summaryrefslogtreecommitdiffstats
path: root/arch/x86/xen/spinlock.c
blob: 6c8792b298ed2fa4926f2a363990ca4334ab8dd5 (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
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
/*
 * 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 <linux/debugfs.h>
#include <linux/log2.h>
#include <linux/gfp.h>
#include <linux/slab.h>

#include <asm/paravirt.h>

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

#include "xen-ops.h"
#include "debugfs.h"

enum xen_contention_stat {
	TAKEN_SLOW,
	TAKEN_SLOW_PICKUP,
	TAKEN_SLOW_SPURIOUS,
	RELEASED_SLOW,
	RELEASED_SLOW_KICKED,
	NR_CONTENTION_STATS
};


#ifdef CONFIG_XEN_DEBUG_FS
#define HISTO_BUCKETS	30
static struct xen_spinlock_stats
{
	u32 contention_stats[NR_CONTENTION_STATS];
	u32 histo_spin_blocked[HISTO_BUCKETS+1];
	u64 time_blocked;
} spinlock_stats;

static u8 zero_stats;

static inline void check_zero(void)
{
	u8 ret;
	u8 old = ACCESS_ONCE(zero_stats);
	if (unlikely(old)) {
		ret = cmpxchg(&zero_stats, old, 0);
		/* This ensures only one fellow resets the stat */
		if (ret == old)
			memset(&spinlock_stats, 0, sizeof(spinlock_stats));
	}
}

static inline void add_stats(enum xen_contention_stat var, u32 val)
{
	check_zero();
	spinlock_stats.contention_stats[var] += val;
}

static inline u64 spin_time_start(void)
{
	return xen_clocksource_read();
}

static void __spin_time_accum(u64 delta, u32 *array)
{
	unsigned index = ilog2(delta);

	check_zero();

	if (index < HISTO_BUCKETS)
		array[index]++;
	else
		array[HISTO_BUCKETS]++;
}

static inline void spin_time_accum_blocked(u64 start)
{
	u32 delta = xen_clocksource_read() - start;

	__spin_time_accum(delta, spinlock_stats.histo_spin_blocked);
	spinlock_stats.time_blocked += delta;
}
#else  /* !CONFIG_XEN_DEBUG_FS */
#define TIMEOUT			(1 << 10)
static inline void add_stats(enum xen_contention_stat var, u32 val)
{
}

static inline u64 spin_time_start(void)
{
	return 0;
}

static inline void spin_time_accum_blocked(u64 start)
{
}
#endif  /* CONFIG_XEN_DEBUG_FS */

/*
 * Size struct xen_spinlock so it's the same as arch_spinlock_t.
 */
#if NR_CPUS < 256
typedef u8 xen_spinners_t;
# define inc_spinners(xl) \
	asm(LOCK_PREFIX " incb %0" : "+m" ((xl)->spinners) : : "memory");
# define dec_spinners(xl) \
	asm(LOCK_PREFIX " decb %0" : "+m" ((xl)->spinners) : : "memory");
#else
typedef u16 xen_spinners_t;
# define inc_spinners(xl) \
	asm(LOCK_PREFIX " incw %0" : "+m" ((xl)->spinners) : : "memory");
# define dec_spinners(xl) \
	asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory");
#endif

struct xen_lock_waiting {
	struct arch_spinlock *lock;
	__ticket_t want;
};

static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
static DEFINE_PER_CPU(char *, irq_name);
static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
static cpumask_t waiting_cpus;

static void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
{
	int irq = __this_cpu_read(lock_kicker_irq);
	struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting);
	int cpu = smp_processor_id();
	u64 start;
	unsigned long flags;

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

	start = spin_time_start();

	/*
	 * Make sure an interrupt handler can't upset things in a
	 * partially setup state.
	 */
	local_irq_save(flags);

	w->want = want;
	smp_wmb();
	w->lock = lock;

	/* This uses set_bit, which atomic and therefore a barrier */
	cpumask_set_cpu(cpu, &waiting_cpus);
	add_stats(TAKEN_SLOW, 1);

	/* clear pending */
	xen_clear_irq_pending(irq);

	/* Only check lock once pending cleared */
	barrier();

	/* check again make sure it didn't become free while
	   we weren't looking  */
	if (ACCESS_ONCE(lock->tickets.head) == want) {
		add_stats(TAKEN_SLOW_PICKUP, 1);
		goto out;
	}
	/* Block until irq becomes pending (or perhaps a spurious wakeup) */
	xen_poll_irq(irq);
	add_stats(TAKEN_SLOW_SPURIOUS, !xen_test_irq_pending(irq));
	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
out:
	cpumask_clear_cpu(cpu, &waiting_cpus);
	w->lock = NULL;
	local_irq_restore(flags);
	spin_time_accum_blocked(start);
}
PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning);

static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
{
	int cpu;

	add_stats(RELEASED_SLOW, 1);

	for_each_cpu(cpu, &waiting_cpus) {
		const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu);

		if (w->lock == lock && w->want == next) {
			add_stats(RELEASED_SLOW_KICKED, 1);
			xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
			break;
		}
	}
}

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

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

	WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n",
	     cpu, per_cpu(lock_kicker_irq, cpu));

	/*
	 * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
	 * (xen: disable PV spinlocks on HVM)
	 */
	if (xen_hvm_domain())
		return;

	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;
		per_cpu(irq_name, cpu) = name;
	}

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

void xen_uninit_lock_cpu(int cpu)
{
	/*
	 * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
	 * (xen: disable PV spinlocks on HVM)
	 */
	if (xen_hvm_domain())
		return;

	unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL);
	per_cpu(lock_kicker_irq, cpu) = -1;
	kfree(per_cpu(irq_name, cpu));
	per_cpu(irq_name, cpu) = NULL;
}

static bool xen_pvspin __initdata = true;

void __init xen_init_spinlocks(void)
{
	/*
	 * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
	 * (xen: disable PV spinlocks on HVM)
	 */
	if (xen_hvm_domain())
		return;

	if (!xen_pvspin) {
		printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
		return;
	}

	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
	pv_lock_ops.unlock_kick = xen_unlock_kick;
}

static __init int xen_parse_nopvspin(char *arg)
{
	xen_pvspin = false;
	return 0;
}
early_param("xen_nopvspin", xen_parse_nopvspin);

#ifdef CONFIG_XEN_DEBUG_FS

static struct dentry *d_spin_debug;

static int __init xen_spinlock_debugfs(void)
{
	struct dentry *d_xen = xen_init_debugfs();

	if (d_xen == NULL)
		return -ENOMEM;

	d_spin_debug = debugfs_create_dir("spinlocks", d_xen);

	debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats);

	debugfs_create_u32("taken_slow", 0444, d_spin_debug,
			   &spinlock_stats.contention_stats[TAKEN_SLOW]);
	debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug,
			   &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]);
	debugfs_create_u32("taken_slow_spurious", 0444, d_spin_debug,
			   &spinlock_stats.contention_stats[TAKEN_SLOW_SPURIOUS]);

	debugfs_create_u32("released_slow", 0444, d_spin_debug,
			   &spinlock_stats.contention_stats[RELEASED_SLOW]);
	debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug,
			   &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]);

	debugfs_create_u64("time_blocked", 0444, d_spin_debug,
			   &spinlock_stats.time_blocked);

	debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
				spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);

	return 0;
}
fs_initcall(xen_spinlock_debugfs);

#endif	/* CONFIG_XEN_DEBUG_FS */