summaryrefslogtreecommitdiffstats
path: root/lib/percpu-refcount.c
blob: ebeaac274cb9ac6f51bc54eba44301fd1d988273 (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
#define pr_fmt(fmt) "%s: " fmt "\n", __func__

#include <linux/kernel.h>
#include <linux/percpu-refcount.h>

/*
 * Initially, a percpu refcount is just a set of percpu counters. Initially, we
 * don't try to detect the ref hitting 0 - which means that get/put can just
 * increment or decrement the local counter. Note that the counter on a
 * particular cpu can (and will) wrap - this is fine, when we go to shutdown the
 * percpu counters will all sum to the correct value
 *
 * (More precisely: because moduler arithmatic is commutative the sum of all the
 * pcpu_count vars will be equal to what it would have been if all the gets and
 * puts were done to a single integer, even if some of the percpu integers
 * overflow or underflow).
 *
 * The real trick to implementing percpu refcounts is shutdown. We can't detect
 * the ref hitting 0 on every put - this would require global synchronization
 * and defeat the whole purpose of using percpu refs.
 *
 * What we do is require the user to keep track of the initial refcount; we know
 * the ref can't hit 0 before the user drops the initial ref, so as long as we
 * convert to non percpu mode before the initial ref is dropped everything
 * works.
 *
 * Converting to non percpu mode is done with some RCUish stuff in
 * percpu_ref_kill. Additionally, we need a bias value so that the atomic_t
 * can't hit 0 before we've added up all the percpu refs.
 */

#define PCPU_COUNT_BIAS		(1U << 31)

/**
 * percpu_ref_init - initialize a percpu refcount
 * @ref: percpu_ref to initialize
 * @release: function which will be called when refcount hits 0
 *
 * Initializes the refcount in single atomic counter mode with a refcount of 1;
 * analagous to atomic_set(ref, 1).
 *
 * Note that @release must not sleep - it may potentially be called from RCU
 * callback context by percpu_ref_kill().
 */
int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release)
{
	atomic_set(&ref->count, 1 + PCPU_COUNT_BIAS);

	ref->pcpu_count = alloc_percpu(unsigned);
	if (!ref->pcpu_count)
		return -ENOMEM;

	ref->release = release;
	return 0;
}

/**
 * percpu_ref_cancel_init - cancel percpu_ref_init()
 * @ref: percpu_ref to cancel init for
 *
 * Once a percpu_ref is initialized, its destruction is initiated by
 * percpu_ref_kill() and completes asynchronously, which can be painful to
 * do when destroying a half-constructed object in init failure path.
 *
 * This function destroys @ref without invoking @ref->release and the
 * memory area containing it can be freed immediately on return.  To
 * prevent accidental misuse, it's required that @ref has finished
 * percpu_ref_init(), whether successful or not, but never used.
 *
 * The weird name and usage restriction are to prevent people from using
 * this function by mistake for normal shutdown instead of
 * percpu_ref_kill().
 */
void percpu_ref_cancel_init(struct percpu_ref *ref)
{
	unsigned __percpu *pcpu_count = ref->pcpu_count;
	int cpu;

	WARN_ON_ONCE(atomic_read(&ref->count) != 1 + PCPU_COUNT_BIAS);

	if (pcpu_count) {
		for_each_possible_cpu(cpu)
			WARN_ON_ONCE(*per_cpu_ptr(pcpu_count, cpu));
		free_percpu(ref->pcpu_count);
	}
}

static void percpu_ref_kill_rcu(struct rcu_head *rcu)
{
	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
	unsigned __percpu *pcpu_count = ref->pcpu_count;
	unsigned count = 0;
	int cpu;

	/* Mask out PCPU_REF_DEAD */
	pcpu_count = (unsigned __percpu *)
		(((unsigned long) pcpu_count) & ~PCPU_STATUS_MASK);

	for_each_possible_cpu(cpu)
		count += *per_cpu_ptr(pcpu_count, cpu);

	free_percpu(pcpu_count);

	pr_debug("global %i pcpu %i", atomic_read(&ref->count), (int) count);

	/*
	 * It's crucial that we sum the percpu counters _before_ adding the sum
	 * to &ref->count; since gets could be happening on one cpu while puts
	 * happen on another, adding a single cpu's count could cause
	 * @ref->count to hit 0 before we've got a consistent value - but the
	 * sum of all the counts will be consistent and correct.
	 *
	 * Subtracting the bias value then has to happen _after_ adding count to
	 * &ref->count; we need the bias value to prevent &ref->count from
	 * reaching 0 before we add the percpu counts. But doing it at the same
	 * time is equivalent and saves us atomic operations:
	 */

	atomic_add((int) count - PCPU_COUNT_BIAS, &ref->count);

	/*
	 * Now we're in single atomic_t mode with a consistent refcount, so it's
	 * safe to drop our initial ref:
	 */
	percpu_ref_put(ref);
}

/**
 * percpu_ref_kill - safely drop initial ref
 * @ref: percpu_ref to kill
 *
 * Must be used to drop the initial ref on a percpu refcount; must be called
 * precisely once before shutdown.
 *
 * Puts @ref in non percpu mode, then does a call_rcu() before gathering up the
 * percpu counters and dropping the initial ref.
 */
void percpu_ref_kill(struct percpu_ref *ref)
{
	WARN_ONCE(REF_STATUS(ref->pcpu_count) == PCPU_REF_DEAD,
		  "percpu_ref_kill() called more than once!\n");

	ref->pcpu_count = (unsigned __percpu *)
		(((unsigned long) ref->pcpu_count)|PCPU_REF_DEAD);

	call_rcu(&ref->rcu, percpu_ref_kill_rcu);
}