summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm/percpu.h
blob: 0da5200ee79d149bdefe5aaddf917a536c85caa4 (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
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
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
#ifndef _ASM_X86_PERCPU_H
#define _ASM_X86_PERCPU_H

#ifdef CONFIG_X86_64
#define __percpu_seg		gs
#define __percpu_mov_op		movq
#else
#define __percpu_seg		fs
#define __percpu_mov_op		movl
#endif

#ifdef __ASSEMBLY__

/*
 * PER_CPU finds an address of a per-cpu variable.
 *
 * Args:
 *    var - variable name
 *    reg - 32bit register
 *
 * The resulting address is stored in the "reg" argument.
 *
 * Example:
 *    PER_CPU(cpu_gdt_descr, %ebx)
 */
#ifdef CONFIG_SMP
#define PER_CPU(var, reg)						\
	__percpu_mov_op %__percpu_seg:this_cpu_off, reg;		\
	lea var(reg), reg
#define PER_CPU_VAR(var)	%__percpu_seg:var
#else /* ! SMP */
#define PER_CPU(var, reg)	__percpu_mov_op $var, reg
#define PER_CPU_VAR(var)	var
#endif	/* SMP */

#ifdef CONFIG_X86_64_SMP
#define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
#else
#define INIT_PER_CPU_VAR(var)  var
#endif

#else /* ...!ASSEMBLY */

#include <linux/kernel.h>
#include <linux/stringify.h>

#ifdef CONFIG_SMP
#define __percpu_prefix		"%%"__stringify(__percpu_seg)":"
#define __my_cpu_offset		this_cpu_read(this_cpu_off)

/*
 * Compared to the generic __my_cpu_offset version, the following
 * saves one instruction and avoids clobbering a temp register.
 */
#define __this_cpu_ptr(ptr)				\
({							\
	unsigned long tcp_ptr__;			\
	__verify_pcpu_ptr(ptr);				\
	asm volatile("add " __percpu_arg(1) ", %0"	\
		     : "=r" (tcp_ptr__)			\
		     : "m" (this_cpu_off), "0" (ptr));	\
	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;	\
})
#else
#define __percpu_prefix		""
#endif

#define __percpu_arg(x)		__percpu_prefix "%P" #x

/*
 * Initialized pointers to per-cpu variables needed for the boot
 * processor need to use these macros to get the proper address
 * offset from __per_cpu_load on SMP.
 *
 * There also must be an entry in vmlinux_64.lds.S
 */
#define DECLARE_INIT_PER_CPU(var) \
       extern typeof(var) init_per_cpu_var(var)

#ifdef CONFIG_X86_64_SMP
#define init_per_cpu_var(var)  init_per_cpu__##var
#else
#define init_per_cpu_var(var)  var
#endif

/* For arch-specific code, we can use direct single-insn ops (they
 * don't give an lvalue though). */
extern void __bad_percpu_size(void);

#define percpu_to_op(op, var, val)			\
do {							\
	typedef typeof(var) pto_T__;			\
	if (0) {					\
		pto_T__ pto_tmp__;			\
		pto_tmp__ = (val);			\
		(void)pto_tmp__;			\
	}						\
	switch (sizeof(var)) {				\
	case 1:						\
		asm(op "b %1,"__percpu_arg(0)		\
		    : "+m" (var)			\
		    : "qi" ((pto_T__)(val)));		\
		break;					\
	case 2:						\
		asm(op "w %1,"__percpu_arg(0)		\
		    : "+m" (var)			\
		    : "ri" ((pto_T__)(val)));		\
		break;					\
	case 4:						\
		asm(op "l %1,"__percpu_arg(0)		\
		    : "+m" (var)			\
		    : "ri" ((pto_T__)(val)));		\
		break;					\
	case 8:						\
		asm(op "q %1,"__percpu_arg(0)		\
		    : "+m" (var)			\
		    : "re" ((pto_T__)(val)));		\
		break;					\
	default: __bad_percpu_size();			\
	}						\
} while (0)

/*
 * Generate a percpu add to memory instruction and optimize code
 * if one is added or subtracted.
 */
#define percpu_add_op(var, val)						\
do {									\
	typedef typeof(var) pao_T__;					\
	const int pao_ID__ = (__builtin_constant_p(val) &&		\
			      ((val) == 1 || (val) == -1)) ? (val) : 0;	\
	if (0) {							\
		pao_T__ pao_tmp__;					\
		pao_tmp__ = (val);					\
		(void)pao_tmp__;					\
	}								\
	switch (sizeof(var)) {						\
	case 1:								\
		if (pao_ID__ == 1)					\
			asm("incb "__percpu_arg(0) : "+m" (var));	\
		else if (pao_ID__ == -1)				\
			asm("decb "__percpu_arg(0) : "+m" (var));	\
		else							\
			asm("addb %1, "__percpu_arg(0)			\
			    : "+m" (var)				\
			    : "qi" ((pao_T__)(val)));			\
		break;							\
	case 2:								\
		if (pao_ID__ == 1)					\
			asm("incw "__percpu_arg(0) : "+m" (var));	\
		else if (pao_ID__ == -1)				\
			asm("decw "__percpu_arg(0) : "+m" (var));	\
		else							\
			asm("addw %1, "__percpu_arg(0)			\
			    : "+m" (var)				\
			    : "ri" ((pao_T__)(val)));			\
		break;							\
	case 4:								\
		if (pao_ID__ == 1)					\
			asm("incl "__percpu_arg(0) : "+m" (var));	\
		else if (pao_ID__ == -1)				\
			asm("decl "__percpu_arg(0) : "+m" (var));	\
		else							\
			asm("addl %1, "__percpu_arg(0)			\
			    : "+m" (var)				\
			    : "ri" ((pao_T__)(val)));			\
		break;							\
	case 8:								\
		if (pao_ID__ == 1)					\
			asm("incq "__percpu_arg(0) : "+m" (var));	\
		else if (pao_ID__ == -1)				\
			asm("decq "__percpu_arg(0) : "+m" (var));	\
		else							\
			asm("addq %1, "__percpu_arg(0)			\
			    : "+m" (var)				\
			    : "re" ((pao_T__)(val)));			\
		break;							\
	default: __bad_percpu_size();					\
	}								\
} while (0)

#define percpu_from_op(op, var, constraint)		\
({							\
	typeof(var) pfo_ret__;				\
	switch (sizeof(var)) {				\
	case 1:						\
		asm(op "b "__percpu_arg(1)",%0"		\
		    : "=q" (pfo_ret__)			\
		    : constraint);			\
		break;					\
	case 2:						\
		asm(op "w "__percpu_arg(1)",%0"		\
		    : "=r" (pfo_ret__)			\
		    : constraint);			\
		break;					\
	case 4:						\
		asm(op "l "__percpu_arg(1)",%0"		\
		    : "=r" (pfo_ret__)			\
		    : constraint);			\
		break;					\
	case 8:						\
		asm(op "q "__percpu_arg(1)",%0"		\
		    : "=r" (pfo_ret__)			\
		    : constraint);			\
		break;					\
	default: __bad_percpu_size();			\
	}						\
	pfo_ret__;					\
})

#define percpu_unary_op(op, var)			\
({							\
	switch (sizeof(var)) {				\
	case 1:						\
		asm(op "b "__percpu_arg(0)		\
		    : "+m" (var));			\
		break;					\
	case 2:						\
		asm(op "w "__percpu_arg(0)		\
		    : "+m" (var));			\
		break;					\
	case 4:						\
		asm(op "l "__percpu_arg(0)		\
		    : "+m" (var));			\
		break;					\
	case 8:						\
		asm(op "q "__percpu_arg(0)		\
		    : "+m" (var));			\
		break;					\
	default: __bad_percpu_size();			\
	}						\
})

/*
 * Add return operation
 */
#define percpu_add_return_op(var, val)					\
({									\
	typeof(var) paro_ret__ = val;					\
	switch (sizeof(var)) {						\
	case 1:								\
		asm("xaddb %0, "__percpu_arg(1)				\
			    : "+q" (paro_ret__), "+m" (var)		\
			    : : "memory");				\
		break;							\
	case 2:								\
		asm("xaddw %0, "__percpu_arg(1)				\
			    : "+r" (paro_ret__), "+m" (var)		\
			    : : "memory");				\
		break;							\
	case 4:								\
		asm("xaddl %0, "__percpu_arg(1)				\
			    : "+r" (paro_ret__), "+m" (var)		\
			    : : "memory");				\
		break;							\
	case 8:								\
		asm("xaddq %0, "__percpu_arg(1)				\
			    : "+re" (paro_ret__), "+m" (var)		\
			    : : "memory");				\
		break;							\
	default: __bad_percpu_size();					\
	}								\
	paro_ret__ += val;						\
	paro_ret__;							\
})

/*
 * xchg is implemented using cmpxchg without a lock prefix. xchg is
 * expensive due to the implied lock prefix.  The processor cannot prefetch
 * cachelines if xchg is used.
 */
#define percpu_xchg_op(var, nval)					\
({									\
	typeof(var) pxo_ret__;						\
	typeof(var) pxo_new__ = (nval);					\
	switch (sizeof(var)) {						\
	case 1:								\
		asm("\n\tmov "__percpu_arg(1)",%%al"			\
		    "\n1:\tcmpxchgb %2, "__percpu_arg(1)		\
		    "\n\tjnz 1b"					\
			    : "=&a" (pxo_ret__), "+m" (var)		\
			    : "q" (pxo_new__)				\
			    : "memory");				\
		break;							\
	case 2:								\
		asm("\n\tmov "__percpu_arg(1)",%%ax"			\
		    "\n1:\tcmpxchgw %2, "__percpu_arg(1)		\
		    "\n\tjnz 1b"					\
			    : "=&a" (pxo_ret__), "+m" (var)		\
			    : "r" (pxo_new__)				\
			    : "memory");				\
		break;							\
	case 4:								\
		asm("\n\tmov "__percpu_arg(1)",%%eax"			\
		    "\n1:\tcmpxchgl %2, "__percpu_arg(1)		\
		    "\n\tjnz 1b"					\
			    : "=&a" (pxo_ret__), "+m" (var)		\
			    : "r" (pxo_new__)				\
			    : "memory");				\
		break;							\
	case 8:								\
		asm("\n\tmov "__percpu_arg(1)",%%rax"			\
		    "\n1:\tcmpxchgq %2, "__percpu_arg(1)		\
		    "\n\tjnz 1b"					\
			    : "=&a" (pxo_ret__), "+m" (var)		\
			    : "r" (pxo_new__)				\
			    : "memory");				\
		break;							\
	default: __bad_percpu_size();					\
	}								\
	pxo_ret__;							\
})

/*
 * cmpxchg has no such implied lock semantics as a result it is much
 * more efficient for cpu local operations.
 */
#define percpu_cmpxchg_op(var, oval, nval)				\
({									\
	typeof(var) pco_ret__;						\
	typeof(var) pco_old__ = (oval);					\
	typeof(var) pco_new__ = (nval);					\
	switch (sizeof(var)) {						\
	case 1:								\
		asm("cmpxchgb %2, "__percpu_arg(1)			\
			    : "=a" (pco_ret__), "+m" (var)		\
			    : "q" (pco_new__), "0" (pco_old__)		\
			    : "memory");				\
		break;							\
	case 2:								\
		asm("cmpxchgw %2, "__percpu_arg(1)			\
			    : "=a" (pco_ret__), "+m" (var)		\
			    : "r" (pco_new__), "0" (pco_old__)		\
			    : "memory");				\
		break;							\
	case 4:								\
		asm("cmpxchgl %2, "__percpu_arg(1)			\
			    : "=a" (pco_ret__), "+m" (var)		\
			    : "r" (pco_new__), "0" (pco_old__)		\
			    : "memory");				\
		break;							\
	case 8:								\
		asm("cmpxchgq %2, "__percpu_arg(1)			\
			    : "=a" (pco_ret__), "+m" (var)		\
			    : "r" (pco_new__), "0" (pco_old__)		\
			    : "memory");				\
		break;							\
	default: __bad_percpu_size();					\
	}								\
	pco_ret__;							\
})

/*
 * this_cpu_read() makes gcc load the percpu variable every time it is
 * accessed while this_cpu_read_stable() allows the value to be cached.
 * this_cpu_read_stable() is more efficient and can be used if its value
 * is guaranteed to be valid across cpus.  The current users include
 * get_current() and get_thread_info() both of which are actually
 * per-thread variables implemented as per-cpu variables and thus
 * stable for the duration of the respective task.
 */
#define this_cpu_read_stable(var)	percpu_from_op("mov", var, "p" (&(var)))

#define __this_cpu_read_1(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
#define __this_cpu_read_2(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
#define __this_cpu_read_4(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))

#define __this_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
#define __this_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
#define __this_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
#define __this_cpu_add_1(pcp, val)	percpu_add_op((pcp), val)
#define __this_cpu_add_2(pcp, val)	percpu_add_op((pcp), val)
#define __this_cpu_add_4(pcp, val)	percpu_add_op((pcp), val)
#define __this_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
#define __this_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
#define __this_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
#define __this_cpu_or_1(pcp, val)	percpu_to_op("or", (pcp), val)
#define __this_cpu_or_2(pcp, val)	percpu_to_op("or", (pcp), val)
#define __this_cpu_or_4(pcp, val)	percpu_to_op("or", (pcp), val)
#define __this_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
#define __this_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
#define __this_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
#define __this_cpu_xchg_1(pcp, val)	percpu_xchg_op(pcp, val)
#define __this_cpu_xchg_2(pcp, val)	percpu_xchg_op(pcp, val)
#define __this_cpu_xchg_4(pcp, val)	percpu_xchg_op(pcp, val)

#define this_cpu_read_1(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
#define this_cpu_read_2(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
#define this_cpu_read_4(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
#define this_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
#define this_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
#define this_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
#define this_cpu_add_1(pcp, val)	percpu_add_op((pcp), val)
#define this_cpu_add_2(pcp, val)	percpu_add_op((pcp), val)
#define this_cpu_add_4(pcp, val)	percpu_add_op((pcp), val)
#define this_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
#define this_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
#define this_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
#define this_cpu_or_1(pcp, val)		percpu_to_op("or", (pcp), val)
#define this_cpu_or_2(pcp, val)		percpu_to_op("or", (pcp), val)
#define this_cpu_or_4(pcp, val)		percpu_to_op("or", (pcp), val)
#define this_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
#define this_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
#define this_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
#define this_cpu_xchg_1(pcp, nval)	percpu_xchg_op(pcp, nval)
#define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(pcp, nval)
#define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(pcp, nval)

#define __this_cpu_add_return_1(pcp, val) percpu_add_return_op(pcp, val)
#define __this_cpu_add_return_2(pcp, val) percpu_add_return_op(pcp, val)
#define __this_cpu_add_return_4(pcp, val) percpu_add_return_op(pcp, val)
#define __this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
#define __this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
#define __this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)

#define this_cpu_add_return_1(pcp, val)	percpu_add_return_op(pcp, val)
#define this_cpu_add_return_2(pcp, val)	percpu_add_return_op(pcp, val)
#define this_cpu_add_return_4(pcp, val)	percpu_add_return_op(pcp, val)
#define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
#define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
#define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)

#ifdef CONFIG_X86_CMPXCHG64
#define percpu_cmpxchg8b_double(pcp1, pcp2, o1, o2, n1, n2)		\
({									\
	bool __ret;							\
	typeof(pcp1) __o1 = (o1), __n1 = (n1);				\
	typeof(pcp2) __o2 = (o2), __n2 = (n2);				\
	asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t"	\
		    : "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \
		    :  "b" (__n1), "c" (__n2), "a" (__o1));		\
	__ret;								\
})

#define __this_cpu_cmpxchg_double_4	percpu_cmpxchg8b_double
#define this_cpu_cmpxchg_double_4	percpu_cmpxchg8b_double
#endif /* CONFIG_X86_CMPXCHG64 */

/*
 * Per cpu atomic 64 bit operations are only available under 64 bit.
 * 32 bit must fall back to generic operations.
 */
#ifdef CONFIG_X86_64
#define __this_cpu_read_8(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
#define __this_cpu_write_8(pcp, val)	percpu_to_op("mov", (pcp), val)
#define __this_cpu_add_8(pcp, val)	percpu_add_op((pcp), val)
#define __this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
#define __this_cpu_or_8(pcp, val)	percpu_to_op("or", (pcp), val)
#define __this_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
#define __this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val)
#define __this_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
#define __this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)

#define this_cpu_read_8(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
#define this_cpu_write_8(pcp, val)	percpu_to_op("mov", (pcp), val)
#define this_cpu_add_8(pcp, val)	percpu_add_op((pcp), val)
#define this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
#define this_cpu_or_8(pcp, val)		percpu_to_op("or", (pcp), val)
#define this_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
#define this_cpu_add_return_8(pcp, val)	percpu_add_return_op(pcp, val)
#define this_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
#define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)

/*
 * Pretty complex macro to generate cmpxchg16 instruction.  The instruction
 * is not supported on early AMD64 processors so we must be able to emulate
 * it in software.  The address used in the cmpxchg16 instruction must be
 * aligned to a 16 byte boundary.
 */
#define percpu_cmpxchg16b_double(pcp1, pcp2, o1, o2, n1, n2)		\
({									\
	bool __ret;							\
	typeof(pcp1) __o1 = (o1), __n1 = (n1);				\
	typeof(pcp2) __o2 = (o2), __n2 = (n2);				\
	alternative_io("leaq %P1,%%rsi\n\tcall this_cpu_cmpxchg16b_emu\n\t", \
		       "cmpxchg16b " __percpu_arg(1) "\n\tsetz %0\n\t",	\
		       X86_FEATURE_CX16,				\
		       ASM_OUTPUT2("=a" (__ret), "+m" (pcp1),		\
				   "+m" (pcp2), "+d" (__o2)),		\
		       "b" (__n1), "c" (__n2), "a" (__o1) : "rsi");	\
	__ret;								\
})

#define __this_cpu_cmpxchg_double_8	percpu_cmpxchg16b_double
#define this_cpu_cmpxchg_double_8	percpu_cmpxchg16b_double

#endif

/* This is not atomic against other CPUs -- CPU preemption needs to be off */
#define x86_test_and_clear_bit_percpu(bit, var)				\
({									\
	int old__;							\
	asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0"		\
		     : "=r" (old__), "+m" (var)				\
		     : "dIr" (bit));					\
	old__;								\
})

static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
                        const unsigned long __percpu *addr)
{
	unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;

#ifdef CONFIG_X86_64
	return ((1UL << (nr % BITS_PER_LONG)) & __this_cpu_read_8(*a)) != 0;
#else
	return ((1UL << (nr % BITS_PER_LONG)) & __this_cpu_read_4(*a)) != 0;
#endif
}

static inline int x86_this_cpu_variable_test_bit(int nr,
                        const unsigned long __percpu *addr)
{
	int oldbit;

	asm volatile("bt "__percpu_arg(2)",%1\n\t"
			"sbb %0,%0"
			: "=r" (oldbit)
			: "m" (*(unsigned long *)addr), "Ir" (nr));

	return oldbit;
}

#define x86_this_cpu_test_bit(nr, addr)			\
	(__builtin_constant_p((nr))			\
	 ? x86_this_cpu_constant_test_bit((nr), (addr))	\
	 : x86_this_cpu_variable_test_bit((nr), (addr)))


#include <asm-generic/percpu.h>

/* We can use this directly for local CPU (faster). */
DECLARE_PER_CPU(unsigned long, this_cpu_off);

#endif /* !__ASSEMBLY__ */

#ifdef CONFIG_SMP

/*
 * Define the "EARLY_PER_CPU" macros.  These are used for some per_cpu
 * variables that are initialized and accessed before there are per_cpu
 * areas allocated.
 */

#define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)			\
	DEFINE_PER_CPU(_type, _name) = _initvalue;			\
	__typeof__(_type) _name##_early_map[NR_CPUS] __initdata =	\
				{ [0 ... NR_CPUS-1] = _initvalue };	\
	__typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map

#define DEFINE_EARLY_PER_CPU_READ_MOSTLY(_type, _name, _initvalue)	\
	DEFINE_PER_CPU_READ_MOSTLY(_type, _name) = _initvalue;		\
	__typeof__(_type) _name##_early_map[NR_CPUS] __initdata =	\
				{ [0 ... NR_CPUS-1] = _initvalue };	\
	__typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map

#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
	EXPORT_PER_CPU_SYMBOL(_name)

#define DECLARE_EARLY_PER_CPU(_type, _name)			\
	DECLARE_PER_CPU(_type, _name);				\
	extern __typeof__(_type) *_name##_early_ptr;		\
	extern __typeof__(_type)  _name##_early_map[]

#define DECLARE_EARLY_PER_CPU_READ_MOSTLY(_type, _name)		\
	DECLARE_PER_CPU_READ_MOSTLY(_type, _name);		\
	extern __typeof__(_type) *_name##_early_ptr;		\
	extern __typeof__(_type)  _name##_early_map[]

#define	early_per_cpu_ptr(_name) (_name##_early_ptr)
#define	early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
#define	early_per_cpu(_name, _cpu) 				\
	*(early_per_cpu_ptr(_name) ?				\
		&early_per_cpu_ptr(_name)[_cpu] :		\
		&per_cpu(_name, _cpu))

#else	/* !CONFIG_SMP */
#define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)		\
	DEFINE_PER_CPU(_type, _name) = _initvalue

#define DEFINE_EARLY_PER_CPU_READ_MOSTLY(_type, _name, _initvalue)	\
	DEFINE_PER_CPU_READ_MOSTLY(_type, _name) = _initvalue

#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
	EXPORT_PER_CPU_SYMBOL(_name)

#define DECLARE_EARLY_PER_CPU(_type, _name)			\
	DECLARE_PER_CPU(_type, _name)

#define DECLARE_EARLY_PER_CPU_READ_MOSTLY(_type, _name)		\
	DECLARE_PER_CPU_READ_MOSTLY(_type, _name)

#define	early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
#define	early_per_cpu_ptr(_name) NULL
/* no early_per_cpu_map() */

#endif	/* !CONFIG_SMP */

#endif /* _ASM_X86_PERCPU_H */