process.c 19.5 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10
/*
 *  linux/arch/x86-64/kernel/process.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Pentium III FXSR, SSE support
 *	Gareth Hughes <gareth@valinux.com>, May 2000
 * 
 *  X86-64 port
 *	Andi Kleen.
A
Ashok Raj 已提交
11 12
 *
 *	CPU hotplug support - ashok.raj@intel.com
L
Linus Torvalds 已提交
13 14 15 16 17 18 19 20 21
 *  $Id: process.c,v 1.38 2002/01/15 10:08:03 ak Exp $
 */

/*
 * This file handles the architecture-dependent parts of process handling..
 */

#include <stdarg.h>

A
Ashok Raj 已提交
22
#include <linux/cpu.h>
L
Linus Torvalds 已提交
23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/elfcore.h>
#include <linux/smp.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/module.h>
#include <linux/a.out.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/irq.h>
#include <linux/ptrace.h>
#include <linux/utsname.h>
#include <linux/random.h>
39
#include <linux/kprobes.h>
L
Linus Torvalds 已提交
40 41 42 43 44 45 46 47 48 49 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

#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/mmu_context.h>
#include <asm/pda.h>
#include <asm/prctl.h>
#include <asm/kdebug.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/ia32.h>

asmlinkage extern void ret_from_fork(void);

unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;

static atomic_t hlt_counter = ATOMIC_INIT(0);

unsigned long boot_option_idle_override = 0;
EXPORT_SYMBOL(boot_option_idle_override);

/*
 * Powermanagement idle function, if any..
 */
void (*pm_idle)(void);
static DEFINE_PER_CPU(unsigned int, cpu_idle_state);

void disable_hlt(void)
{
	atomic_inc(&hlt_counter);
}

EXPORT_SYMBOL(disable_hlt);

void enable_hlt(void)
{
	atomic_dec(&hlt_counter);
}

EXPORT_SYMBOL(enable_hlt);

/*
 * We use this if we don't have any better
 * idle routine..
 */
void default_idle(void)
{
	if (!atomic_read(&hlt_counter)) {
		local_irq_disable();
		if (!need_resched())
			safe_halt();
		else
			local_irq_enable();
	}
}

/*
 * On SMP it's slightly faster (but much more power-consuming!)
 * to poll the ->need_resched flag instead of waiting for the
 * cross-CPU IPI to arrive. Use this option with caution.
 */
static void poll_idle (void)
{
	int oldval;

	local_irq_enable();

	/*
	 * Deal with another CPU just having chosen a thread to
	 * run here:
	 */
	oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);

	if (!oldval) {
		set_thread_flag(TIF_POLLING_NRFLAG); 
		asm volatile(
			"2:"
			"testl %0,%1;"
			"rep; nop;"
			"je 2b;"
			: :
			"i" (_TIF_NEED_RESCHED), 
			"m" (current_thread_info()->flags));
	} else {
		set_need_resched();
	}
}

void cpu_idle_wait(void)
{
	unsigned int cpu, this_cpu = get_cpu();
	cpumask_t map;

	set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
	put_cpu();

	cpus_clear(map);
	for_each_online_cpu(cpu) {
		per_cpu(cpu_idle_state, cpu) = 1;
		cpu_set(cpu, map);
	}

	__get_cpu_var(cpu_idle_state) = 0;

	wmb();
	do {
		ssleep(1);
		for_each_online_cpu(cpu) {
			if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu))
				cpu_clear(cpu, map);
		}
		cpus_and(map, map, cpu_online_map);
	} while (!cpus_empty(map));
}
EXPORT_SYMBOL_GPL(cpu_idle_wait);

A
Ashok Raj 已提交
159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181
#ifdef CONFIG_HOTPLUG_CPU
DECLARE_PER_CPU(int, cpu_state);

#include <asm/nmi.h>
/* We don't actually take CPU down, just spin without interrupts. */
static inline void play_dead(void)
{
	idle_task_exit();
	wbinvd();
	mb();
	/* Ack it */
	__get_cpu_var(cpu_state) = CPU_DEAD;

	while (1)
		safe_halt();
}
#else
static inline void play_dead(void)
{
	BUG();
}
#endif /* CONFIG_HOTPLUG_CPU */

L
Linus Torvalds 已提交
182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201
/*
 * The idle thread. There's no useful work to be
 * done, so just try to conserve power and have a
 * low exit latency (ie sit in a loop waiting for
 * somebody to say that they'd like to reschedule)
 */
void cpu_idle (void)
{
	/* endless idle loop with no priority at all */
	while (1) {
		while (!need_resched()) {
			void (*idle)(void);

			if (__get_cpu_var(cpu_idle_state))
				__get_cpu_var(cpu_idle_state) = 0;

			rmb();
			idle = pm_idle;
			if (!idle)
				idle = default_idle;
A
Ashok Raj 已提交
202 203
			if (cpu_is_offline(smp_processor_id()))
				play_dead();
L
Linus Torvalds 已提交
204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233
			idle();
		}

		schedule();
	}
}

/*
 * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
 * which can obviate IPI to trigger checking of need_resched.
 * We execute MONITOR against need_resched and enter optimized wait state
 * through MWAIT. Whenever someone changes need_resched, we would be woken
 * up from MWAIT (without an IPI).
 */
static void mwait_idle(void)
{
	local_irq_enable();

	if (!need_resched()) {
		set_thread_flag(TIF_POLLING_NRFLAG);
		do {
			__monitor((void *)&current_thread_info()->flags, 0, 0);
			if (need_resched())
				break;
			__mwait(0, 0);
		} while (!need_resched());
		clear_thread_flag(TIF_POLLING_NRFLAG);
	}
}

234
void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
L
Linus Torvalds 已提交
235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323
{
	static int printed;
	if (cpu_has(c, X86_FEATURE_MWAIT)) {
		/*
		 * Skip, if setup has overridden idle.
		 * One CPU supports mwait => All CPUs supports mwait
		 */
		if (!pm_idle) {
			if (!printed) {
				printk("using mwait in idle threads.\n");
				printed = 1;
			}
			pm_idle = mwait_idle;
		}
	}
}

static int __init idle_setup (char *str)
{
	if (!strncmp(str, "poll", 4)) {
		printk("using polling idle threads.\n");
		pm_idle = poll_idle;
	}

	boot_option_idle_override = 1;
	return 1;
}

__setup("idle=", idle_setup);

/* Prints also some state that isn't saved in the pt_regs */ 
void __show_regs(struct pt_regs * regs)
{
	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
	unsigned int fsindex,gsindex;
	unsigned int ds,cs,es; 

	printk("\n");
	print_modules();
	printk("Pid: %d, comm: %.20s %s %s\n", 
	       current->pid, current->comm, print_tainted(), system_utsname.release);
	printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->rip);
	printk_address(regs->rip); 
	printk("\nRSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss, regs->rsp, regs->eflags);
	printk("RAX: %016lx RBX: %016lx RCX: %016lx\n",
	       regs->rax, regs->rbx, regs->rcx);
	printk("RDX: %016lx RSI: %016lx RDI: %016lx\n",
	       regs->rdx, regs->rsi, regs->rdi); 
	printk("RBP: %016lx R08: %016lx R09: %016lx\n",
	       regs->rbp, regs->r8, regs->r9); 
	printk("R10: %016lx R11: %016lx R12: %016lx\n",
	       regs->r10, regs->r11, regs->r12); 
	printk("R13: %016lx R14: %016lx R15: %016lx\n",
	       regs->r13, regs->r14, regs->r15); 

	asm("movl %%ds,%0" : "=r" (ds)); 
	asm("movl %%cs,%0" : "=r" (cs)); 
	asm("movl %%es,%0" : "=r" (es)); 
	asm("movl %%fs,%0" : "=r" (fsindex));
	asm("movl %%gs,%0" : "=r" (gsindex));

	rdmsrl(MSR_FS_BASE, fs);
	rdmsrl(MSR_GS_BASE, gs); 
	rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); 

	asm("movq %%cr0, %0": "=r" (cr0));
	asm("movq %%cr2, %0": "=r" (cr2));
	asm("movq %%cr3, %0": "=r" (cr3));
	asm("movq %%cr4, %0": "=r" (cr4));

	printk("FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", 
	       fs,fsindex,gs,gsindex,shadowgs); 
	printk("CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, es, cr0); 
	printk("CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, cr4);
}

void show_regs(struct pt_regs *regs)
{
	__show_regs(regs);
	show_trace(&regs->rsp);
}

/*
 * Free current thread data structures etc..
 */
void exit_thread(void)
{
	struct task_struct *me = current;
	struct thread_struct *t = &me->thread;
324 325 326 327 328 329 330 331

	/*
	 * Remove function-return probe instances associated with this task
	 * and put them back on the free list. Do not insert an exit probe for
	 * this function, it will be disabled by kprobe_flush_task if you do.
	 */
	kprobe_flush_task(me);

L
Linus Torvalds 已提交
332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350
	if (me->thread.io_bitmap_ptr) { 
		struct tss_struct *tss = &per_cpu(init_tss, get_cpu());

		kfree(t->io_bitmap_ptr);
		t->io_bitmap_ptr = NULL;
		/*
		 * Careful, clear this in the TSS too:
		 */
		memset(tss->io_bitmap, 0xff, t->io_bitmap_max);
		t->io_bitmap_max = 0;
		put_cpu();
	}
}

void flush_thread(void)
{
	struct task_struct *tsk = current;
	struct thread_info *t = current_thread_info();

351 352 353 354 355 356 357
	/*
	 * Remove function-return probe instances associated with this task
	 * and put them back on the free list. Do not insert an exit probe for
	 * this function, it will be disabled by kprobe_flush_task if you do.
	 */
	kprobe_flush_task(tsk);

L
Linus Torvalds 已提交
358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447
	if (t->flags & _TIF_ABI_PENDING)
		t->flags ^= (_TIF_ABI_PENDING | _TIF_IA32);

	tsk->thread.debugreg0 = 0;
	tsk->thread.debugreg1 = 0;
	tsk->thread.debugreg2 = 0;
	tsk->thread.debugreg3 = 0;
	tsk->thread.debugreg6 = 0;
	tsk->thread.debugreg7 = 0;
	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));	
	/*
	 * Forget coprocessor state..
	 */
	clear_fpu(tsk);
	clear_used_math();
}

void release_thread(struct task_struct *dead_task)
{
	if (dead_task->mm) {
		if (dead_task->mm->context.size) {
			printk("WARNING: dead process %8s still has LDT? <%p/%d>\n",
					dead_task->comm,
					dead_task->mm->context.ldt,
					dead_task->mm->context.size);
			BUG();
		}
	}
}

static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr)
{
	struct user_desc ud = { 
		.base_addr = addr,
		.limit = 0xfffff,
		.seg_32bit = 1,
		.limit_in_pages = 1,
		.useable = 1,
	};
	struct n_desc_struct *desc = (void *)t->thread.tls_array;
	desc += tls;
	desc->a = LDT_entry_a(&ud); 
	desc->b = LDT_entry_b(&ud); 
}

static inline u32 read_32bit_tls(struct task_struct *t, int tls)
{
	struct desc_struct *desc = (void *)t->thread.tls_array;
	desc += tls;
	return desc->base0 | 
		(((u32)desc->base1) << 16) | 
		(((u32)desc->base2) << 24);
}

/*
 * This gets called before we allocate a new thread and copy
 * the current task into it.
 */
void prepare_to_copy(struct task_struct *tsk)
{
	unlazy_fpu(tsk);
}

int copy_thread(int nr, unsigned long clone_flags, unsigned long rsp, 
		unsigned long unused,
	struct task_struct * p, struct pt_regs * regs)
{
	int err;
	struct pt_regs * childregs;
	struct task_struct *me = current;

	childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p->thread_info)) - 1;

	*childregs = *regs;

	childregs->rax = 0;
	childregs->rsp = rsp;
	if (rsp == ~0UL) {
		childregs->rsp = (unsigned long)childregs;
	}

	p->thread.rsp = (unsigned long) childregs;
	p->thread.rsp0 = (unsigned long) (childregs+1);
	p->thread.userrsp = me->thread.userrsp; 

	set_ti_thread_flag(p->thread_info, TIF_FORK);

	p->thread.fs = me->thread.fs;
	p->thread.gs = me->thread.gs;

448 449 450 451
	asm("mov %%gs,%0" : "=m" (p->thread.gsindex));
	asm("mov %%fs,%0" : "=m" (p->thread.fsindex));
	asm("mov %%es,%0" : "=m" (p->thread.es));
	asm("mov %%ds,%0" : "=m" (p->thread.ds));
L
Linus Torvalds 已提交
452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483

	if (unlikely(me->thread.io_bitmap_ptr != NULL)) { 
		p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
		if (!p->thread.io_bitmap_ptr) {
			p->thread.io_bitmap_max = 0;
			return -ENOMEM;
		}
		memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr, IO_BITMAP_BYTES);
	} 

	/*
	 * Set a new TLS for the child thread?
	 */
	if (clone_flags & CLONE_SETTLS) {
#ifdef CONFIG_IA32_EMULATION
		if (test_thread_flag(TIF_IA32))
			err = ia32_child_tls(p, childregs); 
		else 			
#endif	 
			err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); 
		if (err) 
			goto out;
	}
	err = 0;
out:
	if (err && p->thread.io_bitmap_ptr) {
		kfree(p->thread.io_bitmap_ptr);
		p->thread.io_bitmap_max = 0;
	}
	return err;
}

A
Andrea Arcangeli 已提交
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
/*
 * This function selects if the context switch from prev to next
 * has to tweak the TSC disable bit in the cr4.
 */
static inline void disable_tsc(struct task_struct *prev_p,
			       struct task_struct *next_p)
{
	struct thread_info *prev, *next;

	/*
	 * gcc should eliminate the ->thread_info dereference if
	 * has_secure_computing returns 0 at compile time (SECCOMP=n).
	 */
	prev = prev_p->thread_info;
	next = next_p->thread_info;

	if (has_secure_computing(prev) || has_secure_computing(next)) {
		/* slow path here */
		if (has_secure_computing(prev) &&
		    !has_secure_computing(next)) {
			write_cr4(read_cr4() & ~X86_CR4_TSD);
		} else if (!has_secure_computing(prev) &&
			   has_secure_computing(next))
			write_cr4(read_cr4() | X86_CR4_TSD);
	}
}

L
Linus Torvalds 已提交
511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540
/*
 * This special macro can be used to load a debugging register
 */
#define loaddebug(thread,r) set_debug(thread->debugreg ## r, r)

/*
 *	switch_to(x,y) should switch tasks from x to y.
 *
 * This could still be optimized: 
 * - fold all the options into a flag word and test it with a single test.
 * - could test fs/gs bitsliced
 */
struct task_struct *__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
	struct thread_struct *prev = &prev_p->thread,
				 *next = &next_p->thread;
	int cpu = smp_processor_id();  
	struct tss_struct *tss = &per_cpu(init_tss, cpu);

	unlazy_fpu(prev_p);

	/*
	 * Reload esp0, LDT and the page table pointer:
	 */
	tss->rsp0 = next->rsp0;

	/* 
	 * Switch DS and ES.
	 * This won't pick up thread selector changes, but I guess that is ok.
	 */
541
	asm volatile("mov %%es,%0" : "=m" (prev->es));
L
Linus Torvalds 已提交
542 543 544
	if (unlikely(next->es | prev->es))
		loadsegment(es, next->es); 
	
545
	asm volatile ("mov %%ds,%0" : "=m" (prev->ds));
L
Linus Torvalds 已提交
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
	if (unlikely(next->ds | prev->ds))
		loadsegment(ds, next->ds);

	load_TLS(next, cpu);

	/* 
	 * Switch FS and GS.
	 */
	{ 
		unsigned fsindex;
		asm volatile("movl %%fs,%0" : "=r" (fsindex)); 
		/* segment register != 0 always requires a reload. 
		   also reload when it has changed. 
		   when prev process used 64bit base always reload
		   to avoid an information leak. */
		if (unlikely(fsindex | next->fsindex | prev->fs)) {
			loadsegment(fs, next->fsindex);
			/* check if the user used a selector != 0
	                 * if yes clear 64bit base, since overloaded base
                         * is always mapped to the Null selector
                         */
			if (fsindex)
			prev->fs = 0;				
		}
		/* when next process has a 64bit base use it */
		if (next->fs) 
			wrmsrl(MSR_FS_BASE, next->fs); 
		prev->fsindex = fsindex;
	}
	{ 
		unsigned gsindex;
		asm volatile("movl %%gs,%0" : "=r" (gsindex)); 
		if (unlikely(gsindex | next->gsindex | prev->gs)) {
			load_gs_index(next->gsindex);
			if (gsindex)
			prev->gs = 0;				
		}
		if (next->gs)
			wrmsrl(MSR_KERNEL_GS_BASE, next->gs); 
		prev->gsindex = gsindex;
	}

	/* 
	 * Switch the PDA context.
	 */
	prev->userrsp = read_pda(oldrsp); 
	write_pda(oldrsp, next->userrsp); 
	write_pda(pcurrent, next_p); 
	write_pda(kernelstack, (unsigned long)next_p->thread_info + THREAD_SIZE - PDA_STACKOFFSET);

	/*
	 * Now maybe reload the debug registers
	 */
	if (unlikely(next->debugreg7)) {
		loaddebug(next, 0);
		loaddebug(next, 1);
		loaddebug(next, 2);
		loaddebug(next, 3);
		/* no 4 and 5 */
		loaddebug(next, 6);
		loaddebug(next, 7);
	}


	/* 
	 * Handle the IO bitmap 
	 */ 
	if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) {
		if (next->io_bitmap_ptr)
			/*
			 * Copy the relevant range of the IO bitmap.
			 * Normally this is 128 bytes or less:
 			 */
			memcpy(tss->io_bitmap, next->io_bitmap_ptr,
				max(prev->io_bitmap_max, next->io_bitmap_max));
		else {
			/*
			 * Clear any possible leftover bits:
			 */
			memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
		}
	}

A
Andrea Arcangeli 已提交
629 630
	disable_tsc(prev_p, next_p);

L
Linus Torvalds 已提交
631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730
	return prev_p;
}

/*
 * sys_execve() executes a new program.
 */
asmlinkage 
long sys_execve(char __user *name, char __user * __user *argv,
		char __user * __user *envp, struct pt_regs regs)
{
	long error;
	char * filename;

	filename = getname(name);
	error = PTR_ERR(filename);
	if (IS_ERR(filename)) 
		return error;
	error = do_execve(filename, argv, envp, &regs); 
	if (error == 0) {
		task_lock(current);
		current->ptrace &= ~PT_DTRACE;
		task_unlock(current);
	}
	putname(filename);
	return error;
}

void set_personality_64bit(void)
{
	/* inherit personality from parent */

	/* Make sure to be in 64bit mode */
	clear_thread_flag(TIF_IA32); 

	/* TBD: overwrites user setup. Should have two bits.
	   But 64bit processes have always behaved this way,
	   so it's not too bad. The main problem is just that
   	   32bit childs are affected again. */
	current->personality &= ~READ_IMPLIES_EXEC;
}

asmlinkage long sys_fork(struct pt_regs *regs)
{
	return do_fork(SIGCHLD, regs->rsp, regs, 0, NULL, NULL);
}

asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp, void __user *parent_tid, void __user *child_tid, struct pt_regs *regs)
{
	if (!newsp)
		newsp = regs->rsp;
	return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
}

/*
 * This is trivial, and on the face of it looks like it
 * could equally well be done in user mode.
 *
 * Not so, for quite unobvious reasons - register pressure.
 * In user mode vfork() cannot have a stack frame, and if
 * done by calling the "clone()" system call directly, you
 * do not have enough call-clobbered registers to hold all
 * the information you need.
 */
asmlinkage long sys_vfork(struct pt_regs *regs)
{
	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->rsp, regs, 0,
		    NULL, NULL);
}

unsigned long get_wchan(struct task_struct *p)
{
	unsigned long stack;
	u64 fp,rip;
	int count = 0;

	if (!p || p == current || p->state==TASK_RUNNING)
		return 0; 
	stack = (unsigned long)p->thread_info; 
	if (p->thread.rsp < stack || p->thread.rsp > stack+THREAD_SIZE)
		return 0;
	fp = *(u64 *)(p->thread.rsp);
	do { 
		if (fp < (unsigned long)stack || fp > (unsigned long)stack+THREAD_SIZE)
			return 0; 
		rip = *(u64 *)(fp+8); 
		if (!in_sched_functions(rip))
			return rip; 
		fp = *(u64 *)fp; 
	} while (count++ < 16); 
	return 0;
}

long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
{ 
	int ret = 0; 
	int doit = task == current;
	int cpu;

	switch (code) { 
	case ARCH_SET_GS:
731
		if (addr >= TASK_SIZE_OF(task))
L
Linus Torvalds 已提交
732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756
			return -EPERM; 
		cpu = get_cpu();
		/* handle small bases via the GDT because that's faster to 
		   switch. */
		if (addr <= 0xffffffff) {  
			set_32bit_tls(task, GS_TLS, addr); 
			if (doit) { 
				load_TLS(&task->thread, cpu);
				load_gs_index(GS_TLS_SEL); 
			}
			task->thread.gsindex = GS_TLS_SEL; 
			task->thread.gs = 0;
		} else { 
			task->thread.gsindex = 0;
			task->thread.gs = addr;
			if (doit) {
		load_gs_index(0);
		ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr); 
			} 
		}
		put_cpu();
		break;
	case ARCH_SET_FS:
		/* Not strictly needed for fs, but do it for symmetry
		   with gs */
757
		if (addr >= TASK_SIZE_OF(task))
L
Linus Torvalds 已提交
758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842
			return -EPERM; 
		cpu = get_cpu();
		/* handle small bases via the GDT because that's faster to 
		   switch. */
		if (addr <= 0xffffffff) { 
			set_32bit_tls(task, FS_TLS, addr);
			if (doit) { 
				load_TLS(&task->thread, cpu); 
				asm volatile("movl %0,%%fs" :: "r" (FS_TLS_SEL));
			}
			task->thread.fsindex = FS_TLS_SEL;
			task->thread.fs = 0;
		} else { 
			task->thread.fsindex = 0;
			task->thread.fs = addr;
			if (doit) {
				/* set the selector to 0 to not confuse
				   __switch_to */
		asm volatile("movl %0,%%fs" :: "r" (0));
		ret = checking_wrmsrl(MSR_FS_BASE, addr); 
			}
		}
		put_cpu();
		break;
	case ARCH_GET_FS: { 
		unsigned long base; 
		if (task->thread.fsindex == FS_TLS_SEL)
			base = read_32bit_tls(task, FS_TLS);
		else if (doit) {
			rdmsrl(MSR_FS_BASE, base);
		} else
			base = task->thread.fs;
		ret = put_user(base, (unsigned long __user *)addr); 
		break; 
	}
	case ARCH_GET_GS: { 
		unsigned long base;
		if (task->thread.gsindex == GS_TLS_SEL)
			base = read_32bit_tls(task, GS_TLS);
		else if (doit) {
			rdmsrl(MSR_KERNEL_GS_BASE, base);
		} else
			base = task->thread.gs;
		ret = put_user(base, (unsigned long __user *)addr); 
		break;
	}

	default:
		ret = -EINVAL;
		break;
	} 

	return ret;	
} 

long sys_arch_prctl(int code, unsigned long addr)
{
	return do_arch_prctl(current, code, addr);
} 

/* 
 * Capture the user space registers if the task is not running (in user space)
 */
int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs)
{
	struct pt_regs *pp, ptregs;

	pp = (struct pt_regs *)(tsk->thread.rsp0);
	--pp; 

	ptregs = *pp; 
	ptregs.cs &= 0xffff;
	ptregs.ss &= 0xffff;

	elf_core_copy_regs(regs, &ptregs);
 
	return 1;
}

unsigned long arch_align_stack(unsigned long sp)
{
	if (randomize_va_space)
		sp -= get_random_int() % 8192;
	return sp & ~0xf;
}