summaryrefslogtreecommitdiffstats
path: root/arch/um/os-Linux/skas/process.c
blob: 23025d64516019e0d1451298570b5dc845b2bc62 (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
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
/*
 * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de)
 * Copyright (C) 2002- 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
 * Licensed under the GPL
 */

#include <stdlib.h>
#include <unistd.h>
#include <sched.h>
#include <errno.h>
#include <string.h>
#include <sys/mman.h>
#include <sys/wait.h>
#include <asm/unistd.h>
#include <as-layout.h>
#include <init.h>
#include <kern_util.h>
#include <mem.h>
#include <os.h>
#include <ptrace_user.h>
#include <registers.h>
#include <skas.h>
#include <sysdep/stub.h>

int is_skas_winch(int pid, int fd, void *data)
{
	return pid == getpgrp();
}

static int ptrace_dump_regs(int pid)
{
	unsigned long regs[MAX_REG_NR];
	int i;

	if (ptrace(PTRACE_GETREGS, pid, 0, regs) < 0)
		return -errno;

	printk(UM_KERN_ERR "Stub registers -\n");
	for (i = 0; i < ARRAY_SIZE(regs); i++)
		printk(UM_KERN_ERR "\t%d - %lx\n", i, regs[i]);

	return 0;
}

/*
 * Signals that are OK to receive in the stub - we'll just continue it.
 * SIGWINCH will happen when UML is inside a detached screen.
 */
#define STUB_SIG_MASK ((1 << SIGALRM) | (1 << SIGWINCH))

/* Signals that the stub will finish with - anything else is an error */
#define STUB_DONE_MASK (1 << SIGTRAP)

void wait_stub_done(int pid)
{
	int n, status, err;

	while (1) {
		CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL));
		if ((n < 0) || !WIFSTOPPED(status))
			goto bad_wait;

		if (((1 << WSTOPSIG(status)) & STUB_SIG_MASK) == 0)
			break;

		err = ptrace(PTRACE_CONT, pid, 0, 0);
		if (err) {
			printk(UM_KERN_ERR "wait_stub_done : continue failed, "
			       "errno = %d\n", errno);
			fatal_sigsegv();
		}
	}

	if (((1 << WSTOPSIG(status)) & STUB_DONE_MASK) != 0)
		return;

bad_wait:
	err = ptrace_dump_regs(pid);
	if (err)
		printk(UM_KERN_ERR "Failed to get registers from stub, "
		       "errno = %d\n", -err);
	printk(UM_KERN_ERR "wait_stub_done : failed to wait for SIGTRAP, "
	       "pid = %d, n = %d, errno = %d, status = 0x%x\n", pid, n, errno,
	       status);
	fatal_sigsegv();
}

extern unsigned long current_stub_stack(void);

static void get_skas_faultinfo(int pid, struct faultinfo *fi)
{
	int err;
	unsigned long fpregs[FP_SIZE];

	err = get_fp_registers(pid, fpregs);
	if (err < 0) {
		printk(UM_KERN_ERR "save_fp_registers returned %d\n",
		       err);
		fatal_sigsegv();
	}
	err = ptrace(PTRACE_CONT, pid, 0, SIGSEGV);
	if (err) {
		printk(UM_KERN_ERR "Failed to continue stub, pid = %d, "
		       "errno = %d\n", pid, errno);
		fatal_sigsegv();
	}
	wait_stub_done(pid);

	/*
	 * faultinfo is prepared by the stub-segv-handler at start of
	 * the stub stack page. We just have to copy it.
	 */
	memcpy(fi, (void *)current_stub_stack(), sizeof(*fi));

	err = put_fp_registers(pid, fpregs);
	if (err < 0) {
		printk(UM_KERN_ERR "put_fp_registers returned %d\n",
		       err);
		fatal_sigsegv();
	}
}

static void handle_segv(int pid, struct uml_pt_regs * regs)
{
	get_skas_faultinfo(pid, &regs->faultinfo);
	segv(regs->faultinfo, 0, 1, NULL);
}

/*
 * To use the same value of using_sysemu as the caller, ask it that value
 * (in local_using_sysemu
 */
static void handle_trap(int pid, struct uml_pt_regs *regs,
			int local_using_sysemu)
{
	int err, status;

	if ((UPT_IP(regs) >= STUB_START) && (UPT_IP(regs) < STUB_END))
		fatal_sigsegv();

	if (!local_using_sysemu)
	{
		err = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_NR_OFFSET,
			     __NR_getpid);
		if (err < 0) {
			printk(UM_KERN_ERR "handle_trap - nullifying syscall "
			       "failed, errno = %d\n", errno);
			fatal_sigsegv();
		}

		err = ptrace(PTRACE_SYSCALL, pid, 0, 0);
		if (err < 0) {
			printk(UM_KERN_ERR "handle_trap - continuing to end of "
			       "syscall failed, errno = %d\n", errno);
			fatal_sigsegv();
		}

		CATCH_EINTR(err = waitpid(pid, &status, WUNTRACED | __WALL));
		if ((err < 0) || !WIFSTOPPED(status) ||
		    (WSTOPSIG(status) != SIGTRAP + 0x80)) {
			err = ptrace_dump_regs(pid);
			if (err)
				printk(UM_KERN_ERR "Failed to get registers "
				       "from process, errno = %d\n", -err);
			printk(UM_KERN_ERR "handle_trap - failed to wait at "
			       "end of syscall, errno = %d, status = %d\n",
			       errno, status);
			fatal_sigsegv();
		}
	}

	handle_syscall(regs);
}

extern char __syscall_stub_start[];

static int userspace_tramp(void *stack)
{
	void *addr;
	int fd;
	unsigned long long offset;

	ptrace(PTRACE_TRACEME, 0, 0, 0);

	signal(SIGTERM, SIG_DFL);
	signal(SIGWINCH, SIG_IGN);

	/*
	 * This has a pte, but it can't be mapped in with the usual
	 * tlb_flush mechanism because this is part of that mechanism
	 */
	fd = phys_mapping(to_phys(__syscall_stub_start), &offset);
	addr = mmap64((void *) STUB_CODE, UM_KERN_PAGE_SIZE,
		      PROT_EXEC, MAP_FIXED | MAP_PRIVATE, fd, offset);
	if (addr == MAP_FAILED) {
		printk(UM_KERN_ERR "mapping mmap stub at 0x%lx failed, "
		       "errno = %d\n", STUB_CODE, errno);
		exit(1);
	}

	if (stack != NULL) {
		fd = phys_mapping(to_phys(stack), &offset);
		addr = mmap((void *) STUB_DATA,
			    UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE,
			    MAP_FIXED | MAP_SHARED, fd, offset);
		if (addr == MAP_FAILED) {
			printk(UM_KERN_ERR "mapping segfault stack "
			       "at 0x%lx failed, errno = %d\n",
			       STUB_DATA, errno);
			exit(1);
		}
	}
	if (stack != NULL) {
		struct sigaction sa;

		unsigned long v = STUB_CODE +
				  (unsigned long) stub_segv_handler -
				  (unsigned long) __syscall_stub_start;

		set_sigstack((void *) STUB_DATA, UM_KERN_PAGE_SIZE);
		sigemptyset(&sa.sa_mask);
		sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
		sa.sa_sigaction = (void *) v;
		sa.sa_restorer = NULL;
		if (sigaction(SIGSEGV, &sa, NULL) < 0) {
			printk(UM_KERN_ERR "userspace_tramp - setting SIGSEGV "
			       "handler failed - errno = %d\n", errno);
			exit(1);
		}
	}

	kill(os_getpid(), SIGSTOP);
	return 0;
}

/* Each element set once, and only accessed by a single processor anyway */
#undef NR_CPUS
#define NR_CPUS 1
int userspace_pid[NR_CPUS];

int start_userspace(unsigned long stub_stack)
{
	void *stack;
	unsigned long sp;
	int pid, status, n, flags, err;

	stack = mmap(NULL, UM_KERN_PAGE_SIZE,
		     PROT_READ | PROT_WRITE | PROT_EXEC,
		     MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
	if (stack == MAP_FAILED) {
		err = -errno;
		printk(UM_KERN_ERR "start_userspace : mmap failed, "
		       "errno = %d\n", errno);
		return err;
	}

	sp = (unsigned long) stack + UM_KERN_PAGE_SIZE - sizeof(void *);

	flags = CLONE_FILES | SIGCHLD;

	pid = clone(userspace_tramp, (void *) sp, flags, (void *) stub_stack);
	if (pid < 0) {
		err = -errno;
		printk(UM_KERN_ERR "start_userspace : clone failed, "
		       "errno = %d\n", errno);
		return err;
	}

	do {
		CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL));
		if (n < 0) {
			err = -errno;
			printk(UM_KERN_ERR "start_userspace : wait failed, "
			       "errno = %d\n", errno);
			goto out_kill;
		}
	} while (WIFSTOPPED(status) && (WSTOPSIG(status) == SIGALRM));

	if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGSTOP)) {
		err = -EINVAL;
		printk(UM_KERN_ERR "start_userspace : expected SIGSTOP, got "
		       "status = %d\n", status);
		goto out_kill;
	}

	if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL,
		   (void *) PTRACE_O_TRACESYSGOOD) < 0) {
		err = -errno;
		printk(UM_KERN_ERR "start_userspace : PTRACE_OLDSETOPTIONS "
		       "failed, errno = %d\n", errno);
		goto out_kill;
	}

	if (munmap(stack, UM_KERN_PAGE_SIZE) < 0) {
		err = -errno;
		printk(UM_KERN_ERR "start_userspace : munmap failed, "
		       "errno = %d\n", errno);
		goto out_kill;
	}

	return pid;

 out_kill:
	os_kill_ptraced_process(pid, 1);
	return err;
}

void userspace(struct uml_pt_regs *regs)
{
	int err, status, op, pid = userspace_pid[0];
	/* To prevent races if using_sysemu changes under us.*/
	int local_using_sysemu;
	siginfo_t si;

	/* Handle any immediate reschedules or signals */
	interrupt_end();

	while (1) {

		/*
		 * This can legitimately fail if the process loads a
		 * bogus value into a segment register.  It will
		 * segfault and PTRACE_GETREGS will read that value
		 * out of the process.  However, PTRACE_SETREGS will
		 * fail.  In this case, there is nothing to do but
		 * just kill the process.
		 */
		if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp))
			fatal_sigsegv();

		if (put_fp_registers(pid, regs->fp))
			fatal_sigsegv();

		/* Now we set local_using_sysemu to be used for one loop */
		local_using_sysemu = get_using_sysemu();

		op = SELECT_PTRACE_OPERATION(local_using_sysemu,
					     singlestepping(NULL));

		if (ptrace(op, pid, 0, 0)) {
			printk(UM_KERN_ERR "userspace - ptrace continue "
			       "failed, op = %d, errno = %d\n", op, errno);
			fatal_sigsegv();
		}

		CATCH_EINTR(err = waitpid(pid, &status, WUNTRACED | __WALL));
		if (err < 0) {
			printk(UM_KERN_ERR "userspace - wait failed, "
			       "errno = %d\n", errno);
			fatal_sigsegv();
		}

		regs->is_user = 1;
		if (ptrace(PTRACE_GETREGS, pid, 0, regs->gp)) {
			printk(UM_KERN_ERR "userspace - PTRACE_GETREGS failed, "
			       "errno = %d\n", errno);
			fatal_sigsegv();
		}

		if (get_fp_registers(pid, regs->fp)) {
			printk(UM_KERN_ERR "userspace -  get_fp_registers failed, "
			       "errno = %d\n", errno);
			fatal_sigsegv();
		}

		UPT_SYSCALL_NR(regs) = -1; /* Assume: It's not a syscall */

		if (WIFSTOPPED(status)) {
			int sig = WSTOPSIG(status);

			ptrace(PTRACE_GETSIGINFO, pid, 0, (struct siginfo *)&si);

			switch (sig) {
			case SIGSEGV:
				if (PTRACE_FULL_FAULTINFO) {
					get_skas_faultinfo(pid,
							   &regs->faultinfo);
					(*sig_info[SIGSEGV])(SIGSEGV, (struct siginfo *)&si,
							     regs);
				}
				else handle_segv(pid, regs);
				break;
			case SIGTRAP + 0x80:
			        handle_trap(pid, regs, local_using_sysemu);
				break;
			case SIGTRAP:
				relay_signal(SIGTRAP, (struct siginfo *)&si, regs);
				break;
			case SIGALRM:
				break;
			case SIGIO:
			case SIGILL:
			case SIGBUS:
			case SIGFPE:
			case SIGWINCH:
				block_signals();
				(*sig_info[sig])(sig, (struct siginfo *)&si, regs);
				unblock_signals();
				break;
			default:
				printk(UM_KERN_ERR "userspace - child stopped "
				       "with signal %d\n", sig);
				fatal_sigsegv();
			}
			pid = userspace_pid[0];
			interrupt_end();

			/* Avoid -ERESTARTSYS handling in host */
			if (PT_SYSCALL_NR_OFFSET != PT_SYSCALL_RET_OFFSET)
				PT_SYSCALL_NR(regs->gp) = -1;
		}
	}
}

static unsigned long thread_regs[MAX_REG_NR];
static unsigned long thread_fp_regs[FP_SIZE];

static int __init init_thread_regs(void)
{
	get_safe_registers(thread_regs, thread_fp_regs);
	/* Set parent's instruction pointer to start of clone-stub */
	thread_regs[REGS_IP_INDEX] = STUB_CODE +
				(unsigned long) stub_clone_handler -
				(unsigned long) __syscall_stub_start;
	thread_regs[REGS_SP_INDEX] = STUB_DATA + UM_KERN_PAGE_SIZE -
		sizeof(void *);
#ifdef __SIGNAL_FRAMESIZE
	thread_regs[REGS_SP_INDEX] -= __SIGNAL_FRAMESIZE;
#endif
	return 0;
}

__initcall(init_thread_regs);

int copy_context_skas0(unsigned long new_stack, int pid)
{
	int err;
	unsigned long current_stack = current_stub_stack();
	struct stub_data *data = (struct stub_data *) current_stack;
	struct stub_data *child_data = (struct stub_data *) new_stack;
	unsigned long long new_offset;
	int new_fd = phys_mapping(to_phys((void *)new_stack), &new_offset);

	/*
	 * prepare offset and fd of child's stack as argument for parent's
	 * and child's mmap2 calls
	 */
	*data = ((struct stub_data) {
			.offset	= MMAP_OFFSET(new_offset),
			.fd     = new_fd
	});

	err = ptrace_setregs(pid, thread_regs);
	if (err < 0) {
		err = -errno;
		printk(UM_KERN_ERR "copy_context_skas0 : PTRACE_SETREGS "
		       "failed, pid = %d, errno = %d\n", pid, -err);
		return err;
	}

	err = put_fp_registers(pid, thread_fp_regs);
	if (err < 0) {
		printk(UM_KERN_ERR "copy_context_skas0 : put_fp_registers "
		       "failed, pid = %d, err = %d\n", pid, err);
		return err;
	}

	/* set a well known return code for detection of child write failure */
	child_data->err = 12345678;

	/*
	 * Wait, until parent has finished its work: read child's pid from
	 * parent's stack, and check, if bad result.
	 */
	err = ptrace(PTRACE_CONT, pid, 0, 0);
	if (err) {
		err = -errno;
		printk(UM_KERN_ERR "Failed to continue new process, pid = %d, "
		       "errno = %d\n", pid, errno);
		return err;
	}

	wait_stub_done(pid);

	pid = data->err;
	if (pid < 0) {
		printk(UM_KERN_ERR "copy_context_skas0 - stub-parent reports "
		       "error %d\n", -pid);
		return pid;
	}

	/*
	 * Wait, until child has finished too: read child's result from
	 * child's stack and check it.
	 */
	wait_stub_done(pid);
	if (child_data->err != STUB_DATA) {
		printk(UM_KERN_ERR "copy_context_skas0 - stub-child reports "
		       "error %ld\n", child_data->err);
		err = child_data->err;
		goto out_kill;
	}

	if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL,
		   (void *)PTRACE_O_TRACESYSGOOD) < 0) {
		err = -errno;
		printk(UM_KERN_ERR "copy_context_skas0 : PTRACE_OLDSETOPTIONS "
		       "failed, errno = %d\n", errno);
		goto out_kill;
	}

	return pid;

 out_kill:
	os_kill_ptraced_process(pid, 1);
	return err;
}

void new_thread(void *stack, jmp_buf *buf, void (*handler)(void))
{
	(*buf)[0].JB_IP = (unsigned long) handler;
	(*buf)[0].JB_SP = (unsigned long) stack + UM_THREAD_SIZE -
		sizeof(void *);
}

#define INIT_JMP_NEW_THREAD 0
#define INIT_JMP_CALLBACK 1
#define INIT_JMP_HALT 2
#define INIT_JMP_REBOOT 3

void switch_threads(jmp_buf *me, jmp_buf *you)
{
	if (UML_SETJMP(me) == 0)
		UML_LONGJMP(you, 1);
}

static jmp_buf initial_jmpbuf;

/* XXX Make these percpu */
static void (*cb_proc)(void *arg);
static void *cb_arg;
static jmp_buf *cb_back;

int start_idle_thread(void *stack, jmp_buf *switch_buf)
{
	int n;

	set_handler(SIGWINCH);

	/*
	 * Can't use UML_SETJMP or UML_LONGJMP here because they save
	 * and restore signals, with the possible side-effect of
	 * trying to handle any signals which came when they were
	 * blocked, which can't be done on this stack.
	 * Signals must be blocked when jumping back here and restored
	 * after returning to the jumper.
	 */
	n = setjmp(initial_jmpbuf);
	switch (n) {
	case INIT_JMP_NEW_THREAD:
		(*switch_buf)[0].JB_IP = (unsigned long) uml_finishsetup;
		(*switch_buf)[0].JB_SP = (unsigned long) stack +
			UM_THREAD_SIZE - sizeof(void *);
		break;
	case INIT_JMP_CALLBACK:
		(*cb_proc)(cb_arg);
		longjmp(*cb_back, 1);
		break;
	case INIT_JMP_HALT:
		kmalloc_ok = 0;
		return 0;
	case INIT_JMP_REBOOT:
		kmalloc_ok = 0;
		return 1;
	default:
		printk(UM_KERN_ERR "Bad sigsetjmp return in "
		       "start_idle_thread - %d\n", n);
		fatal_sigsegv();
	}
	longjmp(*switch_buf, 1);
}

void initial_thread_cb_skas(void (*proc)(void *), void *arg)
{
	jmp_buf here;

	cb_proc = proc;
	cb_arg = arg;
	cb_back = &here;

	block_signals();
	if (UML_SETJMP(&here) == 0)
		UML_LONGJMP(&initial_jmpbuf, INIT_JMP_CALLBACK);
	unblock_signals();

	cb_proc = NULL;
	cb_arg = NULL;
	cb_back = NULL;
}

void halt_skas(void)
{
	block_signals();
	UML_LONGJMP(&initial_jmpbuf, INIT_JMP_HALT);
}

void reboot_skas(void)
{
	block_signals();
	UML_LONGJMP(&initial_jmpbuf, INIT_JMP_REBOOT);
}

void __switch_mm(struct mm_id *mm_idp)
{
	userspace_pid[0] = mm_idp->u.pid;
}
OpenPOWER on IntegriCloud