summaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel/pci-common.c
blob: 9979c43cc8c715bc0f6fb59924aa3ba46327789d (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
/*
 * Contains common pci routines for ALL ppc platform
 * (based on pci_32.c and pci_64.c)
 *
 * Port for PPC64 David Engebretsen, IBM Corp.
 * Contains common pci routines for ppc64 platform, pSeries and iSeries brands.
 *
 * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
 *   Rework, based on alpha PCI code.
 *
 * Common pmac/prep/chrp pci routines. -- Cort
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#undef DEBUG

#include <linux/kernel.h>
#include <linux/pci.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/mm.h>
#include <linux/list.h>
#include <linux/syscalls.h>
#include <linux/irq.h>
#include <linux/vmalloc.h>

#include <asm/processor.h>
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/pci-bridge.h>
#include <asm/byteorder.h>
#include <asm/machdep.h>
#include <asm/ppc-pci.h>
#include <asm/firmware.h>

#ifdef DEBUG
#include <asm/udbg.h>
#define DBG(fmt...) printk(fmt)
#else
#define DBG(fmt...)
#endif

static DEFINE_SPINLOCK(hose_spinlock);

/* XXX kill that some day ... */
static int global_phb_number;		/* Global phb counter */

/* ISA Memory physical address */
resource_size_t isa_mem_base;


struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
{
	struct pci_controller *phb;

	phb = zalloc_maybe_bootmem(sizeof(struct pci_controller), GFP_KERNEL);
	if (phb == NULL)
		return NULL;
	spin_lock(&hose_spinlock);
	phb->global_number = global_phb_number++;
	list_add_tail(&phb->list_node, &hose_list);
	spin_unlock(&hose_spinlock);
	phb->dn = dev;
	phb->is_dynamic = mem_init_done;
#ifdef CONFIG_PPC64
	if (dev) {
		int nid = of_node_to_nid(dev);

		if (nid < 0 || !node_online(nid))
			nid = -1;

		PHB_SET_NODE(phb, nid);
	}
#endif
	return phb;
}

void pcibios_free_controller(struct pci_controller *phb)
{
	spin_lock(&hose_spinlock);
	list_del(&phb->list_node);
	spin_unlock(&hose_spinlock);

	if (phb->is_dynamic)
		kfree(phb);
}

int pcibios_vaddr_is_ioport(void __iomem *address)
{
	int ret = 0;
	struct pci_controller *hose;
	unsigned long size;

	spin_lock(&hose_spinlock);
	list_for_each_entry(hose, &hose_list, list_node) {
#ifdef CONFIG_PPC64
		size = hose->pci_io_size;
#else
		size = hose->io_resource.end - hose->io_resource.start + 1;
#endif
		if (address >= hose->io_base_virt &&
		    address < (hose->io_base_virt + size)) {
			ret = 1;
			break;
		}
	}
	spin_unlock(&hose_spinlock);
	return ret;
}

/*
 * Return the domain number for this bus.
 */
int pci_domain_nr(struct pci_bus *bus)
{
	struct pci_controller *hose = pci_bus_to_host(bus);

	return hose->global_number;
}
EXPORT_SYMBOL(pci_domain_nr);

#ifdef CONFIG_PPC_OF

/* This routine is meant to be used early during boot, when the
 * PCI bus numbers have not yet been assigned, and you need to
 * issue PCI config cycles to an OF device.
 * It could also be used to "fix" RTAS config cycles if you want
 * to set pci_assign_all_buses to 1 and still use RTAS for PCI
 * config cycles.
 */
struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node)
{
	if (!have_of)
		return NULL;
	while(node) {
		struct pci_controller *hose, *tmp;
		list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
			if (hose->dn == node)
				return hose;
		node = node->parent;
	}
	return NULL;
}

static ssize_t pci_show_devspec(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct pci_dev *pdev;
	struct device_node *np;

	pdev = to_pci_dev (dev);
	np = pci_device_to_OF_node(pdev);
	if (np == NULL || np->full_name == NULL)
		return 0;
	return sprintf(buf, "%s", np->full_name);
}
static DEVICE_ATTR(devspec, S_IRUGO, pci_show_devspec, NULL);
#endif /* CONFIG_PPC_OF */

/* Add sysfs properties */
int pcibios_add_platform_entries(struct pci_dev *pdev)
{
#ifdef CONFIG_PPC_OF
	return device_create_file(&pdev->dev, &dev_attr_devspec);
#else
	return 0;
#endif /* CONFIG_PPC_OF */

}

char __devinit *pcibios_setup(char *str)
{
	return str;
}

/*
 * Reads the interrupt pin to determine if interrupt is use by card.
 * If the interrupt is used, then gets the interrupt line from the
 * openfirmware and sets it in the pci_dev and pci_config line.
 */
int pci_read_irq_line(struct pci_dev *pci_dev)
{
	struct of_irq oirq;
	unsigned int virq;

	DBG("Try to map irq for %s...\n", pci_name(pci_dev));

#ifdef DEBUG
	memset(&oirq, 0xff, sizeof(oirq));
#endif
	/* Try to get a mapping from the device-tree */
	if (of_irq_map_pci(pci_dev, &oirq)) {
		u8 line, pin;

		/* If that fails, lets fallback to what is in the config
		 * space and map that through the default controller. We
		 * also set the type to level low since that's what PCI
		 * interrupts are. If your platform does differently, then
		 * either provide a proper interrupt tree or don't use this
		 * function.
		 */
		if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_PIN, &pin))
			return -1;
		if (pin == 0)
			return -1;
		if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_LINE, &line) ||
		    line == 0xff) {
			return -1;
		}
		DBG(" -> no map ! Using irq line %d from PCI config\n", line);

		virq = irq_create_mapping(NULL, line);
		if (virq != NO_IRQ)
			set_irq_type(virq, IRQ_TYPE_LEVEL_LOW);
	} else {
		DBG(" -> got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
		    oirq.size, oirq.specifier[0], oirq.specifier[1],
		    oirq.controller->full_name);

		virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
					     oirq.size);
	}
	if(virq == NO_IRQ) {
		DBG(" -> failed to map !\n");
		return -1;
	}

	DBG(" -> mapped to linux irq %d\n", virq);

	pci_dev->irq = virq;

	return 0;
}
EXPORT_SYMBOL(pci_read_irq_line);

/*
 * Platform support for /proc/bus/pci/X/Y mmap()s,
 * modelled on the sparc64 implementation by Dave Miller.
 *  -- paulus.
 */

/*
 * Adjust vm_pgoff of VMA such that it is the physical page offset
 * corresponding to the 32-bit pci bus offset for DEV requested by the user.
 *
 * Basically, the user finds the base address for his device which he wishes
 * to mmap.  They read the 32-bit value from the config space base register,
 * add whatever PAGE_SIZE multiple offset they wish, and feed this into the
 * offset parameter of mmap on /proc/bus/pci/XXX for that device.
 *
 * Returns negative error code on failure, zero on success.
 */
static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
					       resource_size_t *offset,
					       enum pci_mmap_state mmap_state)
{
	struct pci_controller *hose = pci_bus_to_host(dev->bus);
	unsigned long io_offset = 0;
	int i, res_bit;

	if (hose == 0)
		return NULL;		/* should never happen */

	/* If memory, add on the PCI bridge address offset */
	if (mmap_state == pci_mmap_mem) {
#if 0 /* See comment in pci_resource_to_user() for why this is disabled */
		*offset += hose->pci_mem_offset;
#endif
		res_bit = IORESOURCE_MEM;
	} else {
		io_offset = (unsigned long)hose->io_base_virt - _IO_BASE;
		*offset += io_offset;
		res_bit = IORESOURCE_IO;
	}

	/*
	 * Check that the offset requested corresponds to one of the
	 * resources of the device.
	 */
	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
		struct resource *rp = &dev->resource[i];
		int flags = rp->flags;

		/* treat ROM as memory (should be already) */
		if (i == PCI_ROM_RESOURCE)
			flags |= IORESOURCE_MEM;

		/* Active and same type? */
		if ((flags & res_bit) == 0)
			continue;

		/* In the range of this resource? */
		if (*offset < (rp->start & PAGE_MASK) || *offset > rp->end)
			continue;

		/* found it! construct the final physical address */
		if (mmap_state == pci_mmap_io)
			*offset += hose->io_base_phys - io_offset;
		return rp;
	}

	return NULL;
}

/*
 * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
 * device mapping.
 */
static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
				      pgprot_t protection,
				      enum pci_mmap_state mmap_state,
				      int write_combine)
{
	unsigned long prot = pgprot_val(protection);

	/* Write combine is always 0 on non-memory space mappings. On
	 * memory space, if the user didn't pass 1, we check for a
	 * "prefetchable" resource. This is a bit hackish, but we use
	 * this to workaround the inability of /sysfs to provide a write
	 * combine bit
	 */
	if (mmap_state != pci_mmap_mem)
		write_combine = 0;
	else if (write_combine == 0) {
		if (rp->flags & IORESOURCE_PREFETCH)
			write_combine = 1;
	}

	/* XXX would be nice to have a way to ask for write-through */
	prot |= _PAGE_NO_CACHE;
	if (write_combine)
		prot &= ~_PAGE_GUARDED;
	else
		prot |= _PAGE_GUARDED;

	return __pgprot(prot);
}

/*
 * This one is used by /dev/mem and fbdev who have no clue about the
 * PCI device, it tries to find the PCI device first and calls the
 * above routine
 */
pgprot_t pci_phys_mem_access_prot(struct file *file,
				  unsigned long pfn,
				  unsigned long size,
				  pgprot_t protection)
{
	struct pci_dev *pdev = NULL;
	struct resource *found = NULL;
	unsigned long prot = pgprot_val(protection);
	unsigned long offset = pfn << PAGE_SHIFT;
	int i;

	if (page_is_ram(pfn))
		return __pgprot(prot);

	prot |= _PAGE_NO_CACHE | _PAGE_GUARDED;

	for_each_pci_dev(pdev) {
		for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
			struct resource *rp = &pdev->resource[i];
			int flags = rp->flags;

			/* Active and same type? */
			if ((flags & IORESOURCE_MEM) == 0)
				continue;
			/* In the range of this resource? */
			if (offset < (rp->start & PAGE_MASK) ||
			    offset > rp->end)
				continue;
			found = rp;
			break;
		}
		if (found)
			break;
	}
	if (found) {
		if (found->flags & IORESOURCE_PREFETCH)
			prot &= ~_PAGE_GUARDED;
		pci_dev_put(pdev);
	}

	DBG("non-PCI map for %lx, prot: %lx\n", offset, prot);

	return __pgprot(prot);
}


/*
 * Perform the actual remap of the pages for a PCI device mapping, as
 * appropriate for this architecture.  The region in the process to map
 * is described by vm_start and vm_end members of VMA, the base physical
 * address is found in vm_pgoff.
 * The pci device structure is provided so that architectures may make mapping
 * decisions on a per-device or per-bus basis.
 *
 * Returns a negative error code on failure, zero on success.
 */
int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
			enum pci_mmap_state mmap_state, int write_combine)
{
	resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT;
	struct resource *rp;
	int ret;

	rp = __pci_mmap_make_offset(dev, &offset, mmap_state);
	if (rp == NULL)
		return -EINVAL;

	vma->vm_pgoff = offset >> PAGE_SHIFT;
	vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp,
						  vma->vm_page_prot,
						  mmap_state, write_combine);

	ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
			       vma->vm_end - vma->vm_start, vma->vm_page_prot);

	return ret;
}

void pci_resource_to_user(const struct pci_dev *dev, int bar,
			  const struct resource *rsrc,
			  resource_size_t *start, resource_size_t *end)
{
	struct pci_controller *hose = pci_bus_to_host(dev->bus);
	resource_size_t offset = 0;

	if (hose == NULL)
		return;

	if (rsrc->flags & IORESOURCE_IO)
		offset = (unsigned long)hose->io_base_virt - _IO_BASE;

	/* We pass a fully fixed up address to userland for MMIO instead of
	 * a BAR value because X is lame and expects to be able to use that
	 * to pass to /dev/mem !
	 *
	 * That means that we'll have potentially 64 bits values where some
	 * userland apps only expect 32 (like X itself since it thinks only
	 * Sparc has 64 bits MMIO) but if we don't do that, we break it on
	 * 32 bits CHRPs :-(
	 *
	 * Hopefully, the sysfs insterface is immune to that gunk. Once X
	 * has been fixed (and the fix spread enough), we can re-enable the
	 * 2 lines below and pass down a BAR value to userland. In that case
	 * we'll also have to re-enable the matching code in
	 * __pci_mmap_make_offset().
	 *
	 * BenH.
	 */
#if 0
	else if (rsrc->flags & IORESOURCE_MEM)
		offset = hose->pci_mem_offset;
#endif

	*start = rsrc->start - offset;
	*end = rsrc->end - offset;
}

/**
 * pci_process_bridge_OF_ranges - Parse PCI bridge resources from device tree
 * @hose: newly allocated pci_controller to be setup
 * @dev: device node of the host bridge
 * @primary: set if primary bus (32 bits only, soon to be deprecated)
 *
 * This function will parse the "ranges" property of a PCI host bridge device
 * node and setup the resource mapping of a pci controller based on its
 * content.
 *
 * Life would be boring if it wasn't for a few issues that we have to deal
 * with here:
 *
 *   - We can only cope with one IO space range and up to 3 Memory space
 *     ranges. However, some machines (thanks Apple !) tend to split their
 *     space into lots of small contiguous ranges. So we have to coalesce.
 *
 *   - We can only cope with all memory ranges having the same offset
 *     between CPU addresses and PCI addresses. Unfortunately, some bridges
 *     are setup for a large 1:1 mapping along with a small "window" which
 *     maps PCI address 0 to some arbitrary high address of the CPU space in
 *     order to give access to the ISA memory hole.
 *     The way out of here that I've chosen for now is to always set the
 *     offset based on the first resource found, then override it if we
 *     have a different offset and the previous was set by an ISA hole.
 *
 *   - Some busses have IO space not starting at 0, which causes trouble with
 *     the way we do our IO resource renumbering. The code somewhat deals with
 *     it for 64 bits but I would expect problems on 32 bits.
 *
 *   - Some 32 bits platforms such as 4xx can have physical space larger than
 *     32 bits so we need to use 64 bits values for the parsing
 */
void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose,
					    struct device_node *dev,
					    int primary)
{
	const u32 *ranges;
	int rlen;
	int pna = of_n_addr_cells(dev);
	int np = pna + 5;
	int memno = 0, isa_hole = -1;
	u32 pci_space;
	unsigned long long pci_addr, cpu_addr, pci_next, cpu_next, size;
	unsigned long long isa_mb = 0;
	struct resource *res;

	printk(KERN_INFO "PCI host bridge %s %s ranges:\n",
	       dev->full_name, primary ? "(primary)" : "");

	/* Get ranges property */
	ranges = of_get_property(dev, "ranges", &rlen);
	if (ranges == NULL)
		return;

	/* Parse it */
	while ((rlen -= np * 4) >= 0) {
		/* Read next ranges element */
		pci_space = ranges[0];
		pci_addr = of_read_number(ranges + 1, 2);
		cpu_addr = of_translate_address(dev, ranges + 3);
		size = of_read_number(ranges + pna + 3, 2);
		ranges += np;
		if (cpu_addr == OF_BAD_ADDR || size == 0)
			continue;

		/* Now consume following elements while they are contiguous */
		for (; rlen >= np * sizeof(u32);
		     ranges += np, rlen -= np * 4) {
			if (ranges[0] != pci_space)
				break;
			pci_next = of_read_number(ranges + 1, 2);
			cpu_next = of_translate_address(dev, ranges + 3);
			if (pci_next != pci_addr + size ||
			    cpu_next != cpu_addr + size)
				break;
			size += of_read_number(ranges + pna + 3, 2);
		}

		/* Act based on address space type */
		res = NULL;
		switch ((pci_space >> 24) & 0x3) {
		case 1:		/* PCI IO space */
			printk(KERN_INFO
			       "  IO 0x%016llx..0x%016llx -> 0x%016llx\n",
			       cpu_addr, cpu_addr + size - 1, pci_addr);

			/* We support only one IO range */
			if (hose->pci_io_size) {
				printk(KERN_INFO
				       " \\--> Skipped (too many) !\n");
				continue;
			}
#ifdef CONFIG_PPC32
			/* On 32 bits, limit I/O space to 16MB */
			if (size > 0x01000000)
				size = 0x01000000;

			/* 32 bits needs to map IOs here */
			hose->io_base_virt = ioremap(cpu_addr, size);

			/* Expect trouble if pci_addr is not 0 */
			if (primary)
				isa_io_base =
					(unsigned long)hose->io_base_virt;
#endif /* CONFIG_PPC32 */
			/* pci_io_size and io_base_phys always represent IO
			 * space starting at 0 so we factor in pci_addr
			 */
			hose->pci_io_size = pci_addr + size;
			hose->io_base_phys = cpu_addr - pci_addr;

			/* Build resource */
			res = &hose->io_resource;
			res->flags = IORESOURCE_IO;
			res->start = pci_addr;
			break;
		case 2:		/* PCI Memory space */
			printk(KERN_INFO
			       " MEM 0x%016llx..0x%016llx -> 0x%016llx %s\n",
			       cpu_addr, cpu_addr + size - 1, pci_addr,
			       (pci_space & 0x40000000) ? "Prefetch" : "");

			/* We support only 3 memory ranges */
			if (memno >= 3) {
				printk(KERN_INFO
				       " \\--> Skipped (too many) !\n");
				continue;
			}
			/* Handles ISA memory hole space here */
			if (pci_addr == 0) {
				isa_mb = cpu_addr;
				isa_hole = memno;
				if (primary || isa_mem_base == 0)
					isa_mem_base = cpu_addr;
			}

			/* We get the PCI/Mem offset from the first range or
			 * the, current one if the offset came from an ISA
			 * hole. If they don't match, bugger.
			 */
			if (memno == 0 ||
			    (isa_hole >= 0 && pci_addr != 0 &&
			     hose->pci_mem_offset == isa_mb))
				hose->pci_mem_offset = cpu_addr - pci_addr;
			else if (pci_addr != 0 &&
				 hose->pci_mem_offset != cpu_addr - pci_addr) {
				printk(KERN_INFO
				       " \\--> Skipped (offset mismatch) !\n");
				continue;
			}

			/* Build resource */
			res = &hose->mem_resources[memno++];
			res->flags = IORESOURCE_MEM;
			if (pci_space & 0x40000000)
				res->flags |= IORESOURCE_PREFETCH;
			res->start = cpu_addr;
			break;
		}
		if (res != NULL) {
			res->name = dev->full_name;
			res->end = res->start + size - 1;
			res->parent = NULL;
			res->sibling = NULL;
			res->child = NULL;
		}
	}

	/* Out of paranoia, let's put the ISA hole last if any */
	if (isa_hole >= 0 && memno > 0 && isa_hole != (memno-1)) {
		struct resource tmp = hose->mem_resources[isa_hole];
		hose->mem_resources[isa_hole] = hose->mem_resources[memno-1];
		hose->mem_resources[memno-1] = tmp;
	}
}