summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/process_64.c
blob: 4285f6adcc5eec7f7ca8998e2797d5a03c4c8009 (plain)
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
/*
 *  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 <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/delay.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/prctl.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/ftrace.h>

#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/fpu/internal.h>
#include <asm/mmu_context.h>
#include <asm/prctl.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/ia32.h>
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/debugreg.h>
#include <asm/switch_to.h>
#include <asm/xen/hypervisor.h>

asmlinkage extern void ret_from_fork(void);

__visible DEFINE_PER_CPU(unsigned long, rsp_scratch);

/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs *regs, int all)
{
	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(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
	printk_address(regs->ip);
	printk(KERN_DEFAULT "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
			regs->sp, regs->flags);
	printk(KERN_DEFAULT "RAX: %016lx RBX: %016lx RCX: %016lx\n",
	       regs->ax, regs->bx, regs->cx);
	printk(KERN_DEFAULT "RDX: %016lx RSI: %016lx RDI: %016lx\n",
	       regs->dx, regs->si, regs->di);
	printk(KERN_DEFAULT "RBP: %016lx R08: %016lx R09: %016lx\n",
	       regs->bp, regs->r8, regs->r9);
	printk(KERN_DEFAULT "R10: %016lx R11: %016lx R12: %016lx\n",
	       regs->r10, regs->r11, regs->r12);
	printk(KERN_DEFAULT "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);

	if (!all)
		return;

	cr0 = read_cr0();
	cr2 = read_cr2();
	cr3 = read_cr3();
	cr4 = __read_cr4();

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

	get_debugreg(d0, 0);
	get_debugreg(d1, 1);
	get_debugreg(d2, 2);
	get_debugreg(d3, 3);
	get_debugreg(d6, 6);
	get_debugreg(d7, 7);

	/* Only print out debug registers if they are in their non-default state. */
	if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
	    (d6 == DR6_RESERVED) && (d7 == 0x400))
		return;

	printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
	printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);

	if (boot_cpu_has(X86_FEATURE_OSPKE))
		printk(KERN_DEFAULT "PKRU: %08x\n", read_pkru());
}

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

int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
		unsigned long arg, struct task_struct *p, unsigned long tls)
{
	int err;
	struct pt_regs *childregs;
	struct task_struct *me = current;

	p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE;
	childregs = task_pt_regs(p);
	p->thread.sp = (unsigned long) childregs;
	set_tsk_thread_flag(p, TIF_FORK);
	p->thread.io_bitmap_ptr = NULL;

	savesegment(gs, p->thread.gsindex);
	p->thread.gsbase = p->thread.gsindex ? 0 : me->thread.gsbase;
	savesegment(fs, p->thread.fsindex);
	p->thread.fsbase = p->thread.fsindex ? 0 : me->thread.fsbase;
	savesegment(es, p->thread.es);
	savesegment(ds, p->thread.ds);
	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));

	if (unlikely(p->flags & PF_KTHREAD)) {
		/* kernel thread */
		memset(childregs, 0, sizeof(struct pt_regs));
		childregs->sp = (unsigned long)childregs;
		childregs->ss = __KERNEL_DS;
		childregs->bx = sp; /* function */
		childregs->bp = arg;
		childregs->orig_ax = -1;
		childregs->cs = __KERNEL_CS | get_kernel_rpl();
		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
		return 0;
	}
	*childregs = *current_pt_regs();

	childregs->ax = 0;
	if (sp)
		childregs->sp = sp;

	err = -ENOMEM;
	if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
		p->thread.io_bitmap_ptr = kmemdup(me->thread.io_bitmap_ptr,
						  IO_BITMAP_BYTES, GFP_KERNEL);
		if (!p->thread.io_bitmap_ptr) {
			p->thread.io_bitmap_max = 0;
			return -ENOMEM;
		}
		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 (in_ia32_syscall())
			err = do_set_thread_area(p, -1,
				(struct user_desc __user *)tls, 0);
		else
#endif
			err = do_arch_prctl(p, ARCH_SET_FS, tls);
		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;
}

static void
start_thread_common(struct pt_regs *regs, unsigned long new_ip,
		    unsigned long new_sp,
		    unsigned int _cs, unsigned int _ss, unsigned int _ds)
{
	loadsegment(fs, 0);
	loadsegment(es, _ds);
	loadsegment(ds, _ds);
	load_gs_index(0);
	regs->ip		= new_ip;
	regs->sp		= new_sp;
	regs->cs		= _cs;
	regs->ss		= _ss;
	regs->flags		= X86_EFLAGS_IF;
	force_iret();
}

void
start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
{
	start_thread_common(regs, new_ip, new_sp,
			    __USER_CS, __USER_DS, 0);
}

#ifdef CONFIG_COMPAT
void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp)
{
	start_thread_common(regs, new_ip, new_sp,
			    test_thread_flag(TIF_X32)
			    ? __USER_CS : __USER32_CS,
			    __USER_DS, __USER_DS);
}
#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.
 * Function graph tracer not supported too.
 */
__visible __notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
	struct thread_struct *prev = &prev_p->thread;
	struct thread_struct *next = &next_p->thread;
	struct fpu *prev_fpu = &prev->fpu;
	struct fpu *next_fpu = &next->fpu;
	int cpu = smp_processor_id();
	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
	unsigned prev_fsindex, prev_gsindex;
	fpu_switch_t fpu_switch;

	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);

	/* We must save %fs and %gs before load_TLS() because
	 * %fs and %gs may be cleared by load_TLS().
	 *
	 * (e.g. xen_load_tls())
	 */
	savesegment(fs, prev_fsindex);
	savesegment(gs, prev_gsindex);

	/*
	 * Load TLS before restoring any segments so that segment loads
	 * reference the correct GDT entries.
	 */
	load_TLS(next, cpu);

	/*
	 * Leave lazy mode, flushing any hypercalls made here.  This
	 * must be done after loading TLS entries in the GDT but before
	 * loading segments that might reference them, and and it must
	 * be done before fpu__restore(), so the TS bit is up to
	 * date.
	 */
	arch_end_context_switch(next_p);

	/* Switch DS and ES.
	 *
	 * Reading them only returns the selectors, but writing them (if
	 * nonzero) loads the full descriptor from the GDT or LDT.  The
	 * LDT for next is loaded in switch_mm, and the GDT is loaded
	 * above.
	 *
	 * We therefore need to write new values to the segment
	 * registers on every context switch unless both the new and old
	 * values are zero.
	 *
	 * Note that we don't need to do anything for CS and SS, as
	 * those are saved and restored as part of pt_regs.
	 */
	savesegment(es, prev->es);
	if (unlikely(next->es | prev->es))
		loadsegment(es, next->es);

	savesegment(ds, prev->ds);
	if (unlikely(next->ds | prev->ds))
		loadsegment(ds, next->ds);

	/*
	 * Switch FS and GS.
	 *
	 * These are even more complicated than DS and ES: they have
	 * 64-bit bases are that controlled by arch_prctl.  The bases
	 * don't necessarily match the selectors, as user code can do
	 * any number of things to cause them to be inconsistent.
	 *
	 * We don't promise to preserve the bases if the selectors are
	 * nonzero.  We also don't promise to preserve the base if the
	 * selector is zero and the base doesn't match whatever was
	 * most recently passed to ARCH_SET_FS/GS.  (If/when the
	 * FSGSBASE instructions are enabled, we'll need to offer
	 * stronger guarantees.)
	 *
	 * As an invariant,
	 * (fsbase != 0 && fsindex != 0) || (gsbase != 0 && gsindex != 0) is
	 * impossible.
	 */
	if (next->fsindex) {
		/* Loading a nonzero value into FS sets the index and base. */
		loadsegment(fs, next->fsindex);
	} else {
		if (next->fsbase) {
			/* Next index is zero but next base is nonzero. */
			if (prev_fsindex)
				loadsegment(fs, 0);
			wrmsrl(MSR_FS_BASE, next->fsbase);
		} else {
			/* Next base and index are both zero. */
			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
				/*
				 * We don't know the previous base and can't
				 * find out without RDMSR.  Forcibly clear it.
				 */
				loadsegment(fs, __USER_DS);
				loadsegment(fs, 0);
			} else {
				/*
				 * If the previous index is zero and ARCH_SET_FS
				 * didn't change the base, then the base is
				 * also zero and we don't need to do anything.
				 */
				if (prev->fsbase || prev_fsindex)
					loadsegment(fs, 0);
			}
		}
	}
	/*
	 * Save the old state and preserve the invariant.
	 * NB: if prev_fsindex == 0, then we can't reliably learn the base
	 * without RDMSR because Intel user code can zero it without telling
	 * us and AMD user code can program any 32-bit value without telling
	 * us.
	 */
	if (prev_fsindex)
		prev->fsbase = 0;
	prev->fsindex = prev_fsindex;

	if (next->gsindex) {
		/* Loading a nonzero value into GS sets the index and base. */
		load_gs_index(next->gsindex);
	} else {
		if (next->gsbase) {
			/* Next index is zero but next base is nonzero. */
			if (prev_gsindex)
				load_gs_index(0);
			wrmsrl(MSR_KERNEL_GS_BASE, next->gsbase);
		} else {
			/* Next base and index are both zero. */
			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
				/*
				 * We don't know the previous base and can't
				 * find out without RDMSR.  Forcibly clear it.
				 *
				 * This contains a pointless SWAPGS pair.
				 * Fixing it would involve an explicit check
				 * for Xen or a new pvop.
				 */
				load_gs_index(__USER_DS);
				load_gs_index(0);
			} else {
				/*
				 * If the previous index is zero and ARCH_SET_GS
				 * didn't change the base, then the base is
				 * also zero and we don't need to do anything.
				 */
				if (prev->gsbase || prev_gsindex)
					load_gs_index(0);
			}
		}
	}
	/*
	 * Save the old state and preserve the invariant.
	 * NB: if prev_gsindex == 0, then we can't reliably learn the base
	 * without RDMSR because Intel user code can zero it without telling
	 * us and AMD user code can program any 32-bit value without telling
	 * us.
	 */
	if (prev_gsindex)
		prev->gsbase = 0;
	prev->gsindex = prev_gsindex;

	switch_fpu_finish(next_fpu, fpu_switch);

	/*
	 * Switch the PDA and FPU contexts.
	 */
	this_cpu_write(current_task, next_p);

	/* Reload esp0 and ss1.  This changes current_thread_info(). */
	load_sp0(tss, next);

	/*
	 * 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);

#ifdef CONFIG_XEN
	/*
	 * On Xen PV, IOPL bits in pt_regs->flags have no effect, and
	 * current_pt_regs()->flags may not match the current task's
	 * intended IOPL.  We need to switch it manually.
	 */
	if (unlikely(static_cpu_has(X86_FEATURE_XENPV) &&
		     prev->iopl != next->iopl))
		xen_set_iopl_mask(next->iopl);
#endif

	if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) {
		/*
		 * AMD CPUs have a misfeature: SYSRET sets the SS selector but
		 * does not update the cached descriptor.  As a result, if we
		 * do SYSRET while SS is NULL, we'll end up in user mode with
		 * SS apparently equal to __USER_DS but actually unusable.
		 *
		 * The straightforward workaround would be to fix it up just
		 * before SYSRET, but that would slow down the system call
		 * fast paths.  Instead, we ensure that SS is never NULL in
		 * system call context.  We do this by replacing NULL SS
		 * selectors at every context switch.  SYSCALL sets up a valid
		 * SS, so the only way to get NULL is to re-enter the kernel
		 * from CPL 3 through an interrupt.  Since that can't happen
		 * in the same task as a running syscall, we are guaranteed to
		 * context switch between every interrupt vector entry and a
		 * subsequent SYSRET.
		 *
		 * We read SS first because SS reads are much faster than
		 * writes.  Out of caution, we force SS to __KERNEL_DS even if
		 * it previously had a different non-NULL value.
		 */
		unsigned short ss_sel;
		savesegment(ss, ss_sel);
		if (ss_sel != __KERNEL_DS)
			loadsegment(ss, __KERNEL_DS);
	}

	return prev_p;
}

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

	/* Make sure to be in 64bit mode */
	clear_thread_flag(TIF_IA32);
	clear_thread_flag(TIF_ADDR32);
	clear_thread_flag(TIF_X32);

	/* Ensure the corresponding mm is not marked. */
	if (current->mm)
		current->mm->context.ia32_compat = 0;

	/* 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;
}

void set_personality_ia32(bool x32)
{
	/* inherit personality from parent */

	/* Make sure to be in 32bit mode */
	set_thread_flag(TIF_ADDR32);

	/* Mark the associated mm as containing 32-bit tasks. */
	if (x32) {
		clear_thread_flag(TIF_IA32);
		set_thread_flag(TIF_X32);
		if (current->mm)
			current->mm->context.ia32_compat = TIF_X32;
		current->personality &= ~READ_IMPLIES_EXEC;
		/* in_compat_syscall() uses the presence of the x32
		   syscall bit flag to determine compat status */
		current_thread_info()->status &= ~TS_COMPAT;
	} else {
		set_thread_flag(TIF_IA32);
		clear_thread_flag(TIF_X32);
		if (current->mm)
			current->mm->context.ia32_compat = TIF_IA32;
		current->personality |= force_personality32;
		/* Prepare the first "return" to user space */
		current_thread_info()->status |= TS_COMPAT;
	}
}
EXPORT_SYMBOL_GPL(set_personality_ia32);

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();
		task->thread.gsindex = 0;
		task->thread.gsbase = addr;
		if (doit) {
			load_gs_index(0);
			ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr);
		}
		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();
		task->thread.fsindex = 0;
		task->thread.fsbase = addr;
		if (doit) {
			/* set the selector to 0 to not confuse __switch_to */
			loadsegment(fs, 0);
			ret = wrmsrl_safe(MSR_FS_BASE, addr);
		}
		put_cpu();
		break;
	case ARCH_GET_FS: {
		unsigned long base;
		if (doit)
			rdmsrl(MSR_FS_BASE, base);
		else
			base = task->thread.fsbase;
		ret = put_user(base, (unsigned long __user *)addr);
		break;
	}
	case ARCH_GET_GS: {
		unsigned long base;
		if (doit)
			rdmsrl(MSR_KERNEL_GS_BASE, base);
		else
			base = task->thread.gsbase;
		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 KSTK_ESP(struct task_struct *task)
{
	return task_pt_regs(task)->sp;
}