0);

	if (!atomic_long_dec_and_test(&ioc->refcount))
		return;

	rcu_read_lock();
	cfq_dtor(ioc);
	rcu_read_unlock();

	kmem_cache_free(iocontext_cachep, ioc);
}
EXPORT_SYMBOL(put_io_context);

static void cfq_exit(struct io_context *ioc)
{
	rcu_read_lock();

	if (!hlist_empty(&ioc->cic_list)) {
		struct cfq_io_context *cic;

		cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
								cic_list);
		cic->exit(ioc);
	}
	rcu_read_unlock();
}

/* Called by the exiting task */
void exit_io_context(struct task_struct *task)
{
	struct io_context *ioc;

	/* PF_EXITING prevents new io_context from being attached to @task */
	WARN_ON_ONCE(!(current->flags & PF_EXITING));

	task_lock(task);
	ioc = task->io_context;
	task->io_context = NULL;
	task_unlock(task);

	if (atomic_dec_and_test(&ioc->nr_tasks))
		cfq_exit(ioc);

	put_io_context(ioc);
}

static struct io_context *create_task_io_context(struct task_struct *task,
						 gfp_t gfp_flags, int node,
						 bool take_ref)
{
	struct io_context *ioc;

	ioc = kmem_cache_alloc_node(iocontext_cachep, gfp_flags | __GFP_ZERO,
				    node);
	if (unlikely(!ioc))
		return NULL;

	/* initialize */
	atomic_long_set(&ioc->refcount, 1);
	atomic_set(&ioc->nr_tasks, 1);
	spin_lock_init(&ioc->lock);
	INIT_RADIX_TREE(&ioc->radix_root, GFP_ATOMIC | __GFP_HIGH);
	INIT_HLIST_HEAD(&ioc->cic_list);

	/* try to install, somebody might already have beaten us to it */
	task_lock(task);

	if (!task->io_context && !(task->flags & PF_EXITING)) {
		task->io_context = ioc;
	} else {
		kmem_cache_free(iocontext_cachep, ioc);
		ioc = task->io_context;
	}

	if (ioc && take_ref)
		get_io_context(ioc);

	task_unlock(task);
	return ioc;
}

/**
 * current_io_context - get io_context of %current
 * @gfp_flags: allocation flags, used if allocation is necessary
 * @node: allocation node, used if allocation is necessary
 *
 * Return io_context of %current.  If it doesn't exist, it is created with
 * @gfp_flags and @node.  The returned io_context does NOT have its
 * reference count incremented.  Because io_context is exited only on task
 * exit, %current can be sure that the returned io_context is valid and
 * alive as long as it is executing.
 */
struct io_context *current_io_context(gfp_t gfp_flags, int node)
{
	might_sleep_if(gfp_flags & __GFP_WAIT);

	if (current->io_context)
		return current->io_context;

	return create_task_io_context(current, gfp_flags, node, false);
}
EXPORT_SYMBOL(current_io_context);

/**
 * get_task_io_context - get io_context of a task
 * @task: task of interest
 * @gfp_flags: allocation flags, used if allocation is necessary
 * @node: allocation node, used if allocation is necessary
 *
 * Return io_context of @task.  If it doesn't exist, it is created with
 * @gfp_flags and @node.  The returned io_context has its reference count
 * incremented.
 *
 * This function always goes through task_lock() and it's better to use
 * current_io_context() + get_io_context() for %current.
 */
struct io_context *get_task_io_context(struct task_struct *task,
				       gfp_t gfp_flags, int node)
{
	struct io_context *ioc;

	might_sleep_if(gfp_flags & __GFP_WAIT);

	task_lock(task);
	ioc = task->io_context;
	if (likely(ioc)) {
		get_io_context(ioc);
		task_unlock(task);
		return ioc;
	}
	task_unlock(task);

	return create_task_io_context(task, gfp_flags, node, true);
}
EXPORT_SYMBOL(get_task_io_context);

static int __init blk_ioc_init(void)
{
	iocontext_cachep = kmem_cache_create("blkdev_ioc",
			sizeof(struct io_context), 0, SLAB_PANIC, NULL);
	return 0;
}
subsys_initcall(blk_ioc_init);