summaryrefslogtreecommitdiff
path: root/arch/hexagon/include/asm/bitops.h
blob: da500471ac73ccb0a6569992c4f189d1bce5f2f4 (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Bit operations for the Hexagon architecture
 *
 * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
 */

#ifndef _ASM_BITOPS_H
#define _ASM_BITOPS_H

#include <linux/compiler.h>
#include <asm/byteorder.h>
#include <asm/atomic.h>
#include <asm/barrier.h>

#ifdef __KERNEL__

/*
 * The offset calculations for these are based on BITS_PER_LONG == 32
 * (i.e. I get to shift by #5-2 (32 bits per long, 4 bytes per access),
 * mask by 0x0000001F)
 *
 * Typically, R10 is clobbered for address, R11 bit nr, and R12 is temp
 */

/**
 * test_and_clear_bit - clear a bit and return its old value
 * @nr:  bit number to clear
 * @addr:  pointer to memory
 */
static inline int test_and_clear_bit(int nr, volatile void *addr)
{
	int oldval;

	__asm__ __volatile__ (
	"	{R10 = %1; R11 = asr(%2,#5); }\n"
	"	{R10 += asl(R11,#2); R11 = and(%2,#0x1f)}\n"
	"1:	R12 = memw_locked(R10);\n"
	"	{ P0 = tstbit(R12,R11); R12 = clrbit(R12,R11); }\n"
	"	memw_locked(R10,P1) = R12;\n"
	"	{if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
	: "=&r" (oldval)
	: "r" (addr), "r" (nr)
	: "r10", "r11", "r12", "p0", "p1", "memory"
	);

	return oldval;
}

/**
 * test_and_set_bit - set a bit and return its old value
 * @nr:  bit number to set
 * @addr:  pointer to memory
 */
static inline int test_and_set_bit(int nr, volatile void *addr)
{
	int oldval;

	__asm__ __volatile__ (
	"	{R10 = %1; R11 = asr(%2,#5); }\n"
	"	{R10 += asl(R11,#2); R11 = and(%2,#0x1f)}\n"
	"1:	R12 = memw_locked(R10);\n"
	"	{ P0 = tstbit(R12,R11); R12 = setbit(R12,R11); }\n"
	"	memw_locked(R10,P1) = R12;\n"
	"	{if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
	: "=&r" (oldval)
	: "r" (addr), "r" (nr)
	: "r10", "r11", "r12", "p0", "p1", "memory"
	);


	return oldval;

}

/**
 * test_and_change_bit - toggle a bit and return its old value
 * @nr:  bit number to set
 * @addr:  pointer to memory
 */
static inline int test_and_change_bit(int nr, volatile void *addr)
{
	int oldval;

	__asm__ __volatile__ (
	"	{R10 = %1; R11 = asr(%2,#5); }\n"
	"	{R10 += asl(R11,#2); R11 = and(%2,#0x1f)}\n"
	"1:	R12 = memw_locked(R10);\n"
	"	{ P0 = tstbit(R12,R11); R12 = togglebit(R12,R11); }\n"
	"	memw_locked(R10,P1) = R12;\n"
	"	{if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
	: "=&r" (oldval)
	: "r" (addr), "r" (nr)
	: "r10", "r11", "r12", "p0", "p1", "memory"
	);

	return oldval;

}

/*
 * Atomic, but doesn't care about the return value.
 * Rewrite later to save a cycle or two.
 */

static inline void clear_bit(int nr, volatile void *addr)
{
	test_and_clear_bit(nr, addr);
}

static inline void set_bit(int nr, volatile void *addr)
{
	test_and_set_bit(nr, addr);
}

static inline void change_bit(int nr, volatile void *addr)
{
	test_and_change_bit(nr, addr);
}


/*
 * These are allowed to be non-atomic.  In fact the generic flavors are
 * in non-atomic.h.  Would it be better to use intrinsics for this?
 *
 * OK, writes in our architecture do not invalidate LL/SC, so this has to
 * be atomic, particularly for things like slab_lock and slab_unlock.
 *
 */
static __always_inline void
arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
{
	test_and_clear_bit(nr, addr);
}

static __always_inline void
arch___set_bit(unsigned long nr, volatile unsigned long *addr)
{
	test_and_set_bit(nr, addr);
}

static __always_inline void
arch___change_bit(unsigned long nr, volatile unsigned long *addr)
{
	test_and_change_bit(nr, addr);
}

/*  Apparently, at least some of these are allowed to be non-atomic  */
static __always_inline bool
arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
{
	return test_and_clear_bit(nr, addr);
}

static __always_inline bool
arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
{
	return test_and_set_bit(nr, addr);
}

static __always_inline bool
arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
{
	return test_and_change_bit(nr, addr);
}

static __always_inline bool
arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
{
	int retval;

	asm volatile(
	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
	: "=&r" (retval)
	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
	: "p0"
	);

	return retval;
}

/*
 * ffz - find first zero in word.
 * @word: The word to search
 *
 * Undefined if no zero exists, so code should check against ~0UL first.
 */
static inline long ffz(int x)
{
	int r;

	asm("%0 = ct1(%1);\n"
		: "=&r" (r)
		: "r" (x));
	return r;
}

/*
 * fls - find last (most-significant) bit set
 * @x: the word to search
 *
 * This is defined the same way as ffs.
 * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
 */
static inline int fls(unsigned int x)
{
	int r;

	asm("{ %0 = cl0(%1);}\n"
		"%0 = sub(#32,%0);\n"
		: "=&r" (r)
		: "r" (x)
		: "p0");

	return r;
}

/*
 * ffs - find first bit set
 * @x: the word to search
 *
 * This is defined the same way as
 * the libc and compiler builtin ffs routines, therefore
 * differs in spirit from the above ffz (man ffs).
 */
static inline int ffs(int x)
{
	int r;

	asm("{ P0 = cmp.eq(%1,#0); %0 = ct0(%1);}\n"
		"{ if (P0) %0 = #0; if (!P0) %0 = add(%0,#1);}\n"
		: "=&r" (r)
		: "r" (x)
		: "p0");

	return r;
}

/*
 * __ffs - find first bit in word.
 * @word: The word to search
 *
 * Undefined if no bit exists, so code should check against 0 first.
 *
 * bits_per_long assumed to be 32
 * numbering starts at 0 I think (instead of 1 like ffs)
 */
static inline unsigned long __ffs(unsigned long word)
{
	int num;

	asm("%0 = ct0(%1);\n"
		: "=&r" (num)
		: "r" (word));

	return num;
}

/*
 * __fls - find last (most-significant) set bit in a long word
 * @word: the word to search
 *
 * Undefined if no set bit exists, so code should check against 0 first.
 * bits_per_long assumed to be 32
 */
static inline unsigned long __fls(unsigned long word)
{
	int num;

	asm("%0 = cl0(%1);\n"
		"%0 = sub(#31,%0);\n"
		: "=&r" (num)
		: "r" (word));

	return num;
}

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

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

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

#endif /* __KERNEL__ */
#endif