prom.c 42.3 KB
Newer Older
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
/*
 * Procedures for creating, accessing and interpreting the device tree.
 *
 * Paul Mackerras	August 1996.
 * Copyright (C) 1996-2005 Paul Mackerras.
 * 
 *  Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner.
 *    {engebret|bergner}@us.ibm.com 
 *
 *      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 <stdarg.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/threads.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/pci.h>
#include <linux/stringify.h>
#include <linux/delay.h>
#include <linux/initrd.h>
#include <linux/bitops.h>
#include <linux/module.h>
31
#include <linux/kexec.h>
32
#include <linux/debugfs.h>
33
#include <linux/irq.h>
34
#include <linux/lmb.h>
35 36 37 38 39 40 41

#include <asm/prom.h>
#include <asm/rtas.h>
#include <asm/page.h>
#include <asm/processor.h>
#include <asm/irq.h>
#include <asm/io.h>
42
#include <asm/kdump.h>
43 44 45 46 47 48 49 50 51 52
#include <asm/smp.h>
#include <asm/system.h>
#include <asm/mmu.h>
#include <asm/pgtable.h>
#include <asm/pci.h>
#include <asm/iommu.h>
#include <asm/btext.h>
#include <asm/sections.h>
#include <asm/machdep.h>
#include <asm/pSeries_reconfig.h>
53
#include <asm/pci-bridge.h>
54
#include <asm/phyp_dump.h>
55
#include <asm/kexec.h>
56
#include <mm/mmu_decl.h>
57 58 59 60 61 62 63 64 65 66 67 68

#ifdef DEBUG
#define DBG(fmt...) printk(KERN_ERR fmt)
#else
#define DBG(fmt...)
#endif


static int __initdata dt_root_addr_cells;
static int __initdata dt_root_size_cells;

#ifdef CONFIG_PPC64
69
int __initdata iommu_is_off;
70
int __initdata iommu_force_on;
71
unsigned long tce_alloc_start, tce_alloc_end;
72 73 74 75 76 77 78 79 80 81
#endif

typedef u32 cell_t;

#if 0
static struct boot_param_header *initial_boot_params __initdata;
#else
struct boot_param_header *initial_boot_params;
#endif

82
extern struct device_node *allnodes;	/* temporary while merging */
83

S
Stephen Rothwell 已提交
84
extern rwlock_t devtree_lock;	/* temporary while merging */
85 86 87 88 89 90 91 92 93 94 95 96 97 98 99

/* export that to outside world */
struct device_node *of_chosen;

static inline char *find_flat_dt_string(u32 offset)
{
	return ((char *)initial_boot_params) +
		initial_boot_params->off_dt_strings + offset;
}

/**
 * This function is used to scan the flattened device-tree, it is
 * used to extract the memory informations at boot before we can
 * unflatten the tree
 */
100 101 102 103
int __init of_scan_flat_dt(int (*it)(unsigned long node,
				     const char *uname, int depth,
				     void *data),
			   void *data)
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
{
	unsigned long p = ((unsigned long)initial_boot_params) +
		initial_boot_params->off_dt_struct;
	int rc = 0;
	int depth = -1;

	do {
		u32 tag = *((u32 *)p);
		char *pathp;
		
		p += 4;
		if (tag == OF_DT_END_NODE) {
			depth --;
			continue;
		}
		if (tag == OF_DT_NOP)
			continue;
		if (tag == OF_DT_END)
			break;
		if (tag == OF_DT_PROP) {
			u32 sz = *((u32 *)p);
			p += 8;
			if (initial_boot_params->version < 0x10)
				p = _ALIGN(p, sz >= 8 ? 8 : 4);
			p += sz;
			p = _ALIGN(p, 4);
			continue;
		}
		if (tag != OF_DT_BEGIN_NODE) {
			printk(KERN_WARNING "Invalid tag %x scanning flattened"
			       " device tree !\n", tag);
			return -EINVAL;
		}
		depth++;
		pathp = (char *)p;
		p = _ALIGN(p + strlen(pathp) + 1, 4);
		if ((*pathp) == '/') {
			char *lp, *np;
			for (lp = NULL, np = pathp; *np; np++)
				if ((*np) == '/')
					lp = np+1;
			if (lp != NULL)
				pathp = lp;
		}
		rc = it(p, pathp, depth, data);
		if (rc != 0)
			break;		
	} while(1);

	return rc;
}

156 157 158 159 160 161 162 163 164 165 166 167
unsigned long __init of_get_flat_dt_root(void)
{
	unsigned long p = ((unsigned long)initial_boot_params) +
		initial_boot_params->off_dt_struct;

	while(*((u32 *)p) == OF_DT_NOP)
		p += 4;
	BUG_ON (*((u32 *)p) != OF_DT_BEGIN_NODE);
	p += 4;
	return _ALIGN(p + strlen((char *)p) + 1, 4);
}

168 169 170 171
/**
 * This  function can be used within scan_flattened_dt callback to get
 * access to properties
 */
172 173
void* __init of_get_flat_dt_prop(unsigned long node, const char *name,
				 unsigned long *size)
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
{
	unsigned long p = node;

	do {
		u32 tag = *((u32 *)p);
		u32 sz, noff;
		const char *nstr;

		p += 4;
		if (tag == OF_DT_NOP)
			continue;
		if (tag != OF_DT_PROP)
			return NULL;

		sz = *((u32 *)p);
		noff = *((u32 *)(p + 4));
		p += 8;
		if (initial_boot_params->version < 0x10)
			p = _ALIGN(p, sz >= 8 ? 8 : 4);

		nstr = find_flat_dt_string(noff);
		if (nstr == NULL) {
			printk(KERN_WARNING "Can't find property index"
			       " name !\n");
			return NULL;
		}
		if (strcmp(name, nstr) == 0) {
			if (size)
				*size = sz;
			return (void *)p;
		}
		p += sz;
		p = _ALIGN(p, 4);
	} while(1);
}

210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228
int __init of_flat_dt_is_compatible(unsigned long node, const char *compat)
{
	const char* cp;
	unsigned long cplen, l;

	cp = of_get_flat_dt_prop(node, "compatible", &cplen);
	if (cp == NULL)
		return 0;
	while (cplen > 0) {
		if (strncasecmp(cp, compat, strlen(compat)) == 0)
			return 1;
		l = strlen(cp) + 1;
		cp += l;
		cplen -= l;
	}

	return 0;
}

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
static void *__init unflatten_dt_alloc(unsigned long *mem, unsigned long size,
				       unsigned long align)
{
	void *res;

	*mem = _ALIGN(*mem, align);
	res = (void *)*mem;
	*mem += size;

	return res;
}

static unsigned long __init unflatten_dt_node(unsigned long mem,
					      unsigned long *p,
					      struct device_node *dad,
					      struct device_node ***allnextpp,
					      unsigned long fpsize)
{
	struct device_node *np;
	struct property *pp, **prev_pp = NULL;
	char *pathp;
	u32 tag;
	unsigned int l, allocl;
	int has_name = 0;
	int new_format = 0;

	tag = *((u32 *)(*p));
	if (tag != OF_DT_BEGIN_NODE) {
		printk("Weird tag at start of node: %x\n", tag);
		return mem;
	}
	*p += 4;
	pathp = (char *)*p;
	l = allocl = strlen(pathp) + 1;
	*p = _ALIGN(*p + l, 4);

	/* version 0x10 has a more compact unit name here instead of the full
	 * path. we accumulate the full path size using "fpsize", we'll rebuild
	 * it later. We detect this because the first character of the name is
	 * not '/'.
	 */
	if ((*pathp) != '/') {
		new_format = 1;
		if (fpsize == 0) {
			/* root node: special case. fpsize accounts for path
			 * plus terminating zero. root node only has '/', so
			 * fpsize should be 2, but we want to avoid the first
			 * level nodes to have two '/' so we use fpsize 1 here
			 */
			fpsize = 1;
			allocl = 2;
		} else {
			/* account for '/' and path size minus terminal 0
			 * already in 'l'
			 */
			fpsize += l;
			allocl = fpsize;
		}
	}


	np = unflatten_dt_alloc(&mem, sizeof(struct device_node) + allocl,
				__alignof__(struct device_node));
	if (allnextpp) {
		memset(np, 0, sizeof(*np));
		np->full_name = ((char*)np) + sizeof(struct device_node);
		if (new_format) {
			char *p = np->full_name;
			/* rebuild full path for new format */
			if (dad && dad->parent) {
				strcpy(p, dad->full_name);
#ifdef DEBUG
				if ((strlen(p) + l + 1) != allocl) {
					DBG("%s: p: %d, l: %d, a: %d\n",
303
					    pathp, (int)strlen(p), l, allocl);
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
				}
#endif
				p += strlen(p);
			}
			*(p++) = '/';
			memcpy(p, pathp, l);
		} else
			memcpy(np->full_name, pathp, l);
		prev_pp = &np->properties;
		**allnextpp = np;
		*allnextpp = &np->allnext;
		if (dad != NULL) {
			np->parent = dad;
			/* we temporarily use the next field as `last_child'*/
			if (dad->next == 0)
				dad->child = np;
			else
				dad->next->sibling = np;
			dad->next = np;
		}
		kref_init(&np->kref);
	}
	while(1) {
		u32 sz, noff;
		char *pname;

		tag = *((u32 *)(*p));
		if (tag == OF_DT_NOP) {
			*p += 4;
			continue;
		}
		if (tag != OF_DT_PROP)
			break;
		*p += 4;
		sz = *((u32 *)(*p));
		noff = *((u32 *)((*p) + 4));
		*p += 8;
		if (initial_boot_params->version < 0x10)
			*p = _ALIGN(*p, sz >= 8 ? 8 : 4);

		pname = find_flat_dt_string(noff);
		if (pname == NULL) {
			printk("Can't find property name in list !\n");
			break;
		}
		if (strcmp(pname, "name") == 0)
			has_name = 1;
		l = strlen(pname) + 1;
		pp = unflatten_dt_alloc(&mem, sizeof(struct property),
					__alignof__(struct property));
		if (allnextpp) {
			if (strcmp(pname, "linux,phandle") == 0) {
				np->node = *((u32 *)*p);
				if (np->linux_phandle == 0)
					np->linux_phandle = np->node;
			}
			if (strcmp(pname, "ibm,phandle") == 0)
				np->linux_phandle = *((u32 *)*p);
			pp->name = pname;
			pp->length = sz;
			pp->value = (void *)*p;
			*prev_pp = pp;
			prev_pp = &pp->next;
		}
		*p = _ALIGN((*p) + sz, 4);
	}
	/* with version 0x10 we may not have the name property, recreate
	 * it here from the unit name if absent
	 */
	if (!has_name) {
		char *p = pathp, *ps = pathp, *pa = NULL;
		int sz;

		while (*p) {
			if ((*p) == '@')
				pa = p;
			if ((*p) == '/')
				ps = p + 1;
			p++;
		}
		if (pa < ps)
			pa = p;
		sz = (pa - ps) + 1;
		pp = unflatten_dt_alloc(&mem, sizeof(struct property) + sz,
					__alignof__(struct property));
		if (allnextpp) {
			pp->name = "name";
			pp->length = sz;
392
			pp->value = pp + 1;
393 394 395 396
			*prev_pp = pp;
			prev_pp = &pp->next;
			memcpy(pp->value, ps, sz - 1);
			((char *)pp->value)[sz - 1] = 0;
397 398
			DBG("fixed up name for %s -> %s\n", pathp,
				(char *)pp->value);
399 400 401 402
		}
	}
	if (allnextpp) {
		*prev_pp = NULL;
403 404
		np->name = of_get_property(np, "name", NULL);
		np->type = of_get_property(np, "device_type", NULL);
405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422

		if (!np->name)
			np->name = "<NULL>";
		if (!np->type)
			np->type = "<NULL>";
	}
	while (tag == OF_DT_BEGIN_NODE) {
		mem = unflatten_dt_node(mem, p, np, allnextpp, fpsize);
		tag = *((u32 *)(*p));
	}
	if (tag != OF_DT_END_NODE) {
		printk("Weird tag at end of node: %x\n", tag);
		return mem;
	}
	*p += 4;
	return mem;
}

423 424 425 426 427 428 429 430 431 432 433 434
static int __init early_parse_mem(char *p)
{
	if (!p)
		return 1;

	memory_limit = PAGE_ALIGN(memparse(p, &p));
	DBG("memory limit = 0x%lx\n", memory_limit);

	return 0;
}
early_param("mem", early_parse_mem);

435 436 437 438 439
/**
 * move_device_tree - move tree to an unused area, if needed.
 *
 * The device tree may be allocated beyond our memory limit, or inside the
 * crash kernel region for kdump. If so, move it out of the way.
440
 */
441
static void __init move_device_tree(void)
442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460
{
	unsigned long start, size;
	void *p;

	DBG("-> move_device_tree\n");

	start = __pa(initial_boot_params);
	size = initial_boot_params->totalsize;

	if ((memory_limit && (start + size) > memory_limit) ||
			overlaps_crashkernel(start, size)) {
		p = __va(lmb_alloc_base(size, PAGE_SIZE, lmb.rmo_size));
		memcpy(p, initial_boot_params, size);
		initial_boot_params = (struct boot_param_header *)p;
		DBG("Moved device tree to 0x%p\n", p);
	}

	DBG("<- move_device_tree\n");
}
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

/**
 * unflattens the device-tree passed by the firmware, creating the
 * tree of struct device_node. It also fills the "name" and "type"
 * pointers of the nodes so the normal device-tree walking functions
 * can be used (this used to be done by finish_device_tree)
 */
void __init unflatten_device_tree(void)
{
	unsigned long start, mem, size;
	struct device_node **allnextp = &allnodes;

	DBG(" -> unflatten_device_tree()\n");

	/* First pass, scan for size */
	start = ((unsigned long)initial_boot_params) +
		initial_boot_params->off_dt_struct;
	size = unflatten_dt_node(0, &start, NULL, NULL, 0);
	size = (size | 3) + 1;

	DBG("  size is %lx, allocating...\n", size);

	/* Allocate memory for the expanded device tree */
	mem = lmb_alloc(size + 4, __alignof__(struct device_node));
	mem = (unsigned long) __va(mem);

	((u32 *)mem)[size / 4] = 0xdeadbeef;

	DBG("  unflattening %lx...\n", mem);

	/* Second pass, do actual unflattening */
	start = ((unsigned long)initial_boot_params) +
		initial_boot_params->off_dt_struct;
	unflatten_dt_node(mem, &start, NULL, &allnextp, 0);
	if (*((u32 *)start) != OF_DT_END)
		printk(KERN_WARNING "Weird tag at end of tree: %08x\n", *((u32 *)start));
	if (((u32 *)mem)[size / 4] != 0xdeadbeef)
		printk(KERN_WARNING "End of tree marker overwritten: %08x\n",
		       ((u32 *)mem)[size / 4] );
	*allnextp = NULL;

	/* Get pointer to OF "/chosen" node for use everywhere */
	of_chosen = of_find_node_by_path("/chosen");
P
Paul Mackerras 已提交
504 505
	if (of_chosen == NULL)
		of_chosen = of_find_node_by_path("/chosen@0");
506 507 508 509

	DBG(" <- unflatten_device_tree()\n");
}

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
/*
 * ibm,pa-features is a per-cpu property that contains a string of
 * attribute descriptors, each of which has a 2 byte header plus up
 * to 254 bytes worth of processor attribute bits.  First header
 * byte specifies the number of bytes following the header.
 * Second header byte is an "attribute-specifier" type, of which
 * zero is the only currently-defined value.
 * Implementation:  Pass in the byte and bit offset for the feature
 * that we are interested in.  The function will return -1 if the
 * pa-features property is missing, or a 1/0 to indicate if the feature
 * is supported/not supported.  Note that the bit numbers are
 * big-endian to match the definition in PAPR.
 */
static struct ibm_pa_feature {
	unsigned long	cpu_features;	/* CPU_FTR_xxx bit */
	unsigned int	cpu_user_ftrs;	/* PPC_FEATURE_xxx bit */
	unsigned char	pabyte;		/* byte number in ibm,pa-features */
	unsigned char	pabit;		/* bit number (big-endian) */
	unsigned char	invert;		/* if 1, pa bit set => clear feature */
} ibm_pa_features[] __initdata = {
	{0, PPC_FEATURE_HAS_MMU,	0, 0, 0},
	{0, PPC_FEATURE_HAS_FPU,	0, 1, 0},
	{CPU_FTR_SLB, 0,		0, 2, 0},
	{CPU_FTR_CTRL, 0,		0, 3, 0},
	{CPU_FTR_NOEXECUTE, 0,		0, 6, 0},
	{CPU_FTR_NODSISRALIGN, 0,	1, 1, 1},
	{CPU_FTR_CI_LARGE_PAGE, 0,	1, 2, 0},
537
	{CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0},
538 539
};

540 541 542 543
static void __init scan_features(unsigned long node, unsigned char *ftrs,
				 unsigned long tablelen,
				 struct ibm_pa_feature *fp,
				 unsigned long ft_size)
544
{
545
	unsigned long i, len, bit;
546 547 548 549 550

	/* find descriptor with type == 0 */
	for (;;) {
		if (tablelen < 3)
			return;
551
		len = 2 + ftrs[0];
552 553
		if (tablelen < len)
			return;		/* descriptor 0 not found */
554
		if (ftrs[1] == 0)
555 556
			break;
		tablelen -= len;
557
		ftrs += len;
558 559 560
	}

	/* loop over bits we know about */
561 562
	for (i = 0; i < ft_size; ++i, ++fp) {
		if (fp->pabyte >= ftrs[0])
563
			continue;
564
		bit = (ftrs[2 + fp->pabyte] >> (7 - fp->pabit)) & 1;
565 566 567 568 569 570 571 572 573 574
		if (bit ^ fp->invert) {
			cur_cpu_spec->cpu_features |= fp->cpu_features;
			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
		} else {
			cur_cpu_spec->cpu_features &= ~fp->cpu_features;
			cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs;
		}
	}
}

575 576 577 578 579 580 581 582 583 584 585 586 587
static void __init check_cpu_pa_features(unsigned long node)
{
	unsigned char *pa_ftrs;
	unsigned long tablelen;

	pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen);
	if (pa_ftrs == NULL)
		return;

	scan_features(node, pa_ftrs, tablelen,
		      ibm_pa_features, ARRAY_SIZE(ibm_pa_features));
}

588 589 590 591 592
#ifdef CONFIG_PPC64
static void __init check_cpu_slb_size(unsigned long node)
{
	u32 *slb_size_ptr;

593 594 595 596 597
	slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL);
	if (slb_size_ptr != NULL) {
		mmu_slb_size = *slb_size_ptr;
		return;
	}
598 599 600 601 602 603 604 605 606
	slb_size_ptr = of_get_flat_dt_prop(node, "ibm,slb-size", NULL);
	if (slb_size_ptr != NULL) {
		mmu_slb_size = *slb_size_ptr;
	}
}
#else
#define check_cpu_slb_size(node) do { } while(0)
#endif

607 608 609 610 611 612 613 614 615 616
static struct feature_property {
	const char *name;
	u32 min_value;
	unsigned long cpu_feature;
	unsigned long cpu_user_ftr;
} feature_properties[] __initdata = {
#ifdef CONFIG_ALTIVEC
	{"altivec", 0, CPU_FTR_ALTIVEC, PPC_FEATURE_HAS_ALTIVEC},
	{"ibm,vmx", 1, CPU_FTR_ALTIVEC, PPC_FEATURE_HAS_ALTIVEC},
#endif /* CONFIG_ALTIVEC */
M
Michael Neuling 已提交
617 618 619 620
#ifdef CONFIG_VSX
	/* Yes, this _really_ is ibm,vmx == 2 to enable VSX */
	{"ibm,vmx", 2, CPU_FTR_VSX, PPC_FEATURE_HAS_VSX},
#endif /* CONFIG_VSX */
621 622 623 624 625 626 627
#ifdef CONFIG_PPC64
	{"ibm,dfp", 1, 0, PPC_FEATURE_HAS_DFP},
	{"ibm,purr", 1, CPU_FTR_PURR, 0},
	{"ibm,spurr", 1, CPU_FTR_SPURR, 0},
#endif /* CONFIG_PPC64 */
};

628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650
#if defined(CONFIG_44x) && defined(CONFIG_PPC_FPU)
static inline void identical_pvr_fixup(unsigned long node)
{
	unsigned int pvr;
	char *model = of_get_flat_dt_prop(node, "model", NULL);

	/*
	 * Since 440GR(x)/440EP(x) processors have the same pvr,
	 * we check the node path and set bit 28 in the cur_cpu_spec
	 * pvr for EP(x) processor version. This bit is always 0 in
	 * the "real" pvr. Then we call identify_cpu again with
	 * the new logical pvr to enable FPU support.
	 */
	if (model && strstr(model, "440EP")) {
		pvr = cur_cpu_spec->pvr_value | 0x8;
		identify_cpu(0, pvr);
		DBG("Using logical pvr %x for %s\n", pvr, model);
	}
}
#else
#define identical_pvr_fixup(node) do { } while(0)
#endif

651 652 653 654 655 656 657 658 659 660 661 662 663 664 665
static void __init check_cpu_feature_properties(unsigned long node)
{
	unsigned long i;
	struct feature_property *fp = feature_properties;
	const u32 *prop;

	for (i = 0; i < ARRAY_SIZE(feature_properties); ++i, ++fp) {
		prop = of_get_flat_dt_prop(node, fp->name, NULL);
		if (prop && *prop >= fp->min_value) {
			cur_cpu_spec->cpu_features |= fp->cpu_feature;
			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftr;
		}
	}
}

666
static int __init early_init_dt_scan_cpus(unsigned long node,
667 668
					  const char *uname, int depth,
					  void *data)
669
{
670 671
	static int logical_cpuid = 0;
	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
672 673
	const u32 *prop;
	const u32 *intserv;
674 675 676
	int i, nthreads;
	unsigned long len;
	int found = 0;
677 678 679 680 681

	/* We are scanning "cpu" nodes only */
	if (type == NULL || strcmp(type, "cpu") != 0)
		return 0;

682 683 684 685
	/* Get physical cpuid */
	intserv = of_get_flat_dt_prop(node, "ibm,ppc-interrupt-server#s", &len);
	if (intserv) {
		nthreads = len / sizeof(int);
686
	} else {
687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712
		intserv = of_get_flat_dt_prop(node, "reg", NULL);
		nthreads = 1;
	}

	/*
	 * Now see if any of these threads match our boot cpu.
	 * NOTE: This must match the parsing done in smp_setup_cpu_maps.
	 */
	for (i = 0; i < nthreads; i++) {
		/*
		 * version 2 of the kexec param format adds the phys cpuid of
		 * booted proc.
		 */
		if (initial_boot_params && initial_boot_params->version >= 2) {
			if (intserv[i] ==
					initial_boot_params->boot_cpuid_phys) {
				found = 1;
				break;
			}
		} else {
			/*
			 * Check if it's the boot-cpu, set it's hw index now,
			 * unfortunately this format did not support booting
			 * off secondary threads.
			 */
			if (of_get_flat_dt_prop(node,
713
					"linux,boot-cpu", NULL) != NULL) {
714 715 716
				found = 1;
				break;
			}
717
		}
718 719 720 721 722 723 724 725 726 727 728 729

#ifdef CONFIG_SMP
		/* logical cpu id is always 0 on UP kernels */
		logical_cpuid++;
#endif
	}

	if (found) {
		DBG("boot cpu: logical %d physical %d\n", logical_cpuid,
			intserv[i]);
		boot_cpuid = logical_cpuid;
		set_hard_smp_processor_id(boot_cpuid, intserv[i]);
730

731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747
		/*
		 * PAPR defines "logical" PVR values for cpus that
		 * meet various levels of the architecture:
		 * 0x0f000001	Architecture version 2.04
		 * 0x0f000002	Architecture version 2.05
		 * If the cpu-version property in the cpu node contains
		 * such a value, we call identify_cpu again with the
		 * logical PVR value in order to use the cpu feature
		 * bits appropriate for the architecture level.
		 *
		 * A POWER6 partition in "POWER6 architected" mode
		 * uses the 0x0f000002 PVR value; in POWER5+ mode
		 * it uses 0x0f000001.
		 */
		prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
		if (prop && (*prop & 0xff000000) == 0x0f000000)
			identify_cpu(0, *prop);
748 749

		identical_pvr_fixup(node);
750 751
	}

752
	check_cpu_feature_properties(node);
753
	check_cpu_pa_features(node);
754
	check_cpu_slb_size(node);
755

756
#ifdef CONFIG_PPC_PSERIES
757
	if (nthreads > 1)
758
		cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
759 760
	else
		cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
761 762 763 764 765
#endif

	return 0;
}

766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795
#ifdef CONFIG_BLK_DEV_INITRD
static void __init early_init_dt_check_for_initrd(unsigned long node)
{
	unsigned long l;
	u32 *prop;

	DBG("Looking for initrd properties... ");

	prop = of_get_flat_dt_prop(node, "linux,initrd-start", &l);
	if (prop) {
		initrd_start = (unsigned long)__va(of_read_ulong(prop, l/4));

		prop = of_get_flat_dt_prop(node, "linux,initrd-end", &l);
		if (prop) {
			initrd_end = (unsigned long)
					__va(of_read_ulong(prop, l/4));
			initrd_below_start_ok = 1;
		} else {
			initrd_start = 0;
		}
	}

	DBG("initrd_start=0x%lx  initrd_end=0x%lx\n", initrd_start, initrd_end);
}
#else
static inline void early_init_dt_check_for_initrd(unsigned long node)
{
}
#endif /* CONFIG_BLK_DEV_INITRD */

796 797 798 799
static int __init early_init_dt_scan_chosen(unsigned long node,
					    const char *uname, int depth, void *data)
{
	unsigned long *lprop;
800 801
	unsigned long l;
	char *p;
802 803 804

	DBG("search \"chosen\", depth: %d, uname: %s\n", depth, uname);

P
Paul Mackerras 已提交
805 806
	if (depth != 1 ||
	    (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0))
807 808 809 810
		return 0;

#ifdef CONFIG_PPC64
	/* check if iommu is forced on or off */
811
	if (of_get_flat_dt_prop(node, "linux,iommu-off", NULL) != NULL)
812
		iommu_is_off = 1;
813
	if (of_get_flat_dt_prop(node, "linux,iommu-force-on", NULL) != NULL)
814 815 816
		iommu_force_on = 1;
#endif

817
	/* mem=x on the command line is the preferred mechanism */
818
 	lprop = of_get_flat_dt_prop(node, "linux,memory-limit", NULL);
819 820 821 822
 	if (lprop)
 		memory_limit = *lprop;

#ifdef CONFIG_PPC64
823
 	lprop = of_get_flat_dt_prop(node, "linux,tce-alloc-start", NULL);
824 825
 	if (lprop)
 		tce_alloc_start = *lprop;
826
 	lprop = of_get_flat_dt_prop(node, "linux,tce-alloc-end", NULL);
827 828 829 830
 	if (lprop)
 		tce_alloc_end = *lprop;
#endif

831
#ifdef CONFIG_KEXEC
832
	lprop = of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL);
833 834
	if (lprop)
		crashk_res.start = *lprop;
835

836
	lprop = of_get_flat_dt_prop(node, "linux,crashkernel-size", NULL);
837 838
	if (lprop)
		crashk_res.end = crashk_res.start + *lprop - 1;
839 840
#endif

841
	early_init_dt_check_for_initrd(node);
842

843 844 845 846 847 848
	/* Retreive command line */
 	p = of_get_flat_dt_prop(node, "bootargs", &l);
	if (p != NULL && l > 0)
		strlcpy(cmd_line, p, min((int)l, COMMAND_LINE_SIZE));

#ifdef CONFIG_CMDLINE
849
	if (p == NULL || l == 0 || (l == 1 && (*p) == 0))
850 851 852 853 854
		strlcpy(cmd_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
#endif /* CONFIG_CMDLINE */

	DBG("Command line is: %s\n", cmd_line);

855 856 857 858 859 860 861 862 863 864 865 866
	/* break now */
	return 1;
}

static int __init early_init_dt_scan_root(unsigned long node,
					  const char *uname, int depth, void *data)
{
	u32 *prop;

	if (depth != 0)
		return 0;

867
	prop = of_get_flat_dt_prop(node, "#size-cells", NULL);
868 869 870
	dt_root_size_cells = (prop == NULL) ? 1 : *prop;
	DBG("dt_root_size_cells = %x\n", dt_root_size_cells);

871
	prop = of_get_flat_dt_prop(node, "#address-cells", NULL);
872 873 874 875 876 877 878
	dt_root_addr_cells = (prop == NULL) ? 2 : *prop;
	DBG("dt_root_addr_cells = %x\n", dt_root_addr_cells);
	
	/* break now */
	return 1;
}

879
static u64 __init dt_mem_next_cell(int s, cell_t **cellp)
880 881 882
{
	cell_t *p = *cellp;

883
	*cellp = p + s;
884
	return of_read_number(p, s);
885 886
}

887 888 889 890 891 892 893 894 895
#ifdef CONFIG_PPC_PSERIES
/*
 * Interpret the ibm,dynamic-memory property in the
 * /ibm,dynamic-reconfiguration-memory node.
 * This contains a list of memory blocks along with NUMA affinity
 * information.
 */
static int __init early_init_dt_scan_drconf_memory(unsigned long node)
{
896
	cell_t *dm, *ls, *usm;
897 898
	unsigned long l, n, flags;
	u64 base, size, lmb_size;
899
	unsigned int is_kexec_kdump = 0, rngs;
900

901
	ls = of_get_flat_dt_prop(node, "ibm,lmb-size", &l);
902 903 904 905
	if (ls == NULL || l < dt_root_size_cells * sizeof(cell_t))
		return 0;
	lmb_size = dt_mem_next_cell(dt_root_size_cells, &ls);

906
	dm = of_get_flat_dt_prop(node, "ibm,dynamic-memory", &l);
907 908 909 910 911 912 913
	if (dm == NULL || l < sizeof(cell_t))
		return 0;

	n = *dm++;	/* number of entries */
	if (l < (n * (dt_root_addr_cells + 4) + 1) * sizeof(cell_t))
		return 0;

914
	/* check if this is a kexec/kdump kernel. */
915
	usm = of_get_flat_dt_prop(node, "linux,drconf-usable-memory",
916 917 918 919
						 &l);
	if (usm != NULL)
		is_kexec_kdump = 1;

920 921 922 923 924 925 926 927 928 929
	for (; n != 0; --n) {
		base = dt_mem_next_cell(dt_root_addr_cells, &dm);
		flags = dm[3];
		/* skip DRC index, pad, assoc. list index, flags */
		dm += 4;
		/* skip this block if the reserved bit is set in flags (0x80)
		   or if the block is not assigned to this partition (0x8) */
		if ((flags & 0x80) || !(flags & 0x8))
			continue;
		size = lmb_size;
930 931 932 933 934 935 936 937 938 939 940
		rngs = 1;
		if (is_kexec_kdump) {
			/*
			 * For each lmb in ibm,dynamic-memory, a corresponding
			 * entry in linux,drconf-usable-memory property contains
			 * a counter 'p' followed by 'p' (base, size) duple.
			 * Now read the counter from
			 * linux,drconf-usable-memory property
			 */
			rngs = dt_mem_next_cell(dt_root_size_cells, &usm);
			if (!rngs) /* there are no (base, size) duple */
941 942
				continue;
		}
943 944 945 946 947 948 949 950 951 952 953 954 955 956 957
		do {
			if (is_kexec_kdump) {
				base = dt_mem_next_cell(dt_root_addr_cells,
							 &usm);
				size = dt_mem_next_cell(dt_root_size_cells,
							 &usm);
			}
			if (iommu_is_off) {
				if (base >= 0x80000000ul)
					continue;
				if ((base + size) > 0x80000000ul)
					size = 0x80000000ul - base;
			}
			lmb_add(base, size);
		} while (--rngs);
958 959 960 961 962 963 964
	}
	lmb_dump_all();
	return 0;
}
#else
#define early_init_dt_scan_drconf_memory(node)	0
#endif /* CONFIG_PPC_PSERIES */
965 966 967 968

static int __init early_init_dt_scan_memory(unsigned long node,
					    const char *uname, int depth, void *data)
{
969
	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
970 971 972
	cell_t *reg, *endp;
	unsigned long l;

973 974 975 976 977
	/* Look for the ibm,dynamic-reconfiguration-memory node */
	if (depth == 1 &&
	    strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0)
		return early_init_dt_scan_drconf_memory(node);

978
	/* We are scanning "memory" nodes only */
979 980 981 982 983 984 985 986
	if (type == NULL) {
		/*
		 * The longtrail doesn't have a device_type on the
		 * /memory node, so look for the node called /memory@0.
		 */
		if (depth != 1 || strcmp(uname, "memory@0") != 0)
			return 0;
	} else if (strcmp(type, "memory") != 0)
987 988
		return 0;

989
	reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l);
990
	if (reg == NULL)
991
		reg = of_get_flat_dt_prop(node, "reg", &l);
992 993 994 995 996
	if (reg == NULL)
		return 0;

	endp = reg + (l / sizeof(cell_t));

997
	DBG("memory scan node %s, reg size %ld, data: %x %x %x %x,\n",
998 999 1000
	    uname, l, reg[0], reg[1], reg[2], reg[3]);

	while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) {
1001
		u64 base, size;
1002 1003 1004 1005 1006 1007

		base = dt_mem_next_cell(dt_root_addr_cells, &reg);
		size = dt_mem_next_cell(dt_root_size_cells, &reg);

		if (size == 0)
			continue;
1008 1009
		DBG(" - %llx ,  %llx\n", (unsigned long long)base,
		    (unsigned long long)size);
1010 1011 1012 1013 1014 1015 1016 1017 1018
#ifdef CONFIG_PPC64
		if (iommu_is_off) {
			if (base >= 0x80000000ul)
				continue;
			if ((base + size) > 0x80000000ul)
				size = 0x80000000ul - base;
		}
#endif
		lmb_add(base, size);
1019 1020

		memstart_addr = min((u64)memstart_addr, base);
1021
	}
1022

1023 1024 1025 1026 1027
	return 0;
}

static void __init early_reserve_mem(void)
{
1028 1029
	u64 base, size;
	u64 *reserve_map;
1030 1031
	unsigned long self_base;
	unsigned long self_size;
1032

1033
	reserve_map = (u64 *)(((unsigned long)initial_boot_params) +
1034
					initial_boot_params->off_mem_rsvmap);
1035 1036

	/* before we do anything, lets reserve the dt blob */
1037 1038 1039
	self_base = __pa((unsigned long)initial_boot_params);
	self_size = initial_boot_params->totalsize;
	lmb_reserve(self_base, self_size);
1040

1041 1042 1043 1044 1045 1046
#ifdef CONFIG_BLK_DEV_INITRD
	/* then reserve the initrd, if any */
	if (initrd_start && (initrd_end > initrd_start))
		lmb_reserve(__pa(initrd_start), initrd_end - initrd_start);
#endif /* CONFIG_BLK_DEV_INITRD */

1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060
#ifdef CONFIG_PPC32
	/* 
	 * Handle the case where we might be booting from an old kexec
	 * image that setup the mem_rsvmap as pairs of 32-bit values
	 */
	if (*reserve_map > 0xffffffffull) {
		u32 base_32, size_32;
		u32 *reserve_map_32 = (u32 *)reserve_map;

		while (1) {
			base_32 = *(reserve_map_32++);
			size_32 = *(reserve_map_32++);
			if (size_32 == 0)
				break;
1061 1062 1063
			/* skip if the reservation is for the blob */
			if (base_32 == self_base && size_32 == self_size)
				continue;
1064
			DBG("reserving: %x -> %x\n", base_32, size_32);
1065 1066 1067 1068 1069
			lmb_reserve(base_32, size_32);
		}
		return;
	}
#endif
1070 1071 1072 1073 1074
	while (1) {
		base = *(reserve_map++);
		size = *(reserve_map++);
		if (size == 0)
			break;
1075
		DBG("reserving: %llx -> %llx\n", base, size);
1076 1077 1078 1079 1080 1081 1082 1083 1084
		lmb_reserve(base, size);
	}

#if 0
	DBG("memory reserved, lmbs :\n");
      	lmb_dump_all();
#endif
}

1085
#ifdef CONFIG_PHYP_DUMP
1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112
/**
 * phyp_dump_calculate_reserve_size() - reserve variable boot area 5% or arg
 *
 * Function to find the largest size we need to reserve
 * during early boot process.
 *
 * It either looks for boot param and returns that OR
 * returns larger of 256 or 5% rounded down to multiples of 256MB.
 *
 */
static inline unsigned long phyp_dump_calculate_reserve_size(void)
{
	unsigned long tmp;

	if (phyp_dump_info->reserve_bootvar)
		return phyp_dump_info->reserve_bootvar;

	/* divide by 20 to get 5% of value */
	tmp = lmb_end_of_DRAM();
	do_div(tmp, 20);

	/* round it down in multiples of 256 */
	tmp = tmp & ~0x0FFFFFFFUL;

	return (tmp > PHYP_DUMP_RMR_END ? tmp : PHYP_DUMP_RMR_END);
}

1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125
/**
 * phyp_dump_reserve_mem() - reserve all not-yet-dumped mmemory
 *
 * This routine may reserve memory regions in the kernel only
 * if the system is supported and a dump was taken in last
 * boot instance or if the hardware is supported and the
 * scratch area needs to be setup. In other instances it returns
 * without reserving anything. The memory in case of dump being
 * active is freed when the dump is collected (by userland tools).
 */
static void __init phyp_dump_reserve_mem(void)
{
	unsigned long base, size;
1126 1127
	unsigned long variable_reserve_size;

1128 1129 1130 1131 1132
	if (!phyp_dump_info->phyp_dump_configured) {
		printk(KERN_ERR "Phyp-dump not supported on this hardware\n");
		return;
	}

1133 1134 1135 1136 1137
	if (!phyp_dump_info->phyp_dump_at_boot) {
		printk(KERN_INFO "Phyp-dump disabled at boot time\n");
		return;
	}

1138 1139
	variable_reserve_size = phyp_dump_calculate_reserve_size();

1140 1141
	if (phyp_dump_info->phyp_dump_is_active) {
		/* Reserve *everything* above RMR.Area freed by userland tools*/
1142
		base = variable_reserve_size;
1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153
		size = lmb_end_of_DRAM() - base;

		/* XXX crashed_ram_end is wrong, since it may be beyond
		 * the memory_limit, it will need to be adjusted. */
		lmb_reserve(base, size);

		phyp_dump_info->init_reserve_start = base;
		phyp_dump_info->init_reserve_size = size;
	} else {
		size = phyp_dump_info->cpu_state_size +
			phyp_dump_info->hpte_region_size +
1154
			variable_reserve_size;
1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165
		base = lmb_end_of_DRAM() - size;
		lmb_reserve(base, size);
		phyp_dump_info->init_reserve_start = base;
		phyp_dump_info->init_reserve_size = size;
	}
}
#else
static inline void __init phyp_dump_reserve_mem(void) {}
#endif /* CONFIG_PHYP_DUMP  && CONFIG_PPC_RTAS */


1166 1167
void __init early_init_devtree(void *params)
{
1168 1169
	unsigned long limit;

1170
	DBG(" -> early_init_devtree(%p)\n", params);
1171 1172 1173 1174

	/* Setup flat device-tree pointer */
	initial_boot_params = params;

1175 1176 1177 1178 1179
#ifdef CONFIG_PPC_RTAS
	/* Some machines might need RTAS info for debugging, grab it now. */
	of_scan_flat_dt(early_init_dt_scan_rtas, NULL);
#endif

1180 1181 1182 1183 1184
#ifdef CONFIG_PHYP_DUMP
	/* scan tree to see if dump occured during last boot */
	of_scan_flat_dt(early_init_dt_scan_phyp_dump, NULL);
#endif

1185 1186 1187 1188
	/* Retrieve various informations from the /chosen node of the
	 * device-tree, including the platform type, initrd location and
	 * size, TCE reserve, and more ...
	 */
1189
	of_scan_flat_dt(early_init_dt_scan_chosen, NULL);
1190 1191 1192

	/* Scan memory nodes and rebuild LMBs */
	lmb_init();
1193 1194
	of_scan_flat_dt(early_init_dt_scan_root, NULL);
	of_scan_flat_dt(early_init_dt_scan_memory, NULL);
1195 1196

	/* Save command line for /proc/cmdline and then parse parameters */
1197
	strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE);
1198 1199
	parse_early_param();

1200
	/* Reserve LMB regions used by kernel, initrd, dt, etc... */
1201
	lmb_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START);
1202 1203 1204
	/* If relocatable, reserve first 32k for interrupt vectors etc. */
	if (PHYSICAL_START > MEMORY_START)
		lmb_reserve(MEMORY_START, 0x8000);
1205
	reserve_kdump_trampoline();
1206
	reserve_crashkernel();
1207
	early_reserve_mem();
1208
	phyp_dump_reserve_mem();
1209

1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222
	limit = memory_limit;
	if (! limit) {
		unsigned long memsize;

		/* Ensure that total memory size is page-aligned, because
		 * otherwise mark_bootmem() gets upset. */
		lmb_analyze();
		memsize = lmb_phys_mem_size();
		if ((memsize & PAGE_MASK) != memsize)
			limit = memsize & PAGE_MASK;
	}
	lmb_enforce_memory_limit(limit);

1223 1224 1225 1226 1227 1228 1229 1230
	lmb_analyze();

	DBG("Phys. mem: %lx\n", lmb_phys_mem_size());

	/* We may need to relocate the flat tree, do it now.
	 * FIXME .. and the initrd too? */
	move_device_tree();

1231 1232
	DBG("Scanning CPUs ...\n");

1233 1234
	/* Retreive CPU related informations from the flat tree
	 * (altivec support, boot CPU ID, ...)
1235
	 */
1236
	of_scan_flat_dt(early_init_dt_scan_cpus, NULL);
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252

	DBG(" <- early_init_devtree()\n");
}


/**
 * Indicates whether the root node has a given value in its
 * compatible property.
 */
int machine_is_compatible(const char *compat)
{
	struct device_node *root;
	int rc = 0;

	root = of_find_node_by_path("/");
	if (root) {
1253
		rc = of_device_is_compatible(root, compat);
1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285
		of_node_put(root);
	}
	return rc;
}
EXPORT_SYMBOL(machine_is_compatible);

/*******
 *
 * New implementation of the OF "find" APIs, return a refcounted
 * object, call of_node_put() when done.  The device tree and list
 * are protected by a rw_lock.
 *
 * Note that property management will need some locking as well,
 * this isn't dealt with yet.
 *
 *******/

/**
 *	of_find_node_by_phandle - Find a node given a phandle
 *	@handle:	phandle of the node to find
 *
 *	Returns a node pointer with refcount incremented, use
 *	of_node_put() on it when done.
 */
struct device_node *of_find_node_by_phandle(phandle handle)
{
	struct device_node *np;

	read_lock(&devtree_lock);
	for (np = allnodes; np != 0; np = np->allnext)
		if (np->linux_phandle == handle)
			break;
1286
	of_node_get(np);
1287 1288 1289 1290 1291
	read_unlock(&devtree_lock);
	return np;
}
EXPORT_SYMBOL(of_find_node_by_phandle);

1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322
/**
 *	of_find_next_cache_node - Find a node's subsidiary cache
 *	@np:	node of type "cpu" or "cache"
 *
 *	Returns a node pointer with refcount incremented, use
 *	of_node_put() on it when done.  Caller should hold a reference
 *	to np.
 */
struct device_node *of_find_next_cache_node(struct device_node *np)
{
	struct device_node *child;
	const phandle *handle;

	handle = of_get_property(np, "l2-cache", NULL);
	if (!handle)
		handle = of_get_property(np, "next-level-cache", NULL);

	if (handle)
		return of_find_node_by_phandle(*handle);

	/* OF on pmac has nodes instead of properties named "l2-cache"
	 * beneath CPU nodes.
	 */
	if (!strcmp(np->type, "cpu"))
		for_each_child_of_node(np, child)
			if (!strcmp(child->type, "cache"))
				return child;

	return NULL;
}

1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339
/**
 *	of_find_all_nodes - Get next node in global list
 *	@prev:	Previous node or NULL to start iteration
 *		of_node_put() will be called on it
 *
 *	Returns a node pointer with refcount incremented, use
 *	of_node_put() on it when done.
 */
struct device_node *of_find_all_nodes(struct device_node *prev)
{
	struct device_node *np;

	read_lock(&devtree_lock);
	np = prev ? prev->allnext : allnodes;
	for (; np != 0; np = np->allnext)
		if (of_node_get(np))
			break;
1340
	of_node_put(prev);
1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377
	read_unlock(&devtree_lock);
	return np;
}
EXPORT_SYMBOL(of_find_all_nodes);

/**
 *	of_node_get - Increment refcount of a node
 *	@node:	Node to inc refcount, NULL is supported to
 *		simplify writing of callers
 *
 *	Returns node.
 */
struct device_node *of_node_get(struct device_node *node)
{
	if (node)
		kref_get(&node->kref);
	return node;
}
EXPORT_SYMBOL(of_node_get);

static inline struct device_node * kref_to_device_node(struct kref *kref)
{
	return container_of(kref, struct device_node, kref);
}

/**
 *	of_node_release - release a dynamically allocated node
 *	@kref:  kref element of the node to be released
 *
 *	In of_node_put() this function is passed to kref_put()
 *	as the destructor.
 */
static void of_node_release(struct kref *kref)
{
	struct device_node *node = kref_to_device_node(kref);
	struct property *prop = node->properties;

1378 1379 1380 1381 1382 1383 1384 1385
	/* We should never be releasing nodes that haven't been detached. */
	if (!of_node_check_flag(node, OF_DETACHED)) {
		printk("WARNING: Bad of_node_put() on %s\n", node->full_name);
		dump_stack();
		kref_init(&node->kref);
		return;
	}

1386
	if (!of_node_check_flag(node, OF_DYNAMIC))
1387
		return;
1388

1389 1390 1391 1392 1393 1394
	while (prop) {
		struct property *next = prop->next;
		kfree(prop->name);
		kfree(prop->value);
		kfree(prop);
		prop = next;
1395 1396 1397 1398 1399

		if (!prop) {
			prop = node->deadprops;
			node->deadprops = NULL;
		}
1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423
	}
	kfree(node->full_name);
	kfree(node->data);
	kfree(node);
}

/**
 *	of_node_put - Decrement refcount of a node
 *	@node:	Node to dec refcount, NULL is supported to
 *		simplify writing of callers
 *
 */
void of_node_put(struct device_node *node)
{
	if (node)
		kref_put(&node->kref, of_node_release);
}
EXPORT_SYMBOL(of_node_put);

/*
 * Plug a device node into the tree and global list.
 */
void of_attach_node(struct device_node *np)
{
1424 1425 1426
	unsigned long flags;

	write_lock_irqsave(&devtree_lock, flags);
1427 1428 1429 1430
	np->sibling = np->parent->child;
	np->allnext = allnodes;
	np->parent->child = np;
	allnodes = np;
1431
	write_unlock_irqrestore(&devtree_lock, flags);
1432 1433 1434 1435 1436 1437 1438
}

/*
 * "Unplug" a node from the device tree.  The caller must hold
 * a reference to the node.  The memory associated with the node
 * is not freed until its refcount goes to zero.
 */
1439
void of_detach_node(struct device_node *np)
1440 1441
{
	struct device_node *parent;
1442
	unsigned long flags;
1443

1444
	write_lock_irqsave(&devtree_lock, flags);
1445 1446

	parent = np->parent;
1447 1448
	if (!parent)
		goto out_unlock;
1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471

	if (allnodes == np)
		allnodes = np->allnext;
	else {
		struct device_node *prev;
		for (prev = allnodes;
		     prev->allnext != np;
		     prev = prev->allnext)
			;
		prev->allnext = np->allnext;
	}

	if (parent->child == np)
		parent->child = np->sibling;
	else {
		struct device_node *prevsib;
		for (prevsib = np->parent->child;
		     prevsib->sibling != np;
		     prevsib = prevsib->sibling)
			;
		prevsib->sibling = np->sibling;
	}

1472 1473
	of_node_set_flag(np, OF_DETACHED);

1474
out_unlock:
1475
	write_unlock_irqrestore(&devtree_lock, flags);
1476 1477 1478 1479 1480
}

#ifdef CONFIG_PPC_PSERIES
/*
 * Fix up the uninitialized fields in a new device node:
1481
 * name, type and pci-specific fields
1482 1483
 */

1484
static int of_finish_dynamic_node(struct device_node *node)
1485 1486 1487
{
	struct device_node *parent = of_get_parent(node);
	int err = 0;
1488
	const phandle *ibm_phandle;
1489

1490 1491
	node->name = of_get_property(node, "name", NULL);
	node->type = of_get_property(node, "device_type", NULL);
1492

1493 1494 1495 1496 1497
	if (!node->name)
		node->name = "<NULL>";
	if (!node->type)
		node->type = "<NULL>";

1498 1499 1500 1501 1502 1503 1504 1505
	if (!parent) {
		err = -ENODEV;
		goto out;
	}

	/* We don't support that function on PowerMac, at least
	 * not yet
	 */
1506
	if (machine_is(powermac))
1507 1508 1509
		return -ENODEV;

	/* fix up new node's linux_phandle field */
1510
	if ((ibm_phandle = of_get_property(node, "ibm,phandle", NULL)))
1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524
		node->linux_phandle = *ibm_phandle;

out:
	of_node_put(parent);
	return err;
}

static int prom_reconfig_notifier(struct notifier_block *nb,
				  unsigned long action, void *node)
{
	int err;

	switch (action) {
	case PSERIES_RECONFIG_ADD:
1525
		err = of_finish_dynamic_node(node);
1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552
		if (err < 0) {
			printk(KERN_ERR "finish_node returned %d\n", err);
			err = NOTIFY_BAD;
		}
		break;
	default:
		err = NOTIFY_DONE;
		break;
	}
	return err;
}

static struct notifier_block prom_reconfig_nb = {
	.notifier_call = prom_reconfig_notifier,
	.priority = 10, /* This one needs to run first */
};

static int __init prom_reconfig_setup(void)
{
	return pSeries_reconfig_notifier_register(&prom_reconfig_nb);
}
__initcall(prom_reconfig_setup);
#endif

/*
 * Add a property to a node
 */
1553
int prom_add_property(struct device_node* np, struct property* prop)
1554
{
1555
	struct property **next;
1556
	unsigned long flags;
1557 1558

	prop->next = NULL;	
1559
	write_lock_irqsave(&devtree_lock, flags);
1560 1561 1562 1563
	next = &np->properties;
	while (*next) {
		if (strcmp(prop->name, (*next)->name) == 0) {
			/* duplicate ! don't insert it */
1564
			write_unlock_irqrestore(&devtree_lock, flags);
1565 1566
			return -1;
		}
1567
		next = &(*next)->next;
1568
	}
1569
	*next = prop;
1570
	write_unlock_irqrestore(&devtree_lock, flags);
1571

1572
#ifdef CONFIG_PROC_DEVICETREE
1573 1574 1575
	/* try to add to proc as well if it was initialized */
	if (np->pde)
		proc_device_tree_add_prop(np->pde, prop);
1576
#endif /* CONFIG_PROC_DEVICETREE */
1577 1578

	return 0;
1579 1580
}

1581 1582 1583 1584 1585 1586 1587 1588 1589
/*
 * Remove a property from a node.  Note that we don't actually
 * remove it, since we have given out who-knows-how-many pointers
 * to the data using get-property.  Instead we just move the property
 * to the "dead properties" list, so it won't be found any more.
 */
int prom_remove_property(struct device_node *np, struct property *prop)
{
	struct property **next;
1590
	unsigned long flags;
1591 1592
	int found = 0;

1593
	write_lock_irqsave(&devtree_lock, flags);
1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605
	next = &np->properties;
	while (*next) {
		if (*next == prop) {
			/* found the node */
			*next = prop->next;
			prop->next = np->deadprops;
			np->deadprops = prop;
			found = 1;
			break;
		}
		next = &(*next)->next;
	}
1606
	write_unlock_irqrestore(&devtree_lock, flags);
1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631

	if (!found)
		return -ENODEV;

#ifdef CONFIG_PROC_DEVICETREE
	/* try to remove the proc node as well */
	if (np->pde)
		proc_device_tree_remove_prop(np->pde, prop);
#endif /* CONFIG_PROC_DEVICETREE */

	return 0;
}

/*
 * Update a property in a node.  Note that we don't actually
 * remove it, since we have given out who-knows-how-many pointers
 * to the data using get-property.  Instead we just move the property
 * to the "dead properties" list, and add the new property to the
 * property list
 */
int prom_update_property(struct device_node *np,
			 struct property *newprop,
			 struct property *oldprop)
{
	struct property **next;
1632
	unsigned long flags;
1633 1634
	int found = 0;

1635
	write_lock_irqsave(&devtree_lock, flags);
1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648
	next = &np->properties;
	while (*next) {
		if (*next == oldprop) {
			/* found the node */
			newprop->next = oldprop->next;
			*next = newprop;
			oldprop->next = np->deadprops;
			np->deadprops = oldprop;
			found = 1;
			break;
		}
		next = &(*next)->next;
	}
1649
	write_unlock_irqrestore(&devtree_lock, flags);
1650 1651 1652

	if (!found)
		return -ENODEV;
1653

1654 1655 1656 1657 1658 1659 1660 1661
#ifdef CONFIG_PROC_DEVICETREE
	/* try to add to proc as well if it was initialized */
	if (np->pde)
		proc_device_tree_update_prop(np->pde, newprop, oldprop);
#endif /* CONFIG_PROC_DEVICETREE */

	return 0;
}
1662

1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675

/* Find the device node for a given logical cpu number, also returns the cpu
 * local thread number (index in ibm,interrupt-server#s) if relevant and
 * asked for (non NULL)
 */
struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
{
	int hardid;
	struct device_node *np;

	hardid = get_hard_smp_processor_id(cpu);

	for_each_node_by_type(np, "cpu") {
1676
		const u32 *intserv;
1677 1678 1679 1680 1681
		unsigned int plen, t;

		/* Check for ibm,ppc-interrupt-server#s. If it doesn't exist
		 * fallback to "reg" property and assume no threads
		 */
1682
		intserv = of_get_property(np, "ibm,ppc-interrupt-server#s",
1683
				&plen);
1684
		if (intserv == NULL) {
1685
			const u32 *reg = of_get_property(np, "reg", NULL);
1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705
			if (reg == NULL)
				continue;
			if (*reg == hardid) {
				if (thread)
					*thread = 0;
				return np;
			}
		} else {
			plen /= sizeof(u32);
			for (t = 0; t < plen; t++) {
				if (hardid == intserv[t]) {
					if (thread)
						*thread = t;
					return np;
				}
			}
		}
	}
	return NULL;
}
1706
EXPORT_SYMBOL(of_get_cpu_node);
1707

1708
#if defined(CONFIG_DEBUG_FS) && defined(DEBUG)
1709 1710 1711 1712 1713 1714 1715 1716 1717 1718
static struct debugfs_blob_wrapper flat_dt_blob;

static int __init export_flat_device_tree(void)
{
	struct dentry *d;

	flat_dt_blob.data = initial_boot_params;
	flat_dt_blob.size = initial_boot_params->totalsize;

	d = debugfs_create_blob("flat-device-tree", S_IFREG | S_IRUSR,
1719
				powerpc_debugfs_root, &flat_dt_blob);
1720 1721 1722 1723 1724 1725 1726
	if (!d)
		return 1;

	return 0;
}
__initcall(export_flat_device_tree);
#endif