summaryrefslogtreecommitdiff
path: root/arch/sh/include/asm/system.h
blob: a62c42261d7af4bb562d3dbf56f150be5ea29250 (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
#ifndef __ASM_SH_SYSTEM_H
#define __ASM_SH_SYSTEM_H

/*
 * Copyright (C) 1999, 2000  Niibe Yutaka  &  Kaz Kojima
 * Copyright (C) 2002 Paul Mundt
 *
 * from linux kernel code.
 */

#include <linux/irqflags.h>
#include <asm/types.h>

/*
 *	switch_to() should switch tasks to task nr n, first
 */

#define switch_to(prev, next, last) do {				\
 struct task_struct *__last;						\
 register unsigned long *__ts1 __asm__ ("r1") = &prev->thread.sp;	\
 register unsigned long *__ts2 __asm__ ("r2") = &prev->thread.pc;	\
 register unsigned long *__ts4 __asm__ ("r4") = (unsigned long *)prev;	\
 register unsigned long *__ts5 __asm__ ("r5") = (unsigned long *)next;	\
 register unsigned long *__ts6 __asm__ ("r6") = &next->thread.sp;	\
 register unsigned long __ts7 __asm__ ("r7") = next->thread.pc;		\
 __asm__ __volatile__ (".balign 4\n\t"					\
		       "stc.l	gbr, @-r15\n\t"				\
		       "sts.l	pr, @-r15\n\t"				\
		       "mov.l	r8, @-r15\n\t"				\
		       "mov.l	r9, @-r15\n\t"				\
		       "mov.l	r10, @-r15\n\t"				\
		       "mov.l	r11, @-r15\n\t"				\
		       "mov.l	r12, @-r15\n\t"				\
		       "mov.l	r13, @-r15\n\t"				\
		       "mov.l	r14, @-r15\n\t"				\
		       "mov.l	r15, @r1	! save SP\n\t"		\
		       "mov.l	@r6, r15	! change to new stack\n\t" \
		       "mova	1f, %0\n\t"				\
		       "mov.l	%0, @r2		! save PC\n\t"		\
		       "mov.l	2f, %0\n\t"				\
		       "jmp	@%0		! call __switch_to\n\t" \
		       " lds	r7, pr		!  with return to new PC\n\t" \
		       ".balign	4\n"					\
		       "2:\n\t"						\
		       ".long	__switch_to\n"				\
		       "1:\n\t"						\
		       "mov.l	@r15+, r14\n\t"				\
		       "mov.l	@r15+, r13\n\t"				\
		       "mov.l	@r15+, r12\n\t"				\
		       "mov.l	@r15+, r11\n\t"				\
		       "mov.l	@r15+, r10\n\t"				\
		       "mov.l	@r15+, r9\n\t"				\
		       "mov.l	@r15+, r8\n\t"				\
		       "lds.l	@r15+, pr\n\t"				\
		       "ldc.l	@r15+, gbr\n\t"				\
		       : "=z" (__last)					\
		       : "r" (__ts1), "r" (__ts2), "r" (__ts4),		\
			 "r" (__ts5), "r" (__ts6), "r" (__ts7)		\
		       : "r3", "t");					\
	last = __last;							\
} while (0)

/*
 * On SMP systems, when the scheduler does migration-cost autodetection,
 * it needs a way to flush as much of the CPU's caches as possible.
 *
 * TODO: fill this in!
 */
static inline void sched_cacheflush(void)
{
}

#ifdef CONFIG_CPU_SH4A
#define __icbi()			\
{					\
	unsigned long __addr;		\
	__addr = 0xa8000000;		\
	__asm__ __volatile__(		\
		"icbi   %0\n\t"		\
		: /* no output */	\
		: "m" (__m(__addr)));	\
}
#endif

static inline unsigned long tas(volatile int *m)
{
	unsigned long retval;

	__asm__ __volatile__ ("tas.b	@%1\n\t"
			      "movt	%0"
			      : "=r" (retval): "r" (m): "t", "memory");
	return retval;
}

/*
 * A brief note on ctrl_barrier(), the control register write barrier.
 *
 * Legacy SH cores typically require a sequence of 8 nops after
 * modification of a control register in order for the changes to take
 * effect. On newer cores (like the sh4a and sh5) this is accomplished
 * with icbi.
 *
 * Also note that on sh4a in the icbi case we can forego a synco for the
 * write barrier, as it's not necessary for control registers.
 *
 * Historically we have only done this type of barrier for the MMUCR, but
 * it's also necessary for the CCR, so we make it generic here instead.
 */
#ifdef CONFIG_CPU_SH4A
#define mb()		__asm__ __volatile__ ("synco": : :"memory")
#define rmb()		mb()
#define wmb()		__asm__ __volatile__ ("synco": : :"memory")
#define ctrl_barrier()	__icbi()
#define read_barrier_depends()	do { } while(0)
#else
#define mb()		__asm__ __volatile__ ("": : :"memory")
#define rmb()		mb()
#define wmb()		__asm__ __volatile__ ("": : :"memory")
#define ctrl_barrier()	__asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
#define read_barrier_depends()	do { } while(0)
#endif

#ifdef CONFIG_SMP
#define smp_mb()	mb()
#define smp_rmb()	rmb()
#define smp_wmb()	wmb()
#define smp_read_barrier_depends()	read_barrier_depends()
#else
#define smp_mb()	barrier()
#define smp_rmb()	barrier()
#define smp_wmb()	barrier()
#define smp_read_barrier_depends()	do { } while(0)
#endif

#define set_mb(var, value) do { xchg(&var, value); } while (0)

/*
 * Jump to P2 area.
 * When handling TLB or caches, we need to do it from P2 area.
 */
#define jump_to_P2()			\
do {					\
	unsigned long __dummy;		\
	__asm__ __volatile__(		\
		"mov.l	1f, %0\n\t"	\
		"or	%1, %0\n\t"	\
		"jmp	@%0\n\t"	\
		" nop\n\t"		\
		".balign 4\n"		\
		"1:	.long 2f\n"	\
		"2:"			\
		: "=&r" (__dummy)	\
		: "r" (0x20000000));	\
} while (0)

/*
 * Back to P1 area.
 */
#define back_to_P1()					\
do {							\
	unsigned long __dummy;				\
	ctrl_barrier();					\
	__asm__ __volatile__(				\
		"mov.l	1f, %0\n\t"			\
		"jmp	@%0\n\t"			\
		" nop\n\t"				\
		".balign 4\n"				\
		"1:	.long 2f\n"			\
		"2:"					\
		: "=&r" (__dummy));			\
} while (0)

static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
{
	unsigned long flags, retval;

	local_irq_save(flags);
	retval = *m;
	*m = val;
	local_irq_restore(flags);
	return retval;
}

static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
{
	unsigned long flags, retval;

	local_irq_save(flags);
	retval = *m;
	*m = val & 0xff;
	local_irq_restore(flags);
	return retval;
}

extern void __xchg_called_with_bad_pointer(void);

#define __xchg(ptr, x, size)				\
({							\
	unsigned long __xchg__res;			\
	volatile void *__xchg_ptr = (ptr);		\
	switch (size) {					\
	case 4:						\
		__xchg__res = xchg_u32(__xchg_ptr, x);	\
		break;					\
	case 1:						\
		__xchg__res = xchg_u8(__xchg_ptr, x);	\
		break;					\
	default:					\
		__xchg_called_with_bad_pointer();	\
		__xchg__res = x;			\
		break;					\
	}						\
							\
	__xchg__res;					\
})

#define xchg(ptr,x)	\
	((__typeof__(*(ptr)))__xchg((ptr),(unsigned long)(x), sizeof(*(ptr))))

static inline unsigned long __cmpxchg_u32(volatile int * m, unsigned long old,
	unsigned long new)
{
	__u32 retval;
	unsigned long flags;

	local_irq_save(flags);
	retval = *m;
	if (retval == old)
		*m = new;
	local_irq_restore(flags);       /* implies memory barrier  */
	return retval;
}

/* This function doesn't exist, so you'll get a linker error
 * if something tries to do an invalid cmpxchg(). */
extern void __cmpxchg_called_with_bad_pointer(void);

#define __HAVE_ARCH_CMPXCHG 1

static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
		unsigned long new, int size)
{
	switch (size) {
	case 4:
		return __cmpxchg_u32(ptr, old, new);
	}
	__cmpxchg_called_with_bad_pointer();
	return old;
}

#define cmpxchg(ptr,o,n)						 \
  ({									 \
     __typeof__(*(ptr)) _o_ = (o);					 \
     __typeof__(*(ptr)) _n_ = (n);					 \
     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
				    (unsigned long)_n_, sizeof(*(ptr))); \
  })

extern void *set_exception_table_vec(unsigned int vec, void *handler);

static inline void *set_exception_table_evt(unsigned int evt, void *handler)
{
	return set_exception_table_vec(evt >> 5, handler);
}

/* XXX
 * disable hlt during certain critical i/o operations
 */
#define HAVE_DISABLE_HLT
void disable_hlt(void);
void enable_hlt(void);

#define arch_align_stack(x) (x)

#endif