summaryrefslogtreecommitdiffstats
path: root/arch/sparc/include/asm/system_64.h
blob: 8759f2a1b837c3f4c655cf48d10b91475f54da12 (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
#ifndef __SPARC64_SYSTEM_H
#define __SPARC64_SYSTEM_H

#include <asm/ptrace.h>
#include <asm/processor.h>
#include <asm/visasm.h>

#ifndef __ASSEMBLY__

#include <linux/irqflags.h>
#include <asm-generic/cmpxchg-local.h>

/*
 * Sparc (general) CPU types
 */
enum sparc_cpu {
  sun4        = 0x00,
  sun4c       = 0x01,
  sun4m       = 0x02,
  sun4d       = 0x03,
  sun4e       = 0x04,
  sun4u       = 0x05, /* V8 ploos ploos */
  sun_unknown = 0x06,
  ap1000      = 0x07, /* almost a sun4m */
};

#define sparc_cpu_model sun4u

/* This cannot ever be a sun4c :) That's just history. */
#define ARCH_SUN4C 0

extern char reboot_command[];

/* These are here in an effort to more fully work around Spitfire Errata
 * #51.  Essentially, if a memory barrier occurs soon after a mispredicted
 * branch, the chip can stop executing instructions until a trap occurs.
 * Therefore, if interrupts are disabled, the chip can hang forever.
 *
 * It used to be believed that the memory barrier had to be right in the
 * delay slot, but a case has been traced recently wherein the memory barrier
 * was one instruction after the branch delay slot and the chip still hung.
 * The offending sequence was the following in sym_wakeup_done() of the
 * sym53c8xx_2 driver:
 *
 *	call	sym_ccb_from_dsa, 0
 *	 movge	%icc, 0, %l0
 *	brz,pn	%o0, .LL1303
 *	 mov	%o0, %l2
 *	membar	#LoadLoad
 *
 * The branch has to be mispredicted for the bug to occur.  Therefore, we put
 * the memory barrier explicitly into a "branch always, predicted taken"
 * delay slot to avoid the problem case.
 */
#define membar_safe(type) \
do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
			     " membar	" type "\n" \
			     "1:\n" \
			     : : : "memory"); \
} while (0)

#define mb()	\
	membar_safe("#LoadLoad | #LoadStore | #StoreStore | #StoreLoad")
#define rmb()	\
	membar_safe("#LoadLoad")
#define wmb()	\
	membar_safe("#StoreStore")
#define membar_storeload() \
	membar_safe("#StoreLoad")
#define membar_storeload_storestore() \
	membar_safe("#StoreLoad | #StoreStore")
#define membar_storeload_loadload() \
	membar_safe("#StoreLoad | #LoadLoad")
#define membar_storestore_loadstore() \
	membar_safe("#StoreStore | #LoadStore")

#endif

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

#define read_barrier_depends()		do { } while(0)
#define set_mb(__var, __value) \
	do { __var = __value; membar_storeload_storestore(); } while(0)

#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()	__asm__ __volatile__("":::"memory")
#define smp_rmb()	__asm__ __volatile__("":::"memory")
#define smp_wmb()	__asm__ __volatile__("":::"memory")
#define smp_read_barrier_depends()	do { } while(0)
#endif

#define flushi(addr)	__asm__ __volatile__ ("flush %0" : : "r" (addr) : "memory")

#define flushw_all()	__asm__ __volatile__("flushw")

/* Performance counter register access. */
#define read_pcr(__p)  __asm__ __volatile__("rd	%%pcr, %0" : "=r" (__p))
#define write_pcr(__p) __asm__ __volatile__("wr	%0, 0x0, %%pcr" : : "r" (__p))
#define read_pic(__p)  __asm__ __volatile__("rd %%pic, %0" : "=r" (__p))

/* Blackbird errata workaround.  See commentary in
 * arch/sparc64/kernel/smp.c:smp_percpu_timer_interrupt()
 * for more information.
 */
#define reset_pic()    						\
	__asm__ __volatile__("ba,pt	%xcc, 99f\n\t"		\
			     ".align	64\n"			\
			  "99:wr	%g0, 0x0, %pic\n\t"	\
			     "rd	%pic, %g0")

#ifndef __ASSEMBLY__

extern void sun_do_break(void);
extern int stop_a_enabled;
extern int scons_pwroff;

extern void fault_in_user_windows(void);
extern void synchronize_user_stack(void);

extern void __flushw_user(void);
#define flushw_user() __flushw_user()

#define flush_user_windows flushw_user
#define flush_register_windows flushw_all

/* Don't hold the runqueue lock over context switch */
#define __ARCH_WANT_UNLOCKED_CTXSW
#define prepare_arch_switch(next)		\
do {						\
	flushw_all();				\
} while (0)

	/* See what happens when you design the chip correctly?
	 *
	 * We tell gcc we clobber all non-fixed-usage registers except
	 * for l0/l1.  It will use one for 'next' and the other to hold
	 * the output value of 'last'.  'next' is not referenced again
	 * past the invocation of switch_to in the scheduler, so we need
	 * not preserve it's value.  Hairy, but it lets us remove 2 loads
	 * and 2 stores in this critical code path.  -DaveM
	 */
#define switch_to(prev, next, last)					\
do {	if (test_thread_flag(TIF_PERFCTR)) {				\
		unsigned long __tmp;					\
		read_pcr(__tmp);					\
		current_thread_info()->pcr_reg = __tmp;			\
		read_pic(__tmp);					\
		current_thread_info()->kernel_cntd0 += (unsigned int)(__tmp);\
		current_thread_info()->kernel_cntd1 += ((__tmp) >> 32);	\
	}								\
	flush_tlb_pending();						\
	save_and_clear_fpu();						\
	/* If you are tempted to conditionalize the following */	\
	/* so that ASI is only written if it changes, think again. */	\
	__asm__ __volatile__("wr %%g0, %0, %%asi"			\
	: : "r" (__thread_flag_byte_ptr(task_thread_info(next))[TI_FLAG_BYTE_CURRENT_DS]));\
	trap_block[current_thread_info()->cpu].thread =			\
		task_thread_info(next);					\
	__asm__ __volatile__(						\
	"mov	%%g4, %%g7\n\t"						\
	"stx	%%i6, [%%sp + 2047 + 0x70]\n\t"				\
	"stx	%%i7, [%%sp + 2047 + 0x78]\n\t"				\
	"rdpr	%%wstate, %%o5\n\t"					\
	"stx	%%o6, [%%g6 + %6]\n\t"					\
	"stb	%%o5, [%%g6 + %5]\n\t"					\
	"rdpr	%%cwp, %%o5\n\t"					\
	"stb	%%o5, [%%g6 + %8]\n\t"					\
	"mov	%4, %%g6\n\t"						\
	"ldub	[%4 + %8], %%g1\n\t"					\
	"wrpr	%%g1, %%cwp\n\t"					\
	"ldx	[%%g6 + %6], %%o6\n\t"					\
	"ldub	[%%g6 + %5], %%o5\n\t"					\
	"ldub	[%%g6 + %7], %%o7\n\t"					\
	"wrpr	%%o5, 0x0, %%wstate\n\t"				\
	"ldx	[%%sp + 2047 + 0x70], %%i6\n\t"				\
	"ldx	[%%sp + 2047 + 0x78], %%i7\n\t"				\
	"ldx	[%%g6 + %9], %%g4\n\t"					\
	"brz,pt %%o7, switch_to_pc\n\t"					\
	" mov	%%g7, %0\n\t"						\
	"sethi	%%hi(ret_from_syscall), %%g1\n\t"			\
	"jmpl	%%g1 + %%lo(ret_from_syscall), %%g0\n\t"		\
	" nop\n\t"							\
	".globl switch_to_pc\n\t"					\
	"switch_to_pc:\n\t"						\
	: "=&r" (last), "=r" (current), "=r" (current_thread_info_reg),	\
	  "=r" (__local_per_cpu_offset)					\
	: "0" (task_thread_info(next)),					\
	  "i" (TI_WSTATE), "i" (TI_KSP), "i" (TI_NEW_CHILD),            \
	  "i" (TI_CWP), "i" (TI_TASK)					\
	: "cc",								\
	        "g1", "g2", "g3",                   "g7",		\
	        "l1", "l2", "l3", "l4", "l5", "l6", "l7",		\
	  "i0", "i1", "i2", "i3", "i4", "i5",				\
	  "o0", "o1", "o2", "o3", "o4", "o5",       "o7");		\
	/* If you fuck with this, update ret_from_syscall code too. */	\
	if (test_thread_flag(TIF_PERFCTR)) {				\
		write_pcr(current_thread_info()->pcr_reg);		\
		reset_pic();						\
	}								\
} while(0)

static inline unsigned long xchg32(__volatile__ unsigned int *m, unsigned int val)
{
	unsigned long tmp1, tmp2;

	__asm__ __volatile__(
"	membar		#StoreLoad | #LoadLoad\n"
"	mov		%0, %1\n"
"1:	lduw		[%4], %2\n"
"	cas		[%4], %2, %0\n"
"	cmp		%2, %0\n"
"	bne,a,pn	%%icc, 1b\n"
"	 mov		%1, %0\n"
"	membar		#StoreLoad | #StoreStore\n"
	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
	: "0" (val), "r" (m)
	: "cc", "memory");
	return val;
}

static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long val)
{
	unsigned long tmp1, tmp2;

	__asm__ __volatile__(
"	membar		#StoreLoad | #LoadLoad\n"
"	mov		%0, %1\n"
"1:	ldx		[%4], %2\n"
"	casx		[%4], %2, %0\n"
"	cmp		%2, %0\n"
"	bne,a,pn	%%xcc, 1b\n"
"	 mov		%1, %0\n"
"	membar		#StoreLoad | #StoreStore\n"
	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
	: "0" (val), "r" (m)
	: "cc", "memory");
	return val;
}

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

extern void __xchg_called_with_bad_pointer(void);

static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
				       int size)
{
	switch (size) {
	case 4:
		return xchg32(ptr, x);
	case 8:
		return xchg64(ptr, x);
	};
	__xchg_called_with_bad_pointer();
	return x;
}

extern void die_if_kernel(char *str, struct pt_regs *regs) __attribute__ ((noreturn));

/*
 * 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.
 */

#define __HAVE_ARCH_CMPXCHG 1

static inline unsigned long
__cmpxchg_u32(volatile int *m, int old, int new)
{
	__asm__ __volatile__("membar #StoreLoad | #LoadLoad\n"
			     "cas [%2], %3, %0\n\t"
			     "membar #StoreLoad | #StoreStore"
			     : "=&r" (new)
			     : "0" (new), "r" (m), "r" (old)
			     : "memory");

	return new;
}

static inline unsigned long
__cmpxchg_u64(volatile long *m, unsigned long old, unsigned long new)
{
	__asm__ __volatile__("membar #StoreLoad | #LoadLoad\n"
			     "casx [%2], %3, %0\n\t"
			     "membar #StoreLoad | #StoreStore"
			     : "=&r" (new)
			     : "0" (new), "r" (m), "r" (old)
			     : "memory");

	return new;
}

/* 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);

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);
		case 8:
			return __cmpxchg_u64(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))); \
  })

/*
 * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
 * them available.
 */

static inline unsigned long __cmpxchg_local(volatile void *ptr,
				      unsigned long old,
				      unsigned long new, int size)
{
	switch (size) {
	case 4:
	case 8:	return __cmpxchg(ptr, old, new, size);
	default:
		return __cmpxchg_local_generic(ptr, old, new, size);
	}

	return old;
}

#define cmpxchg_local(ptr, o, n)				  	\
	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
			(unsigned long)(n), sizeof(*(ptr))))
#define cmpxchg64_local(ptr, o, n)					\
  ({									\
	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
	cmpxchg_local((ptr), (o), (n));					\
  })

#endif /* !(__ASSEMBLY__) */

#define arch_align_stack(x) (x)

#endif /* !(__SPARC64_SYSTEM_H) */