process.c 28.1 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
/*
 *  Derived from "arch/i386/kernel/process.c"
 *    Copyright (C) 1995  Linus Torvalds
 *
 *  Updated and modified by Cort Dougan (cort@cs.nmt.edu) and
 *  Paul Mackerras (paulus@cs.anu.edu.au)
 *
 *  PowerPC version
 *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
 *
 *  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.
 */

#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/elf.h>
#include <linux/init.h>
#include <linux/prctl.h>
#include <linux/init_task.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/mqueue.h>
#include <linux/hardirq.h>
35
#include <linux/utsname.h>
36
#include <linux/ftrace.h>
37
#include <linux/kernel_stat.h>
38 39
#include <linux/personality.h>
#include <linux/random.h>
40 41 42 43 44 45 46 47

#include <asm/pgtable.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/prom.h>
48
#include <asm/machdep.h>
49
#include <asm/time.h>
50
#include <asm/syscalls.h>
51 52 53
#ifdef CONFIG_PPC64
#include <asm/firmware.h>
#endif
54 55
#include <linux/kprobes.h>
#include <linux/kdebug.h>
56 57 58 59 60 61

extern unsigned long _get_SP(void);

#ifndef CONFIG_SMP
struct task_struct *last_task_used_math = NULL;
struct task_struct *last_task_used_altivec = NULL;
62
struct task_struct *last_task_used_vsx = NULL;
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
struct task_struct *last_task_used_spe = NULL;
#endif

/*
 * Make sure the floating-point register state in the
 * the thread_struct is up to date for task tsk.
 */
void flush_fp_to_thread(struct task_struct *tsk)
{
	if (tsk->thread.regs) {
		/*
		 * We need to disable preemption here because if we didn't,
		 * another process could get scheduled after the regs->msr
		 * test but before we have finished saving the FP registers
		 * to the thread_struct.  That process could take over the
		 * FPU, and then when we get scheduled again we would store
		 * bogus values for the remaining FP registers.
		 */
		preempt_disable();
		if (tsk->thread.regs->msr & MSR_FP) {
#ifdef CONFIG_SMP
			/*
			 * This should only ever be called for current or
			 * for a stopped child process.  Since we save away
			 * the FP register state on context switch on SMP,
			 * there is something wrong if a stopped child appears
			 * to still have its FP state in the CPU registers.
			 */
			BUG_ON(tsk != current);
#endif
93
			giveup_fpu(tsk);
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
		}
		preempt_enable();
	}
}

void enable_kernel_fp(void)
{
	WARN_ON(preemptible());

#ifdef CONFIG_SMP
	if (current->thread.regs && (current->thread.regs->msr & MSR_FP))
		giveup_fpu(current);
	else
		giveup_fpu(NULL);	/* just enables FP for kernel */
#else
	giveup_fpu(last_task_used_math);
#endif /* CONFIG_SMP */
}
EXPORT_SYMBOL(enable_kernel_fp);

#ifdef CONFIG_ALTIVEC
void enable_kernel_altivec(void)
{
	WARN_ON(preemptible());

#ifdef CONFIG_SMP
	if (current->thread.regs && (current->thread.regs->msr & MSR_VEC))
		giveup_altivec(current);
	else
		giveup_altivec(NULL);	/* just enable AltiVec for kernel - force */
#else
	giveup_altivec(last_task_used_altivec);
#endif /* CONFIG_SMP */
}
EXPORT_SYMBOL(enable_kernel_altivec);

/*
 * Make sure the VMX/Altivec register state in the
 * the thread_struct is up to date for task tsk.
 */
void flush_altivec_to_thread(struct task_struct *tsk)
{
	if (tsk->thread.regs) {
		preempt_disable();
		if (tsk->thread.regs->msr & MSR_VEC) {
#ifdef CONFIG_SMP
			BUG_ON(tsk != current);
#endif
142
			giveup_altivec(tsk);
143 144 145 146 147 148
		}
		preempt_enable();
	}
}
#endif /* CONFIG_ALTIVEC */

149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167
#ifdef CONFIG_VSX
#if 0
/* not currently used, but some crazy RAID module might want to later */
void enable_kernel_vsx(void)
{
	WARN_ON(preemptible());

#ifdef CONFIG_SMP
	if (current->thread.regs && (current->thread.regs->msr & MSR_VSX))
		giveup_vsx(current);
	else
		giveup_vsx(NULL);	/* just enable vsx for kernel - force */
#else
	giveup_vsx(last_task_used_vsx);
#endif /* CONFIG_SMP */
}
EXPORT_SYMBOL(enable_kernel_vsx);
#endif

168 169 170 171 172 173 174
void giveup_vsx(struct task_struct *tsk)
{
	giveup_fpu(tsk);
	giveup_altivec(tsk);
	__giveup_vsx(tsk);
}

175 176 177 178 179 180 181 182 183 184 185 186 187 188 189
void flush_vsx_to_thread(struct task_struct *tsk)
{
	if (tsk->thread.regs) {
		preempt_disable();
		if (tsk->thread.regs->msr & MSR_VSX) {
#ifdef CONFIG_SMP
			BUG_ON(tsk != current);
#endif
			giveup_vsx(tsk);
		}
		preempt_enable();
	}
}
#endif /* CONFIG_VSX */

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
#ifdef CONFIG_SPE

void enable_kernel_spe(void)
{
	WARN_ON(preemptible());

#ifdef CONFIG_SMP
	if (current->thread.regs && (current->thread.regs->msr & MSR_SPE))
		giveup_spe(current);
	else
		giveup_spe(NULL);	/* just enable SPE for kernel - force */
#else
	giveup_spe(last_task_used_spe);
#endif /* __SMP __ */
}
EXPORT_SYMBOL(enable_kernel_spe);

void flush_spe_to_thread(struct task_struct *tsk)
{
	if (tsk->thread.regs) {
		preempt_disable();
		if (tsk->thread.regs->msr & MSR_SPE) {
#ifdef CONFIG_SMP
			BUG_ON(tsk != current);
#endif
215
			giveup_spe(tsk);
216 217 218 219 220 221
		}
		preempt_enable();
	}
}
#endif /* CONFIG_SPE */

222
#ifndef CONFIG_SMP
223 224 225 226
/*
 * If we are doing lazy switching of CPU state (FP, altivec or SPE),
 * and the current task has some state, discard it.
 */
227
void discard_lazy_cpu_state(void)
228 229 230 231 232 233 234 235
{
	preempt_disable();
	if (last_task_used_math == current)
		last_task_used_math = NULL;
#ifdef CONFIG_ALTIVEC
	if (last_task_used_altivec == current)
		last_task_used_altivec = NULL;
#endif /* CONFIG_ALTIVEC */
236 237 238 239
#ifdef CONFIG_VSX
	if (last_task_used_vsx == current)
		last_task_used_vsx = NULL;
#endif /* CONFIG_VSX */
240 241 242 243 244 245
#ifdef CONFIG_SPE
	if (last_task_used_spe == current)
		last_task_used_spe = NULL;
#endif
	preempt_enable();
}
246
#endif /* CONFIG_SMP */
247

248 249 250 251 252 253 254 255 256 257 258 259 260
void do_dabr(struct pt_regs *regs, unsigned long address,
		    unsigned long error_code)
{
	siginfo_t info;

	if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
			11, SIGSEGV) == NOTIFY_STOP)
		return;

	if (debugger_dabr_match(regs))
		return;

	/* Clear the DAC and struct entries.  One shot trigger */
261
#if defined(CONFIG_BOOKE)
262 263 264 265 266 267 268 269 270 271 272 273 274 275 276
	mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~(DBSR_DAC1R | DBSR_DAC1W
							| DBCR0_IDM));
#endif

	/* Clear the DABR */
	set_dabr(0);

	/* Deliver the signal to userspace */
	info.si_signo = SIGTRAP;
	info.si_errno = 0;
	info.si_code = TRAP_HWBKPT;
	info.si_addr = (void __user *)address;
	force_sig_info(SIGTRAP, &info, current);
}

277 278
static DEFINE_PER_CPU(unsigned long, current_dabr);

279 280
int set_dabr(unsigned long dabr)
{
281 282
	__get_cpu_var(current_dabr) = dabr;

283 284
	if (ppc_md.set_dabr)
		return ppc_md.set_dabr(dabr);
285

286 287
	/* XXX should we have a CPU_FTR_HAS_DABR ? */
#if defined(CONFIG_PPC64) || defined(CONFIG_6xx)
288
	mtspr(SPRN_DABR, dabr);
289
#endif
290

291
#if defined(CONFIG_BOOKE)
292 293 294
	mtspr(SPRN_DAC1, dabr);
#endif

295
	return 0;
296 297
}

298 299 300
#ifdef CONFIG_PPC64
DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array);
#endif
301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335

struct task_struct *__switch_to(struct task_struct *prev,
	struct task_struct *new)
{
	struct thread_struct *new_thread, *old_thread;
	unsigned long flags;
	struct task_struct *last;

#ifdef CONFIG_SMP
	/* avoid complexity of lazy save/restore of fpu
	 * by just saving it every time we switch out if
	 * this task used the fpu during the last quantum.
	 *
	 * If it tries to use the fpu again, it'll trap and
	 * reload its fp regs.  So we don't have to do a restore
	 * every switch, just a save.
	 *  -- Cort
	 */
	if (prev->thread.regs && (prev->thread.regs->msr & MSR_FP))
		giveup_fpu(prev);
#ifdef CONFIG_ALTIVEC
	/*
	 * If the previous thread used altivec in the last quantum
	 * (thus changing altivec regs) then save them.
	 * We used to check the VRSAVE register but not all apps
	 * set it, so we don't rely on it now (and in fact we need
	 * to save & restore VSCR even if VRSAVE == 0).  -- paulus
	 *
	 * On SMP we always save/restore altivec regs just to avoid the
	 * complexity of changing processors.
	 *  -- Cort
	 */
	if (prev->thread.regs && (prev->thread.regs->msr & MSR_VEC))
		giveup_altivec(prev);
#endif /* CONFIG_ALTIVEC */
336 337
#ifdef CONFIG_VSX
	if (prev->thread.regs && (prev->thread.regs->msr & MSR_VSX))
338 339
		/* VMX and FPU registers are already save here */
		__giveup_vsx(prev);
340
#endif /* CONFIG_VSX */
341 342 343 344 345 346 347 348 349 350
#ifdef CONFIG_SPE
	/*
	 * If the previous thread used spe in the last quantum
	 * (thus changing spe regs) then save them.
	 *
	 * On SMP we always save/restore spe regs just to avoid the
	 * complexity of changing processors.
	 */
	if ((prev->thread.regs && (prev->thread.regs->msr & MSR_SPE)))
		giveup_spe(prev);
351 352 353 354 355 356 357 358 359 360
#endif /* CONFIG_SPE */

#else  /* CONFIG_SMP */
#ifdef CONFIG_ALTIVEC
	/* Avoid the trap.  On smp this this never happens since
	 * we don't set last_task_used_altivec -- Cort
	 */
	if (new->thread.regs && last_task_used_altivec == new)
		new->thread.regs->msr |= MSR_VEC;
#endif /* CONFIG_ALTIVEC */
361 362 363 364
#ifdef CONFIG_VSX
	if (new->thread.regs && last_task_used_vsx == new)
		new->thread.regs->msr |= MSR_VSX;
#endif /* CONFIG_VSX */
365
#ifdef CONFIG_SPE
366 367 368 369 370 371
	/* Avoid the trap.  On smp this this never happens since
	 * we don't set last_task_used_spe
	 */
	if (new->thread.regs && last_task_used_spe == new)
		new->thread.regs->msr |= MSR_SPE;
#endif /* CONFIG_SPE */
372

373 374
#endif /* CONFIG_SMP */

375
	if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr))
376 377
		set_dabr(new->thread.dabr);

378
#if defined(CONFIG_BOOKE)
379 380 381 382 383
	/* If new thread DAC (HW breakpoint) is the same then leave it */
	if (new->thread.dabr)
		set_dabr(new->thread.dabr);
#endif

384 385
	new_thread = &new->thread;
	old_thread = &current->thread;
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400

#ifdef CONFIG_PPC64
	/*
	 * Collect processor utilization data per process
	 */
	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
		long unsigned start_tb, current_tb;
		start_tb = old_thread->start_tb;
		cu->current_tb = current_tb = mfspr(SPRN_PURR);
		old_thread->accum_tb += (current_tb - start_tb);
		new_thread->start_tb = current_tb;
	}
#endif

401
	local_irq_save(flags);
402 403

	account_system_vtime(current);
404
	account_process_vtime(current);
405 406
	calculate_steal_time();

407 408 409 410 411 412
	/*
	 * We can't take a PMU exception inside _switch() since there is a
	 * window where the kernel stack SLB and the kernel stack are out
	 * of sync. Hard disable here.
	 */
	hard_irq_disable();
413 414 415 416 417 418 419
	last = _switch(old_thread, new_thread);

	local_irq_restore(flags);

	return last;
}

420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435
static int instructions_to_print = 16;

static void show_instructions(struct pt_regs *regs)
{
	int i;
	unsigned long pc = regs->nip - (instructions_to_print * 3 / 4 *
			sizeof(int));

	printk("Instruction dump:");

	for (i = 0; i < instructions_to_print; i++) {
		int instr;

		if (!(i % 8))
			printk("\n");

436 437 438 439 440 441 442 443
#if !defined(CONFIG_BOOKE)
		/* If executing with the IMMU off, adjust pc rather
		 * than print XXXXXXXX.
		 */
		if (!(regs->msr & MSR_IR))
			pc = (unsigned long)phys_to_virt(pc);
#endif

444 445 446 447
		/* We use __get_user here *only* to avoid an OOPS on a
		 * bad address because the pc *should* only be a
		 * kernel address.
		 */
448 449
		if (!__kernel_text_address(pc) ||
		     __get_user(instr, (unsigned int __user *)pc)) {
450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470
			printk("XXXXXXXX ");
		} else {
			if (regs->nip == pc)
				printk("<%08x> ", instr);
			else
				printk("%08x ", instr);
		}

		pc += sizeof(int);
	}

	printk("\n");
}

static struct regbit {
	unsigned long bit;
	const char *name;
} msr_bits[] = {
	{MSR_EE,	"EE"},
	{MSR_PR,	"PR"},
	{MSR_FP,	"FP"},
471 472
	{MSR_VEC,	"VEC"},
	{MSR_VSX,	"VSX"},
473
	{MSR_ME,	"ME"},
474 475
	{MSR_CE,	"CE"},
	{MSR_DE,	"DE"},
476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494
	{MSR_IR,	"IR"},
	{MSR_DR,	"DR"},
	{0,		NULL}
};

static void printbits(unsigned long val, struct regbit *bits)
{
	const char *sep = "";

	printk("<");
	for (; bits->bit; ++bits)
		if (val & bits->bit) {
			printk("%s%s", sep, bits->name);
			sep = ",";
		}
	printk(">");
}

#ifdef CONFIG_PPC64
495
#define REG		"%016lx"
496 497 498
#define REGS_PER_LINE	4
#define LAST_VOLATILE	13
#else
499
#define REG		"%08lx"
500 501 502 503
#define REGS_PER_LINE	8
#define LAST_VOLATILE	12
#endif

504 505 506 507
void show_regs(struct pt_regs * regs)
{
	int i, trap;

508 509 510
	printk("NIP: "REG" LR: "REG" CTR: "REG"\n",
	       regs->nip, regs->link, regs->ctr);
	printk("REGS: %p TRAP: %04lx   %s  (%s)\n",
511
	       regs, regs->trap, print_tainted(), init_utsname()->release);
512 513
	printk("MSR: "REG" ", regs->msr);
	printbits(regs->msr, msr_bits);
514
	printk("  CR: %08lx  XER: %08lx\n", regs->ccr, regs->xer);
515 516
	trap = TRAP(regs);
	if (trap == 0x300 || trap == 0x600)
517 518 519
#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
		printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr);
#else
520
		printk("DAR: "REG", DSISR: "REG"\n", regs->dar, regs->dsisr);
521
#endif
522
	printk("TASK = %p[%d] '%s' THREAD: %p",
523
	       current, task_pid_nr(current), current->comm, task_thread_info(current));
524 525

#ifdef CONFIG_SMP
526
	printk(" CPU: %d", raw_smp_processor_id());
527 528 529
#endif /* CONFIG_SMP */

	for (i = 0;  i < 32;  i++) {
530
		if ((i % REGS_PER_LINE) == 0)
531
			printk("\n" KERN_INFO "GPR%02d: ", i);
532 533
		printk(REG " ", regs->gpr[i]);
		if (i == LAST_VOLATILE && !FULL_REGS(regs))
534 535 536 537 538 539 540 541
			break;
	}
	printk("\n");
#ifdef CONFIG_KALLSYMS
	/*
	 * Lookup NIP late so we have the best change of getting the
	 * above info out without failing
	 */
542 543
	printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip);
	printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link);
544 545
#endif
	show_stack(current, (unsigned long *) regs->gpr[1]);
546 547
	if (!user_mode(regs))
		show_instructions(regs);
548 549 550 551
}

void exit_thread(void)
{
552
	discard_lazy_cpu_state();
553 554 555 556
}

void flush_thread(void)
{
557 558 559
#ifdef CONFIG_PPC64
	struct thread_info *t = current_thread_info();

560 561 562 563 564 565 566
	if (test_ti_thread_flag(t, TIF_ABI_PENDING)) {
		clear_ti_thread_flag(t, TIF_ABI_PENDING);
		if (test_ti_thread_flag(t, TIF_32BIT))
			clear_ti_thread_flag(t, TIF_32BIT);
		else
			set_ti_thread_flag(t, TIF_32BIT);
	}
567 568
#endif

569
	discard_lazy_cpu_state();
570 571 572 573

	if (current->thread.dabr) {
		current->thread.dabr = 0;
		set_dabr(0);
574

575
#if defined(CONFIG_BOOKE)
576 577
		current->thread.dbcr0 &= ~(DBSR_DAC1R | DBSR_DAC1W);
#endif
578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593
	}
}

void
release_thread(struct task_struct *t)
{
}

/*
 * This gets called before we allocate a new thread and copy
 * the current task into it.
 */
void prepare_to_copy(struct task_struct *tsk)
{
	flush_fp_to_thread(current);
	flush_altivec_to_thread(current);
594
	flush_vsx_to_thread(current);
595 596 597 598 599 600
	flush_spe_to_thread(current);
}

/*
 * Copy a thread..
 */
601 602 603
int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
		unsigned long unused, struct task_struct *p,
		struct pt_regs *regs)
604 605 606
{
	struct pt_regs *childregs, *kregs;
	extern void ret_from_fork(void);
A
Al Viro 已提交
607
	unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
608 609 610 611 612 613 614 615 616

	CHECK_FULL_REGS(regs);
	/* Copy registers */
	sp -= sizeof(struct pt_regs);
	childregs = (struct pt_regs *) sp;
	*childregs = *regs;
	if ((childregs->msr & MSR_PR) == 0) {
		/* for kernel thread, set `current' and stackptr in new task */
		childregs->gpr[1] = sp + sizeof(struct pt_regs);
617
#ifdef CONFIG_PPC32
618
		childregs->gpr[2] = (unsigned long) p;
619
#else
A
Al Viro 已提交
620
		clear_tsk_thread_flag(p, TIF_32BIT);
621
#endif
622 623 624 625
		p->thread.regs = NULL;	/* no user register state */
	} else {
		childregs->gpr[1] = usp;
		p->thread.regs = childregs;
626 627 628 629 630 631 632 633
		if (clone_flags & CLONE_SETTLS) {
#ifdef CONFIG_PPC64
			if (!test_thread_flag(TIF_32BIT))
				childregs->gpr[13] = childregs->gpr[6];
			else
#endif
				childregs->gpr[2] = childregs->gpr[6];
		}
634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649
	}
	childregs->gpr[3] = 0;  /* Result from fork() */
	sp -= STACK_FRAME_OVERHEAD;

	/*
	 * The way this works is that at some point in the future
	 * some task will call _switch to switch to the new task.
	 * That will pop off the stack frame created below and start
	 * the new task running at ret_from_fork.  The new task will
	 * do some house keeping and then return from the fork or clone
	 * system call, using the stack frame created above.
	 */
	sp -= sizeof(struct pt_regs);
	kregs = (struct pt_regs *) sp;
	sp -= STACK_FRAME_OVERHEAD;
	p->thread.ksp = sp;
650 651
	p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
				_ALIGN_UP(sizeof(struct thread_info), 16);
652

653 654
#ifdef CONFIG_PPC64
	if (cpu_has_feature(CPU_FTR_SLB)) {
P
Paul Mackerras 已提交
655
		unsigned long sp_vsid;
656
		unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp;
657

P
Paul Mackerras 已提交
658 659 660 661 662 663
		if (cpu_has_feature(CPU_FTR_1T_SEGMENT))
			sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T)
				<< SLB_VSID_SHIFT_1T;
		else
			sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_256M)
				<< SLB_VSID_SHIFT;
664
		sp_vsid |= SLB_VSID_KERNEL | llp;
665 666 667 668 669 670 671 672 673 674 675 676 677
		p->thread.ksp_vsid = sp_vsid;
	}

	/*
	 * The PPC64 ABI makes use of a TOC to contain function 
	 * pointers.  The function (ret_from_except) is actually a pointer
	 * to the TOC entry.  The first entry is a pointer to the actual
	 * function.
 	 */
	kregs->nip = *((unsigned long *)ret_from_fork);
#else
	kregs->nip = (unsigned long)ret_from_fork;
#endif
678 679 680 681 682 683 684

	return 0;
}

/*
 * Set up a thread for executing a new program
 */
685
void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
686
{
687 688 689 690
#ifdef CONFIG_PPC64
	unsigned long load_addr = regs->gpr[2];	/* saved by ELF_PLAT_INIT */
#endif

691
	set_fs(USER_DS);
692 693 694 695 696 697

	/*
	 * If we exec out of a kernel thread then thread.regs will not be
	 * set.  Do it now.
	 */
	if (!current->thread.regs) {
A
Al Viro 已提交
698 699
		struct pt_regs *regs = task_stack_page(current) + THREAD_SIZE;
		current->thread.regs = regs - 1;
700 701
	}

702 703 704 705 706 707
	memset(regs->gpr, 0, sizeof(regs->gpr));
	regs->ctr = 0;
	regs->link = 0;
	regs->xer = 0;
	regs->ccr = 0;
	regs->gpr[1] = sp;
708

709 710 711 712 713 714 715
	/*
	 * We have just cleared all the nonvolatile GPRs, so make
	 * FULL_REGS(regs) return true.  This is necessary to allow
	 * ptrace to examine the thread immediately after exec.
	 */
	regs->trap &= ~1UL;

716 717 718
#ifdef CONFIG_PPC32
	regs->mq = 0;
	regs->nip = start;
719
	regs->msr = MSR_USER;
720
#else
S
Stephen Rothwell 已提交
721
	if (!test_thread_flag(TIF_32BIT)) {
722
		unsigned long entry, toc;
723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741

		/* start is a relocated pointer to the function descriptor for
		 * the elf _start routine.  The first entry in the function
		 * descriptor is the entry address of _start and the second
		 * entry is the TOC value we need to use.
		 */
		__get_user(entry, (unsigned long __user *)start);
		__get_user(toc, (unsigned long __user *)start+1);

		/* Check whether the e_entry function descriptor entries
		 * need to be relocated before we can use them.
		 */
		if (load_addr != 0) {
			entry += load_addr;
			toc   += load_addr;
		}
		regs->nip = entry;
		regs->gpr[2] = toc;
		regs->msr = MSR_USER64;
S
Stephen Rothwell 已提交
742 743 744 745
	} else {
		regs->nip = start;
		regs->gpr[2] = 0;
		regs->msr = MSR_USER32;
746 747 748
	}
#endif

749
	discard_lazy_cpu_state();
750 751 752
#ifdef CONFIG_VSX
	current->thread.used_vsr = 0;
#endif
753
	memset(current->thread.fpr, 0, sizeof(current->thread.fpr));
754
	current->thread.fpscr.val = 0;
755 756 757
#ifdef CONFIG_ALTIVEC
	memset(current->thread.vr, 0, sizeof(current->thread.vr));
	memset(&current->thread.vscr, 0, sizeof(current->thread.vscr));
758
	current->thread.vscr.u[3] = 0x00010000; /* Java mode disabled */
759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782
	current->thread.vrsave = 0;
	current->thread.used_vr = 0;
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_SPE
	memset(current->thread.evr, 0, sizeof(current->thread.evr));
	current->thread.acc = 0;
	current->thread.spefscr = 0;
	current->thread.used_spe = 0;
#endif /* CONFIG_SPE */
}

#define PR_FP_ALL_EXCEPT (PR_FP_EXC_DIV | PR_FP_EXC_OVF | PR_FP_EXC_UND \
		| PR_FP_EXC_RES | PR_FP_EXC_INV)

int set_fpexc_mode(struct task_struct *tsk, unsigned int val)
{
	struct pt_regs *regs = tsk->thread.regs;

	/* This is a bit hairy.  If we are an SPE enabled  processor
	 * (have embedded fp) we store the IEEE exception enable flags in
	 * fpexc_mode.  fpexc_mode is also used for setting FP exception
	 * mode (asyn, precise, disabled) for 'Classic' FP. */
	if (val & PR_FP_EXC_SW_ENABLE) {
#ifdef CONFIG_SPE
783 784 785 786 787 788 789
		if (cpu_has_feature(CPU_FTR_SPE)) {
			tsk->thread.fpexc_mode = val &
				(PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT);
			return 0;
		} else {
			return -EINVAL;
		}
790 791 792 793
#else
		return -EINVAL;
#endif
	}
794 795 796 797 798 799 800 801 802 803 804 805

	/* on a CONFIG_SPE this does not hurt us.  The bits that
	 * __pack_fe01 use do not overlap with bits used for
	 * PR_FP_EXC_SW_ENABLE.  Additionally, the MSR[FE0,FE1] bits
	 * on CONFIG_SPE implementations are reserved so writing to
	 * them does not change anything */
	if (val > PR_FP_EXC_PRECISE)
		return -EINVAL;
	tsk->thread.fpexc_mode = __pack_fe01(val);
	if (regs != NULL && (regs->msr & MSR_FP) != 0)
		regs->msr = (regs->msr & ~(MSR_FE0|MSR_FE1))
			| tsk->thread.fpexc_mode;
806 807 808 809 810 811 812 813 814
	return 0;
}

int get_fpexc_mode(struct task_struct *tsk, unsigned long adr)
{
	unsigned int val;

	if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE)
#ifdef CONFIG_SPE
815 816 817 818
		if (cpu_has_feature(CPU_FTR_SPE))
			val = tsk->thread.fpexc_mode;
		else
			return -EINVAL;
819 820 821 822 823 824 825 826
#else
		return -EINVAL;
#endif
	else
		val = __unpack_fe01(tsk->thread.fpexc_mode);
	return put_user(val, (unsigned int __user *) adr);
}

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
int set_endian(struct task_struct *tsk, unsigned int val)
{
	struct pt_regs *regs = tsk->thread.regs;

	if ((val == PR_ENDIAN_LITTLE && !cpu_has_feature(CPU_FTR_REAL_LE)) ||
	    (val == PR_ENDIAN_PPC_LITTLE && !cpu_has_feature(CPU_FTR_PPC_LE)))
		return -EINVAL;

	if (regs == NULL)
		return -EINVAL;

	if (val == PR_ENDIAN_BIG)
		regs->msr &= ~MSR_LE;
	else if (val == PR_ENDIAN_LITTLE || val == PR_ENDIAN_PPC_LITTLE)
		regs->msr |= MSR_LE;
	else
		return -EINVAL;

	return 0;
}

int get_endian(struct task_struct *tsk, unsigned long adr)
{
	struct pt_regs *regs = tsk->thread.regs;
	unsigned int val;

	if (!cpu_has_feature(CPU_FTR_PPC_LE) &&
	    !cpu_has_feature(CPU_FTR_REAL_LE))
		return -EINVAL;

	if (regs == NULL)
		return -EINVAL;

	if (regs->msr & MSR_LE) {
		if (cpu_has_feature(CPU_FTR_REAL_LE))
			val = PR_ENDIAN_LITTLE;
		else
			val = PR_ENDIAN_PPC_LITTLE;
	} else
		val = PR_ENDIAN_BIG;

	return put_user(val, (unsigned int __user *)adr);
}

871 872 873 874 875 876 877 878 879 880 881
int set_unalign_ctl(struct task_struct *tsk, unsigned int val)
{
	tsk->thread.align_ctl = val;
	return 0;
}

int get_unalign_ctl(struct task_struct *tsk, unsigned long adr)
{
	return put_user(tsk->thread.align_ctl, (unsigned int __user *)adr);
}

882 883
#define TRUNC_PTR(x)	((typeof(x))(((unsigned long)(x)) & 0xffffffff))

884 885 886 887 888 889 890 891
int sys_clone(unsigned long clone_flags, unsigned long usp,
	      int __user *parent_tidp, void __user *child_threadptr,
	      int __user *child_tidp, int p6,
	      struct pt_regs *regs)
{
	CHECK_FULL_REGS(regs);
	if (usp == 0)
		usp = regs->gpr[1];	/* stack pointer for child */
892 893 894 895 896 897
#ifdef CONFIG_PPC64
	if (test_thread_flag(TIF_32BIT)) {
		parent_tidp = TRUNC_PTR(parent_tidp);
		child_tidp = TRUNC_PTR(child_tidp);
	}
#endif
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
 	return do_fork(clone_flags, usp, regs, 0, parent_tidp, child_tidp);
}

int sys_fork(unsigned long p1, unsigned long p2, unsigned long p3,
	     unsigned long p4, unsigned long p5, unsigned long p6,
	     struct pt_regs *regs)
{
	CHECK_FULL_REGS(regs);
	return do_fork(SIGCHLD, regs->gpr[1], regs, 0, NULL, NULL);
}

int sys_vfork(unsigned long p1, unsigned long p2, unsigned long p3,
	      unsigned long p4, unsigned long p5, unsigned long p6,
	      struct pt_regs *regs)
{
	CHECK_FULL_REGS(regs);
	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->gpr[1],
			regs, 0, NULL, NULL);
}

int sys_execve(unsigned long a0, unsigned long a1, unsigned long a2,
	       unsigned long a3, unsigned long a4, unsigned long a5,
	       struct pt_regs *regs)
{
	int error;
923
	char *filename;
924 925 926 927 928 929 930 931

	filename = getname((char __user *) a0);
	error = PTR_ERR(filename);
	if (IS_ERR(filename))
		goto out;
	flush_fp_to_thread(current);
	flush_altivec_to_thread(current);
	flush_spe_to_thread(current);
932 933
	error = do_execve(filename, (char __user * __user *) a1,
			  (char __user * __user *) a2, regs);
934 935 936 937 938
	putname(filename);
out:
	return error;
}

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
#ifdef CONFIG_IRQSTACKS
static inline int valid_irq_stack(unsigned long sp, struct task_struct *p,
				  unsigned long nbytes)
{
	unsigned long stack_page;
	unsigned long cpu = task_cpu(p);

	/*
	 * Avoid crashing if the stack has overflowed and corrupted
	 * task_cpu(p), which is in the thread_info struct.
	 */
	if (cpu < NR_CPUS && cpu_possible(cpu)) {
		stack_page = (unsigned long) hardirq_ctx[cpu];
		if (sp >= stack_page + sizeof(struct thread_struct)
		    && sp <= stack_page + THREAD_SIZE - nbytes)
			return 1;

		stack_page = (unsigned long) softirq_ctx[cpu];
		if (sp >= stack_page + sizeof(struct thread_struct)
		    && sp <= stack_page + THREAD_SIZE - nbytes)
			return 1;
	}
	return 0;
}

#else
#define valid_irq_stack(sp, p, nb)	0
#endif /* CONFIG_IRQSTACKS */

968
int validate_sp(unsigned long sp, struct task_struct *p,
969 970
		       unsigned long nbytes)
{
A
Al Viro 已提交
971
	unsigned long stack_page = (unsigned long)task_stack_page(p);
972 973 974 975 976

	if (sp >= stack_page + sizeof(struct thread_struct)
	    && sp <= stack_page + THREAD_SIZE - nbytes)
		return 1;

977
	return valid_irq_stack(sp, p, nbytes);
978 979
}

980 981
EXPORT_SYMBOL(validate_sp);

982 983 984 985 986 987 988 989 990
unsigned long get_wchan(struct task_struct *p)
{
	unsigned long ip, sp;
	int count = 0;

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

	sp = p->thread.ksp;
991
	if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD))
992 993 994 995
		return 0;

	do {
		sp = *(unsigned long *)sp;
996
		if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD))
997 998
			return 0;
		if (count > 0) {
999
			ip = ((unsigned long *)sp)[STACK_FRAME_LR_SAVE];
1000 1001 1002 1003 1004 1005
			if (!in_sched_functions(ip))
				return ip;
		}
	} while (count++ < 16);
	return 0;
}
1006

1007
static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
1008 1009 1010 1011 1012 1013

void show_stack(struct task_struct *tsk, unsigned long *stack)
{
	unsigned long sp, ip, lr, newsp;
	int count = 0;
	int firstframe = 1;
1014 1015 1016 1017 1018 1019 1020 1021
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
	int curr_frame = current->curr_ret_stack;
	extern void return_to_handler(void);
	unsigned long addr = (unsigned long)return_to_handler;
#ifdef CONFIG_PPC64
	addr = *(unsigned long*)addr;
#endif
#endif
1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035

	sp = (unsigned long) stack;
	if (tsk == NULL)
		tsk = current;
	if (sp == 0) {
		if (tsk == current)
			asm("mr %0,1" : "=r" (sp));
		else
			sp = tsk->thread.ksp;
	}

	lr = 0;
	printk("Call Trace:\n");
	do {
1036
		if (!validate_sp(sp, tsk, STACK_FRAME_OVERHEAD))
1037 1038 1039 1040
			return;

		stack = (unsigned long *) sp;
		newsp = stack[0];
1041
		ip = stack[STACK_FRAME_LR_SAVE];
1042
		if (!firstframe || ip != lr) {
1043
			printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip);
1044 1045 1046 1047 1048 1049 1050
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
			if (ip == addr && curr_frame >= 0) {
				printk(" (%pS)",
				       (void *)current->ret_stack[curr_frame].ret);
				curr_frame--;
			}
#endif
1051 1052 1053 1054 1055 1056 1057 1058 1059 1060
			if (firstframe)
				printk(" (unreliable)");
			printk("\n");
		}
		firstframe = 0;

		/*
		 * See if this is an exception frame.
		 * We look for the "regshere" marker in the current frame.
		 */
1061 1062
		if (validate_sp(sp, tsk, STACK_INT_FRAME_SIZE)
		    && stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
1063 1064 1065
			struct pt_regs *regs = (struct pt_regs *)
				(sp + STACK_FRAME_OVERHEAD);
			lr = regs->link;
1066 1067
			printk("--- Exception: %lx at %pS\n    LR = %pS\n",
			       regs->trap, (void *)regs->nip, (void *)lr);
1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079
			firstframe = 1;
		}

		sp = newsp;
	} while (count++ < kstack_depth_to_print);
}

void dump_stack(void)
{
	show_stack(current, NULL);
}
EXPORT_SYMBOL(dump_stack);
1080 1081 1082 1083 1084 1085 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

#ifdef CONFIG_PPC64
void ppc64_runlatch_on(void)
{
	unsigned long ctrl;

	if (cpu_has_feature(CPU_FTR_CTRL) && !test_thread_flag(TIF_RUNLATCH)) {
		HMT_medium();

		ctrl = mfspr(SPRN_CTRLF);
		ctrl |= CTRL_RUNLATCH;
		mtspr(SPRN_CTRLT, ctrl);

		set_thread_flag(TIF_RUNLATCH);
	}
}

void ppc64_runlatch_off(void)
{
	unsigned long ctrl;

	if (cpu_has_feature(CPU_FTR_CTRL) && test_thread_flag(TIF_RUNLATCH)) {
		HMT_medium();

		clear_thread_flag(TIF_RUNLATCH);

		ctrl = mfspr(SPRN_CTRLF);
		ctrl &= ~CTRL_RUNLATCH;
		mtspr(SPRN_CTRLT, ctrl);
	}
}
#endif
1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142

#if THREAD_SHIFT < PAGE_SHIFT

static struct kmem_cache *thread_info_cache;

struct thread_info *alloc_thread_info(struct task_struct *tsk)
{
	struct thread_info *ti;

	ti = kmem_cache_alloc(thread_info_cache, GFP_KERNEL);
	if (unlikely(ti == NULL))
		return NULL;
#ifdef CONFIG_DEBUG_STACK_USAGE
	memset(ti, 0, THREAD_SIZE);
#endif
	return ti;
}

void free_thread_info(struct thread_info *ti)
{
	kmem_cache_free(thread_info_cache, ti);
}

void thread_info_cache_init(void)
{
	thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
					      THREAD_SIZE, 0, NULL);
	BUG_ON(thread_info_cache == NULL);
}

#endif /* THREAD_SHIFT < PAGE_SHIFT */
1143 1144 1145 1146 1147 1148 1149

unsigned long arch_align_stack(unsigned long sp)
{
	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
		sp -= get_random_int() & ~PAGE_MASK;
	return sp & ~0xf;
}
1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172

static inline unsigned long brk_rnd(void)
{
        unsigned long rnd = 0;

	/* 8MB for 32bit, 1GB for 64bit */
	if (is_32bit_task())
		rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT)));
	else
		rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT)));

	return rnd << PAGE_SHIFT;
}

unsigned long arch_randomize_brk(struct mm_struct *mm)
{
	unsigned long ret = PAGE_ALIGN(mm->brk + brk_rnd());

	if (ret < mm->brk)
		return mm->brk;

	return ret;
}