summaryrefslogtreecommitdiff
path: root/lib/irq_poll.c
blob: e6fd1dc0908bdb61ed244b29ec84dbda18adb8c6 (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
/*
 * Functions related to interrupt-poll handling in the block layer. This
 * is similar to NAPI for network devices.
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/bio.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/irq_poll.h>
#include <linux/delay.h>

static unsigned int irq_poll_budget __read_mostly = 256;

static DEFINE_PER_CPU(struct list_head, blk_cpu_iopoll);

/**
 * irq_poll_sched - Schedule a run of the iopoll handler
 * @iop:      The parent iopoll structure
 *
 * Description:
 *     Add this irq_poll structure to the pending poll list and trigger the
 *     raise of the blk iopoll softirq. The driver must already have gotten a
 *     successful return from irq_poll_sched_prep() before calling this.
 **/
void irq_poll_sched(struct irq_poll *iop)
{
	unsigned long flags;

	local_irq_save(flags);
	list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll));
	__raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(irq_poll_sched);

/**
 * __irq_poll_complete - Mark this @iop as un-polled again
 * @iop:      The parent iopoll structure
 *
 * Description:
 *     See irq_poll_complete(). This function must be called with interrupts
 *     disabled.
 **/
void __irq_poll_complete(struct irq_poll *iop)
{
	list_del(&iop->list);
	smp_mb__before_atomic();
	clear_bit_unlock(IRQ_POLL_F_SCHED, &iop->state);
}
EXPORT_SYMBOL(__irq_poll_complete);

/**
 * irq_poll_complete - Mark this @iop as un-polled again
 * @iop:      The parent iopoll structure
 *
 * Description:
 *     If a driver consumes less than the assigned budget in its run of the
 *     iopoll handler, it'll end the polled mode by calling this function. The
 *     iopoll handler will not be invoked again before irq_poll_sched_prep()
 *     is called.
 **/
void irq_poll_complete(struct irq_poll *iop)
{
	unsigned long flags;

	local_irq_save(flags);
	__irq_poll_complete(iop);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(irq_poll_complete);

static void irq_poll_softirq(struct softirq_action *h)
{
	struct list_head *list = this_cpu_ptr(&blk_cpu_iopoll);
	int rearm = 0, budget = irq_poll_budget;
	unsigned long start_time = jiffies;

	local_irq_disable();

	while (!list_empty(list)) {
		struct irq_poll *iop;
		int work, weight;

		/*
		 * If softirq window is exhausted then punt.
		 */
		if (budget <= 0 || time_after(jiffies, start_time)) {
			rearm = 1;
			break;
		}

		local_irq_enable();

		/* Even though interrupts have been re-enabled, this
		 * access is safe because interrupts can only add new
		 * entries to the tail of this list, and only ->poll()
		 * calls can remove this head entry from the list.
		 */
		iop = list_entry(list->next, struct irq_poll, list);

		weight = iop->weight;
		work = 0;
		if (test_bit(IRQ_POLL_F_SCHED, &iop->state))
			work = iop->poll(iop, weight);

		budget -= work;

		local_irq_disable();

		/*
		 * Drivers must not modify the iopoll state, if they
		 * consume their assigned weight (or more, some drivers can't
		 * easily just stop processing, they have to complete an
		 * entire mask of commands).In such cases this code
		 * still "owns" the iopoll instance and therefore can
		 * move the instance around on the list at-will.
		 */
		if (work >= weight) {
			if (irq_poll_disable_pending(iop))
				__irq_poll_complete(iop);
			else
				list_move_tail(&iop->list, list);
		}
	}

	if (rearm)
		__raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);

	local_irq_enable();
}

/**
 * irq_poll_disable - Disable iopoll on this @iop
 * @iop:      The parent iopoll structure
 *
 * Description:
 *     Disable io polling and wait for any pending callbacks to have completed.
 **/
void irq_poll_disable(struct irq_poll *iop)
{
	set_bit(IRQ_POLL_F_DISABLE, &iop->state);
	while (test_and_set_bit(IRQ_POLL_F_SCHED, &iop->state))
		msleep(1);
	clear_bit(IRQ_POLL_F_DISABLE, &iop->state);
}
EXPORT_SYMBOL(irq_poll_disable);

/**
 * irq_poll_enable - Enable iopoll on this @iop
 * @iop:      The parent iopoll structure
 *
 * Description:
 *     Enable iopoll on this @iop. Note that the handler run will not be
 *     scheduled, it will only mark it as active.
 **/
void irq_poll_enable(struct irq_poll *iop)
{
	BUG_ON(!test_bit(IRQ_POLL_F_SCHED, &iop->state));
	smp_mb__before_atomic();
	clear_bit_unlock(IRQ_POLL_F_SCHED, &iop->state);
}
EXPORT_SYMBOL(irq_poll_enable);

/**
 * irq_poll_init - Initialize this @iop
 * @iop:      The parent iopoll structure
 * @weight:   The default weight (or command completion budget)
 * @poll_fn:  The handler to invoke
 *
 * Description:
 *     Initialize this irq_poll structure. Before being actively used, the
 *     driver must call irq_poll_enable().
 **/
void irq_poll_init(struct irq_poll *iop, int weight, irq_poll_fn *poll_fn)
{
	memset(iop, 0, sizeof(*iop));
	INIT_LIST_HEAD(&iop->list);
	iop->weight = weight;
	iop->poll = poll_fn;
	set_bit(IRQ_POLL_F_SCHED, &iop->state);
}
EXPORT_SYMBOL(irq_poll_init);

static int irq_poll_cpu_notify(struct notifier_block *self,
				 unsigned long action, void *hcpu)
{
	/*
	 * If a CPU goes away, splice its entries to the current CPU
	 * and trigger a run of the softirq
	 */
	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
		int cpu = (unsigned long) hcpu;

		local_irq_disable();
		list_splice_init(&per_cpu(blk_cpu_iopoll, cpu),
				 this_cpu_ptr(&blk_cpu_iopoll));
		__raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
		local_irq_enable();
	}

	return NOTIFY_OK;
}

static struct notifier_block irq_poll_cpu_notifier = {
	.notifier_call	= irq_poll_cpu_notify,
};

static __init int irq_poll_setup(void)
{
	int i;

	for_each_possible_cpu(i)
		INIT_LIST_HEAD(&per_cpu(blk_cpu_iopoll, i));

	open_softirq(IRQ_POLL_SOFTIRQ, irq_poll_softirq);
	register_hotcpu_notifier(&irq_poll_cpu_notifier);
	return 0;
}
subsys_initcall(irq_poll_setup);