summaryrefslogtreecommitdiffstats
path: root/arch/x86/xen/spinlock.c
blob: 4884bc603aa7ed0c591289c3035b69558bb99da8 (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
/*
 * Split spinlock implementation out into its own file, so it can be
 * compiled in a FTRACE-compatible way.
 */
#include <linux/kernel_stat.h>
#include <linux/spinlock.h>

#include <asm/paravirt.h>

#include <xen/interface/xen.h>
#include <xen/events.h>

#include "xen-ops.h"

struct xen_spinlock {
	unsigned char lock;		/* 0 -> free; 1 -> locked */
	unsigned short spinners;	/* count of waiting cpus */
};

static int xen_spin_is_locked(struct raw_spinlock *lock)
{
	struct xen_spinlock *xl = (struct xen_spinlock *)lock;

	return xl->lock != 0;
}

static int xen_spin_is_contended(struct raw_spinlock *lock)
{
	struct xen_spinlock *xl = (struct xen_spinlock *)lock;

	/* Not strictly true; this is only the count of contended
	   lock-takers entering the slow path. */
	return xl->spinners != 0;
}

static int xen_spin_trylock(struct raw_spinlock *lock)
{
	struct xen_spinlock *xl = (struct xen_spinlock *)lock;
	u8 old = 1;

	asm("xchgb %b0,%1"
	    : "+q" (old), "+m" (xl->lock) : : "memory");

	return old == 0;
}

static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
static DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners);

/*
 * Mark a cpu as interested in a lock.  Returns the CPU's previous
 * lock of interest, in case we got preempted by an interrupt.
 */
static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
{
	struct xen_spinlock *prev;

	prev = __get_cpu_var(lock_spinners);
	__get_cpu_var(lock_spinners) = xl;

	wmb();			/* set lock of interest before count */

	asm(LOCK_PREFIX " incw %0"
	    : "+m" (xl->spinners) : : "memory");

	return prev;
}

/*
 * Mark a cpu as no longer interested in a lock.  Restores previous
 * lock of interest (NULL for none).
 */
static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev)
{
	asm(LOCK_PREFIX " decw %0"
	    : "+m" (xl->spinners) : : "memory");
	wmb();			/* decrement count before restoring lock */
	__get_cpu_var(lock_spinners) = prev;
}

static noinline int xen_spin_lock_slow(struct raw_spinlock *lock)
{
	struct xen_spinlock *xl = (struct xen_spinlock *)lock;
	struct xen_spinlock *prev;
	int irq = __get_cpu_var(lock_kicker_irq);
	int ret;

	/* If kicker interrupts not initialized yet, just spin */
	if (irq == -1)
		return 0;

	/* announce we're spinning */
	prev = spinning_lock(xl);

	do {
		/* clear pending */
		xen_clear_irq_pending(irq);

		/* check again make sure it didn't become free while
		   we weren't looking  */
		ret = xen_spin_trylock(lock);
		if (ret) {
			/*
			 * If we interrupted another spinlock while it
			 * was blocking, make sure it doesn't block
			 * without rechecking the lock.
			 */
			if (prev != NULL)
				xen_set_irq_pending(irq);
			goto out;
		}

		/*
		 * Block until irq becomes pending.  If we're
		 * interrupted at this point (after the trylock but
		 * before entering the block), then the nested lock
		 * handler guarantees that the irq will be left
		 * pending if there's any chance the lock became free;
		 * xen_poll_irq() returns immediately if the irq is
		 * pending.
		 */
		xen_poll_irq(irq);
	} while (!xen_test_irq_pending(irq)); /* check for spurious wakeups */

	kstat_this_cpu.irqs[irq]++;

out:
	unspinning_lock(xl, prev);
	return ret;
}

static void xen_spin_lock(struct raw_spinlock *lock)
{
	struct xen_spinlock *xl = (struct xen_spinlock *)lock;
	int timeout;
	u8 oldval;

	do {
		timeout = 1 << 10;

		asm("1: xchgb %1,%0\n"
		    "   testb %1,%1\n"
		    "   jz 3f\n"
		    "2: rep;nop\n"
		    "   cmpb $0,%0\n"
		    "   je 1b\n"
		    "   dec %2\n"
		    "   jnz 2b\n"
		    "3:\n"
		    : "+m" (xl->lock), "=q" (oldval), "+r" (timeout)
		    : "1" (1)
		    : "memory");

	} while (unlikely(oldval != 0 && !xen_spin_lock_slow(lock)));
}

static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl)
{
	int cpu;

	for_each_online_cpu(cpu) {
		/* XXX should mix up next cpu selection */
		if (per_cpu(lock_spinners, cpu) == xl) {
			xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
			break;
		}
	}
}

static void xen_spin_unlock(struct raw_spinlock *lock)
{
	struct xen_spinlock *xl = (struct xen_spinlock *)lock;

	smp_wmb();		/* make sure no writes get moved after unlock */
	xl->lock = 0;		/* release lock */

	/* make sure unlock happens before kick */
	barrier();

	if (unlikely(xl->spinners))
		xen_spin_unlock_slow(xl);
}

static irqreturn_t dummy_handler(int irq, void *dev_id)
{
	BUG();
	return IRQ_HANDLED;
}

void __cpuinit xen_init_lock_cpu(int cpu)
{
	int irq;
	const char *name;

	name = kasprintf(GFP_KERNEL, "spinlock%d", cpu);
	irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR,
				     cpu,
				     dummy_handler,
				     IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
				     name,
				     NULL);

	if (irq >= 0) {
		disable_irq(irq); /* make sure it's never delivered */
		per_cpu(lock_kicker_irq, cpu) = irq;
	}

	printk("cpu %d spinlock event irq %d\n", cpu, irq);
}

void __init xen_init_spinlocks(void)
{
	pv_lock_ops.spin_is_locked = xen_spin_is_locked;
	pv_lock_ops.spin_is_contended = xen_spin_is_contended;
	pv_lock_ops.spin_lock = xen_spin_lock;
	pv_lock_ops.spin_trylock = xen_spin_trylock;
	pv_lock_ops.spin_unlock = xen_spin_unlock;
}