setup_64.c 26.6 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 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
/*
 * 
 * Common boot and setup code.
 *
 * Copyright (C) 2001 PPC64 Team, IBM Corp
 *
 *      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/config.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/reboot.h>
#include <linux/delay.h>
#include <linux/initrd.h>
#include <linux/ide.h>
#include <linux/seq_file.h>
#include <linux/ioport.h>
#include <linux/console.h>
#include <linux/utsname.h>
#include <linux/tty.h>
#include <linux/root_dev.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/unistd.h>
#include <linux/serial.h>
#include <linux/serial_8250.h>
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/processor.h>
#include <asm/pgtable.h>
#include <asm/smp.h>
#include <asm/elf.h>
#include <asm/machdep.h>
#include <asm/paca.h>
#include <asm/ppcdebug.h>
#include <asm/time.h>
#include <asm/cputable.h>
#include <asm/sections.h>
#include <asm/btext.h>
#include <asm/nvram.h>
#include <asm/setup.h>
#include <asm/system.h>
#include <asm/rtas.h>
#include <asm/iommu.h>
#include <asm/serial.h>
#include <asm/cache.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/lmb.h>
59
#include <asm/iseries/it_lp_naca.h>
60 61
#include <asm/firmware.h>
#include <asm/systemcfg.h>
P
Paul Mackerras 已提交
62
#include <asm/xmon.h>
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

#ifdef DEBUG
#define DBG(fmt...) udbg_printf(fmt)
#else
#define DBG(fmt...)
#endif

/*
 * Here are some early debugging facilities. You can enable one
 * but your kernel will not boot on anything else if you do so
 */

/* This one is for use on LPAR machines that support an HVC console
 * on vterm 0
 */
extern void udbg_init_debug_lpar(void);
/* This one is for use on Apple G5 machines
 */
extern void udbg_init_pmac_realmode(void);
/* That's RTAS panel debug */
extern void call_rtas_display_status_delay(unsigned char c);
/* Here's maple real mode debug */
extern void udbg_init_maple_realmode(void);

#define EARLY_DEBUG_INIT() do {} while(0)

#if 0
#define EARLY_DEBUG_INIT() udbg_init_debug_lpar()
#define EARLY_DEBUG_INIT() udbg_init_maple_realmode()
#define EARLY_DEBUG_INIT() udbg_init_pmac_realmode()
#define EARLY_DEBUG_INIT()						\
	do { udbg_putc = call_rtas_display_status_delay; } while(0)
#endif

/* extern void *stab; */
extern unsigned long klimit;

extern void mm_init_ppc64(void);
extern void stab_initialize(unsigned long stab);
extern void htab_initialize(void);
extern void early_init_devtree(void *flat_dt);
extern void unflatten_device_tree(void);

int have_of = 1;
int boot_cpuid = 0;
int boot_cpuid_phys = 0;
dev_t boot_dev;
u64 ppc64_pft_size;

struct ppc64_caches ppc64_caches;
EXPORT_SYMBOL_GPL(ppc64_caches);

/*
 * These are used in binfmt_elf.c to put aux entries on the stack
 * for each elf executable being started.
 */
int dcache_bsize;
int icache_bsize;
int ucache_bsize;

/* The main machine-dep calls structure
 */
struct machdep_calls ppc_md;
EXPORT_SYMBOL(ppc_md);

#ifdef CONFIG_MAGIC_SYSRQ
unsigned long SYSRQ_KEY;
#endif /* CONFIG_MAGIC_SYSRQ */


static int ppc64_panic_event(struct notifier_block *, unsigned long, void *);
static struct notifier_block ppc64_panic_block = {
	.notifier_call = ppc64_panic_event,
	.priority = INT_MIN /* may not return; must be done last */
};

#ifdef CONFIG_SMP

static int smt_enabled_cmdline;

/* Look for ibm,smt-enabled OF option */
static void check_smt_enabled(void)
{
	struct device_node *dn;
	char *smt_option;

	/* Allow the command line to overrule the OF option */
	if (smt_enabled_cmdline)
		return;

	dn = of_find_node_by_path("/options");

	if (dn) {
		smt_option = (char *)get_property(dn, "ibm,smt-enabled", NULL);

                if (smt_option) {
			if (!strcmp(smt_option, "on"))
				smt_enabled_at_boot = 1;
			else if (!strcmp(smt_option, "off"))
				smt_enabled_at_boot = 0;
                }
        }
}

/* Look for smt-enabled= cmdline option */
static int __init early_smt_enabled(char *p)
{
	smt_enabled_cmdline = 1;

	if (!p)
		return 0;

	if (!strcmp(p, "on") || !strcmp(p, "1"))
		smt_enabled_at_boot = 1;
	else if (!strcmp(p, "off") || !strcmp(p, "0"))
		smt_enabled_at_boot = 0;

	return 0;
}
early_param("smt-enabled", early_smt_enabled);

/**
 * setup_cpu_maps - initialize the following cpu maps:
 *                  cpu_possible_map
 *                  cpu_present_map
 *                  cpu_sibling_map
 *
 * Having the possible map set up early allows us to restrict allocations
 * of things like irqstacks to num_possible_cpus() rather than NR_CPUS.
 *
 * We do not initialize the online map here; cpus set their own bits in
 * cpu_online_map as they come up.
 *
 * This function is valid only for Open Firmware systems.  finish_device_tree
 * must be called before using this.
 *
 * While we're here, we may as well set the "physical" cpu ids in the paca.
 */
static void __init setup_cpu_maps(void)
{
	struct device_node *dn = NULL;
	int cpu = 0;
	int swap_cpuid = 0;

	check_smt_enabled();

	while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < NR_CPUS) {
		u32 *intserv;
		int j, len = sizeof(u32), nthreads;

		intserv = (u32 *)get_property(dn, "ibm,ppc-interrupt-server#s",
					      &len);
		if (!intserv)
			intserv = (u32 *)get_property(dn, "reg", NULL);

		nthreads = len / sizeof(u32);

		for (j = 0; j < nthreads && cpu < NR_CPUS; j++) {
			cpu_set(cpu, cpu_present_map);
			set_hard_smp_processor_id(cpu, intserv[j]);

			if (intserv[j] == boot_cpuid_phys)
				swap_cpuid = cpu;
			cpu_set(cpu, cpu_possible_map);
			cpu++;
		}
	}

	/* Swap CPU id 0 with boot_cpuid_phys, so we can always assume that
	 * boot cpu is logical 0.
	 */
	if (boot_cpuid_phys != get_hard_smp_processor_id(0)) {
		u32 tmp;
		tmp = get_hard_smp_processor_id(0);
		set_hard_smp_processor_id(0, boot_cpuid_phys);
		set_hard_smp_processor_id(swap_cpuid, tmp);
	}

	/*
	 * On pSeries LPAR, we need to know how many cpus
	 * could possibly be added to this partition.
	 */
	if (systemcfg->platform == PLATFORM_PSERIES_LPAR &&
				(dn = of_find_node_by_path("/rtas"))) {
		int num_addr_cell, num_size_cell, maxcpus;
		unsigned int *ireg;

		num_addr_cell = prom_n_addr_cells(dn);
		num_size_cell = prom_n_size_cells(dn);

		ireg = (unsigned int *)
			get_property(dn, "ibm,lrdr-capacity", NULL);

		if (!ireg)
			goto out;

		maxcpus = ireg[num_addr_cell + num_size_cell];

		/* Double maxcpus for processors which have SMT capability */
		if (cpu_has_feature(CPU_FTR_SMT))
			maxcpus *= 2;

		if (maxcpus > NR_CPUS) {
			printk(KERN_WARNING
			       "Partition configured for %d cpus, "
			       "operating system maximum is %d.\n",
			       maxcpus, NR_CPUS);
			maxcpus = NR_CPUS;
		} else
			printk(KERN_INFO "Partition configured for %d cpus.\n",
			       maxcpus);

		for (cpu = 0; cpu < maxcpus; cpu++)
			cpu_set(cpu, cpu_possible_map);
	out:
		of_node_put(dn);
	}

	/*
	 * Do the sibling map; assume only two threads per processor.
	 */
	for_each_cpu(cpu) {
		cpu_set(cpu, cpu_sibling_map[cpu]);
		if (cpu_has_feature(CPU_FTR_SMT))
			cpu_set(cpu ^ 0x1, cpu_sibling_map[cpu]);
	}

	systemcfg->processorCount = num_present_cpus();
}
#endif /* CONFIG_SMP */

extern struct machdep_calls pSeries_md;
extern struct machdep_calls pmac_md;
extern struct machdep_calls maple_md;
297
extern struct machdep_calls cell_md;
298 299 300 301 302 303 304 305 306 307 308 309 310
extern struct machdep_calls iseries_md;

/* Ultimately, stuff them in an elf section like initcalls... */
static struct machdep_calls __initdata *machines[] = {
#ifdef CONFIG_PPC_PSERIES
	&pSeries_md,
#endif /* CONFIG_PPC_PSERIES */
#ifdef CONFIG_PPC_PMAC
	&pmac_md,
#endif /* CONFIG_PPC_PMAC */
#ifdef CONFIG_PPC_MAPLE
	&maple_md,
#endif /* CONFIG_PPC_MAPLE */
311 312
#ifdef CONFIG_PPC_CELL
	&cell_md,
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
#endif
#ifdef CONFIG_PPC_ISERIES
	&iseries_md,
#endif
	NULL
};

/*
 * Early initialization entry point. This is called by head.S
 * with MMU translation disabled. We rely on the "feature" of
 * the CPU that ignores the top 2 bits of the address in real
 * mode so we can access kernel globals normally provided we
 * only toy with things in the RMO region. From here, we do
 * some early parsing of the device-tree to setup out LMB
 * data structures, and allocate & initialize the hash table
 * and segment tables so we can start running with translation
 * enabled.
 *
 * It is this function which will call the probe() callback of
 * the various platform types and copy the matching one to the
 * global ppc_md structure. Your platform can eventually do
 * some very early initializations from the probe() routine, but
 * this is not recommended, be very careful as, for example, the
 * device-tree is not accessible via normal means at this point.
 */

void __init early_setup(unsigned long dt_ptr)
{
	struct paca_struct *lpaca = get_paca();
	static struct machdep_calls **mach;

	/*
	 * Enable early debugging if any specified (see top of
	 * this file)
	 */
	EARLY_DEBUG_INIT();

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

	/*
	 * Fill the default DBG level (do we want to keep
	 * that old mecanism around forever ?)
	 */
	ppcdbg_initialize();

	/*
	 * Do early initializations using the flattened device
	 * tree, like retreiving the physical memory map or
	 * calculating/retreiving the hash table size
	 */
	early_init_devtree(__va(dt_ptr));

	/*
	 * Iterate all ppc_md structures until we find the proper
	 * one for the current machine type
	 */
	DBG("Probing machine type for platform %x...\n",
	    systemcfg->platform);

	for (mach = machines; *mach; mach++) {
		if ((*mach)->probe(systemcfg->platform))
			break;
	}
	/* What can we do if we didn't find ? */
	if (*mach == NULL) {
		DBG("No suitable machine found !\n");
		for (;;);
	}
	ppc_md = **mach;

	DBG("Found, Initializing memory management...\n");

	/*
	 * Initialize stab / SLB management
	 */
	if (!firmware_has_feature(FW_FEATURE_ISERIES))
		stab_initialize(lpaca->stab_real);

	/*
	 * Initialize the MMU Hash table and create the linear mapping
	 * of memory
	 */
	htab_initialize();

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


401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421
#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
void smp_release_cpus(void)
{
	extern unsigned long __secondary_hold_spinloop;

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

	/* All secondary cpus are spinning on a common spinloop, release them
	 * all now so they can start to spin on their individual paca
	 * spinloops. For non SMP kernels, the secondary cpus never get out
	 * of the common spinloop.
	 * This is useless but harmless on iSeries, secondaries are already
	 * waiting on their paca spinloops. */

	__secondary_hold_spinloop = 1;
	mb();

	DBG(" <- smp_release_cpus()\n");
}
#endif /* CONFIG_SMP || CONFIG_KEXEC */

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
/*
 * Initialize some remaining members of the ppc64_caches and systemcfg structures
 * (at least until we get rid of them completely). This is mostly some
 * cache informations about the CPU that will be used by cache flush
 * routines and/or provided to userland
 */
static void __init initialize_cache_info(void)
{
	struct device_node *np;
	unsigned long num_cpus = 0;

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

	for (np = NULL; (np = of_find_node_by_type(np, "cpu"));) {
		num_cpus += 1;

		/* We're assuming *all* of the CPUs have the same
		 * d-cache and i-cache sizes... -Peter
		 */

		if ( num_cpus == 1 ) {
			u32 *sizep, *lsizep;
			u32 size, lsize;
			const char *dc, *ic;

			/* Then read cache informations */
			if (systemcfg->platform == PLATFORM_POWERMAC) {
				dc = "d-cache-block-size";
				ic = "i-cache-block-size";
			} else {
				dc = "d-cache-line-size";
				ic = "i-cache-line-size";
			}

			size = 0;
			lsize = cur_cpu_spec->dcache_bsize;
			sizep = (u32 *)get_property(np, "d-cache-size", NULL);
			if (sizep != NULL)
				size = *sizep;
			lsizep = (u32 *) get_property(np, dc, NULL);
			if (lsizep != NULL)
				lsize = *lsizep;
			if (sizep == 0 || lsizep == 0)
				DBG("Argh, can't find dcache properties ! "
				    "sizep: %p, lsizep: %p\n", sizep, lsizep);

			systemcfg->dcache_size = ppc64_caches.dsize = size;
			systemcfg->dcache_line_size =
				ppc64_caches.dline_size = lsize;
			ppc64_caches.log_dline_size = __ilog2(lsize);
			ppc64_caches.dlines_per_page = PAGE_SIZE / lsize;

			size = 0;
			lsize = cur_cpu_spec->icache_bsize;
			sizep = (u32 *)get_property(np, "i-cache-size", NULL);
			if (sizep != NULL)
				size = *sizep;
			lsizep = (u32 *)get_property(np, ic, NULL);
			if (lsizep != NULL)
				lsize = *lsizep;
			if (sizep == 0 || lsizep == 0)
				DBG("Argh, can't find icache properties ! "
				    "sizep: %p, lsizep: %p\n", sizep, lsizep);

			systemcfg->icache_size = ppc64_caches.isize = size;
			systemcfg->icache_line_size =
				ppc64_caches.iline_size = lsize;
			ppc64_caches.log_iline_size = __ilog2(lsize);
			ppc64_caches.ilines_per_page = PAGE_SIZE / lsize;
		}
	}

	/* Add an eye catcher and the systemcfg layout version number */
	strcpy(systemcfg->eye_catcher, "SYSTEMCFG:PPC64");
	systemcfg->version.major = SYSTEMCFG_MAJOR;
	systemcfg->version.minor = SYSTEMCFG_MINOR;
	systemcfg->processor = mfspr(SPRN_PVR);

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

static void __init check_for_initrd(void)
{
#ifdef CONFIG_BLK_DEV_INITRD
	u64 *prop;

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

	if (of_chosen) {
		prop = (u64 *)get_property(of_chosen,
				"linux,initrd-start", NULL);
		if (prop != NULL) {
			initrd_start = (unsigned long)__va(*prop);
			prop = (u64 *)get_property(of_chosen,
					"linux,initrd-end", NULL);
			if (prop != NULL) {
				initrd_end = (unsigned long)__va(*prop);
				initrd_below_start_ok = 1;
			} else
				initrd_start = 0;
		}
	}

	/* If we were passed an initrd, set the ROOT_DEV properly if the values
	 * look sensible. If not, clear initrd reference.
	 */
	if (initrd_start >= KERNELBASE && initrd_end >= KERNELBASE &&
	    initrd_end > initrd_start)
		ROOT_DEV = Root_RAM0;
	else
		initrd_start = initrd_end = 0;

	if (initrd_start)
		printk("Found initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end);

	DBG(" <- check_for_initrd()\n");
#endif /* CONFIG_BLK_DEV_INITRD */
}

/*
 * Do some initial setup of the system.  The parameters are those which 
 * were passed in from the bootloader.
 */
void __init setup_system(void)
{
	DBG(" -> setup_system()\n");

	/*
	 * Unflatten the device-tree passed by prom_init or kexec
	 */
	unflatten_device_tree();

	/*
	 * Fill the ppc64_caches & systemcfg structures with informations
	 * retreived from the device-tree. Need to be called before
	 * finish_device_tree() since the later requires some of the
	 * informations filled up here to properly parse the interrupt
	 * tree.
	 * It also sets up the cache line sizes which allows to call
	 * routines like flush_icache_range (used by the hash init
	 * later on).
	 */
	initialize_cache_info();

#ifdef CONFIG_PPC_RTAS
	/*
	 * Initialize RTAS if available
	 */
	rtas_initialize();
#endif /* CONFIG_PPC_RTAS */

	/*
	 * Check if we have an initrd provided via the device-tree
	 */
	check_for_initrd();

	/*
	 * Do some platform specific early initializations, that includes
	 * setting up the hash table pointers. It also sets up some interrupt-mapping
	 * related options that will be used by finish_device_tree()
	 */
	ppc_md.init_early();

	/*
	 * "Finish" the device-tree, that is do the actual parsing of
	 * some of the properties like the interrupt map
	 */
	finish_device_tree();

591 592 593 594
#ifdef CONFIG_BOOTX_TEXT
	init_boot_display();
#endif

595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704
	/*
	 * Initialize xmon
	 */
#ifdef CONFIG_XMON_DEFAULT
	xmon_init(1);
#endif
	/*
	 * Register early console
	 */
	register_early_udbg_console();

	/* Save unparsed command line copy for /proc/cmdline */
	strlcpy(saved_command_line, cmd_line, COMMAND_LINE_SIZE);

	parse_early_param();

#ifdef CONFIG_SMP
	/*
	 * iSeries has already initialized the cpu maps at this point.
	 */
	setup_cpu_maps();

	/* Release secondary cpus out of their spinloops at 0x60 now that
	 * we can map physical -> logical CPU ids
	 */
	smp_release_cpus();
#endif

	printk("Starting Linux PPC64 %s\n", system_utsname.version);

	printk("-----------------------------------------------------\n");
	printk("ppc64_pft_size                = 0x%lx\n", ppc64_pft_size);
	printk("ppc64_debug_switch            = 0x%lx\n", ppc64_debug_switch);
	printk("ppc64_interrupt_controller    = 0x%ld\n", ppc64_interrupt_controller);
	printk("systemcfg                     = 0x%p\n", systemcfg);
	printk("systemcfg->platform           = 0x%x\n", systemcfg->platform);
	printk("systemcfg->processorCount     = 0x%lx\n", systemcfg->processorCount);
	printk("systemcfg->physicalMemorySize = 0x%lx\n", systemcfg->physicalMemorySize);
	printk("ppc64_caches.dcache_line_size = 0x%x\n",
			ppc64_caches.dline_size);
	printk("ppc64_caches.icache_line_size = 0x%x\n",
			ppc64_caches.iline_size);
	printk("htab_address                  = 0x%p\n", htab_address);
	printk("htab_hash_mask                = 0x%lx\n", htab_hash_mask);
	printk("-----------------------------------------------------\n");

	mm_init_ppc64();

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

static int ppc64_panic_event(struct notifier_block *this,
                             unsigned long event, void *ptr)
{
	ppc_md.panic((char *)ptr);  /* May not return */
	return NOTIFY_DONE;
}

#ifdef CONFIG_IRQSTACKS
static void __init irqstack_early_init(void)
{
	unsigned int i;

	/*
	 * interrupt stacks must be under 256MB, we cannot afford to take
	 * SLB misses on them.
	 */
	for_each_cpu(i) {
		softirq_ctx[i] = (struct thread_info *)__va(lmb_alloc_base(THREAD_SIZE,
					THREAD_SIZE, 0x10000000));
		hardirq_ctx[i] = (struct thread_info *)__va(lmb_alloc_base(THREAD_SIZE,
					THREAD_SIZE, 0x10000000));
	}
}
#else
#define irqstack_early_init()
#endif

/*
 * Stack space used when we detect a bad kernel stack pointer, and
 * early in SMP boots before relocation is enabled.
 */
static void __init emergency_stack_init(void)
{
	unsigned long limit;
	unsigned int i;

	/*
	 * Emergency stacks must be under 256MB, we cannot afford to take
	 * SLB misses on them. The ABI also requires them to be 128-byte
	 * aligned.
	 *
	 * Since we use these as temporary stacks during secondary CPU
	 * bringup, we need to get at them in real mode. This means they
	 * must also be within the RMO region.
	 */
	limit = min(0x10000000UL, lmb.rmo_size);

	for_each_cpu(i)
		paca[i].emergency_sp = __va(lmb_alloc_base(PAGE_SIZE, 128,
						limit)) + PAGE_SIZE;
}

/*
 * Called from setup_arch to initialize the bitmap of available
 * syscalls in the systemcfg page
 */
void __init setup_syscall_map(void)
{
	unsigned int i, count64 = 0, count32 = 0;
705 706 707
	extern unsigned long *sys_call_table;
	extern unsigned long sys_ni_syscall;

708 709

	for (i = 0; i < __NR_syscalls; i++) {
710
		if (sys_call_table[i*2] != sys_ni_syscall) {
711 712 713 714
			count64++;
			systemcfg->syscall_map_64[i >> 5] |=
				0x80000000UL >> (i & 0x1f);
		}
715
		if (sys_call_table[i*2+1] != sys_ni_syscall) {
716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768
			count32++;
			systemcfg->syscall_map_32[i >> 5] |=
				0x80000000UL >> (i & 0x1f);
		}
	}
	printk(KERN_INFO "Syscall map setup, %d 32-bit and %d 64-bit syscalls\n",
	       count32, count64);
}

/*
 * Called into from start_kernel, after lock_kernel has been called.
 * Initializes bootmem, which is unsed to manage page allocation until
 * mem_init is called.
 */
void __init setup_arch(char **cmdline_p)
{
	extern void do_init_bootmem(void);

	ppc64_boot_msg(0x12, "Setup Arch");

	*cmdline_p = cmd_line;

	/*
	 * Set cache line size based on type of cpu as a default.
	 * Systems with OF can look in the properties on the cpu node(s)
	 * for a possibly more accurate value.
	 */
	dcache_bsize = ppc64_caches.dline_size;
	icache_bsize = ppc64_caches.iline_size;

	/* reboot on panic */
	panic_timeout = 180;

	if (ppc_md.panic)
		notifier_chain_register(&panic_notifier_list, &ppc64_panic_block);

	init_mm.start_code = PAGE_OFFSET;
	init_mm.end_code = (unsigned long) _etext;
	init_mm.end_data = (unsigned long) _edata;
	init_mm.brk = klimit;
	
	irqstack_early_init();
	emergency_stack_init();

	stabs_alloc();

	/* set up the bootmem stuff with available memory */
	do_init_bootmem();
	sparse_init();

	/* initialize the syscall map in systemcfg */
	setup_syscall_map();

769 770 771 772
#ifdef CONFIG_DUMMY_CONSOLE
	conswitchp = &dummy_con;
#endif

773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030
	ppc_md.setup_arch();

	/* Use the default idle loop if the platform hasn't provided one. */
	if (NULL == ppc_md.idle_loop) {
		ppc_md.idle_loop = default_idle;
		printk(KERN_INFO "Using default idle loop\n");
	}

	paging_init();
	ppc64_boot_msg(0x15, "Setup Done");
}


/* ToDo: do something useful if ppc_md is not yet setup. */
#define PPC64_LINUX_FUNCTION 0x0f000000
#define PPC64_IPL_MESSAGE 0xc0000000
#define PPC64_TERM_MESSAGE 0xb0000000

static void ppc64_do_msg(unsigned int src, const char *msg)
{
	if (ppc_md.progress) {
		char buf[128];

		sprintf(buf, "%08X\n", src);
		ppc_md.progress(buf, 0);
		snprintf(buf, 128, "%s", msg);
		ppc_md.progress(buf, 0);
	}
}

/* Print a boot progress message. */
void ppc64_boot_msg(unsigned int src, const char *msg)
{
	ppc64_do_msg(PPC64_LINUX_FUNCTION|PPC64_IPL_MESSAGE|src, msg);
	printk("[boot]%04x %s\n", src, msg);
}

/* Print a termination message (print only -- does not stop the kernel) */
void ppc64_terminate_msg(unsigned int src, const char *msg)
{
	ppc64_do_msg(PPC64_LINUX_FUNCTION|PPC64_TERM_MESSAGE|src, msg);
	printk("[terminate]%04x %s\n", src, msg);
}

#ifndef CONFIG_PPC_ISERIES
/*
 * This function can be used by platforms to "find" legacy serial ports.
 * It works for "serial" nodes under an "isa" node, and will try to
 * respect the "ibm,aix-loc" property if any. It works with up to 8
 * ports.
 */

#define MAX_LEGACY_SERIAL_PORTS	8
static struct plat_serial8250_port serial_ports[MAX_LEGACY_SERIAL_PORTS+1];
static unsigned int old_serial_count;

void __init generic_find_legacy_serial_ports(u64 *physport,
		unsigned int *default_speed)
{
	struct device_node *np;
	u32 *sizeprop;

	struct isa_reg_property {
		u32 space;
		u32 address;
		u32 size;
	};
	struct pci_reg_property {
		struct pci_address addr;
		u32 size_hi;
		u32 size_lo;
	};                                                                        

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

	*physport = 0;
	if (default_speed)
		*default_speed = 0;

	np = of_find_node_by_path("/");
	if (!np)
		return;

	/* First fill our array */
	for (np = NULL; (np = of_find_node_by_type(np, "serial"));) {
		struct device_node *isa, *pci;
		struct isa_reg_property *reg;
		unsigned long phys_size, addr_size, io_base;
		u32 *rangesp;
		u32 *interrupts, *clk, *spd;
		char *typep;
		int index, rlen, rentsize;

		/* Ok, first check if it's under an "isa" parent */
		isa = of_get_parent(np);
		if (!isa || strcmp(isa->name, "isa")) {
			DBG("%s: no isa parent found\n", np->full_name);
			continue;
		}
		
		/* Now look for an "ibm,aix-loc" property that gives us ordering
		 * if any...
		 */
	 	typep = (char *)get_property(np, "ibm,aix-loc", NULL);

		/* Get the ISA port number */
		reg = (struct isa_reg_property *)get_property(np, "reg", NULL);	
		if (reg == NULL)
			goto next_port;
		/* We assume the interrupt number isn't translated ... */
		interrupts = (u32 *)get_property(np, "interrupts", NULL);
		/* get clock freq. if present */
		clk = (u32 *)get_property(np, "clock-frequency", NULL);
		/* get default speed if present */
		spd = (u32 *)get_property(np, "current-speed", NULL);
		/* Default to locate at end of array */
		index = old_serial_count; /* end of the array by default */

		/* If we have a location index, then use it */
		if (typep && *typep == 'S') {
			index = simple_strtol(typep+1, NULL, 0) - 1;
			/* if index is out of range, use end of array instead */
			if (index >= MAX_LEGACY_SERIAL_PORTS)
				index = old_serial_count;
			/* if our index is still out of range, that mean that
			 * array is full, we could scan for a free slot but that
			 * make little sense to bother, just skip the port
			 */
			if (index >= MAX_LEGACY_SERIAL_PORTS)
				goto next_port;
			if (index >= old_serial_count)
				old_serial_count = index + 1;
			/* Check if there is a port who already claimed our slot */
			if (serial_ports[index].iobase != 0) {
				/* if we still have some room, move it, else override */
				if (old_serial_count < MAX_LEGACY_SERIAL_PORTS) {
					DBG("Moved legacy port %d -> %d\n", index,
					    old_serial_count);
					serial_ports[old_serial_count++] =
						serial_ports[index];
				} else {
					DBG("Replacing legacy port %d\n", index);
				}
			}
		}
		if (index >= MAX_LEGACY_SERIAL_PORTS)
			goto next_port;
		if (index >= old_serial_count)
			old_serial_count = index + 1;

		/* Now fill the entry */
		memset(&serial_ports[index], 0, sizeof(struct plat_serial8250_port));
		serial_ports[index].uartclk = clk ? *clk : BASE_BAUD * 16;
		serial_ports[index].iobase = reg->address;
		serial_ports[index].irq = interrupts ? interrupts[0] : 0;
		serial_ports[index].flags = ASYNC_BOOT_AUTOCONF;

		DBG("Added legacy port, index: %d, port: %x, irq: %d, clk: %d\n",
		    index,
		    serial_ports[index].iobase,
		    serial_ports[index].irq,
		    serial_ports[index].uartclk);

		/* Get phys address of IO reg for port 1 */
		if (index != 0)
			goto next_port;

		pci = of_get_parent(isa);
		if (!pci) {
			DBG("%s: no pci parent found\n", np->full_name);
			goto next_port;
		}

		rangesp = (u32 *)get_property(pci, "ranges", &rlen);
		if (rangesp == NULL) {
			of_node_put(pci);
			goto next_port;
		}
		rlen /= 4;

		/* we need the #size-cells of the PCI bridge node itself */
		phys_size = 1;
		sizeprop = (u32 *)get_property(pci, "#size-cells", NULL);
		if (sizeprop != NULL)
			phys_size = *sizeprop;
		/* we need the parent #addr-cells */
		addr_size = prom_n_addr_cells(pci);
		rentsize = 3 + addr_size + phys_size;
		io_base = 0;
		for (;rlen >= rentsize; rlen -= rentsize,rangesp += rentsize) {
			if (((rangesp[0] >> 24) & 0x3) != 1)
				continue; /* not IO space */
			io_base = rangesp[3];
			if (addr_size == 2)
				io_base = (io_base << 32) | rangesp[4];
		}
		if (io_base != 0) {
			*physport = io_base + reg->address;
			if (default_speed && spd)
				*default_speed = *spd;
		}
		of_node_put(pci);
	next_port:
		of_node_put(isa);
	}

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

static struct platform_device serial_device = {
	.name	= "serial8250",
	.id	= PLAT8250_DEV_PLATFORM,
	.dev	= {
		.platform_data = serial_ports,
	},
};

static int __init serial_dev_init(void)
{
	return platform_device_register(&serial_device);
}
arch_initcall(serial_dev_init);

#endif /* CONFIG_PPC_ISERIES */

int check_legacy_ioport(unsigned long base_port)
{
	if (ppc_md.check_legacy_ioport == NULL)
		return 0;
	return ppc_md.check_legacy_ioport(base_port);
}
EXPORT_SYMBOL(check_legacy_ioport);

#ifdef CONFIG_XMON
static int __init early_xmon(char *p)
{
	/* ensure xmon is enabled */
	if (p) {
		if (strncmp(p, "on", 2) == 0)
			xmon_init(1);
		if (strncmp(p, "off", 3) == 0)
			xmon_init(0);
		if (strncmp(p, "early", 5) != 0)
			return 0;
	}
	xmon_init(1);
	debugger(NULL);

	return 0;
}
early_param("xmon", early_xmon);
#endif

void cpu_die(void)
{
	if (ppc_md.cpu_die)
		ppc_md.cpu_die();
}