aboutsummaryrefslogtreecommitdiffstats
path: root/arch/ia64/include/asm/bitops.h
blob: e2ca800373351d26b1042394275ebe10f6c8d23e (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
#ifndef _ASM_IA64_BITOPS_H
#define _ASM_IA64_BITOPS_H

/*
 * Copyright (C) 1998-2003 Hewlett-Packard Co
 *	David Mosberger-Tang <davidm@hpl.hp.com>
 *
 * 02/06/02 find_next_bit() and find_first_bit() added from Erich Focht's ia64
 * O(1) scheduler patch
 */

#ifndef _LINUX_BITOPS_H
#error only <linux/bitops.h> can be included directly
#endif

#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/intrinsics.h>

/**
 * set_bit - Atomically set a bit in memory
 * @nr: the bit to set
 * @addr: the address to start counting from
 *
 * This function is atomic and may not be reordered.  See __set_bit()
 * if you do not require the atomic guarantees.
 * Note that @nr may be almost arbitrarily large; this function is not
 * restricted to acting on a single-word quantity.
 *
 * The address must be (at least) "long" aligned.
 * Note that there are driver (e.g., eepro100) which use these operations to
 * operate on hw-defined data-structures, so we can't easily change these
 * operations to force a bigger alignment.
 *
 * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
 */
static __inline__ void
set_bit (int nr, volatile void *addr)
{
	__u32 bit, old, new;
	volatile __u32 *m;
	CMPXCHG_BUGCHECK_DECL

	m = (volatile __u32 *) addr + (nr >> 5);
	bit = 1 << (nr & 31);
	do {
		CMPXCHG_BUGCHECK(m);
		old = *m;
		new = old | bit;
	} while (cmpxchg_acq(m, old, new) != old);
}

/**
 * __set_bit - Set a bit in memory
 * @nr: the bit to set
 * @addr: the address to start counting from
 *
 * Unlike set_bit(), this function is non-atomic and may be reordered.
 * If it's called on the same region of memory simultaneously, the effect
 * may be that only one operation succeeds.
 */
static __inline__ void
__set_bit (int nr, volatile void *addr)
{
	*((__u32 *) addr + (nr >> 5)) |= (1 << (nr & 31));
}

/*
 * clear_bit() has "acquire" semantics.
 */
#define smp_mb__before_clear_bit()	smp_mb()
#define smp_mb__after_clear_bit()	do { /* skip */; } while (0)

/**
 * clear_bit - Clears a bit in memory
 * @nr: Bit to clear
 * @addr: Address to start counting from
 *
 * clear_bit() is atomic and may not be reordered.  However, it does
 * not contain a memory barrier, so if it is used for locking purposes,
 * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
 * in order to ensure changes are visible on other processors.
 */
static __inline__ void
clear_bit (int nr, volatile void *addr)
{
	__u32 mask, old, new;
	volatile __u32 *m;
	CMPXCHG_BUGCHECK_DECL

	m = (volatile __u32 *) addr + (nr >> 5);
	mask = ~(1 << (nr & 31));
	do {
		CMPXCHG_BUGCHECK(m);
		old = *m;
		new = old & mask;
	} while (cmpxchg_acq(m, old, new) != old);
}

/**
 * clear_bit_unlock - Clears a bit in memory with release
 * @nr: Bit to clear
 * @addr: Address to start counting from
 *
 * clear_bit_unlock() is atomic and may not be reordered.  It does
 * contain a memory barrier suitable for unlock type operations.
 */
static __inline__ void
clear_bit_unlock (int nr, volatile void *addr)
{
	__u32 mask, old, new;
	volatile __u32 *m;
	CMPXCHG_BUGCHECK_DECL

	m = (volatile __u32 *) addr + (nr >> 5);
	mask = ~(1 << (nr & 31));
	do {
		CMPXCHG_BUGCHECK(m);
		old = *m;
		new = old & mask;
	} while (cmpxchg_rel(m, old, new) != old);
}

/**
 * __clear_bit_unlock - Non-atomically clears a bit in memory with release
 * @nr: Bit to clear
 * @addr: Address to start counting from
 *
 * Similarly to clear_bit_unlock, the implementation uses a store
 * with release semantics. See also __raw_spin_unlock().
 */
static __inline__ void
__clear_bit_unlock(int nr, void *addr)
{
	__u32 * const m = (__u32 *) addr + (nr >> 5);
	__u32 const new = *m & ~(1 << (nr & 31));

	ia64_st4_rel_nta(m, new);
}

/**
 * __clear_bit - Clears a bit in memory (non-atomic version)
 * @nr: the bit to clear
 * @addr: the address to start counting from
 *
 * Unlike clear_bit(), this function is non-atomic and may be reordered.
 * If it's called on the same region of memory simultaneously, the effect
 * may be that only one operation succeeds.
 */
static __inline__ void
__clear_bit (int nr, volatile void *addr)
{
	*((__u32 *) addr + (nr >> 5)) &= ~(1 << (nr & 31));
}

/**
 * change_bit - Toggle a bit in memory
 * @nr: Bit to toggle
 * @addr: Address to start counting from
 *
 * change_bit() is atomic and may not be reordered.
 * Note that @nr may be almost arbitrarily large; this function is not
 * restricted to acting on a single-word quantity.
 */
static __inline__ void
change_bit (int nr, volatile void *addr)
{
	__u32 bit, old, new;
	volatile __u32 *m;
	CMPXCHG_BUGCHECK_DECL

	m = (volatile __u32 *) addr + (nr >> 5);
	bit = (1 << (nr & 31));
	do {
		CMPXCHG_BUGCHECK(m);
		old = *m;
		new = old ^ bit;
	} while (cmpxchg_acq(m, old, new) != old);
}

/**
 * __change_bit - Toggle a bit in memory
 * @nr: the bit to toggle
 * @addr: the address to start counting from
 *
 * Unlike change_bit(), this function is non-atomic and may be reordered.
 * If it's called on the same region of memory simultaneously, the effect
 * may be that only one operation succeeds.
 */
static __inline__ void
__change_bit (int nr, volatile void *addr)
{
	*((__u32 *) addr + (nr >> 5)) ^= (1 << (nr & 31));
}

/**
 * test_and_set_bit - Set a bit and return its old value
 * @nr: Bit to set
 * @addr: Address to count from
 *
 * This operation is atomic and cannot be reordered.  
 * It also implies the acquisition side of the memory barrier.
 */
static __inline__ int
test_and_set_bit (int nr, volatile void *addr)
{
	__u32 bit, old, new;
	volatile __u32 *m;
	CMPXCHG_BUGCHECK_DECL

	m = (volatile __u32 *) addr + (nr >> 5);
	bit = 1 << (nr & 31);
	do {
		CMPXCHG_BUGCHECK(m);
		old = *m;
		new = old | bit;
	} while (cmpxchg_acq(m, old, new) != old);
	return (old & bit) != 0;
}

/**
 * test_and_set_bit_lock - Set a bit and return its old value for lock
 * @nr: Bit to set
 * @addr: Address to count from
 *
 * This is the same as test_and_set_bit on ia64
 */
#define test_and_set_bit_lock test_and_set_bit

/**
 * __test_and_set_bit - Set a bit and return its old value
 * @nr: Bit to set
 * @addr: Address to count from
 *
 * This operation is non-atomic and can be reordered.  
 * If two examples of this operation race, one can appear to succeed
 * but actually fail.  You must protect multiple accesses with a lock.
 */
static __inline__ int
__test_and_set_bit (int nr, volatile void *addr)
{
	__u32 *p = (__u32 *) addr + (nr >> 5);
	__u32 m = 1 << (nr & 31);
	int oldbitset = (*p & m) != 0;

	*p |= m;
	return oldbitset;
}

/**
 * test_and_clear_bit - Clear a bit and return its old value
 * @nr: Bit to clear
 * @addr: Address to count from
 *
 * This operation is atomic and cannot be reordered.  
 * It also implies the acquisition side of the memory barrier.
 */
static __inline__ int
test_and_clear_bit (int nr, volatile void *addr)
{
	__u32 mask, old, new;
	volatile __u32 *m;
	CMPXCHG_BUGCHECK_DECL

	m = (volatile __u32 *) addr + (nr >> 5);
	mask = ~(1 << (nr & 31));
	do {
		CMPXCHG_BUGCHECK(m);
		old = *m;
		new = old & mask;
	} while (cmpxchg_acq(m, old, new) != old);
	return (old & ~mask) != 0;
}

/**
 * __test_and_clear_bit - Clear a bit and return its old value
 * @nr: Bit to clear
 * @addr: Address to count from
 *
 * This operation is non-atomic and can be reordered.  
 * If two examples of this operation race, one can appear to succeed
 * but actually fail.  You must protect multiple accesses with a lock.
 */
static __inline__ int
__test_and_clear_bit(int nr, volatile void * addr)
{
	__u32 *p = (__u32 *) addr + (nr >> 5);
	__u32 m = 1 << (nr & 31);
	int oldbitset = *p & m;

	*p &= ~m;
	return oldbitset;
}

/**
 * test_and_change_bit - Change a bit and return its old value
 * @nr: Bit to change
 * @addr: Address to count from
 *
 * This operation is atomic and cannot be reordered.  
 * It also implies the acquisition side of the memory barrier.
 */
static __inline__ int
test_and_change_bit (int nr, volatile void *addr)
{
	__u32 bit, old, new;
	volatile __u32 *m;
	CMPXCHG_BUGCHECK_DECL

	m = (volatile __u32 *) addr + (nr >> 5);
	bit = (1 << (nr & 31));
	do {
		CMPXCHG_BUGCHECK(m);
		old = *m;
		new = old ^ bit;
	} while (cmpxchg_acq(m, old, new) != old);
	return (old & bit) != 0;
}

/**
 * __test_and_change_bit - Change a bit and return its old value
 * @nr: Bit to change
 * @addr: Address to count from
 *
 * This operation is non-atomic and can be reordered.
 */
static __inline__ int
__test_and_change_bit (int nr, void *addr)
{
	__u32 old, bit = (1 << (nr & 31));
	__u32 *m = (__u32 *) addr + (nr >> 5);

	old = *m;
	*m = old ^ bit;
	return (old & bit) != 0;
}

static __inline__ int
test_bit (int nr, const volatile void *addr)
{
	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
}

/**
 * ffz - find the first zero bit in a long word
 * @x: The long word to find the bit in
 *
 * Returns the bit-number (0..63) of the first (least significant) zero bit.
 * Undefined if no zero exists, so code should check against ~0UL first...
 */
static inline unsigned long
ffz (unsigned long x)
{
	unsigned long result;

	result = ia64_popcnt(x & (~x - 1));
	return result;
}

/**
 * __ffs - find first bit in word.
 * @x: The word to search
 *
 * Undefined if no bit exists, so code should check against 0 first.
 */
static __inline__ unsigned long
__ffs (unsigned long x)
{
	unsigned long result;

	result = ia64_popcnt((x-1) & ~x);
	return result;
}

#ifdef __KERNEL__

/*
 * Return bit number of last (most-significant) bit set.  Undefined
 * for x==0.  Bits are numbered from 0..63 (e.g., ia64_fls(9) == 3).
 */
static inline unsigned long
ia64_fls (unsigned long x)
{
	long double d = x;
	long exp;

	exp = ia64_getf_exp(d);
	return exp - 0xffff;
}

/*
 * Find the last (most significant) bit set.  Returns 0 for x==0 and
 * bits are numbered from 1..32 (e.g., fls(9) == 4).
 */
static inline int
fls (int t)
{
	unsigned long x = t & 0xffffffffu;

	if (!x)
		return 0;
	x |= x >> 1;
	x |= x >> 2;
	x |= x >> 4;
	x |= x >> 8;
	x |= x >> 16;
	return ia64_popcnt(x);
}

/*
 * Find the last (most significant) bit set.  Undefined for x==0.
 * Bits are numbered from 0..63 (e.g., __fls(9) == 3).
 */
static inline unsigned long
__fls (unsigned long x)
{
	x |= x >> 1;
	x |= x >> 2;
	x |= x >> 4;
	x |= x >> 8;
	x |= x >> 16;
	x |= x >> 32;
	return ia64_popcnt(x) - 1;
}

#include <asm-generic/bitops/fls64.h>

/*
 * ffs: find first bit set. This is defined the same way as the libc and
 * compiler builtin ffs routines, therefore differs in spirit from the above
 * ffz (man ffs): it operates on "int" values only and the result value is the
 * bit number + 1.  ffs(0) is defined to return zero.
 */
#define ffs(x)	__builtin_ffs(x)

/*
 * hweightN: returns the hamming weight (i.e. the number
 * of bits set) of a N-bit word
 */
static __inline__ unsigned long
hweight64 (unsigned long x)
{
	unsigned long result;
	result = ia64_popcnt(x);
	return result;
}

#define hweight32(x)	(unsigned int) hweight64((x) & 0xfffffffful)
#define hweight16(x)	(unsigned int) hweight64((x) & 0xfffful)
#define hweight8(x)	(unsigned int) hweight64((x) & 0xfful)

#endif /* __KERNEL__ */

#include <asm-generic/bitops/find.h>

#ifdef __KERNEL__

#include <asm-generic/bitops/ext2-non-atomic.h>

#define ext2_set_bit_atomic(l,n,a)	test_and_set_bit(n,a)
#define ext2_clear_bit_atomic(l,n,a)	test_and_clear_bit(n,a)

#include <asm-generic/bitops/minix.h>
#include <asm-generic/bitops/sched.h>

#endif /* __KERNEL__ */

#endif /* _ASM_IA64_BITOPS_H */