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
|
#ifndef __ASM_SYSTEM_H
#define __ASM_SYSTEM_H
#include <linux/kernel.h>
#include <asm/segment.h>
#include <asm/cpufeature.h>
#include <linux/bitops.h> /* for LOCK_PREFIX */
#ifdef __KERNEL__
struct task_struct; /* one of the stranger aspects of C forward declarations.. */
extern struct task_struct * FASTCALL(__switch_to(struct task_struct *prev, struct task_struct *next));
#define switch_to(prev,next,last) do { \
unsigned long esi,edi; \
asm volatile("pushl %%ebp\n\t" \
"movl %%esp,%0\n\t" /* save ESP */ \
"movl %5,%%esp\n\t" /* restore ESP */ \
"movl $1f,%1\n\t" /* save EIP */ \
"pushl %6\n\t" /* restore EIP */ \
"jmp __switch_to\n" \
"1:\t" \
"popl %%ebp\n\t" \
:"=m" (prev->thread.esp),"=m" (prev->thread.eip), \
"=a" (last),"=S" (esi),"=D" (edi) \
:"m" (next->thread.esp),"m" (next->thread.eip), \
"2" (prev), "d" (next)); \
} 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) )
/*
* Load a segment. Fall back on loading the zero
* segment if something goes wrong..
*/
#define loadsegment(seg,value) \
asm volatile("\n" \
"1:\t" \
"mov %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" \
: :"rm" (value))
/*
* Save a segment register away
*/
#define savesegment(seg, value) \
asm volatile("mov %%" #seg ",%0":"=rm" (value))
#define read_cr0() ({ \
unsigned int __dummy; \
__asm__ __volatile__( \
"movl %%cr0,%0\n\t" \
:"=r" (__dummy)); \
__dummy; \
})
#define write_cr0(x) \
__asm__ __volatile__("movl %0,%%cr0": :"r" (x))
#define read_cr2() ({ \
unsigned int __dummy; \
__asm__ __volatile__( \
"movl %%cr2,%0\n\t" \
:"=r" (__dummy)); \
__dummy; \
})
#define write_cr2(x) \
__asm__ __volatile__("movl %0,%%cr2": :"r" (x))
#define read_cr3() ({ \
unsigned int __dummy; \
__asm__ ( \
"movl %%cr3,%0\n\t" \
:"=r" (__dummy)); \
__dummy; \
})
#define write_cr3(x) \
__asm__ __volatile__("movl %0,%%cr3": :"r" (x))
#define read_cr4() ({ \
unsigned int __dummy; \
__asm__( \
"movl %%cr4,%0\n\t" \
:"=r" (__dummy)); \
__dummy; \
})
#define read_cr4_safe() ({ \
unsigned int __dummy; \
/* This could fault if %cr4 does not exist */ \
__asm__("1: movl %%cr4, %0 \n" \
"2: \n" \
".section __ex_table,\"a\" \n" \
".long 1b,2b \n" \
".previous \n" \
: "=r" (__dummy): "0" (0)); \
__dummy; \
})
#define write_cr4(x) \
__asm__ __volatile__("movl %0,%%cr4": :"r" (x))
/*
* Clear and set 'TS' bit respectively
*/
#define clts() __asm__ __volatile__ ("clts")
#define stts() write_cr0(8 | read_cr0())
#endif /* __KERNEL__ */
#define wbinvd() \
__asm__ __volatile__ ("wbinvd": : :"memory")
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))
#ifdef CONFIG_X86_CMPXCHG64
/*
* 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.)
*
* cmpxchg8b must be used with the lock prefix here to allow
* the instruction to be executed atomically, see page 3-102
* of the instruction set reference 24319102.pdf. We need
* the reader side to see the coherent 64bit value.
*/
static inline void __set_64bit (unsigned long long * ptr,
unsigned int low, unsigned int high)
{
__asm__ __volatile__ (
"\n1:\t"
"movl (%0), %%eax\n\t"
"movl 4(%0), %%edx\n\t"
"lock cmpxchg8b (%0)\n\t"
"jnz 1b"
: /* no outputs */
: "D"(ptr),
"b"(low),
"c"(high)
: "ax","dx","memory");
}
static inline void __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)
static inline void __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)) )
#endif
/*
* 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
#define cmpxchg(ptr,o,n)\
((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
(unsigned long)(n),sizeof(*(ptr))))
#endif
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)
: "r"(new), "m"(*__xg(ptr)), "0"(old)
: "memory");
return prev;
case 4:
__asm__ __volatile__(LOCK_PREFIX "cmpxchgl %1,%2"
: "=a"(prev)
: "r"(new), "m"(*__xg(ptr)), "0"(old)
: "memory");
return prev;
}
return old;
}
#ifndef CONFIG_X86_CMPXCHG
/*
* Building a kernel capable running on 80386. It may be necessary to
* simulate the cmpxchg on the 80386 CPU. For that purpose we define
* a function for each of the sizes we support.
*/
extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
unsigned long new, int size)
{
switch (size) {
case 1:
return cmpxchg_386_u8(ptr, old, new);
case 2:
return cmpxchg_386_u16(ptr, old, new);
case 4:
return cmpxchg_386_u32(ptr, old, new);
}
return old;
}
#define cmpxchg(ptr,o,n) \
({ \
__typeof__(*(ptr)) __ret; \
if (likely(boot_cpu_data.x86 > 3)) \
__ret = __cmpxchg((ptr), (unsigned long)(o), \
(unsigned long)(n), sizeof(*(ptr))); \
else \
__ret = cmpxchg_386((ptr), (unsigned long)(o), \
(unsigned long)(n), sizeof(*(ptr))); \
__ret; \
})
#endif
#ifdef CONFIG_X86_CMPXCHG64
static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long long old,
unsigned long long new)
{
unsigned long long prev;
__asm__ __volatile__(LOCK_PREFIX "cmpxchg8b %3"
: "=A"(prev)
: "b"((unsigned long)new),
"c"((unsigned long)(new >> 32)),
"m"(*__xg(ptr)),
"0"(old)
: "memory");
return prev;
}
#define cmpxchg64(ptr,o,n)\
((__typeof__(*(ptr)))__cmpxchg64((ptr),(unsigned long long)(o),\
(unsigned long long)(n)))
#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.
*
* Some non intel clones support out of order store. wmb() ceases to be a
* nop for these.
*/
/*
* Actually only lfence would be needed for mb() because all stores done
* by the kernel should be already ordered. But keep a full barrier for now.
*/
#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
/**
* read_barrier_depends - Flush all pending reads that subsequents reads
* depend on.
*
* No data-dependent reads from memory-like regions are ever reordered
* over this barrier. All reads preceding this primitive are guaranteed
* to access memory (but not necessarily other CPUs' caches) before any
* reads following this primitive that depend on the data return by
* any of the preceding reads. This primitive is much lighter weight than
* rmb() on most CPUs, and is never heavier weight than is
* rmb().
*
* These ordering constraints are respected by both the local CPU
* and the compiler.
*
* Ordering is not guaranteed by anything other than these primitives,
* not even by data dependencies. See the documentation for
* memory_barrier() for examples and URLs to more information.
*
* For example, the following code would force ordering (the initial
* value of "a" is zero, &q
|