aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/process_64.c
blob: 131c2ee7ac5618e9fc92f576f4db19676bd235af (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
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
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
200
201
202
203
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
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
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
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
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
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
448
449
450
451
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
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
519
520
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
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
731
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
757
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
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
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
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
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
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
/*
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Pentium III FXSR, SSE support
 *	Gareth Hughes <gareth@valinux.com>, May 2000
 *
 *  X86-64 port
 *	Andi Kleen.
 *
 *	CPU hotplug support - ashok.raj@intel.com
 */

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

#include <stdarg.h>

#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/fs.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/interrupt.h>
#include <linux/utsname.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/random.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/tick.h>
#include <linux/prctl.h>

#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/desc.h>
#include <asm/proto.h>
#include <asm/ia32.h>
#include <asm/idle.h>

asmlinkage extern void ret_from_fork(void);

unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;

unsigned long boot_option_idle_override = 0;
EXPORT_SYMBOL(boot_option_idle_override);

/*
 * Powermanagement idle function, if any..
 */
void (*pm_idle)(void);
EXPORT_SYMBOL(pm_idle);

static ATOMIC_NOTIFIER_HEAD(idle_notifier);

void idle_notifier_register(struct notifier_block *n)
{
	atomic_notifier_chain_register(&idle_notifier, n);
}

void enter_idle(void)
{
	write_pda(isidle, 1);
	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
}

static void __exit_idle(void)
{
	if (test_and_clear_bit_pda(0, isidle) == 0)
		return;
	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
}

/* Called from interrupts to signify idle end */
void exit_idle(void)
{
	/* idle loop has pid 0 */
	if (current->pid)
		return;
	__exit_idle();
}

/*
 * We use this if we don't have any better
 * idle routine..
 */
void default_idle(void)
{
	current_thread_info()->status &= ~TS_POLLING;
	/*
	 * TS_POLLING-cleared state must be visible before we
	 * test NEED_RESCHED:
	 */
	smp_mb();
	local_irq_disable();
	if (!need_resched()) {
		safe_halt();	/* enables interrupts racelessly */
		local_irq_disable();
	}
	local_irq_enable();
	current_thread_info()->status |= TS_POLLING;
}

/*
 * 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)
{
	local_irq_enable();
	cpu_relax();
}

#ifdef CONFIG_HOTPLUG_CPU
DECLARE_PER_CPU(int, cpu_state);

#include <asm/nmi.h>
/* We halt the CPU with physical CPU hotplug */
static inline void play_dead(void)
{
	idle_task_exit();
	wbinvd();
	mb();
	/* Ack it */
	__get_cpu_var(cpu_state) = CPU_DEAD;

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

/*
 * 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)
{
	current_thread_info()->status |= TS_POLLING;
	/* endless idle loop with no priority at all */
	while (1) {
		tick_nohz_stop_sched_tick();
		while (!need_resched()) {
			void (*idle)(void);

			rmb();
			idle = pm_idle;
			if (!idle)
				idle = default_idle;
			if (cpu_is_offline(smp_processor_id()))
				play_dead();
			/*
			 * Idle routines should keep interrupts disabled
			 * from here on, until they go to idle.
			 * Otherwise, idle callbacks can misfire.
			 */
			local_irq_disable();
			enter_idle();
			idle();
			/* In many cases the interrupt that ended idle
			   has already called exit_idle. But some idle
			   loops can be woken up without interrupt. */
			__exit_idle();
		}

		tick_nohz_restart_sched_tick();
		preempt_enable_no_resched();
		schedule();
		preempt_disable();
	}
}

static void do_nothing(void *unused)
{
}

/*
 * 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 */
	smp_call_function(do_nothing, NULL, 0, 1);
}
EXPORT_SYMBOL_GPL(cpu_idle_wait);

/*
 * 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).
 *
 * New with Core Duo processors, MWAIT can take some hints based on CPU
 * capability.
 */
void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
{
	if (!need_resched()) {
		__monitor((void *)&current_thread_info()->flags, 0, 0);
		smp_mb();
		if (!need_resched())
			__mwait(ax, cx);
	}
}

/* Default MONITOR/MWAIT with no hints, used for default C1 state */
static void mwait_idle(void)
{
	if (!need_resched()) {
		__monitor((void *)&current_thread_info()->flags, 0, 0);
		smp_mb();
		if (!need_resched())
			__sti_mwait(0, 0);
		else
			local_irq_enable();
	} else {
		local_irq_enable();
	}
}


static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
{
	if (force_mwait)
		return 1;
	/* Any C1 states supported? */
	return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
}

void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
{
	static int selected;

	if (selected)
		return;
#ifdef CONFIG_X86_SMP
	if (pm_idle == poll_idle && smp_num_siblings > 1) {
		printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
			" performance may degrade.\n");
	}
#endif
	if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
		/*
		 * Skip, if setup has overridden idle.
		 * One CPU supports mwait => All CPUs supports mwait
		 */
		if (!pm_idle) {
			printk(KERN_INFO "using mwait in idle threads.\n");
			pm_idle = mwait_idle;
		}
	}
	selected = 1;
}

static int __init idle_setup(char *str)
{
	if (!strcmp(str, "poll")) {
		printk("using polling idle threads.\n");
		pm_idle = poll_idle;
	} else if (!strcmp(str, "mwait"))
		force_mwait = 1;
	else
		return -1;

	boot_option_idle_override = 1;
	return 0;
}
early_param("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 long d0, d1, d2, d3, d6, d7;
	unsigned int fsindex, gsindex;
	unsigned int ds, cs, es;

	printk("\n");
	print_modules();
	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
		current->pid, current->comm, print_tainted(),
		init_utsname()->release,
		(int)strcspn(init_utsname()->version, " "),
		init_utsname()->version);
	printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
	printk_address(regs->ip, 1);
	printk("RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss, regs->sp,
		regs->flags);
	printk("RAX: %016lx RBX: %016lx RCX: %016lx\n",
	       regs->ax, regs->bx, regs->cx);
	printk("RDX: %016lx RSI: %016lx RDI: %016lx\n",
	       regs->dx, regs->si, regs->di);
	printk("RBP: %016lx R08: %016lx R09: %016lx\n",
	       regs->bp, 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); 

	cr0 = read_cr0();
	cr2 = read_cr2();
	cr3 = read_cr3();
	cr4 = read_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);

	get_debugreg(d0, 0);
	get_debugreg(d1, 1);
	get_debugreg(d2, 2);
	printk("DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
	get_debugreg(d3, 3);
	get_debugreg(d6, 6);
	get_debugreg(d7, 7);
	printk("DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
}

void show_regs(struct pt_regs *regs)
{
	printk("CPU %d:", smp_processor_id());
	__show_regs(regs);
	show_trace(NULL, regs, (void *)(regs + 1), regs->bp);
}

/*
 * Free current thread data structures etc..
 */
void exit_thread(void)
{
	struct task_struct *me = current;
	struct thread_struct *t = &me->thread;

	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;
		clear_thread_flag(TIF_IO_BITMAP);
		/*
		 * 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;

	if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) {
		clear_tsk_thread_flag(tsk, TIF_ABI_PENDING);
		if (test_tsk_thread_flag(tsk, TIF_IA32)) {
			clear_tsk_thread_flag(tsk, TIF_IA32);
		} else {
			set_tsk_thread_flag(tsk, TIF_IA32);
			current_thread_info()->status |= TS_COMPAT;
		}
	}
	clear_tsk_thread_flag(tsk, TIF_DEBUG);

	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 desc_struct *desc = t->thread.tls_array;
	desc += tls;
	fill_ldt(desc, &ud);
}

static inline u32 read_32bit_tls(struct task_struct *t, int tls)
{
	return get_desc_base(&t->thread.tls_array[tls]);
}

/*
 * 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 sp,
		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 + task_stack_page(p))) - 1;
	*childregs = *regs;

	childregs->ax = 0;
	childregs->sp = sp;
	if (sp == ~0UL)
		childregs->sp = (unsigned long)childregs;

	p->thread.sp = (unsigned long) childregs;
	p->thread.sp0 = (unsigned long) (childregs+1);
	p->thread.usersp = me->thread.usersp;

	set_tsk_thread_flag(p, TIF_FORK);

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

	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));

	if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
		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_tsk_thread_flag(p, TIF_IO_BITMAP);
	}

	/*
	 * Set a new TLS for the child thread?
	 */
	if (clone_flags & CLONE_SETTLS) {
#ifdef CONFIG_IA32_EMULATION
		if (test_thread_flag(TIF_IA32))
			err = do_set_thread_area(p, -1,
				(struct user_desc __user *)childregs->si, 0);
		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;
}

void
start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
{
	asm volatile("movl %0, %%fs; movl %0, %%es; movl %0, %%ds" :: "r"(0));
	load_gs_index(0);
	regs->ip		= new_ip;
	regs->sp		= new_sp;
	write_pda(oldrsp, new_sp);
	regs->cs		= __USER_CS;
	regs->ss		= __USER_DS;
	regs->flags		= 0x200;
	set_fs(USER_DS);
	/*
	 * Free the old FP and other extended state
	 */
	free_thread_xstate(current);
}
EXPORT_SYMBOL_GPL(start_thread);

static void hard_disable_TSC(void)
{
	write_cr4(read_cr4() | X86_CR4_TSD);
}

void disable_TSC(void)
{
	preempt_disable();
	if (!test_and_set_thread_flag(TIF_NOTSC))
		/*
		 * Must flip the CPU state synchronously with
		 * TIF_NOTSC in the current running context.
		 */
		hard_disable_TSC();
	preempt_enable();
}

static void hard_enable_TSC(void)
{
	write_cr4(read_cr4() & ~X86_CR4_TSD);
}

static void enable_TSC(void)
{
	preempt_disable();
	if (test_and_clear_thread_flag(TIF_NOTSC))
		/*
		 * Must flip the CPU state synchronously with
		 * TIF_NOTSC in the current running context.
		 */
		hard_enable_TSC();
	preempt_enable();
}

int get_tsc_mode(unsigned long adr)
{
	unsigned int val;

	if (test_thread_flag(TIF_NOTSC))
		val = PR_TSC_SIGSEGV;
	else
		val = PR_TSC_ENABLE;

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

int set_tsc_mode(unsigned int val)
{
	if (val == PR_TSC_SIGSEGV)
		disable_TSC();
	else if (val == PR_TSC_ENABLE)
		enable_TSC();
	else
		return -EINVAL;

	return 0;
}

/*
 * This special macro can be used to load a debugging register
 */
#define loaddebug(thread, r) set_debugreg(thread->debugreg ## r, r)

static inline void __switch_to_xtra(struct task_struct *prev_p,
				    struct task_struct *next_p,
				    struct tss_struct *tss)
{
	struct thread_struct *prev, *next;
	unsigned long debugctl;

	prev = &prev_p->thread,
	next = &next_p->thread;

	debugctl = prev->debugctlmsr;
	if (next->ds_area_msr != prev->ds_area_msr) {
		/* we clear debugctl to make sure DS
		 * is not in use when we change it */
		debugctl = 0;
		update_debugctlmsr(0);
		wrmsrl(MSR_IA32_DS_AREA, next->ds_area_msr);
	}

	if (next->debugctlmsr != debugctl)
		update_debugctlmsr(next->debugctlmsr);

	if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
		loaddebug(next, 0);
		loaddebug(next, 1);
		loaddebug(next, 2);
		loaddebug(next, 3);
		/* no 4 and 5 */
		loaddebug(next, 6);
		loaddebug(next, 7);
	}

	if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
	    test_tsk_thread_flag(next_p, TIF_NOTSC)) {
		/* prev and next are different */
		if (test_tsk_thread_flag(next_p, TIF_NOTSC))
			hard_disable_TSC();
		else
			hard_enable_TSC();
	}

	if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
		/*
		 * 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 if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
		/*
		 * Clear any possible leftover bits:
		 */
		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
	}

#ifdef X86_BTS
	if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
		ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);

	if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
		ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
#endif
}

/*
 *	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
 *
 * Kprobes not supported here. Set the probe on schedule instead.
 */
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);

	/* we're going to use this soon, after a few expensive things */
	if (next_p->fpu_counter>5)
		prefetch(next->xstate);

	/*
	 * Reload esp0, LDT and the page table pointer:
	 */
	load_sp0(tss, next);

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

	/* Must be after DS reload */
	unlazy_fpu(prev_p);

	/* 
	 * Switch the PDA and FPU contexts.
	 */
	prev->usersp = read_pda(oldrsp);
	write_pda(oldrsp, next->usersp);
	write_pda(pcurrent, next_p); 

	write_pda(kernelstack,
	(unsigned long)task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET);
#ifdef CONFIG_CC_STACKPROTECTOR
	write_pda(stack_canary, next_p->stack_canary);
	/*
	 * Build time only check to make sure the stack_canary is at
	 * offset 40 in the pda; this is a gcc ABI requirement
	 */
	BUILD_BUG_ON(offsetof(struct x8664_pda, stack_canary) != 40);
#endif

	/*
	 * Now maybe reload the debug registers and handle I/O bitmaps
	 */
	if (unlikely(task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT ||
		     task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
		__switch_to_xtra(prev_p, next_p, tss);

	/* If the task has used fpu the last 5 timeslices, just do a full
	 * restore of the math state immediately to avoid the trap; the
	 * chances of needing FPU soon are obviously high now
	 */
	if (next_p->fpu_counter>5)
		math_state_restore();
	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);
	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->sp, 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->sp;
	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->sp, regs, 0,
		    NULL, NULL);
}

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

	if (!p || p == current || p->state==TASK_RUNNING)
		return 0; 
	stack = (unsigned long)task_stack_page(p);
	if (p->thread.sp < stack || p->thread.sp > stack+THREAD_SIZE)
		return 0;
	fp = *(u64 *)(p->thread.sp);
	do { 
		if (fp < (unsigned long)stack ||
		    fp > (unsigned long)stack+THREAD_SIZE)
			return 0; 
		ip = *(u64 *)(fp+8);
		if (!in_sched_functions(ip))
			return ip;
		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:
		if (addr >= TASK_SIZE_OF(task))
			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 */
		if (addr >= TASK_SIZE_OF(task))
			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;
		unsigned gsindex;
		if (task->thread.gsindex == GS_TLS_SEL)
			base = read_32bit_tls(task, GS_TLS);
		else if (doit) {
			asm("movl %%gs,%0" : "=r" (gsindex));
			if (gsindex)
				rdmsrl(MSR_KERNEL_GS_BASE, base);
			else
				base = task->thread.gs;
		}
		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);
}

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

unsigned long arch_randomize_brk(struct mm_struct *mm)
{
	unsigned long range_end = mm->brk + 0x02000000;
	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
}