summaryrefslogtreecommitdiffstats
path: root/include/asm-i386/system.h
blob: 52e24682e154fe822476eb8b1ea4a1b0998d9c14 (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
#ifndef __ASM_SYSTEM_H
#define __ASM_SYSTEM_H

#include <linux/config.h>
#include <linux/kernel.h>
#include <asm/segment.h>
#include <linux/bitops.h> /* for LOCK_PREFIX */

#ifdef __KERNEL__

struct task_struct;	/* one of the stranger aspects of C forward declarations.. */
extern void FASTCALL(__switch_to(struct task_struct *prev, struct task_struct *next));

#define prepare_to_switch()	do { } while(0)
#define switch_to(prev,next,last) do {					\
	asm volatile("pushl %%esi\n\t"					\
		     "pushl %%edi\n\t"					\
		     "pushl %%ebp\n\t"					\
		     "movl %%esp,%0\n\t"	/* save ESP */		\
		     "movl %3,%%esp\n\t"	/* restore ESP */	\
		     "movl $1f,%1\n\t"		/* save EIP */		\
		     "pushl %4\n\t"		/* restore EIP */	\
		     "jmp __switch_to\n"				\
		     "1:\t"						\
		     "popl %%ebp\n\t"					\
		     "popl %%edi\n\t"					\
		     "popl %%esi\n\t"					\
		     :"=m" (prev->thread.esp),"=m" (prev->thread.eip),	\
		      "=b" (last)					\
		     :"m" (next->thread.esp),"m" (next->thread.eip),	\
		      "a" (prev), "d" (next),				\
		      "b" (prev));					\
} while (0)

#define _set_base(addr,base) do { unsigned long __pr; \
__asm__ __volatile__ ("movw %%dx,%1\n\t" \
	"rorl $16,%%edx\n\t" \
	"movb %%dl,%2\n\t" \
	"movb %%dh,%3" \
	:"=&d" (__pr) \
	:"m" (*((addr)+2)), \
	 "m" (*((addr)+4)), \
	 "m" (*((addr)+7)), \
         "0" (base) \
        ); } while(0)

#define _set_limit(addr,limit) do { unsigned long __lr; \
__asm__ __volatile__ ("movw %%dx,%1\n\t" \
	"rorl $16,%%edx\n\t" \
	"movb %2,%%dh\n\t" \
	"andb $0xf0,%%dh\n\t" \
	"orb %%dh,%%dl\n\t" \
	"movb %%dl,%2" \
	:"=&d" (__lr) \
	:"m" (*(addr)), \
	 "m" (*((addr)+6)), \
	 "0" (limit) \
        ); } while(0)

#define set_base(ldt,base) _set_base( ((char *)&(ldt)) , (base) )
#define set_limit(ldt,limit) _set_limit( ((char *)&(ldt)) , ((limit)-1)>>12 )

static inline unsigned long _get_base(char * addr)
{
	unsigned long __base;
	__asm__("movb %3,%%dh\n\t"
		"movb %2,%%dl\n\t"
		"shll $16,%%edx\n\t"
		"movw %1,%%dx"
		:"=&d" (__base)
		:"m" (*((addr)+2)),
		 "m" (*((addr)+4)),
		 "m" (*((addr)+7)));
	return __base;
}

#define get_base(ldt) _get_base( ((char *)&(ldt)) )

/*
 * Load a segment. Fall back on loading the zero
 * segment if something goes wrong..
 */
#define loadsegment(seg,value)			\
	asm volatile("\n"			\
		"1:\t"				\
		"movl %0,%%" #seg "\n"		\
		"2:\n"				\
		".section .fixup,\"ax\"\n"	\
		"3:\t"				\
		"pushl $0\n\t"			\
		"popl %%" #seg "\n\t"		\
		"jmp 2b\n"			\
		".previous\n"			\
		".section __ex_table,\"a\"\n\t"	\
		".align 4\n\t"			\
		".long 1b,3b\n"			\
		".previous"			\
		: :"m" (*(unsigned int *)&(value)))

/*
 * Clear and set 'TS' bit respectively
 */
#define clts() __asm__ __volatile__ ("clts")
#define read_cr0() ({ \
	unsigned int __dummy; \
	__asm__( \
		"movl %%cr0,%0\n\t" \
		:"=r" (__dummy)); \
	__dummy; \
})
#define write_cr0(x) \
	__asm__("movl %0,%%cr0": :"r" (x));
#define stts() write_cr0(8 | read_cr0())

#endif	/* __KERNEL__ */

static inline unsigned long get_limit(unsigned long segment)
{
	unsigned long __limit;
	__asm__("lsll %1,%0"
		:"=r" (__limit):"r" (segment));
	return __limit+1;
}

#define nop() __asm__ __volatile__ ("nop")

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

#define tas(ptr) (xchg((ptr),1))

struct __xchg_dummy { unsigned long a[100]; };
#define __xg(x) ((struct __xchg_dummy *)(x))


/*
 * The semantics of XCHGCMP8B are a bit strange, this is why
 * there is a loop and the loading of %%eax and %%edx has to
 * be inside. This inlines well in most cases, the cached
 * cost is around ~38 cycles. (in the future we might want
 * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
 * might have an implicit FPU-save as a cost, so it's not
 * clear which path to go.)
 */
extern inline void __set_64bit (unsigned long long * ptr,
		unsigned int low, unsigned int high)
{
__asm__ __volatile__ (
	"1:	movl (%0), %%eax;
		movl 4(%0), %%edx;
		cmpxchg8b (%0);
		jnz 1b"
	::		"D"(ptr),
			"b"(low),
			"c"(high)
	:
			"ax","dx","memory");
}

extern void inline __set_64bit_constant (unsigned long long *ptr,
						 unsigned long long value)
{
	__set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL));
}
#define ll_low(x)	*(((unsigned int*)&(x))+0)
#define ll_high(x)	*(((unsigned int*)&(x))+1)

extern void inline __set_64bit_var (unsigned long long *ptr,
			 unsigned long long value)
{
	__set_64bit(ptr,ll_low(value), ll_high(value));
}

#define set_64bit(ptr,value) \
(__builtin_constant_p(value) ? \
 __set_64bit_constant(ptr, value) : \
 __set_64bit_var(ptr, value) )

#define _set_64bit(ptr,value) \
(__builtin_constant_p(value) ? \
 __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
 __set_64bit(ptr, ll_low(value), ll_high(value)) )

/*
 * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
 * Note 2: xchg has side effect, so that attribute volatile is necessary,
 *	  but generally the primitive is invalid, *ptr is output argument. --ANK
 */
static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
{
	switch (size) {
		case 1:
			__asm__ __volatile__("xchgb %b0,%1"
				:"=q" (x)
				:"m" (*__xg(ptr)), "0" (x)
				:"memory");
			break;
		case 2:
			__asm__ __volatile__("xchgw %w0,%1"
				:"=r" (x)
				:"m" (*__xg(ptr)), "0" (x)
				:"memory");
			break;
		case 4:
			__asm__ __volatile__("xchgl %0,%1"
				:"=r" (x)
				:"m" (*__xg(ptr)), "0" (x)
				:"memory");
			break;
	}
	return x;
}

/*
 * Atomic compare and exchange.  Compare OLD with MEM, if identical,
 * store NEW in MEM.  Return the initial value in MEM.  Success is
 * indicated by comparing RETURN with OLD.
 */

#ifdef CONFIG_X86_CMPXCHG
#define __HAVE_ARCH_CMPXCHG 1

static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
				      unsigned long new, int size)
{
	unsigned long prev;
	switch (size) {
	case 1:
		__asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2"
				     : "=a"(prev)
				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 2:
		__asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2"
				     : "=a"(prev)
				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 4:
		__asm__ __volatile__(LOCK_PREFIX "cmpxchgl %1,%2"
				     : "=a"(prev)
				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	}
	return old;
}

#define cmpxchg(ptr,o,n)\
	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
					(unsigned long)(n),sizeof(*(ptr))))
    
#else
/* Compiling for a 386 proper.	Is it worth implementing via cli/sti?  */
#endif

/*
 * Force strict CPU ordering.
 * And yes, this is required on UP too when we're talking
 * to devices.
 *
 * For now, "wmb()" doesn't actually do anything, as all
 * Intel CPU's follow what Intel calls a *Processor Order*,
 * in which all writes are seen in the program order even
 * outside the CPU.
 *
 * I expect future Intel CPU's to have a weaker ordering,
 * but I'd also expect them to finally get their act together
 * and add some real memory barriers if so.
 */
#define mb() 	__asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory")
#define rmb()	mb()
#define wmb()	__asm__ __volatile__ ("": : :"memory")

#ifdef CONFIG_SMP
#define smp_mb()	mb()
#define smp_rmb()	rmb()
#define smp_wmb()	wmb()
#else
#define smp_mb()	barrier()
#define smp_rmb()	barrier()
#define smp_wmb()	barrier()
#endif

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

/* interrupt control.. */
#define __save_flags(x)		__asm__ __volatile__("pushfl ; popl %0":"=g" (x): /* no input */)
#define __restore_flags(x) 	__asm__ __volatile__("pushl %0 ; popfl": /* no output */ :"g" (x):"memory")
#define __cli() 		__asm__ __volatile__("cli": : :"memory")
#define __sti()			__asm__ __volatile__("sti": : :"memory")
/* used in the idle loop; sti takes one instruction cycle to complete */
#define safe_halt()		__asm__ __volatile__("sti; hlt": : :"memory")

/* For spinlocks etc */
#define local_irq_save(x)	__asm__ __volatile__("pushfl ; popl %0 ; cli":"=g" (x): /* no input */ :"memory")
#define local_irq_restore(x)	__restore_flags(x)
#define local_irq_disable()	__cli()
#define local_irq_enable()	__sti()

#ifdef CONFIG_SMP

extern void __global_cli(void);
extern void __global_sti(void);
extern unsigned long __global_save_flags(void);
extern void __global_restore_flags(unsigned long);
#define cli() __global_cli()
#define sti() __global_sti()
#define save_flags(x) ((x)=__global_save_flags())
#define restore_flags(x) __global_restore_flags(x)

#else

#define cli() __cli()
#define sti() __sti()
#define save_flags(x) __save_flags(x)
#define restore_flags(x) __restore_flags(x)

#endif

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

#endif