process.c 24.0 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 37 38 39 40 41 42 43

#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>
44
#include <asm/machdep.h>
45
#include <asm/time.h>
46
#include <asm/syscalls.h>
47 48 49
#ifdef CONFIG_PPC64
#include <asm/firmware.h>
#endif
50 51 52 53 54 55 56 57 58 59 60 61 62 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

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;
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
			giveup_fpu(current);
		}
		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);

int dump_task_fpu(struct task_struct *tsk, elf_fpregset_t *fpregs)
{
	if (!tsk->thread.regs)
		return 0;
	flush_fp_to_thread(current);

	memcpy(fpregs, &tsk->thread.fpr[0], sizeof(*fpregs));

	return 1;
}

#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
			giveup_altivec(current);
		}
		preempt_enable();
	}
}

int dump_task_altivec(struct pt_regs *regs, elf_vrregset_t *vrregs)
{
	flush_altivec_to_thread(current);
	memcpy(vrregs, &current->thread.vr[0], sizeof(*vrregs));
	return 1;
}
#endif /* CONFIG_ALTIVEC */

#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
			giveup_spe(current);
		}
		preempt_enable();
	}
}

int dump_spe(struct pt_regs *regs, elf_vrregset_t *evrregs)
{
	flush_spe_to_thread(current);
	/* We copy u32 evr[32] + u64 acc + u32 spefscr -> 35 */
	memcpy(evrregs, &current->thread.evr[0], sizeof(u32) * 35);
	return 1;
}
#endif /* CONFIG_SPE */

200
#ifndef CONFIG_SMP
201 202 203 204
/*
 * If we are doing lazy switching of CPU state (FP, altivec or SPE),
 * and the current task has some state, discard it.
 */
205
void discard_lazy_cpu_state(void)
206 207 208 209 210 211 212 213 214 215 216 217 218 219
{
	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 */
#ifdef CONFIG_SPE
	if (last_task_used_spe == current)
		last_task_used_spe = NULL;
#endif
	preempt_enable();
}
220
#endif /* CONFIG_SMP */
221

222 223
int set_dabr(unsigned long dabr)
{
224
#ifdef CONFIG_PPC_MERGE		/* XXX for now */
225 226
	if (ppc_md.set_dabr)
		return ppc_md.set_dabr(dabr);
227
#endif
228

229 230
	/* XXX should we have a CPU_FTR_HAS_DABR ? */
#if defined(CONFIG_PPC64) || defined(CONFIG_6xx)
231
	mtspr(SPRN_DABR, dabr);
232
#endif
233
	return 0;
234 235
}

236 237 238
#ifdef CONFIG_PPC64
DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array);
#endif
239

240 241
static DEFINE_PER_CPU(unsigned long, current_dabr);

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
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 */
#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);
286 287 288 289 290 291 292 293 294 295 296
#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 */
#ifdef CONFIG_SPE
297 298 299 300 301 302
	/* 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 */
303

304 305 306 307 308 309 310 311 312
#endif /* CONFIG_SMP */

	if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr)) {
		set_dabr(new->thread.dabr);
		__get_cpu_var(current_dabr) = new->thread.dabr;
	}

	new_thread = &new->thread;
	old_thread = &current->thread;
313 314 315 316 317 318 319 320 321 322 323 324 325 326 327

#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

328
	local_irq_save(flags);
329 330 331 332 333

	account_system_vtime(current);
	account_process_vtime(current);
	calculate_steal_time();

334 335 336 337 338 339 340
	last = _switch(old_thread, new_thread);

	local_irq_restore(flags);

	return last;
}

341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356
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");

357 358 359 360
		/* We use __get_user here *only* to avoid an OOPS on a
		 * bad address because the pc *should* only be a
		 * kernel address.
		 */
361 362
		if (!__kernel_text_address(pc) ||
		     __get_user(instr, (unsigned int __user *)pc)) {
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
			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"},
	{MSR_ME,	"ME"},
	{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
404
#define REG		"%016lx"
405 406 407
#define REGS_PER_LINE	4
#define LAST_VOLATILE	13
#else
408
#define REG		"%08lx"
409 410 411 412
#define REGS_PER_LINE	8
#define LAST_VOLATILE	12
#endif

413 414 415 416
void show_regs(struct pt_regs * regs)
{
	int i, trap;

417 418 419
	printk("NIP: "REG" LR: "REG" CTR: "REG"\n",
	       regs->nip, regs->link, regs->ctr);
	printk("REGS: %p TRAP: %04lx   %s  (%s)\n",
420
	       regs, regs->trap, print_tainted(), init_utsname()->release);
421 422
	printk("MSR: "REG" ", regs->msr);
	printbits(regs->msr, msr_bits);
423
	printk("  CR: %08lx  XER: %08lx\n", regs->ccr, regs->xer);
424 425
	trap = TRAP(regs);
	if (trap == 0x300 || trap == 0x600)
426 427
		printk("DAR: "REG", DSISR: "REG"\n", regs->dar, regs->dsisr);
	printk("TASK = %p[%d] '%s' THREAD: %p",
A
Al Viro 已提交
428
	       current, current->pid, current->comm, task_thread_info(current));
429 430 431 432 433 434

#ifdef CONFIG_SMP
	printk(" CPU: %d", smp_processor_id());
#endif /* CONFIG_SMP */

	for (i = 0;  i < 32;  i++) {
435
		if ((i % REGS_PER_LINE) == 0)
436
			printk("\n" KERN_INFO "GPR%02d: ", i);
437 438
		printk(REG " ", regs->gpr[i]);
		if (i == LAST_VOLATILE && !FULL_REGS(regs))
439 440 441 442 443 444 445 446
			break;
	}
	printk("\n");
#ifdef CONFIG_KALLSYMS
	/*
	 * Lookup NIP late so we have the best change of getting the
	 * above info out without failing
	 */
447
	printk("NIP ["REG"] ", regs->nip);
448
	print_symbol("%s\n", regs->nip);
449
	printk("LR ["REG"] ", regs->link);
450 451 452
	print_symbol("%s\n", regs->link);
#endif
	show_stack(current, (unsigned long *) regs->gpr[1]);
453 454
	if (!user_mode(regs))
		show_instructions(regs);
455 456 457 458
}

void exit_thread(void)
{
459
	discard_lazy_cpu_state();
460 461 462 463
}

void flush_thread(void)
{
464 465 466
#ifdef CONFIG_PPC64
	struct thread_info *t = current_thread_info();

467 468 469 470 471 472 473
	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);
	}
474 475
#endif

476
	discard_lazy_cpu_state();
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

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

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);
	flush_spe_to_thread(current);
}

/*
 * Copy a thread..
 */
503 504 505
int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
		unsigned long unused, struct task_struct *p,
		struct pt_regs *regs)
506 507 508
{
	struct pt_regs *childregs, *kregs;
	extern void ret_from_fork(void);
A
Al Viro 已提交
509
	unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
510 511 512 513 514 515 516 517 518

	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);
519
#ifdef CONFIG_PPC32
520
		childregs->gpr[2] = (unsigned long) p;
521
#else
A
Al Viro 已提交
522
		clear_tsk_thread_flag(p, TIF_32BIT);
523
#endif
524 525 526 527
		p->thread.regs = NULL;	/* no user register state */
	} else {
		childregs->gpr[1] = usp;
		p->thread.regs = childregs;
528 529 530 531 532 533 534 535
		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];
		}
536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552
	}
	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;

553 554 555
#ifdef CONFIG_PPC64
	if (cpu_has_feature(CPU_FTR_SLB)) {
		unsigned long sp_vsid = get_kernel_vsid(sp);
556
		unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp;
557 558

		sp_vsid <<= SLB_VSID_SHIFT;
559
		sp_vsid |= SLB_VSID_KERNEL | llp;
560 561 562 563 564 565 566 567 568 569 570 571 572
		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
573 574 575 576 577 578 579

	return 0;
}

/*
 * Set up a thread for executing a new program
 */
580
void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
581
{
582 583 584 585
#ifdef CONFIG_PPC64
	unsigned long load_addr = regs->gpr[2];	/* saved by ELF_PLAT_INIT */
#endif

586
	set_fs(USER_DS);
587 588 589 590 591 592

	/*
	 * 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
593 594
		struct pt_regs *regs = task_stack_page(current) + THREAD_SIZE;
		current->thread.regs = regs - 1;
595 596
	}

597 598 599 600 601 602
	memset(regs->gpr, 0, sizeof(regs->gpr));
	regs->ctr = 0;
	regs->link = 0;
	regs->xer = 0;
	regs->ccr = 0;
	regs->gpr[1] = sp;
603 604 605 606

#ifdef CONFIG_PPC32
	regs->mq = 0;
	regs->nip = start;
607
	regs->msr = MSR_USER;
608
#else
S
Stephen Rothwell 已提交
609
	if (!test_thread_flag(TIF_32BIT)) {
610
		unsigned long entry, toc;
611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629

		/* 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
630 631 632 633
	} else {
		regs->nip = start;
		regs->gpr[2] = 0;
		regs->msr = MSR_USER32;
634 635 636
	}
#endif

637
	discard_lazy_cpu_state();
638
	memset(current->thread.fpr, 0, sizeof(current->thread.fpr));
639
	current->thread.fpscr.val = 0;
640 641 642
#ifdef CONFIG_ALTIVEC
	memset(current->thread.vr, 0, sizeof(current->thread.vr));
	memset(&current->thread.vscr, 0, sizeof(current->thread.vscr));
643
	current->thread.vscr.u[3] = 0x00010000; /* Java mode disabled */
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
	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
		tsk->thread.fpexc_mode = val &
			(PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT);
670
		return 0;
671 672 673 674
#else
		return -EINVAL;
#endif
	}
675 676 677 678 679 680 681 682 683 684 685 686

	/* 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;
687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704
	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
		val = tsk->thread.fpexc_mode;
#else
		return -EINVAL;
#endif
	else
		val = __unpack_fe01(tsk->thread.fpexc_mode);
	return put_user(val, (unsigned int __user *) adr);
}

705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748
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);
}

749 750 751 752 753 754 755 756 757 758 759
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);
}

760 761
#define TRUNC_PTR(x)	((typeof(x))(((unsigned long)(x)) & 0xffffffff))

762 763 764 765 766 767 768 769
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 */
770 771 772 773 774 775
#ifdef CONFIG_PPC64
	if (test_thread_flag(TIF_32BIT)) {
		parent_tidp = TRUNC_PTR(parent_tidp);
		child_tidp = TRUNC_PTR(child_tidp);
	}
#endif
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
 	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;
801
	char *filename;
802 803 804 805 806 807 808 809

	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);
810 811
	error = do_execve(filename, (char __user * __user *) a1,
			  (char __user * __user *) a2, regs);
812 813 814 815 816 817 818 819 820 821
	if (error == 0) {
		task_lock(current);
		current->ptrace &= ~PT_DTRACE;
		task_unlock(current);
	}
	putname(filename);
out:
	return error;
}

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
#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 */

851
int validate_sp(unsigned long sp, struct task_struct *p,
852 853
		       unsigned long nbytes)
{
A
Al Viro 已提交
854
	unsigned long stack_page = (unsigned long)task_stack_page(p);
855 856 857 858 859

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

860
	return valid_irq_stack(sp, p, nbytes);
861 862
}

863 864 865 866 867 868 869 870 871 872 873 874
#ifdef CONFIG_PPC64
#define MIN_STACK_FRAME	112	/* same as STACK_FRAME_OVERHEAD, in fact */
#define FRAME_LR_SAVE	2
#define INT_FRAME_SIZE	(sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD + 288)
#define REGS_MARKER	0x7265677368657265ul
#define FRAME_MARKER	12
#else
#define MIN_STACK_FRAME	16
#define FRAME_LR_SAVE	1
#define INT_FRAME_SIZE	(sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD)
#define REGS_MARKER	0x72656773ul
#define FRAME_MARKER	2
875 876
#endif

877 878
EXPORT_SYMBOL(validate_sp);

879 880 881 882 883 884 885 886 887
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;
888
	if (!validate_sp(sp, p, MIN_STACK_FRAME))
889 890 891 892
		return 0;

	do {
		sp = *(unsigned long *)sp;
893
		if (!validate_sp(sp, p, MIN_STACK_FRAME))
894 895
			return 0;
		if (count > 0) {
896
			ip = ((unsigned long *)sp)[FRAME_LR_SAVE];
897 898 899 900 901 902
			if (!in_sched_functions(ip))
				return ip;
		}
	} while (count++ < 16);
	return 0;
}
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

static int kstack_depth_to_print = 64;

void show_stack(struct task_struct *tsk, unsigned long *stack)
{
	unsigned long sp, ip, lr, newsp;
	int count = 0;
	int firstframe = 1;

	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 {
		if (!validate_sp(sp, tsk, MIN_STACK_FRAME))
			return;

		stack = (unsigned long *) sp;
		newsp = stack[0];
		ip = stack[FRAME_LR_SAVE];
		if (!firstframe || ip != lr) {
			printk("["REG"] ["REG"] ", sp, ip);
			print_symbol("%s", ip);
			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.
		 */
		if (validate_sp(sp, tsk, INT_FRAME_SIZE)
		    && stack[FRAME_MARKER] == REGS_MARKER) {
			struct pt_regs *regs = (struct pt_regs *)
				(sp + STACK_FRAME_OVERHEAD);
			printk("--- Exception: %lx", regs->trap);
			print_symbol(" at %s\n", regs->nip);
			lr = regs->link;
			print_symbol("    LR = %s\n", lr);
			firstframe = 1;
		}

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

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

#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