summaryrefslogtreecommitdiffstats
path: root/kernel/locking/mcs_spinlock.c
blob: 838dc9e0066975943f835960b9801cdb6561afc5 (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

#include <linux/percpu.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include "mcs_spinlock.h"

#ifdef CONFIG_SMP

/*
 * An MCS like lock especially tailored for optimistic spinning for sleeping
 * lock implementations (mutex, rwsem, etc).
 *
 * Using a single mcs node per CPU is safe because sleeping locks should not be
 * called from interrupt context and we have preemption disabled while
 * spinning.
 */
static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_queue, osq_node);

/*
 * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
 * Can return NULL in case we were the last queued and we updated @lock instead.
 */
static inline struct optimistic_spin_queue *
osq_wait_next(struct optimistic_spin_queue **lock,
	      struct optimistic_spin_queue *node,
	      struct optimistic_spin_queue *prev)
{
	struct optimistic_spin_queue *next = NULL;

	for (;;) {
		if (*lock == node && cmpxchg(lock, node, prev) == node) {
			/*
			 * We were the last queued, we moved @lock back. @prev
			 * will now observe @lock and will complete its
			 * unlock()/unqueue().
			 */
			break;
		}

		/*
		 * We must xchg() the @node->next value, because if we were to
		 * leave it in, a concurrent unlock()/unqueue() from
		 * @node->next might complete Step-A and think its @prev is
		 * still valid.
		 *
		 * If the concurrent unlock()/unqueue() wins the race, we'll
		 * wait for either @lock to point to us, through its Step-B, or
		 * wait for a new @node->next from its Step-C.
		 */
		if (node->next) {
			next = xchg(&node->next, NULL);
			if (next)
				break;
		}

		arch_mutex_cpu_relax();
	}

	return next;
}

bool osq_lock(struct optimistic_spin_queue **lock)
{
	struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
	struct optimistic_spin_queue *prev, *next;

	node->locked = 0;
	node->next = NULL;

	node->prev = prev = xchg(lock, node);
	if (likely(prev == NULL))
		return true;

	ACCESS_ONCE(prev->next) = node;

	/*
	 * Normally @prev is untouchable after the above store; because at that
	 * moment unlock can proceed and wipe the node element from stack.
	 *
	 * However, since our nodes are static per-cpu storage, we're
	 * guaranteed their existence -- this allows us to apply
	 * cmpxchg in an attempt to undo our queueing.
	 */

	while (!smp_load_acquire(&node->locked)) {
		/*
		 * If we need to reschedule bail... so we can block.
		 */
		if (need_resched())
			goto unqueue;

		arch_mutex_cpu_relax();
	}
	return true;

unqueue:
	/*
	 * Step - A  -- stabilize @prev
	 *
	 * Undo our @prev->next assignment; this will make @prev's
	 * unlock()/unqueue() wait for a next pointer since @lock points to us
	 * (or later).
	 */

	for (;;) {
		if (prev->next == node &&
		    cmpxchg(&prev->next, node, NULL) == node)
			break;

		/*
		 * We can only fail the cmpxchg() racing against an unlock(),
		 * in which case we should observe @node->locked becomming
		 * true.
		 */
		if (smp_load_acquire(&node->locked))
			return true;

		arch_mutex_cpu_relax();

		/*
		 * Or we race against a concurrent unqueue()'s step-B, in which
		 * case its step-C will write us a new @node->prev pointer.
		 */
		prev = ACCESS_ONCE(node->prev);
	}

	/*
	 * Step - B -- stabilize @next
	 *
	 * Similar to unlock(), wait for @node->next or move @lock from @node
	 * back to @prev.
	 */

	next = osq_wait_next(lock, node, prev);
	if (!next)
		return false;

	/*
	 * Step - C -- unlink
	 *
	 * @prev is stable because its still waiting for a new @prev->next
	 * pointer, @next is stable because our @node->next pointer is NULL and
	 * it will wait in Step-A.
	 */

	ACCESS_ONCE(next->prev) = prev;
	ACCESS_ONCE(prev->next) = next;

	return false;
}

void osq_unlock(struct optimistic_spin_queue **lock)
{
	struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
	struct optimistic_spin_queue *next;

	/*
	 * Fast path for the uncontended case.
	 */
	if (likely(cmpxchg(lock, node, NULL) == node))
		return;

	/*
	 * Second most likely case.
	 */
	next = xchg(&node->next, NULL);
	if (next) {
		ACCESS_ONCE(next->locked) = 1;
		return;
	}

	next = osq_wait_next(lock, node, NULL);
	if (next)
		ACCESS_ONCE(next->locked) = 1;
}

#endif

OpenPOWER on IntegriCloud