aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/mm/ioremap.c
blob: c246d259822d8b5a3d32a35275368a5bcbbf19b8 (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
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
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
/*
 * Re-map IO memory to kernel address space so that we can access it.
 * This is needed for high PCI addresses that aren't mapped in the
 * 640k-1MB IO memory area on PC's
 *
 * (C) Copyright 1995 1996 Linus Torvalds
 */

#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/io.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/mmiotrace.h>

#include <asm/cacheflush.h>
#include <asm/e820.h>
#include <asm/fixmap.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
#include <asm/pat.h>

#include "physaddr.h"

int page_is_ram(unsigned long pagenr)
{
	resource_size_t addr, end;
	int i;

	/*
	 * A special case is the first 4Kb of memory;
	 * This is a BIOS owned area, not kernel ram, but generally
	 * not listed as such in the E820 table.
	 */
	if (pagenr == 0)
		return 0;

	/*
	 * Second special case: Some BIOSen report the PC BIOS
	 * area (640->1Mb) as ram even though it is not.
	 */
	if (pagenr >= (BIOS_BEGIN >> PAGE_SHIFT) &&
		    pagenr < (BIOS_END >> PAGE_SHIFT))
		return 0;

	for (i = 0; i < e820.nr_map; i++) {
		/*
		 * Not usable memory:
		 */
		if (e820.map[i].type != E820_RAM)
			continue;
		addr = (e820.map[i].addr + PAGE_SIZE-1) >> PAGE_SHIFT;
		end = (e820.map[i].addr + e820.map[i].size) >> PAGE_SHIFT;


		if ((pagenr >= addr) && (pagenr < end))
			return 1;
	}
	return 0;
}

/*
 * Fix up the linear direct mapping of the kernel to avoid cache attribute
 * conflicts.
 */
int ioremap_change_attr(unsigned long vaddr, unsigned long size,
			       unsigned long prot_val)
{
	unsigned long nrpages = size >> PAGE_SHIFT;
	int err;

	switch (prot_val) {
	case _PAGE_CACHE_UC:
	default:
		err = _set_memory_uc(vaddr, nrpages);
		break;
	case _PAGE_CACHE_WC:
		err = _set_memory_wc(vaddr, nrpages);
		break;
	case _PAGE_CACHE_WB:
		err = _set_memory_wb(vaddr, nrpages);
		break;
	}

	return err;
}

/*
 * Remap an arbitrary physical address space into the kernel virtual
 * address space. Needed when the kernel wants to access high addresses
 * directly.
 *
 * NOTE! We need to allow non-page-aligned mappings too: we will obviously
 * have to convert them into an offset in a page-aligned mapping, but the
 * caller shouldn't need to know that small detail.
 */
static void __iomem *__ioremap_caller(resource_size_t phys_addr,
		unsigned long size, unsigned long prot_val, void *caller)
{
	unsigned long pfn, offset, vaddr;
	resource_size_t last_addr;
	const resource_size_t unaligned_phys_addr = phys_addr;
	const unsigned long unaligned_size = size;
	struct vm_struct *area;
	unsigned long new_prot_val;
	pgprot_t prot;
	int retval;
	void __iomem *ret_addr;

	/* Don't allow wraparound or zero size */
	last_addr = phys_addr + size - 1;
	if (!size || last_addr < phys_addr)
		return NULL;

	if (!phys_addr_valid(phys_addr)) {
		printk(KERN_WARNING "ioremap: invalid physical address %llx\n",
		       (unsigned long long)phys_addr);
		WARN_ON_ONCE(1);
		return NULL;
	}

	/*
	 * Don't remap the low PCI/ISA area, it's always mapped..
	 */
	if (is_ISA_range(phys_addr, last_addr))
		return (__force void __iomem *)phys_to_virt(phys_addr);

	/*
	 * Check if the request spans more than any BAR in the iomem resource
	 * tree.
	 */
	WARN_ONCE(iomem_map_sanity_check(phys_addr, size),
		  KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");

	/*
	 * Don't allow anybody to remap normal RAM that we're using..
	 */
	for (pfn = phys_addr >> PAGE_SHIFT;
				(pfn << PAGE_SHIFT) < (last_addr & PAGE_MASK);
				pfn++) {

		int is_ram = page_is_ram(pfn);

		if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn)))
			return NULL;
		WARN_ON_ONCE(is_ram);
	}

	/*
	 * Mappings have to be page-aligned
	 */
	offset = phys_addr & ~PAGE_MASK;
	phys_addr &= PAGE_MASK;
	size = PAGE_ALIGN(last_addr+1) - phys_addr;

	retval = reserve_memtype(phys_addr, (u64)phys_addr + size,
						prot_val, &new_prot_val);
	if (retval) {
		printk(KERN_ERR "ioremap reserve_memtype failed %d\n", retval);
		return NULL;
	}

	if (prot_val != new_prot_val) {
		if (!is_new_memtype_allowed(phys_addr, size,
					    prot_val, new_prot_val)) {
			printk(KERN_ERR
		"ioremap error for 0x%llx-0x%llx, requested 0x%lx, got 0x%lx\n",
				(unsigned long long)phys_addr,
				(unsigned long long)(phys_addr + size),
				prot_val, new_prot_val);
			goto err_free_memtype;
		}
		prot_val = new_prot_val;
	}

	switch (prot_val) {
	case _PAGE_CACHE_UC:
	default:
		prot = PAGE_KERNEL_IO_NOCACHE;
		break;
	case _PAGE_CACHE_UC_MINUS:
		prot = PAGE_KERNEL_IO_UC_MINUS;
		break;
	case _PAGE_CACHE_WC:
		prot = PAGE_KERNEL_IO_WC;
		break;
	case _PAGE_CACHE_WB:
		prot = PAGE_KERNEL_IO;
		break;
	}

	/*
	 * Ok, go for it..
	 */
	area = get_vm_area_caller(size, VM_IOREMAP, caller);
	if (!area)
		goto err_free_memtype;
	area->phys_addr = phys_addr;
	vaddr = (unsigned long) area->addr;

	if (kernel_map_sync_memtype(phys_addr, size, prot_val))
		goto err_free_area;

	if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot))
		goto err_free_area;

	ret_addr = (void __iomem *) (vaddr + offset);
	mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr);

	return ret_addr;
err_free_area:
	free_vm_area(area);
err_free_memtype:
	free_memtype(phys_addr, phys_addr + size);
	return NULL;
}

/**
 * ioremap_nocache     -   map bus memory into CPU space
 * @offset:    bus address of the memory
 * @size:      size of the resource to map
 *
 * ioremap_nocache performs a platform specific sequence of operations to
 * make bus memory CPU accessible via the readb/readw/readl/writeb/
 * writew/writel functions and the other mmio helpers. The returned
 * address is not guaranteed to be usable directly as a virtual
 * address.
 *
 * This version of ioremap ensures that the memory is marked uncachable
 * on the CPU as well as honouring existing caching rules from things like
 * the PCI bus. Note that there are other caches and buffers on many
 * busses. In particular driver authors should read up on PCI writes
 *
 * It's useful if some control registers are in such an area and
 * write combining or read caching is not desirable:
 *
 * Must be freed with iounmap.
 */
void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
{
	/*
	 * Ideally, this should be:
	 *	pat_enabled ? _PAGE_CACHE_UC : _PAGE_CACHE_UC_MINUS;
	 *
	 * Till we fix all X drivers to use ioremap_wc(), we will use
	 * UC MINUS.
	 */
	unsigned long val = _PAGE_CACHE_UC_MINUS;

	return __ioremap_caller(phys_addr, size, val,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_nocache);

/**
 * ioremap_wc	-	map memory into CPU space write combined
 * @offset:	bus address of the memory
 * @size:	size of the resource to map
 *
 * This version of ioremap ensures that the memory is marked write combining.
 * Write combining allows faster writes to some hardware devices.
 *
 * Must be freed with iounmap.
 */
void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
{
	if (pat_enabled)
		return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC,
					__builtin_return_address(0));
	else
		return ioremap_nocache(phys_addr, size);
}
EXPORT_SYMBOL(ioremap_wc);

void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
{
	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WB,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_cache);

void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
				unsigned long prot_val)
{
	return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK),
				__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_prot);

/**
 * iounmap - Free a IO remapping
 * @addr: virtual address from ioremap_*
 *
 * Caller must ensure there is only one unmapping for the same pointer.
 */
void iounmap(volatile void __iomem *addr)
{
	struct vm_struct *p, *o;

	if ((void __force *)addr <= high_memory)
		return;

	/*
	 * __ioremap special-cases the PCI/ISA range by not instantiating a
	 * vm_area and by simply returning an address into the kernel mapping
	 * of ISA space.   So handle that here.
	 */
	if ((void __force *)addr >= phys_to_virt(ISA_START_ADDRESS) &&
	    (void __force *)addr < phys_to_virt(ISA_END_ADDRESS))
		return;

	addr = (volatile void __iomem *)
		(PAGE_MASK & (unsigned long __force)addr);

	mmiotrace_iounmap(addr);

	/* Use the vm area unlocked, assuming the caller
	   ensures there isn't another iounmap for the same address
	   in parallel. Reuse of the virtual address is prevented by
	   leaving it in the global lists until we're done with it.
	   cpa takes care of the direct mappings. */
	read_lock(&vmlist_lock);
	for (p = vmlist; p; p = p->next) {
		if (p->addr == (void __force *)addr)
			break;
	}
	read_unlock(&vmlist_lock);

	if (!p) {
		printk(KERN_ERR "iounmap: bad address %p\n", addr);
		dump_stack();
		return;
	}

	free_memtype(p->phys_addr, p->phys_addr + get_vm_area_size(p));

	/* Finally remove it */
	o = remove_vm_area((void __force *)addr);
	BUG_ON(p != o || o == NULL);
	kfree(p);
}
EXPORT_SYMBOL(iounmap);

/*
 * Convert a physical pointer to a virtual kernel pointer for /dev/mem
 * access
 */
void *xlate_dev_mem_ptr(unsigned long phys)
{
	void *addr;
	unsigned long start = phys & PAGE_MASK;

	/* If page is RAM, we can use __va. Otherwise ioremap and unmap. */
	if (page_is_ram(start >> PAGE_SHIFT))
		return __va(phys);

	addr = (void __force *)ioremap_cache(start, PAGE_SIZE);
	if (addr)
		addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK));

	return addr;
}

void unxlate_dev_mem_ptr(unsigned long phys, void *addr)
{
	if (page_is_ram(phys >> PAGE_SHIFT))
		return;

	iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK));
	return;
}

static int __initdata early_ioremap_debug;

static int __init early_ioremap_debug_setup(char *str)
{
	early_ioremap_debug = 1;

	return 0;
}
early_param("early_ioremap_debug", early_ioremap_debug_setup);

static __initdata int after_paging_init;
static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss;

static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
{
	/* Don't assume we're using swapper_pg_dir at this point */
	pgd_t *base = __va(read_cr3());
	pgd_t *pgd = &base[pgd_index(addr)];
	pud_t *pud = pud_offset(pgd, addr);
	pmd_t *pmd = pmd_offset(pud, addr);

	return pmd;
}

static inline pte_t * __init early_ioremap_pte(unsigned long addr)
{
	return &bm_pte[pte_index(addr)];
}

static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata;

void __init early_ioremap_init(void)
{
	pmd_t *pmd;
	int i;

	if (early_ioremap_debug)
		printk(KERN_INFO "early_ioremap_init()\n");

	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
		slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i);

	pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
	memset(bm_pte, 0, sizeof(bm_pte));
	pmd_populate_kernel(&init_mm, pmd, bm_pte);

	/*
	 * The boot-ioremap range spans multiple pmds, for which
	 * we are not prepared:
	 */
	if (pmd != early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END))) {
		WARN_ON(1);
		printk(KERN_WARNING "pmd %p != %p\n",
		       pmd, early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END)));
		printk(KERN_WARNING "fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
			fix_to_virt(FIX_BTMAP_BEGIN));
		printk(KERN_WARNING "fix_to_virt(FIX_BTMAP_END):   %08lx\n",
			fix_to_virt(FIX_BTMAP_END));

		printk(KERN_WARNING "FIX_BTMAP_END:       %d\n", FIX_BTMAP_END);
		printk(KERN_WARNING "FIX_BTMAP_BEGIN:     %d\n",
		       FIX_BTMAP_BEGIN);
	}
}

void __init early_ioremap_reset(void)
{
	after_paging_init = 1;
}

static void __init __early_set_fixmap(enum fixed_addresses idx,
				      phys_addr_t phys, pgprot_t flags)
{
	unsigned long addr = __fix_to_virt(idx);
	pte_t *pte;

	if (idx >= __end_of_fixed_addresses) {
		BUG();
		return;
	}
	pte = early_ioremap_pte(addr);

	if (pgprot_val(flags))
		set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
	else
		pte_clear(&init_mm, addr, pte);
	__flush_tlb_one(addr);
}

static inline void __init early_set_fixmap(enum fixed_addresses idx,
					   phys_addr_t phys, pgprot_t prot)
{
	if (after_paging_init)
		__set_fixmap(idx, phys, prot);
	else
		__early_set_fixmap(idx, phys, prot);
}

static inline void __init early_clear_fixmap(enum fixed_addresses idx)
{
	if (after_paging_init)
		clear_fixmap(idx);
	else
		__early_set_fixmap(idx, 0, __pgprot(0));
}

static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;

static int __init check_early_ioremap_leak(void)
{
	int count = 0;
	int i;

	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
		if (prev_map[i])
			count++;

	if (!count)
		return 0;
	WARN(1, KERN_WARNING
	       "Debug warning: early ioremap leak of %d areas detected.\n",
		count);
	printk(KERN_WARNING
		"please boot with early_ioremap_debug and report the dmesg.\n");

	return 1;
}
late_initcall(check_early_ioremap_leak);

static void __init __iomem *
__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
{
	unsigned long offset;
	resource_size_t last_addr;
	unsigned int nrpages;
	enum fixed_addresses idx0, idx;
	int i, slot;

	WARN_ON(system_state != SYSTEM_BOOTING);

	slot = -1;
	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
		if (!prev_map[i]) {
			slot = i;
			break;
		}
	}

	if (slot < 0) {
		printk(KERN_INFO "early_iomap(%08llx, %08lx) not found slot\n",
			 (u64)phys_addr, size);
		WARN_ON(1);
		return NULL;
	}

	if (early_ioremap_debug) {
		printk(KERN_INFO "early_ioremap(%08llx, %08lx) [%d] => ",
		       (u64)phys_addr, size, slot);
		dump_stack();
	}

	/* Don't allow wraparound or zero size */
	last_addr = phys_addr + size - 1;
	if (!size || last_addr < phys_addr) {
		WARN_ON(1);
		return NULL;
	}

	prev_size[slot] = size;
	/*
	 * Mappings have to be page-aligned
	 */
	offset = phys_addr & ~PAGE_MASK;
	phys_addr &= PAGE_MASK;
	size = PAGE_ALIGN(last_addr + 1) - phys_addr;

	/*
	 * Mappings have to fit in the FIX_BTMAP area.
	 */
	nrpages = size >> PAGE_SHIFT;
	if (nrpages > NR_FIX_BTMAPS) {
		WARN_ON(1);
		return NULL;
	}

	/*
	 * Ok, go for it..
	 */
	idx0 = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
	idx = idx0;
	while (nrpages > 0) {
		early_set_fixmap(idx, phys_addr, prot);
		phys_addr += PAGE_SIZE;
		--idx;
		--nrpages;
	}
	if (early_ioremap_debug)
		printk(KERN_CONT "%08lx + %08lx\n", offset, slot_virt[slot]);

	prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]);
	return prev_map[slot];
}

/* Remap an IO device */
void __init __iomem *
early_ioremap(resource_size_t phys_addr, unsigned long size)
{
	return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO);
}

/* Remap memory */
void __init __iomem *
early_memremap(resource_size_t phys_addr, unsigned long size)
{
	return __early_ioremap(phys_addr, size, PAGE_KERNEL);
}

void __init early_iounmap(void __iomem *addr, unsigned long size)
{
	unsigned long virt_addr;
	unsigned long offset;
	unsigned int nrpages;
	enum fixed_addresses idx;
	int i, slot;

	slot = -1;
	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
		if (prev_map[i] == addr) {
			slot = i;
			break;
		}
	}

	if (slot < 0) {
		printk(KERN_INFO "early_iounmap(%p, %08lx) not found slot\n",
			 addr, size);
		WARN_ON(1);
		return;
	}

	if (prev_size[slot] != size) {
		printk(KERN_INFO "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n",
			 addr, size, slot, prev_size[slot]);
		WARN_ON(1);
		return;
	}

	if (early_ioremap_debug) {
		printk(KERN_INFO "early_iounmap(%p, %08lx) [%d]\n", addr,
		       size, slot);
		dump_stack();
	}

	virt_addr = (unsigned long)addr;
	if (virt_addr < fix_to_virt(FIX_BTMAP_BEGIN)) {
		WARN_ON(1);
		return;
	}
	offset = virt_addr & ~PAGE_MASK;
	nrpages = PAGE_ALIGN(offset + size - 1) >> PAGE_SHIFT;

	idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
	while (nrpages > 0) {
		early_clear_fixmap(idx);
		--idx;
		--nrpages;
	}
	prev_map[slot] = NULL;
}