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
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
|
/*
* 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"
static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
static DEFINE_PER_CPU(char *, irq_name);
static bool xen_pvspin = true;
#ifdef CONFIG_QUEUED_SPINLOCKS
#include <asm/qspinlock.h>
static void xen_qlock_kick(int cpu)
{
int irq = per_cpu(lock_kicker_irq, cpu);
/* Don't kick if the target's kicker interrupt is not initialized. */
if (irq == -1)
return;
xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
}
/*
* Halt the current CPU & release it back to the host
*/
static void xen_qlock_wait(u8 *byte, u8 val)
{
int irq = __this_cpu_read(lock_kicker_irq);
/* If kicker interrupts not initialized yet, just spin */
if (irq == -1)
return;
/* clear pending */
xen_clear_irq_pending(irq);
barrier();
/*
* We check the byte value after clearing pending IRQ to make sure
* that we won't miss a wakeup event because of the clearing.
*
* The sync_clear_bit() call in xen_clear_irq_pending() is atomic.
* So it is effectively a memory barrier for x86.
*/
if (READ_ONCE(*byte) != val)
return;
/*
* If an interrupt happens here, it will leave the wakeup irq
* pending, which will cause xen_poll_irq() to return
* immediately.
*/
/* Block until irq becomes pending (or perhaps a spurious wakeup) */
xen_poll_irq(irq);
}
#else /* CONFIG_QUEUED_SPINLOCKS */
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 = READ_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 */
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 */
struct xen_lock_waiting {
struct arch_spinlock *lock;
__ticket_t want;
};
static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
static cpumask_t waiting_cpus;
__visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
{
int irq = __this_cpu_read(lock_kicker_irq);
struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting);
int cpu = smp_processor_id();
u64 start;
__ticket_t head;
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);
/*
* We don't really care if we're overwriting some other
* (lock,want) pair, as that would mean that we're currently
* in an interrupt context, and the outer context had
* interrupts enabled. That has already kicked the VCPU out
* of xen_poll_irq(), so it will just return spuriously and
* retry with newly setup (lock,want).
*
* The ordering protocol on this is that the "lock" pointer
* may only be set non-NULL if the "want" ticket is correct.
* If we're updating "want", we must first clear "lock".
*/
w->lock = NULL;
smp_wmb();
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();
/*
* Mark entry to slowpath before doing the pickup test to make
* sure we don't deadlock with an unlocker.
*/
__ticket_enter_slowpath(lock);
/* make sure enter_slowpath, which is atomic does not cross the read */
smp_mb__after_atomic();
/*
* check again make sure it didn't become free while
* we weren't looking
*/
head = READ_ONCE(lock->tickets.head);
if (__tickets_equal(head, want)) {
add_stats(TAKEN_SLOW_PICKUP, 1);
goto out;
}
/* Allow interrupts while blocked */
local_irq_restore(flags);
/*
* If an interrupt happens here, it will leave the wakeup irq
* pending, which will cause xen_poll_irq() to return
* immediately.
*/
/* Block until irq becomes pending (or perhaps a spurious wakeup) */
xen_poll_irq(irq);
add_stats(TAKEN_SLOW_SPURIOUS, !xen_test_irq_pending(irq));
local_irq_save(flags);
kstat_incr_irq_this_cpu(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);
/* Make sure we read lock before want */
if (READ_ONCE(w->lock) == lock &&
READ_ONCE(w->want) == next) {
add_stats(RELEASED_SLOW_KICKED, 1);
xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
break;
}
}
}
#endif /* CONFIG_QUEUED_SPINLOCKS */
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;
if (!xen_pvspin)
return;
WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n",
cpu, per_cpu(lock_kicker_irq, cpu));
name = kasprintf(GFP_KERNEL, "spinlock%d", cpu);
irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR,
cpu,
dummy_handler,
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)
{
if (!xen_pvspin)
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;
}
/*
* Our init of PV spinlocks is split in two init functions due to us
* using paravirt patching and jump labels patching and having to do
* all of this before SMP code is invoked.
*
* The paravirt patching needs to be done _before_ the alternative asm code
* is started, otherwise we would not patch the core kernel code.
*/
void __init xen_init_spinlocks(void)
{
if (!xen_pvspin) {
printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
return;
}
printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
#ifdef CONFIG_QUEUED_SPINLOCKS
__pv_init_lock_hash();
pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
pv_lock_ops.wait = xen_qlock_wait;
pv_lock_ops.kick = xen_qlock_kick;
#else
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
pv_lock_ops.unlock_kick = xen_unlock_kick;
#endif
}
/*
* While the jump_label init code needs to happend _after_ the jump labels are
* enabled and before SMP is started. Hence we use pre-SMP initcall level
* init. We cannot do it in xen_init_spinlocks as that is done before
* jump labels are activated.
*/
static __init int xen_init_spinlocks_jump(void)
{
if (!xen_pvspin)
return 0;
if (!xen_domain())
return 0;
static_key_slow_inc(¶v
|