aboutsummaryrefslogtreecommitdiffstats
path: root/lib/kernel_lock.c
blob: f73e2f8c308f2e3b17e0cd21b5f0ab7131872f08 (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
/*
 * lib/kernel_lock.c
 *
 * This is the traditional BKL - big kernel lock. Largely
 * relegated to obsolescence, but used by various less
 * important (or lazy) subsystems.
 */
#include <linux/smp_lock.h>
#include <linux/module.h>
#include <linux/kallsyms.h>

#ifdef CONFIG_PREEMPT_BKL
/*
 * The 'big kernel semaphore'
 *
 * This mutex is taken and released recursively by lock_kernel()
 * and unlock_kernel().  It is transparently dropped and reacquired
 * over schedule().  It is used to protect legacy code that hasn't
 * been migrated to a proper locking design yet.
 *
 * Note: code locked by this semaphore will only be serialized against
 * other code using the same locking facility. The code guarantees that
 * the task remains on the same CPU.
 *
 * Don't use in new code.
 */
static DECLARE_MUTEX(kernel_sem);

/*
 * Re-acquire the kernel semaphore.
 *
 * This function is called with preemption off.
 *
 * We are executing in schedule() so the code must be extremely careful
 * about recursion, both due to the down() and due to the enabling of
 * preemption. schedule() will re-check the preemption flag after
 * reacquiring the semaphore.
 */
int __lockfunc __reacquire_kernel_lock(void)
{
	struct task_struct *task = current;
	int saved_lock_depth = task->lock_depth;

	BUG_ON(saved_lock_depth < 0);

	task->lock_depth = -1;
	preempt_enable_no_resched();

	down(&kernel_sem);

	preempt_disable();
	task->lock_depth = saved_lock_depth;

	return 0;
}

void __lockfunc __release_kernel_lock(void)
{
	up(&kernel_sem);
}

/*
 * Getting the big kernel semaphore.
 */
void __lockfunc lock_kernel(void)
{
	struct task_struct *task = current;
	int depth = task->lock_depth + 1;

	if (likely(!depth))
		/*
		 * No recursion worries - we set up lock_depth _after_
		 */
		down(&kernel_sem);

	task->lock_depth = depth;
}

void __lockfunc unlock_kernel(void)
{
	struct task_struct *task = current;

	BUG_ON(task->lock_depth < 0);

	if (likely(--task->lock_depth < 0))
		up(&kernel_sem);
}

#else

/*
 * The 'big kernel lock'
 *
 * This spinlock is taken and released recursively by lock_kernel()
 * and unlock_kernel().  It is transparently dropped and reacquired
 * over schedule().  It is used to protect legacy code that hasn't
 * been migrated to a proper locking design yet.
 *
 * Don't use in new code.
 */
static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kernel_flag);


/*
 * Acquire/release the underlying lock from the scheduler.
 *
 * This is called with preemption disabled, and should
 * return an error value if it cannot get the lock and
 * TIF_NEED_RESCHED gets set.
 *
 * If it successfully gets the lock, it should increment
 * the preemption count like any spinlock does.
 *
 * (This works on UP too - _raw_spin_trylock will never
 * return false in that case)
 */
int __lockfunc __reacquire_kernel_lock(void)
{
	while (!_raw_spin_trylock(&kernel_flag)) {
		if (test_thread_flag(TIF_NEED_RESCHED))
			return -EAGAIN;
		cpu_relax();
	}
	preempt_disable();
	return 0;
}

void __lockfunc __release_kernel_lock(void)
{
	_raw_spin_unlock(&kernel_flag);
	preempt_enable_no_resched();
}

/*
 * These are the BKL spinlocks - we try to be polite about preemption. 
 * If SMP is not on (ie UP preemption), this all goes away because the
 * _raw_spin_trylock() will always succeed.
 */
#ifdef CONFIG_PREEMPT
static inline void __lock_kernel(void)
{
	preempt_disable();
	if (unlikely(!_raw_spin_trylock(&kernel_flag))) {
		/*
		 * If preemption was disabled even before this
		 * was called, there's nothing we can be polite
		 * about - just spin.
		 */
		if (preempt_count() > 1) {
			_raw_spin_lock(&kernel_flag);
			return;
		}

		/*
		 * Otherwise, let's wait for the kernel lock
		 * with preemption enabled..
		 */
		do {
			preempt_enable();
			while (spin_is_locked(&kernel_flag))
				cpu_relax();
			preempt_disable();
		} while (!_raw_spin_trylock(&kernel_flag));
	}
}

#else

/*
 * Non-preemption case - just get the spinlock
 */
static inline void __lock_kernel(void)
{
	_raw_spin_lock(&kernel_flag);
}
#endif

static inline void __unlock_kernel(void)
{
	/*
	 * the BKL is not covered by lockdep, so we open-code the
	 * unlocking sequence (and thus avoid the dep-chain ops):
	 */
	_raw_spin_unlock(&kernel_flag);
	preempt_enable();
}

/*
 * Getting the big kernel lock.
 *
 * This cannot happen asynchronously, so we only need to
 * worry about other CPU's.
 */
void __lockfunc lock_kernel(void)
{
	int depth = current->lock_depth+1;
	if (likely(!depth))
		__lock_kernel();
	current->lock_depth = depth;
}

void __lockfunc unlock_kernel(void)
{
	BUG_ON(current->lock_depth < 0);
	if (likely(--current->lock_depth < 0))
		__unlock_kernel();
}

#endif

EXPORT_SYMBOL(lock_kernel);
EXPORT_SYMBOL(unlock_kernel);