process.c 20.8 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5
/*
 * Architecture-specific setup.
 *
 * Copyright (C) 1998-2003 Hewlett-Packard Co
 *	David Mosberger-Tang <davidm@hpl.hp.com>
6
 * 04/11/17 Ashok Raj	<ashok.raj@intel.com> Added CPU Hotplug Support
7 8 9
 *
 * 2005-10-07 Keith Owens <kaos@sgi.com>
 *	      Add notify_die() hooks.
L
Linus Torvalds 已提交
10 11 12 13 14 15 16 17
 */
#include <linux/cpu.h>
#include <linux/pm.h>
#include <linux/elf.h>
#include <linux/errno.h>
#include <linux/kallsyms.h>
#include <linux/kernel.h>
#include <linux/mm.h>
18
#include <linux/slab.h>
L
Linus Torvalds 已提交
19 20 21 22 23 24 25 26 27 28
#include <linux/module.h>
#include <linux/notifier.h>
#include <linux/personality.h>
#include <linux/sched.h>
#include <linux/stddef.h>
#include <linux/thread_info.h>
#include <linux/unistd.h>
#include <linux/efi.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
29
#include <linux/kdebug.h>
30
#include <linux/utsname.h>
S
Shaohua Li 已提交
31
#include <linux/tracehook.h>
L
Linus Torvalds 已提交
32 33 34 35 36

#include <asm/cpu.h>
#include <asm/delay.h>
#include <asm/elf.h>
#include <asm/irq.h>
37
#include <asm/kexec.h>
L
Linus Torvalds 已提交
38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57
#include <asm/pgalloc.h>
#include <asm/processor.h>
#include <asm/sal.h>
#include <asm/tlbflush.h>
#include <asm/uaccess.h>
#include <asm/unwind.h>
#include <asm/user.h>

#include "entry.h"

#ifdef CONFIG_PERFMON
# include <asm/perfmon.h>
#endif

#include "sigframe.h"

void (*ia64_mark_idle)(int);

unsigned long boot_option_idle_override = 0;
EXPORT_SYMBOL(boot_option_idle_override);
Z
Zhao Yakui 已提交
58 59
unsigned long idle_halt;
EXPORT_SYMBOL(idle_halt);
60 61
unsigned long idle_nomwait;
EXPORT_SYMBOL(idle_nomwait);
62 63 64 65
void (*pm_idle) (void);
EXPORT_SYMBOL(pm_idle);
void (*pm_power_off) (void);
EXPORT_SYMBOL(pm_power_off);
L
Linus Torvalds 已提交
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

void
ia64_do_show_stack (struct unw_frame_info *info, void *arg)
{
	unsigned long ip, sp, bsp;
	char buf[128];			/* don't make it so big that it overflows the stack! */

	printk("\nCall Trace:\n");
	do {
		unw_get_ip(info, &ip);
		if (ip == 0)
			break;

		unw_get_sp(info, &sp);
		unw_get_bsp(info, &bsp);
		snprintf(buf, sizeof(buf),
			 " [<%016lx>] %%s\n"
			 "                                sp=%016lx bsp=%016lx\n",
			 ip, sp, bsp);
		print_symbol(buf, ip);
	} while (unw_unwind(info) >= 0);
}

void
show_stack (struct task_struct *task, unsigned long *sp)
{
	if (!task)
		unw_init_running(ia64_do_show_stack, NULL);
	else {
		struct unw_frame_info info;

		unw_init_from_blocked_task(&info, task);
		ia64_do_show_stack(&info, NULL);
	}
}

void
dump_stack (void)
{
	show_stack(NULL, NULL);
}

EXPORT_SYMBOL(dump_stack);

void
show_regs (struct pt_regs *regs)
{
	unsigned long ip = regs->cr_iip + ia64_psr(regs)->ri;

	print_modules();
116 117
	printk("\nPid: %d, CPU %d, comm: %20s\n", task_pid_nr(current),
			smp_processor_id(), current->comm);
118 119 120
	printk("psr : %016lx ifs : %016lx ip  : [<%016lx>]    %s (%s)\n",
	       regs->cr_ipsr, regs->cr_ifs, ip, print_tainted(),
	       init_utsname()->release);
L
Linus Torvalds 已提交
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
	print_symbol("ip is at %s\n", ip);
	printk("unat: %016lx pfs : %016lx rsc : %016lx\n",
	       regs->ar_unat, regs->ar_pfs, regs->ar_rsc);
	printk("rnat: %016lx bsps: %016lx pr  : %016lx\n",
	       regs->ar_rnat, regs->ar_bspstore, regs->pr);
	printk("ldrs: %016lx ccv : %016lx fpsr: %016lx\n",
	       regs->loadrs, regs->ar_ccv, regs->ar_fpsr);
	printk("csd : %016lx ssd : %016lx\n", regs->ar_csd, regs->ar_ssd);
	printk("b0  : %016lx b6  : %016lx b7  : %016lx\n", regs->b0, regs->b6, regs->b7);
	printk("f6  : %05lx%016lx f7  : %05lx%016lx\n",
	       regs->f6.u.bits[1], regs->f6.u.bits[0],
	       regs->f7.u.bits[1], regs->f7.u.bits[0]);
	printk("f8  : %05lx%016lx f9  : %05lx%016lx\n",
	       regs->f8.u.bits[1], regs->f8.u.bits[0],
	       regs->f9.u.bits[1], regs->f9.u.bits[0]);
	printk("f10 : %05lx%016lx f11 : %05lx%016lx\n",
	       regs->f10.u.bits[1], regs->f10.u.bits[0],
	       regs->f11.u.bits[1], regs->f11.u.bits[0]);

	printk("r1  : %016lx r2  : %016lx r3  : %016lx\n", regs->r1, regs->r2, regs->r3);
	printk("r8  : %016lx r9  : %016lx r10 : %016lx\n", regs->r8, regs->r9, regs->r10);
	printk("r11 : %016lx r12 : %016lx r13 : %016lx\n", regs->r11, regs->r12, regs->r13);
	printk("r14 : %016lx r15 : %016lx r16 : %016lx\n", regs->r14, regs->r15, regs->r16);
	printk("r17 : %016lx r18 : %016lx r19 : %016lx\n", regs->r17, regs->r18, regs->r19);
	printk("r20 : %016lx r21 : %016lx r22 : %016lx\n", regs->r20, regs->r21, regs->r22);
	printk("r23 : %016lx r24 : %016lx r25 : %016lx\n", regs->r23, regs->r24, regs->r25);
	printk("r26 : %016lx r27 : %016lx r28 : %016lx\n", regs->r26, regs->r27, regs->r28);
	printk("r29 : %016lx r30 : %016lx r31 : %016lx\n", regs->r29, regs->r30, regs->r31);

	if (user_mode(regs)) {
		/* print the stacked registers */
		unsigned long val, *bsp, ndirty;
		int i, sof, is_nat = 0;

		sof = regs->cr_ifs & 0x7f;	/* size of frame */
		ndirty = (regs->loadrs >> 19);
		bsp = ia64_rse_skip_regs((unsigned long *) regs->ar_bspstore, ndirty);
		for (i = 0; i < sof; ++i) {
			get_user(val, (unsigned long __user *) ia64_rse_skip_regs(bsp, i));
			printk("r%-3u:%c%016lx%s", 32 + i, is_nat ? '*' : ' ', val,
			       ((i == sof - 1) || (i % 3) == 2) ? "\n" : " ");
		}
	} else
		show_stack(NULL, NULL);
}

A
Anirban Sinha 已提交
167 168 169 170 171 172 173
/* local support for deprecated console_print */
void
console_print(const char *s)
{
	printk(KERN_EMERG "%s", s);
}

L
Linus Torvalds 已提交
174
void
175
do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall)
L
Linus Torvalds 已提交
176 177
{
	if (fsys_mode(current, &scr->pt)) {
178 179 180 181
		/*
		 * defer signal-handling etc. until we return to
		 * privilege-level 0.
		 */
L
Linus Torvalds 已提交
182 183 184 185 186 187 188
		if (!ia64_psr(&scr->pt)->lp)
			ia64_psr(&scr->pt)->lp = 1;
		return;
	}

#ifdef CONFIG_PERFMON
	if (current->thread.pfm_needs_checking)
189 190 191 192
		/*
		 * Note: pfm_handle_work() allow us to call it with interrupts
		 * disabled, and may enable interrupts within the function.
		 */
L
Linus Torvalds 已提交
193 194 195 196
		pfm_handle_work();
#endif

	/* deal with pending signal delivery */
197 198
	if (test_thread_flag(TIF_SIGPENDING)) {
		local_irq_enable();	/* force interrupt enable */
A
Alexey Dobriyan 已提交
199
		ia64_do_signal(scr, in_syscall);
200
	}
201

S
Shaohua Li 已提交
202 203 204
	if (test_thread_flag(TIF_NOTIFY_RESUME)) {
		clear_thread_flag(TIF_NOTIFY_RESUME);
		tracehook_notify_resume(&scr->pt);
205 206
		if (current->replacement_session_keyring)
			key_replace_session_keyring();
S
Shaohua Li 已提交
207 208
	}

209
	/* copy user rbs to kernel rbs */
210 211
	if (unlikely(test_thread_flag(TIF_RESTORE_RSE))) {
		local_irq_enable();	/* force interrupt enable */
212
		ia64_sync_krbs();
213 214 215
	}

	local_irq_disable();	/* force interrupt disable */
L
Linus Torvalds 已提交
216 217
}

218 219 220
static int pal_halt        = 1;
static int can_do_pal_halt = 1;

L
Linus Torvalds 已提交
221 222
static int __init nohalt_setup(char * str)
{
K
Ken Chen 已提交
223
	pal_halt = can_do_pal_halt = 0;
L
Linus Torvalds 已提交
224 225 226 227
	return 1;
}
__setup("nohalt", nohalt_setup);

228
void
229 230 231 232 233
update_pal_halt_status(int status)
{
	can_do_pal_halt = pal_halt && status;
}

L
Linus Torvalds 已提交
234 235 236 237 238 239
/*
 * We use this if we don't have any better idle routine..
 */
void
default_idle (void)
{
240
	local_irq_enable();
241
	while (!need_resched()) {
242 243 244 245 246 247 248
		if (can_do_pal_halt) {
			local_irq_disable();
			if (!need_resched()) {
				safe_halt();
			}
			local_irq_enable();
		} else
L
Linus Torvalds 已提交
249
			cpu_relax();
250
	}
L
Linus Torvalds 已提交
251 252 253 254 255 256
}

#ifdef CONFIG_HOTPLUG_CPU
/* We don't actually take CPU down, just spin without interrupts. */
static inline void play_dead(void)
{
257 258
	unsigned int this_cpu = smp_processor_id();

L
Linus Torvalds 已提交
259 260 261 262 263
	/* Ack it */
	__get_cpu_var(cpu_state) = CPU_DEAD;

	max_xtp();
	local_irq_disable();
264 265
	idle_task_exit();
	ia64_jump_to_sal(&sal_boot_rendez_state[this_cpu]);
L
Linus Torvalds 已提交
266
	/*
267 268
	 * The above is a point of no-return, the processor is
	 * expected to be in SAL loop now.
L
Linus Torvalds 已提交
269
	 */
270
	BUG();
L
Linus Torvalds 已提交
271 272 273 274 275 276 277 278
}
#else
static inline void play_dead(void)
{
	BUG();
}
#endif /* CONFIG_HOTPLUG_CPU */

T
Tony Luck 已提交
279
static void do_nothing(void *unused)
L
Linus Torvalds 已提交
280
{
T
Tony Luck 已提交
281
}
282

T
Tony Luck 已提交
283 284 285 286 287 288 289 290 291 292 293 294
/*
 * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
 * pm_idle and update to new pm_idle value. Required while changing pm_idle
 * handler on SMP systems.
 *
 * Caller must have changed pm_idle to the new value before the call. Old
 * pm_idle value will not be used by any CPU after the return of this function.
 */
void cpu_idle_wait(void)
{
	smp_mb();
	/* kick all the CPUs so that they exit out of pm_idle */
295
	smp_call_function(do_nothing, NULL, 1);
L
Linus Torvalds 已提交
296 297 298 299 300 301 302
}
EXPORT_SYMBOL_GPL(cpu_idle_wait);

void __attribute__((noreturn))
cpu_idle (void)
{
	void (*mark_idle)(int) = ia64_mark_idle;
303
  	int cpu = smp_processor_id();
L
Linus Torvalds 已提交
304 305 306

	/* endless idle loop with no priority at all */
	while (1) {
307
		if (can_do_pal_halt) {
308
			current_thread_info()->status &= ~TS_POLLING;
309 310 311 312 313 314
			/*
			 * TS_POLLING-cleared state must be visible before we
			 * test NEED_RESCHED:
			 */
			smp_mb();
		} else {
315
			current_thread_info()->status |= TS_POLLING;
316
		}
317

318 319
		if (!need_resched()) {
			void (*idle)(void);
L
Linus Torvalds 已提交
320 321 322
#ifdef CONFIG_SMP
			min_xtp();
#endif
323
			rmb();
L
Linus Torvalds 已提交
324 325 326 327 328 329 330
			if (mark_idle)
				(*mark_idle)(1);

			idle = pm_idle;
			if (!idle)
				idle = default_idle;
			(*idle)();
331 332
			if (mark_idle)
				(*mark_idle)(0);
L
Linus Torvalds 已提交
333
#ifdef CONFIG_SMP
334
			normal_xtp();
L
Linus Torvalds 已提交
335
#endif
336
		}
337
		preempt_enable_no_resched();
L
Linus Torvalds 已提交
338
		schedule();
339
		preempt_disable();
L
Linus Torvalds 已提交
340
		check_pgt_cache();
341
		if (cpu_is_offline(cpu))
L
Linus Torvalds 已提交
342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417
			play_dead();
	}
}

void
ia64_save_extra (struct task_struct *task)
{
#ifdef CONFIG_PERFMON
	unsigned long info;
#endif

	if ((task->thread.flags & IA64_THREAD_DBG_VALID) != 0)
		ia64_save_debug_regs(&task->thread.dbr[0]);

#ifdef CONFIG_PERFMON
	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
		pfm_save_regs(task);

	info = __get_cpu_var(pfm_syst_info);
	if (info & PFM_CPUINFO_SYST_WIDE)
		pfm_syst_wide_update_task(task, info, 0);
#endif
}

void
ia64_load_extra (struct task_struct *task)
{
#ifdef CONFIG_PERFMON
	unsigned long info;
#endif

	if ((task->thread.flags & IA64_THREAD_DBG_VALID) != 0)
		ia64_load_debug_regs(&task->thread.dbr[0]);

#ifdef CONFIG_PERFMON
	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
		pfm_load_regs(task);

	info = __get_cpu_var(pfm_syst_info);
	if (info & PFM_CPUINFO_SYST_WIDE) 
		pfm_syst_wide_update_task(task, info, 1);
#endif
}

/*
 * Copy the state of an ia-64 thread.
 *
 * We get here through the following  call chain:
 *
 *	from user-level:	from kernel:
 *
 *	<clone syscall>	        <some kernel call frames>
 *	sys_clone		   :
 *	do_fork			do_fork
 *	copy_thread		copy_thread
 *
 * This means that the stack layout is as follows:
 *
 *	+---------------------+ (highest addr)
 *	|   struct pt_regs    |
 *	+---------------------+
 *	| struct switch_stack |
 *	+---------------------+
 *	|                     |
 *	|    memory stack     |
 *	|                     | <-- sp (lowest addr)
 *	+---------------------+
 *
 * Observe that we copy the unat values that are in pt_regs and switch_stack.  Spilling an
 * integer to address X causes bit N in ar.unat to be set to the NaT bit of the register,
 * with N=(X & 0x1ff)/8.  Thus, copying the unat value preserves the NaT bits ONLY if the
 * pt_regs structure in the parent is congruent to that of the child, modulo 512.  Since
 * the stack is page aligned and the page size is at least 4KB, this is always the case,
 * so there is nothing to worry about.
 */
int
A
Alexey Dobriyan 已提交
418
copy_thread(unsigned long clone_flags,
L
Linus Torvalds 已提交
419 420 421
	     unsigned long user_stack_base, unsigned long user_stack_size,
	     struct task_struct *p, struct pt_regs *regs)
{
T
Tony Luck 已提交
422
	extern char ia64_ret_from_clone;
L
Linus Torvalds 已提交
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
	struct switch_stack *child_stack, *stack;
	unsigned long rbs, child_rbs, rbs_size;
	struct pt_regs *child_ptregs;
	int retval = 0;

#ifdef CONFIG_SMP
	/*
	 * For SMP idle threads, fork_by_hand() calls do_fork with
	 * NULL regs.
	 */
	if (!regs)
		return 0;
#endif

	stack = ((struct switch_stack *) regs) - 1;

	child_ptregs = (struct pt_regs *) ((unsigned long) p + IA64_STK_OFFSET) - 1;
	child_stack = (struct switch_stack *) child_ptregs - 1;

	/* copy parent's switch_stack & pt_regs to child: */
	memcpy(child_stack, stack, sizeof(*child_ptregs) + sizeof(*child_stack));

	rbs = (unsigned long) current + IA64_RBS_OFFSET;
	child_rbs = (unsigned long) p + IA64_RBS_OFFSET;
	rbs_size = stack->ar_bspstore - rbs;

	/* copy the parent's register backing store to the child: */
	memcpy((void *) child_rbs, (void *) rbs, rbs_size);

	if (likely(user_mode(child_ptregs))) {
T
Tony Luck 已提交
453
		if (clone_flags & CLONE_SETTLS)
L
Linus Torvalds 已提交
454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472
			child_ptregs->r13 = regs->r16;	/* see sys_clone2() in entry.S */
		if (user_stack_base) {
			child_ptregs->r12 = user_stack_base + user_stack_size - 16;
			child_ptregs->ar_bspstore = user_stack_base;
			child_ptregs->ar_rnat = 0;
			child_ptregs->loadrs = 0;
		}
	} else {
		/*
		 * Note: we simply preserve the relative position of
		 * the stack pointer here.  There is no need to
		 * allocate a scratch area here, since that will have
		 * been taken care of by the caller of sys_clone()
		 * already.
		 */
		child_ptregs->r12 = (unsigned long) child_ptregs - 16; /* kernel sp */
		child_ptregs->r13 = (unsigned long) p;		/* set `current' pointer */
	}
	child_stack->ar_bspstore = child_rbs + rbs_size;
T
Tony Luck 已提交
473
	child_stack->b0 = (unsigned long) &ia64_ret_from_clone;
L
Linus Torvalds 已提交
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

	/* copy parts of thread_struct: */
	p->thread.ksp = (unsigned long) child_stack - 16;

	/* stop some PSR bits from being inherited.
	 * the psr.up/psr.pp bits must be cleared on fork but inherited on execve()
	 * therefore we must specify them explicitly here and not include them in
	 * IA64_PSR_BITS_TO_CLEAR.
	 */
	child_ptregs->cr_ipsr = ((child_ptregs->cr_ipsr | IA64_PSR_BITS_TO_SET)
				 & ~(IA64_PSR_BITS_TO_CLEAR | IA64_PSR_PP | IA64_PSR_UP));

	/*
	 * NOTE: The calling convention considers all floating point
	 * registers in the high partition (fph) to be scratch.  Since
	 * the only way to get to this point is through a system call,
	 * we know that the values in fph are all dead.  Hence, there
	 * is no need to inherit the fph state from the parent to the
	 * child and all we have to do is to make sure that
	 * IA64_THREAD_FPH_VALID is cleared in the child.
	 *
	 * XXX We could push this optimization a bit further by
	 * clearing IA64_THREAD_FPH_VALID on ANY system call.
	 * However, it's not clear this is worth doing.  Also, it
	 * would be a slight deviation from the normal Linux system
	 * call behavior where scratch registers are preserved across
	 * system calls (unless used by the system call itself).
	 */
#	define THREAD_FLAGS_TO_CLEAR	(IA64_THREAD_FPH_VALID | IA64_THREAD_DBG_VALID \
					 | IA64_THREAD_PM_VALID)
#	define THREAD_FLAGS_TO_SET	0
	p->thread.flags = ((current->thread.flags & ~THREAD_FLAGS_TO_CLEAR)
			   | THREAD_FLAGS_TO_SET);
	ia64_drop_fpu(p);	/* don't pick up stale state from a CPU's fph */

#ifdef CONFIG_PERFMON
	if (current->thread.pfm_context)
		pfm_inherit(p, child_ptregs);
#endif
	return retval;
}

static void
do_copy_task_regs (struct task_struct *task, struct unw_frame_info *info, void *arg)
{
519 520
	unsigned long mask, sp, nat_bits = 0, ar_rnat, urbs_end, cfm;
	unsigned long uninitialized_var(ip);	/* GCC be quiet */
L
Linus Torvalds 已提交
521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635
	elf_greg_t *dst = arg;
	struct pt_regs *pt;
	char nat;
	int i;

	memset(dst, 0, sizeof(elf_gregset_t));	/* don't leak any kernel bits to user-level */

	if (unw_unwind_to_user(info) < 0)
		return;

	unw_get_sp(info, &sp);
	pt = (struct pt_regs *) (sp + 16);

	urbs_end = ia64_get_user_rbs_end(task, pt, &cfm);

	if (ia64_sync_user_rbs(task, info->sw, pt->ar_bspstore, urbs_end) < 0)
		return;

	ia64_peek(task, info->sw, urbs_end, (long) ia64_rse_rnat_addr((long *) urbs_end),
		  &ar_rnat);

	/*
	 * coredump format:
	 *	r0-r31
	 *	NaT bits (for r0-r31; bit N == 1 iff rN is a NaT)
	 *	predicate registers (p0-p63)
	 *	b0-b7
	 *	ip cfm user-mask
	 *	ar.rsc ar.bsp ar.bspstore ar.rnat
	 *	ar.ccv ar.unat ar.fpsr ar.pfs ar.lc ar.ec
	 */

	/* r0 is zero */
	for (i = 1, mask = (1UL << i); i < 32; ++i) {
		unw_get_gr(info, i, &dst[i], &nat);
		if (nat)
			nat_bits |= mask;
		mask <<= 1;
	}
	dst[32] = nat_bits;
	unw_get_pr(info, &dst[33]);

	for (i = 0; i < 8; ++i)
		unw_get_br(info, i, &dst[34 + i]);

	unw_get_rp(info, &ip);
	dst[42] = ip + ia64_psr(pt)->ri;
	dst[43] = cfm;
	dst[44] = pt->cr_ipsr & IA64_PSR_UM;

	unw_get_ar(info, UNW_AR_RSC, &dst[45]);
	/*
	 * For bsp and bspstore, unw_get_ar() would return the kernel
	 * addresses, but we need the user-level addresses instead:
	 */
	dst[46] = urbs_end;	/* note: by convention PT_AR_BSP points to the end of the urbs! */
	dst[47] = pt->ar_bspstore;
	dst[48] = ar_rnat;
	unw_get_ar(info, UNW_AR_CCV, &dst[49]);
	unw_get_ar(info, UNW_AR_UNAT, &dst[50]);
	unw_get_ar(info, UNW_AR_FPSR, &dst[51]);
	dst[52] = pt->ar_pfs;	/* UNW_AR_PFS is == to pt->cr_ifs for interrupt frames */
	unw_get_ar(info, UNW_AR_LC, &dst[53]);
	unw_get_ar(info, UNW_AR_EC, &dst[54]);
	unw_get_ar(info, UNW_AR_CSD, &dst[55]);
	unw_get_ar(info, UNW_AR_SSD, &dst[56]);
}

void
do_dump_task_fpu (struct task_struct *task, struct unw_frame_info *info, void *arg)
{
	elf_fpreg_t *dst = arg;
	int i;

	memset(dst, 0, sizeof(elf_fpregset_t));	/* don't leak any "random" bits */

	if (unw_unwind_to_user(info) < 0)
		return;

	/* f0 is 0.0, f1 is 1.0 */

	for (i = 2; i < 32; ++i)
		unw_get_fr(info, i, dst + i);

	ia64_flush_fph(task);
	if ((task->thread.flags & IA64_THREAD_FPH_VALID) != 0)
		memcpy(dst + 32, task->thread.fph, 96*16);
}

void
do_copy_regs (struct unw_frame_info *info, void *arg)
{
	do_copy_task_regs(current, info, arg);
}

void
do_dump_fpu (struct unw_frame_info *info, void *arg)
{
	do_dump_task_fpu(current, info, arg);
}

void
ia64_elf_core_copy_regs (struct pt_regs *pt, elf_gregset_t dst)
{
	unw_init_running(do_copy_regs, dst);
}

int
dump_fpu (struct pt_regs *pt, elf_fpregset_t dst)
{
	unw_init_running(do_dump_fpu, dst);
	return 1;	/* f0-f31 are always valid so we always return 1 */
}

long
636
sys_execve (const char __user *filename, char __user * __user *argv, char __user * __user *envp,
L
Linus Torvalds 已提交
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
	    struct pt_regs *regs)
{
	char *fname;
	int error;

	fname = getname(filename);
	error = PTR_ERR(fname);
	if (IS_ERR(fname))
		goto out;
	error = do_execve(fname, argv, envp, regs);
	putname(fname);
out:
	return error;
}

pid_t
kernel_thread (int (*fn)(void *), void *arg, unsigned long flags)
{
	extern void start_kernel_thread (void);
	unsigned long *helper_fptr = (unsigned long *) &start_kernel_thread;
	struct {
		struct switch_stack sw;
		struct pt_regs pt;
	} regs;

	memset(&regs, 0, sizeof(regs));
	regs.pt.cr_iip = helper_fptr[0];	/* set entry point (IP) */
	regs.pt.r1 = helper_fptr[1];		/* set GP */
	regs.pt.r9 = (unsigned long) fn;	/* 1st argument */
	regs.pt.r11 = (unsigned long) arg;	/* 2nd argument */
	/* Preserve PSR bits, except for bits 32-34 and 37-45, which we can't read.  */
	regs.pt.cr_ipsr = ia64_getreg(_IA64_REG_PSR) | IA64_PSR_BN;
	regs.pt.cr_ifs = 1UL << 63;		/* mark as valid, empty frame */
	regs.sw.ar_fpsr = regs.pt.ar_fpsr = ia64_getreg(_IA64_REG_AR_FPSR);
	regs.sw.ar_bspstore = (unsigned long) current + IA64_RBS_OFFSET;
	regs.sw.pr = (1 << PRED_KERNEL_STACK);
	return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs.pt, 0, NULL, NULL);
}
EXPORT_SYMBOL(kernel_thread);

/* This gets called from kernel_thread() via ia64_invoke_thread_helper().  */
int
kernel_thread_helper (int (*fn)(void *), void *arg)
{
	return (*fn)(arg);
}

/*
 * Flush thread state.  This is called when a thread does an execve().
 */
void
flush_thread (void)
{
	/* drop floating-point and debug-register state if it exists: */
	current->thread.flags &= ~(IA64_THREAD_FPH_VALID | IA64_THREAD_DBG_VALID);
	ia64_drop_fpu(current);
}

/*
 * Clean up state associated with current thread.  This is called when
 * the thread calls exit().
 */
void
exit_thread (void)
{
702

L
Linus Torvalds 已提交
703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721
	ia64_drop_fpu(current);
#ifdef CONFIG_PERFMON
       /* if needed, stop monitoring and flush state to perfmon context */
	if (current->thread.pfm_context)
		pfm_exit_thread(current);

	/* free debug register resources */
	if (current->thread.flags & IA64_THREAD_DBG_VALID)
		pfm_release_debug_registers(current);
#endif
}

unsigned long
get_wchan (struct task_struct *p)
{
	struct unw_frame_info info;
	unsigned long ip;
	int count = 0;

722 723 724
	if (!p || p == current || p->state == TASK_RUNNING)
		return 0;

L
Linus Torvalds 已提交
725 726 727 728 729 730 731 732 733 734
	/*
	 * Note: p may not be a blocked task (it could be current or
	 * another process running on some other CPU.  Rather than
	 * trying to determine if p is really blocked, we just assume
	 * it's blocked and rely on the unwind routines to fail
	 * gracefully if the process wasn't really blocked after all.
	 * --davidm 99/12/15
	 */
	unw_init_from_blocked_task(&info, p);
	do {
735 736
		if (p->state == TASK_RUNNING)
			return 0;
L
Linus Torvalds 已提交
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
		if (unw_unwind(&info) < 0)
			return 0;
		unw_get_ip(&info, &ip);
		if (!in_sched_functions(ip))
			return ip;
	} while (count++ < 16);
	return 0;
}

void
cpu_halt (void)
{
	pal_power_mgmt_info_u_t power_info[8];
	unsigned long min_power;
	int i, min_power_state;

	if (ia64_pal_halt_info(power_info) != 0)
		return;

	min_power_state = 0;
	min_power = power_info[0].pal_power_mgmt_info_s.power_consumption;
	for (i = 1; i < 8; ++i)
		if (power_info[i].pal_power_mgmt_info_s.im
		    && power_info[i].pal_power_mgmt_info_s.power_consumption < min_power) {
			min_power = power_info[i].pal_power_mgmt_info_s.power_consumption;
			min_power_state = i;
		}

	while (1)
		ia64_pal_halt(min_power_state);
}

769 770 771 772 773 774 775 776 777 778 779 780 781 782 783
void machine_shutdown(void)
{
#ifdef CONFIG_HOTPLUG_CPU
	int cpu;

	for_each_online_cpu(cpu) {
		if (cpu != smp_processor_id())
			cpu_down(cpu);
	}
#endif
#ifdef CONFIG_KEXEC
	kexec_disable_iosapic();
#endif
}

L
Linus Torvalds 已提交
784 785 786
void
machine_restart (char *restart_cmd)
{
787
	(void) notify_die(DIE_MACHINE_RESTART, restart_cmd, NULL, 0, 0, 0);
L
Linus Torvalds 已提交
788 789 790 791 792 793
	(*efi.reset_system)(EFI_RESET_WARM, 0, 0, NULL);
}

void
machine_halt (void)
{
794
	(void) notify_die(DIE_MACHINE_HALT, "", NULL, 0, 0, 0);
L
Linus Torvalds 已提交
795 796 797 798 799 800 801 802 803 804 805
	cpu_halt();
}

void
machine_power_off (void)
{
	if (pm_power_off)
		pm_power_off();
	machine_halt();
}