aboutsummaryrefslogtreecommitdiffstats
path: root/include/asm-ia64/io.h
blob: 491e9d1fc538d0e31cbc2ecbbf15016cd6d7d194 (plain) (blame)
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_IA64_IO_H
#define _ASM_IA64_IO_H

/*
 * This file contains the definitions for the emulated IO instructions
 * inb/inw/inl/outb/outw/outl and the "string versions" of the same
 * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
 * versions of the single-IO instructions (inb_p/inw_p/..).
 *
 * This file is not meant to be obfuscating: it's just complicated to
 * (a) handle it all in a way that makes gcc able to optimize it as
 * well as possible and (b) trying to avoid writing the same thing
 * over and over again with slight variations and possibly making a
 * mistake somewhere.
 *
 * Copyright (C) 1998-2003 Hewlett-Packard Co
 *	David Mosberger-Tang <davidm@hpl.hp.com>
 * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com>
 * Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
 */

/* We don't use IO slowdowns on the ia64, but.. */
#define __SLOW_DOWN_IO	do { } while (0)
#define SLOW_DOWN_IO	do { } while (0)

#define __IA64_UNCACHED_OFFSET	0xc000000000000000UL	/* region 6 */

/*
 * The legacy I/O space defined by the ia64 architecture supports only 65536 ports, but
 * large machines may have multiple other I/O spaces so we can't place any a priori limit
 * on IO_SPACE_LIMIT.  These additional spaces are described in ACPI.
 */
#define IO_SPACE_LIMIT		0xffffffffffffffffUL

#define MAX_IO_SPACES_BITS		4
#define MAX_IO_SPACES			(1UL << MAX_IO_SPACES_BITS)
#define IO_SPACE_BITS			24
#define IO_SPACE_SIZE			(1UL << IO_SPACE_BITS)

#define IO_SPACE_NR(port)		((port) >> IO_SPACE_BITS)
#define IO_SPACE_BASE(space)		((space) << IO_SPACE_BITS)
#define IO_SPACE_PORT(port)		((port) & (IO_SPACE_SIZE - 1))

#define IO_SPACE_SPARSE_ENCODING(p)	((((p) >> 2) << 12) | (p & 0xfff))

struct io_space {
	unsigned long mmio_base;	/* base in MMIO space */
	int sparse;
};

extern struct io_space io_space[];
extern unsigned int num_io_spaces;

# ifdef __KERNEL__

/*
 * All MMIO iomem cookies are in region 6; anything less is a PIO cookie:
 *	0xCxxxxxxxxxxxxxxx	MMIO cookie (return from ioremap)
 *	0x000000001SPPPPPP	PIO cookie (S=space number, P..P=port)
 *
 * ioread/writeX() uses the leading 1 in PIO cookies (PIO_OFFSET) to catch
 * code that uses bare port numbers without the prerequisite pci_iomap().
 */
#define PIO_OFFSET		(1UL << (MAX_IO_SPACES_BITS + IO_SPACE_BITS))
#define PIO_MASK		(PIO_OFFSET - 1)
#define PIO_RESERVED		__IA64_UNCACHED_OFFSET
#define HAVE_ARCH_PIO_SIZE

#include <asm/intrinsics.h>
#include <asm/machvec.h>
#include <asm/page.h>
#include <asm/system.h>
#include <asm-generic/iomap.h>

/*
 * Change virtual addresses to physical addresses and vv.
 */
static inline unsigned long
virt_to_phys (volatile void *address)
{
	return (unsigned long) address - PAGE_OFFSET;
}

static inline void*
phys_to_virt (unsigned long address)
{
	return (void *) (address + PAGE_OFFSET);
}

#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
extern int valid_phys_addr_range (unsigned long addr, size_t *count); /* efi.c */

/*
 * The following two macros are deprecated and scheduled for removal.
 * Please use the PCI-DMA interface defined in <asm/pci.h> instead.
 */
#define bus_to_virt	phys_to_virt
#define virt_to_bus	virt_to_phys
#define page_to_bus	page_to_phys

# endif /* KERNEL */

/*
 * Memory fence w/accept.  This should never be used in code that is
 * not IA-64 specific.
 */
#define __ia64_mf_a()	ia64_mfa()

/**
 * ___ia64_mmiowb - I/O write barrier
 *
 * Ensure ordering of I/O space writes.  This will make sure that writes
 * following the barrier will arrive after all previous writes.  For most
 * ia64 platforms, this is a simple 'mf.a' instruction.
 *
 * See Documentation/DocBook/deviceiobook.tmpl for more information.
 */
static inline void ___ia64_mmiowb(void)
{
	ia64_mfa();
}

static inline const unsigned long
__ia64_get_io_port_base (void)
{
	extern unsigned long ia64_iobase;

	return ia64_iobase;
}

static inline void*
__ia64_mk_io_addr (unsigned long port)
{
	struct io_space *space;
	unsigned long offset;

	space = &io_space[IO_SPACE_NR(port)];
	port = IO_SPACE_PORT(port);
	if (space->sparse)
		offset = IO_SPACE_SPARSE_ENCODING(port);
	else
		offset = port;

	return (void *) (space->mmio_base | offset);
}

#define __ia64_inb	___ia64_inb
#define __ia64_inw	___ia64_inw
#define __ia64_inl	___ia64_inl
#define __ia64_outb	___ia64_outb
#define __ia64_outw	___ia64_outw
#define __ia64_outl	___ia64_outl
#define __ia64_readb	___ia64_readb
#define __ia64_readw	___ia64_readw
#define __ia64_readl	___ia64_readl
#define __ia64_readq	___ia64_readq
#define __ia64_readb_relaxed	___ia64_readb
#define __ia64_readw_relaxed	___ia64_readw
#define __ia64_readl_relaxed	___ia64_readl
#define __ia64_readq_relaxed	___ia64_readq
#define __ia64_writeb	___ia64_writeb
#define __ia64_writew	___ia64_writew
#define __ia64_writel	___ia64_writel
#define __ia64_writeq	___ia64_writeq
#define __ia64_mmiowb	___ia64_mmiowb

/*
 * For the in/out routines, we need to do "mf.a" _after_ doing the I/O access to ensure
 * that the access has completed before executing other I/O accesses.  Since we're doing
 * the accesses through an uncachable (UC) translation, the CPU will execute them in
 * program order.  However, we still need to tell the compiler not to shuffle them around
 * during optimization, which is why we use "volatile" pointers.
 */

static inline unsigned int
___ia64_inb (unsigned long port)
{
	volatile unsigned char *addr = __ia64_mk_io_addr(port);
	unsigned char ret;

	ret = *addr;
	__ia64_mf_a();
	return ret;
}

static inline unsigned int
___ia64_inw (unsigned long port)
{
	volatile unsigned short *addr = __ia64_mk_io_addr(port);
	unsigned short ret;

	ret = *addr;
	__ia64_mf_a();
	return ret;
}

static inline unsigned int
___ia64_inl (unsigned long port)
{
	volatile unsigned int *addr = __ia64_mk_io_addr(port);
	unsigned int ret;

	ret = *addr;
	__ia64_mf_a();
	return ret;
}

static inline void
___ia64_outb (unsigned char val, unsigned long port)
{
	volatile unsigned char *addr = __ia64_mk_io_addr(port);

	*addr = val;
	__ia64_mf_a();
}

static inline void
___ia64_outw (unsigned short val, unsigned long port)
{
	volatile unsigned short *addr = __ia64_mk_io_addr(port);

	*addr = val;
	__ia64_mf_a();
}

static inline void
___ia64_outl (unsigned int val, unsigned long port)
{
	volatile unsigned int *addr = __ia64_mk_io_addr(port);

	*addr = val;
	__ia64_mf_a();
}

static inline void
__insb (unsigned long port, void *dst, unsigned long count)
{
	unsigned char *dp = dst;

	while (count--)
		*dp++ = platform_inb(port);
}

static inline void
__insw (unsigned long port, void *dst, unsigned long count)
{
	unsigned short *dp = dst;

	while (count--)
		*dp++ = platform_inw(port);
}

static inline void
__insl (unsigned long port, void *dst, unsigned long count)
{
	unsigned int *dp = dst;

	while (count--)
		*dp++ = platform_inl(port);
}

static inline void
__outsb (unsigned long port, const void *src, unsigned long count)
{
	const unsigned char *sp = src;

	while (count--)
		platform_outb(*sp++, port);
}

static inline void
__outsw (unsigned long port, const void *src, unsigned long count)
{
	const unsigned short *sp = src;

	while (count--)
		platform_outw(*sp++, port);
}

static inline void
__outsl (unsigned long port, const void *src, unsigned long count)
{
	const unsigned int *sp = src;

	while (count--)
		platform_outl(*sp++, port);
}

/*
 * Unfortunately, some platforms are broken and do not follow the IA-64 architecture
 * specification regarding legacy I/O support.  Thus, we have to make these operations
 * platform dependent...
 */
#define __inb		platform_inb
#define __inw		platform_inw
#define __inl		platform_inl
#define __outb		platform_outb
#define __outw		platform_outw
#define __outl		platform_outl
#define __mmiowb	platform_mmiowb

#define inb(p)		__inb(p)
#define inw(p)		__inw(p)
#define inl(p)		__inl(p)
#define insb(p,d,c)	__insb(p,d,c)
#define insw(p,d,c)	__insw(p,d,c)
#define insl(p,d,c)	__insl(p,d,c)
#define outb(v,p)	__outb(v,p)
#define outw(v,p)	__outw(v,p)
#define outl(v,p)	__outl(v,p)
#define outsb(p,s,c)	__outsb(p,s,c)
#define outsw(p,s,c)	__outsw(p,s,c)
#define outsl(p,s,c)	__outsl(p,s,c)
#define mmiowb()	__mmiowb()

/*
 * The address passed to these functions are ioremap()ped already.
 *
 * We need these to be machine vectors since some platforms don't provide
 * DMA coherence via PIO reads (PCI drivers and the spec imply that this is
 * a good idea).  Writes are ok though for all existing ia64 platforms (and
 * hopefully it'll stay that way).
 */
static inline unsigned char
___ia64_readb (const volatile void __iomem *addr)
{
	return *(volatile unsigned char __force *)addr;
}

static inline unsigned short
___ia64_readw (const volatile void __iomem *addr)
{
	return *(volatile unsigned short __force *)addr;
}

static inline unsigned int
___ia64_readl (const volatile void __iomem *addr)
{
	return *(volatile unsigned int __force *) addr;
}

static inline unsigned long
___ia64_readq (const volatile void __iomem *addr)
{
	return *(volatile unsigned long __force *) addr;
}

static inline void
__writeb (unsigned char val, volatile void __iomem *addr)
{
	*(volatile unsigned char __force *) addr = val;
}

static inline void
__writew (unsigned short val, volatile void __iomem *addr)
{
	*(volatile unsigned short __force *) addr = val;
}

static inline void
__writel (unsigned int val, volatile void __iomem *addr)
{
	*(volatile unsigned int __force *) addr = val;
}

static inline void
__writeq (unsigned long val, volatile void __iomem *addr)
{
	*(volatile unsigned long __force *) addr = val;
}

#define __readb		platform_readb
#define __readw		platform_readw
#define __readl		platform_readl
#define __readq		platform_readq
#define __readb_relaxed	platform_readb_relaxed
#define __readw_relaxed	platform_readw_relaxed
#define __readl_relaxed	platform_readl_relaxed
#define __readq_relaxed	platform_readq_relaxed

#define readb(a)	__readb((a))
#define readw(a)	__readw((a))
#define readl(a)	__readl((a))
#define readq(a)	__readq((a))
#define readb_relaxed(a)	__readb_relaxed((a))
#define readw_relaxed(a)	__readw_relaxed((a))
#define readl_relaxed(a)	__readl_relaxed((a))
#define readq_relaxed(a)	__readq_relaxed((a))
#define __raw_readb	readb
#define __raw_readw	readw
#define __raw_readl	readl
#define __raw_readq	readq
#define __raw_readb_relaxed	readb_relaxed
#define __raw_readw_relaxed	readw_relaxed
#define __raw_readl_relaxed	readl_relaxed
#define __raw_readq_relaxed	readq_relaxed
#define writeb(v,a)	__writeb((v), (a))
#define writew(v,a)	__writew((v), (a))
#define writel(v,a)	__writel((v), (a))
#define writeq(v,a)	__writeq((v), (a))
#define __raw_writeb	writeb
#define __raw_writew	writew
#define __raw_writel	writel
#define __raw_writeq	writeq

#ifndef inb_p
# define inb_p		inb
#endif
#ifndef inw_p
# define inw_p		inw
#endif
#ifndef inl_p
# define inl_p		inl
#endif

#ifndef outb_p
# define outb_p		outb
#endif
#ifndef outw_p
# define outw_p		outw
#endif
#ifndef outl_p
# define outl_p		outl
#endif

/*
 * An "address" in IO memory space is not clearly either an integer or a pointer. We will
 * accept both, thus the casts.
 *
 * On ia-64, we access the physical I/O memory space through the uncached kernel region.
 */
static inline void __iomem *
ioremap (unsigned long offset, unsigned long size)
{
	return (void __iomem *) (__IA64_UNCACHED_OFFSET | (offset));
}

static inline void
iounmap (volatile void __iomem *addr)
{
}

#define ioremap_nocache(o,s)	ioremap(o,s)

# ifdef __KERNEL__

/*
 * String version of IO memory access ops:
 */
extern void memcpy_fromio(void *dst, const volatile void __iomem *src, long n);
extern void memcpy_toio(volatile void __iomem *dst, const void *src, long n);
extern void memset_io(volatile void __iomem *s, int c, long n);

#define dma_cache_inv(_start,_size)             do { } while (0)
#define dma_cache_wback(_start,_size)           do { } while (0)
#define dma_cache_wback_inv(_start,_size)       do { } while (0)

# endif /* __KERNEL__ */

/*
 * Enabling BIO_VMERGE_BOUNDARY forces us to turn off I/O MMU bypassing.  It is said that
 * BIO-level virtual merging can give up to 4% performance boost (not verified for ia64).
 * On the other hand, we know that I/O MMU bypassing gives ~8% performance improvement on
 * SPECweb-like workloads on zx1-based machines.  Thus, for now we favor I/O MMU bypassing
 * over BIO-level virtual merging.
 */
extern unsigned long ia64_max_iommu_merge_mask;
#if 1
#define BIO_VMERGE_BOUNDARY	0
#else
/*
 * It makes no sense at all to have this BIO_VMERGE_BOUNDARY macro here.  Should be
 * replaced by dma_merge_mask() or something of that sort.  Note: the only way
 * BIO_VMERGE_BOUNDARY is used is to mask off bits.  Effectively, our definition gets
 * expanded into:
 *
 *	addr & ((ia64_max_iommu_merge_mask + 1) - 1) == (addr & ia64_max_iommu_vmerge_mask)
 *
 * which is precisely what we want.
 */
#define BIO_VMERGE_BOUNDARY	(ia64_max_iommu_merge_mask + 1)
#endif

#endif /* _ASM_IA64_IO_H */