setup_64.c 17.1 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
/*
 * 
 * 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>
37
#include <asm/kdump.h>
38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58
#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/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
#include <asm/firmware.h>
P
Paul Mackerras 已提交
61
#include <asm/xmon.h>
D
David Gibson 已提交
62
#include <asm/udbg.h>
63
#include <asm/kexec.h>
64

S
Stephen Rothwell 已提交
65 66
#include "setup.h"

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
#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

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

106 107 108 109 110 111 112 113 114
/* Pick defaults since we might want to patch instructions
 * before we've read this from the device tree.
 */
struct ppc64_caches ppc64_caches = {
	.dline_size = 0x80,
	.log_dline_size = 7,
	.iline_size = 0x80,
	.log_iline_size = 7
};
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
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);

P
Paul Mackerras 已提交
186 187
#else
#define check_smt_enabled()
188 189 190 191 192
#endif /* CONFIG_SMP */

extern struct machdep_calls pSeries_md;
extern struct machdep_calls pmac_md;
extern struct machdep_calls maple_md;
193
extern struct machdep_calls cell_md;
194 195 196 197 198 199 200 201 202 203 204 205 206
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 */
207 208
#ifdef CONFIG_PPC_CELL
	&cell_md,
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
#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");

	/*
	 * 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
	 */
259
	DBG("Probing machine type for platform %x...\n", _machine);
260 261

	for (mach = machines; *mach; mach++) {
262
		if ((*mach)->probe(_machine))
263 264 265 266 267 268 269 270 271
			break;
	}
	/* What can we do if we didn't find ? */
	if (*mach == NULL) {
		DBG("No suitable machine found !\n");
		for (;;);
	}
	ppc_md = **mach;

272 273 274 275
#ifdef CONFIG_CRASH_DUMP
	kdump_setup();
#endif

276 277 278
	DBG("Found, Initializing memory management...\n");

	/*
279 280 281
	 * Initialize the MMU Hash table and create the linear mapping
	 * of memory. Has to be done before stab/slb initialization as
	 * this is currently where the page size encoding is obtained
282
	 */
283
	htab_initialize();
284 285

	/*
286
	 * Initialize stab / SLB management except on iSeries
287
	 */
288 289 290 291 292 293
	if (!firmware_has_feature(FW_FEATURE_ISERIES)) {
		if (cpu_has_feature(CPU_FTR_SLB))
			slb_initialize();
		else
			stab_initialize(lpaca->stab_real);
	}
294 295 296 297

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

298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319
#ifdef CONFIG_SMP
void early_setup_secondary(void)
{
	struct paca_struct *lpaca = get_paca();

	/* Mark enabled in PACA */
	lpaca->proc_enabled = 0;

	/* Initialize hash table for that CPU */
	htab_initialize_secondary();

	/* Initialize STAB/SLB. We use a virtual address as it works
	 * in real mode on pSeries and we want a virutal address on
	 * iSeries anyway
	 */
	if (cpu_has_feature(CPU_FTR_SLB))
		slb_initialize();
	else
		stab_initialize(lpaca->stab_addr);
}

#endif /* CONFIG_SMP */
320

321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339
#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");
}
P
Paul Mackerras 已提交
340 341
#else
#define smp_release_cpus()
342 343
#endif /* CONFIG_SMP || CONFIG_KEXEC */

344
/*
345 346
 * Initialize some remaining members of the ppc64_caches and systemcfg
 * structures
347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370
 * (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 */
371
			if (_machine == PLATFORM_POWERMAC) {
372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390
				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);

391 392
			ppc64_caches.dsize = size;
			ppc64_caches.dline_size = lsize;
393 394 395 396 397 398 399 400 401 402 403 404 405 406 407
			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);

408 409
			ppc64_caches.isize = size;
			ppc64_caches.iline_size = lsize;
410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431
			ppc64_caches.log_iline_size = __ilog2(lsize);
			ppc64_caches.ilines_per_page = PAGE_SIZE / lsize;
		}
	}

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


/*
 * 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();

432 433 434 435
#ifdef CONFIG_KEXEC
	kexec_setup();	/* requires unflattened device tree. */
#endif

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
	/*
	 * 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();

467 468 469 470 471 472 473 474 475
 	/*
	 * We can discover serial ports now since the above did setup the
	 * hash table management for us, thus ioremap works. We do that early
	 * so that further code can be debugged
	 */
#ifdef CONFIG_PPC_MULTIPLATFORM
	find_legacy_serial_ports();
#endif

476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497
	/*
	 * "Finish" the device-tree, that is do the actual parsing of
	 * some of the properties like the interrupt map
	 */
	finish_device_tree();

	/*
	 * 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();

P
Paul Mackerras 已提交
498 499
	check_smt_enabled();
	smp_setup_cpu_maps();
500 501 502 503 504 505 506 507 508 509

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

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

	printk("-----------------------------------------------------\n");
	printk("ppc64_pft_size                = 0x%lx\n", ppc64_pft_size);
510 511 512 513
	printk("ppc64_interrupt_controller    = 0x%ld\n",
	       ppc64_interrupt_controller);
	printk("platform                      = 0x%x\n", _machine);
	printk("physicalMemorySize            = 0x%lx\n", lmb_phys_mem_size());
514
	printk("ppc64_caches.dcache_line_size = 0x%x\n",
515
	       ppc64_caches.dline_size);
516
	printk("ppc64_caches.icache_line_size = 0x%x\n",
517
	       ppc64_caches.iline_size);
518 519
	printk("htab_address                  = 0x%p\n", htab_address);
	printk("htab_hash_mask                = 0x%lx\n", htab_hash_mask);
520 521 522
#if PHYSICAL_START > 0
	printk("physical_start                = 0x%x\n", PHYSICAL_START);
#endif
523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546
	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) {
547 548 549 550 551 552
		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));
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
	}
}
#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)
580 581
		paca[i].emergency_sp =
		__va(lmb_alloc_base(HW_PAGE_SIZE, 128, limit)) + HW_PAGE_SIZE;
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
}

/*
 * 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();

625 626 627 628
#ifdef CONFIG_DUMMY_CONSOLE
	conswitchp = &dummy_con;
#endif

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
	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);
}

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);

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