coredump.c 20.6 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/mm.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/swap.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/perf_event.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/key.h>
#include <linux/personality.h>
#include <linux/binfmts.h>
17
#include <linux/coredump.h>
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
#include <linux/utsname.h>
#include <linux/pid_namespace.h>
#include <linux/module.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/audit.h>
#include <linux/tracehook.h>
#include <linux/kmod.h>
#include <linux/fsnotify.h>
#include <linux/fs_struct.h>
#include <linux/pipe_fs_i.h>
#include <linux/oom.h>
#include <linux/compat.h>
35
36
37
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/path.h>
38
#include <linux/timekeeping.h>
39
40
41
42
43
44
45
46
47
48
49
50
51

#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/tlb.h>
#include <asm/exec.h>

#include <trace/events/task.h>
#include "internal.h"

#include <trace/events/sched.h>

int core_uses_pid;
unsigned int core_pipe_limit;
52
53
char core_pattern[CORENAME_MAX_SIZE] = "core";
static int core_name_size = CORENAME_MAX_SIZE;
54
55
56
57
58
59
60
61

struct core_name {
	char *corename;
	int used, size;
};

/* The maximal length of core_pattern is also specified in sysctl.c */

62
static int expand_corename(struct core_name *cn, int size)
63
{
64
	char *corename = krealloc(cn->corename, size, GFP_KERNEL);
65

66
	if (!corename)
67
68
		return -ENOMEM;

69
70
71
72
	if (size > core_name_size) /* racy but harmless */
		core_name_size = size;

	cn->size = ksize(corename);
73
	cn->corename = corename;
74
75
76
	return 0;
}

77
78
static __printf(2, 0) int cn_vprintf(struct core_name *cn, const char *fmt,
				     va_list arg)
79
{
80
	int free, need;
81
	va_list arg_copy;
82

83
84
again:
	free = cn->size - cn->used;
85
86
87
88
89

	va_copy(arg_copy, arg);
	need = vsnprintf(cn->corename + cn->used, free, fmt, arg_copy);
	va_end(arg_copy);

90
91
92
93
	if (need < free) {
		cn->used += need;
		return 0;
	}
94

95
	if (!expand_corename(cn, cn->size + need - free + 1))
96
		goto again;
97

98
	return -ENOMEM;
99
100
}

101
static __printf(2, 3) int cn_printf(struct core_name *cn, const char *fmt, ...)
102
103
104
105
106
107
108
109
110
111
112
{
	va_list arg;
	int ret;

	va_start(arg, fmt);
	ret = cn_vprintf(cn, fmt, arg);
	va_end(arg);

	return ret;
}

113
114
static __printf(2, 3)
int cn_esc_printf(struct core_name *cn, const char *fmt, ...)
115
{
116
117
118
119
120
121
122
123
	int cur = cn->used;
	va_list arg;
	int ret;

	va_start(arg, fmt);
	ret = cn_vprintf(cn, fmt, arg);
	va_end(arg);

124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
	if (ret == 0) {
		/*
		 * Ensure that this coredump name component can't cause the
		 * resulting corefile path to consist of a ".." or ".".
		 */
		if ((cn->used - cur == 1 && cn->corename[cur] == '.') ||
				(cn->used - cur == 2 && cn->corename[cur] == '.'
				&& cn->corename[cur+1] == '.'))
			cn->corename[cur] = '!';

		/*
		 * Empty names are fishy and could be used to create a "//" in a
		 * corefile name, causing the coredump to happen one directory
		 * level too high. Enforce that all components of the core
		 * pattern are at least one character long.
		 */
		if (cn->used == cur)
			ret = cn_printf(cn, "!");
	}

144
145
146
147
148
	for (; cur < cn->used; ++cur) {
		if (cn->corename[cur] == '/')
			cn->corename[cur] = '!';
	}
	return ret;
149
150
151
152
153
154
155
156
157
}

static int cn_print_exe_file(struct core_name *cn)
{
	struct file *exe_file;
	char *pathbuf, *path;
	int ret;

	exe_file = get_mm_exe_file(current->mm);
158
159
	if (!exe_file)
		return cn_esc_printf(cn, "%s (path unknown)", current->comm);
160
161
162
163
164
165
166

	pathbuf = kmalloc(PATH_MAX, GFP_TEMPORARY);
	if (!pathbuf) {
		ret = -ENOMEM;
		goto put_exe_file;
	}

Miklos Szeredi's avatar
Miklos Szeredi committed
167
	path = file_path(exe_file, pathbuf, PATH_MAX);
168
169
170
171
172
	if (IS_ERR(path)) {
		ret = PTR_ERR(path);
		goto free_buf;
	}

173
	ret = cn_esc_printf(cn, "%s", path);
174
175
176
177
178
179
180
181
182
183
184
185

free_buf:
	kfree(pathbuf);
put_exe_file:
	fput(exe_file);
	return ret;
}

/* format_corename will inspect the pattern parameter, and output a
 * name into corename, which must have space for at least
 * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
 */
186
static int format_corename(struct core_name *cn, struct coredump_params *cprm)
187
188
189
190
191
192
193
{
	const struct cred *cred = current_cred();
	const char *pat_ptr = core_pattern;
	int ispipe = (*pat_ptr == '|');
	int pid_in_pattern = 0;
	int err = 0;

194
	cn->used = 0;
195
196
	cn->corename = NULL;
	if (expand_corename(cn, core_name_size))
197
		return -ENOMEM;
198
199
200
201
	cn->corename[0] = '\0';

	if (ispipe)
		++pat_ptr;
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222

	/* Repeat as long as we have more pattern to process and more output
	   space */
	while (*pat_ptr) {
		if (*pat_ptr != '%') {
			err = cn_printf(cn, "%c", *pat_ptr++);
		} else {
			switch (*++pat_ptr) {
			/* single % at the end, drop that */
			case 0:
				goto out;
			/* Double percent, output one percent */
			case '%':
				err = cn_printf(cn, "%c", '%');
				break;
			/* pid */
			case 'p':
				pid_in_pattern = 1;
				err = cn_printf(cn, "%d",
					      task_tgid_vnr(current));
				break;
223
224
225
226
227
			/* global pid */
			case 'P':
				err = cn_printf(cn, "%d",
					      task_tgid_nr(current));
				break;
228
229
230
231
232
233
234
235
			case 'i':
				err = cn_printf(cn, "%d",
					      task_pid_vnr(current));
				break;
			case 'I':
				err = cn_printf(cn, "%d",
					      task_pid_nr(current));
				break;
236
237
			/* uid */
			case 'u':
238
239
240
				err = cn_printf(cn, "%u",
						from_kuid(&init_user_ns,
							  cred->uid));
241
242
243
				break;
			/* gid */
			case 'g':
244
245
246
				err = cn_printf(cn, "%u",
						from_kgid(&init_user_ns,
							  cred->gid));
247
				break;
248
249
250
251
			case 'd':
				err = cn_printf(cn, "%d",
					__get_dumpable(cprm->mm_flags));
				break;
252
253
			/* signal that caused the coredump */
			case 's':
254
255
				err = cn_printf(cn, "%d",
						cprm->siginfo->si_signo);
256
257
258
				break;
			/* UNIX time of coredump */
			case 't': {
259
260
261
262
				time64_t time;

				time = ktime_get_real_seconds();
				err = cn_printf(cn, "%lld", time);
263
264
265
				break;
			}
			/* hostname */
266
			case 'h':
267
				down_read(&uts_sem);
268
				err = cn_esc_printf(cn, "%s",
269
270
271
272
					      utsname()->nodename);
				up_read(&uts_sem);
				break;
			/* executable */
273
274
			case 'e':
				err = cn_esc_printf(cn, "%s", current->comm);
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
				break;
			case 'E':
				err = cn_print_exe_file(cn);
				break;
			/* core limit size */
			case 'c':
				err = cn_printf(cn, "%lu",
					      rlimit(RLIMIT_CORE));
				break;
			default:
				break;
			}
			++pat_ptr;
		}

		if (err)
			return err;
	}

294
out:
295
296
297
298
299
300
301
302
303
304
305
306
307
	/* Backward compatibility with core_uses_pid:
	 *
	 * If core_pattern does not include a %p (as is the default)
	 * and core_uses_pid is set, then .%pid will be appended to
	 * the filename. Do not do this for piped commands. */
	if (!ispipe && !pid_in_pattern && core_uses_pid) {
		err = cn_printf(cn, ".%d", task_tgid_vnr(current));
		if (err)
			return err;
	}
	return ispipe;
}

308
static int zap_process(struct task_struct *start, int exit_code, int flags)
309
310
311
312
{
	struct task_struct *t;
	int nr = 0;

313
314
	/* ignore all signals except SIGKILL, see prepare_signal() */
	start->signal->flags = SIGNAL_GROUP_COREDUMP | flags;
315
316
317
	start->signal->group_exit_code = exit_code;
	start->signal->group_stop_count = 0;

318
	for_each_thread(start, t) {
319
320
321
322
323
324
		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
		if (t != current && t->mm) {
			sigaddset(&t->pending.signal, SIGKILL);
			signal_wake_up(t, 1);
			nr++;
		}
325
	}
326
327
328
329

	return nr;
}

330
331
static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
			struct core_state *core_state, int exit_code)
332
333
334
335
336
337
338
339
{
	struct task_struct *g, *p;
	unsigned long flags;
	int nr = -EAGAIN;

	spin_lock_irq(&tsk->sighand->siglock);
	if (!signal_group_exit(tsk->signal)) {
		mm->core_state = core_state;
340
		tsk->signal->group_exit_task = tsk;
341
		nr = zap_process(tsk, exit_code, 0);
342
		clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
343
344
345
346
347
	}
	spin_unlock_irq(&tsk->sighand->siglock);
	if (unlikely(nr < 0))
		return nr;

348
	tsk->flags |= PF_DUMPCORE;
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
	if (atomic_read(&mm->mm_users) == nr + 1)
		goto done;
	/*
	 * We should find and kill all tasks which use this mm, and we should
	 * count them correctly into ->nr_threads. We don't take tasklist
	 * lock, but this is safe wrt:
	 *
	 * fork:
	 *	None of sub-threads can fork after zap_process(leader). All
	 *	processes which were created before this point should be
	 *	visible to zap_threads() because copy_process() adds the new
	 *	process to the tail of init_task.tasks list, and lock/unlock
	 *	of ->siglock provides a memory barrier.
	 *
	 * do_exit:
	 *	The caller holds mm->mmap_sem. This means that the task which
	 *	uses this mm can't pass exit_mm(), so it can't exit or clear
	 *	its ->mm.
	 *
	 * de_thread:
	 *	It does list_replace_rcu(&leader->tasks, &current->tasks),
	 *	we must see either old or new leader, this does not matter.
	 *	However, it can change p->sighand, so lock_task_sighand(p)
	 *	must be used. Since p->mm != NULL and we hold ->mmap_sem
	 *	it can't fail.
	 *
	 *	Note also that "g" can be the old leader with ->mm == NULL
	 *	and already unhashed and thus removed from ->thread_group.
	 *	This is OK, __unhash_process()->list_del_rcu() does not
	 *	clear the ->next pointer, we will find the new leader via
	 *	next_thread().
	 */
	rcu_read_lock();
	for_each_process(g) {
		if (g == tsk->group_leader)
			continue;
		if (g->flags & PF_KTHREAD)
			continue;
387
388
389
390
391
392
393
394
395

		for_each_thread(g, p) {
			if (unlikely(!p->mm))
				continue;
			if (unlikely(p->mm == mm)) {
				lock_task_sighand(p, &flags);
				nr += zap_process(p, exit_code,
							SIGNAL_GROUP_EXIT);
				unlock_task_sighand(p, &flags);
396
			}
397
398
			break;
		}
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
	}
	rcu_read_unlock();
done:
	atomic_set(&core_state->nr_threads, nr);
	return nr;
}

static int coredump_wait(int exit_code, struct core_state *core_state)
{
	struct task_struct *tsk = current;
	struct mm_struct *mm = tsk->mm;
	int core_waiters = -EBUSY;

	init_completion(&core_state->startup);
	core_state->dumper.task = tsk;
	core_state->dumper.next = NULL;

	down_write(&mm->mmap_sem);
	if (!mm->core_state)
		core_waiters = zap_threads(tsk, mm, core_state, exit_code);
	up_write(&mm->mmap_sem);

	if (core_waiters > 0) {
		struct core_thread *ptr;

		wait_for_completion(&core_state->startup);
		/*
		 * Wait for all the threads to become inactive, so that
		 * all the thread context (extended register state, like
		 * fpu etc) gets copied to the memory.
		 */
		ptr = core_state->dumper.next;
		while (ptr != NULL) {
			wait_task_inactive(ptr->task, 0);
			ptr = ptr->next;
		}
	}

	return core_waiters;
}

440
static void coredump_finish(struct mm_struct *mm, bool core_dumped)
441
442
443
444
{
	struct core_thread *curr, *next;
	struct task_struct *task;

445
	spin_lock_irq(&current->sighand->siglock);
446
447
	if (core_dumped && !__fatal_signal_pending(current))
		current->signal->group_exit_code |= 0x80;
448
449
450
451
	current->signal->group_exit_task = NULL;
	current->signal->flags = SIGNAL_GROUP_EXIT;
	spin_unlock_irq(&current->sighand->siglock);

452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
	next = mm->core_state->dumper.next;
	while ((curr = next) != NULL) {
		next = curr->next;
		task = curr->task;
		/*
		 * see exit_mm(), curr->task must not see
		 * ->task == NULL before we read ->next.
		 */
		smp_mb();
		curr->task = NULL;
		wake_up_process(task);
	}

	mm->core_state = NULL;
}

468
469
470
471
472
473
474
475
476
477
478
static bool dump_interrupted(void)
{
	/*
	 * SIGKILL or freezing() interrupt the coredumping. Perhaps we
	 * can do try_to_freeze() and check __fatal_signal_pending(),
	 * but then we need to teach dump_write() to restart and clear
	 * TIF_SIGPENDING.
	 */
	return signal_pending(current);
}

479
480
static void wait_for_dump_helpers(struct file *file)
{
481
	struct pipe_inode_info *pipe = file->private_data;
482
483
484
485

	pipe_lock(pipe);
	pipe->readers++;
	pipe->writers--;
486
487
488
	wake_up_interruptible_sync(&pipe->wait);
	kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
	pipe_unlock(pipe);
489

490
491
492
493
494
	/*
	 * We actually want wait_event_freezable() but then we need
	 * to clear TIF_SIGPENDING and improve dump_interrupted().
	 */
	wait_event_interruptible(pipe->wait, pipe->readers == 1);
495

496
	pipe_lock(pipe);
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
	pipe->readers--;
	pipe->writers++;
	pipe_unlock(pipe);
}

/*
 * umh_pipe_setup
 * helper function to customize the process used
 * to collect the core in userspace.  Specifically
 * it sets up a pipe and installs it as fd 0 (stdin)
 * for the process.  Returns 0 on success, or
 * PTR_ERR on failure.
 * Note that it also sets the core limit to 1.  This
 * is a special value that we use to trap recursive
 * core dumps
 */
static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
{
	struct file *files[2];
	struct coredump_params *cp = (struct coredump_params *)info->data;
	int err = create_pipe_files(files, 0);
	if (err)
		return err;

	cp->file = files[1];

Al Viro's avatar
Al Viro committed
523
524
	err = replace_fd(0, files[0], 0);
	fput(files[0]);
525
526
527
	/* and disallow core files too */
	current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1};

Al Viro's avatar
Al Viro committed
528
	return err;
529
530
}

Al Viro's avatar
Al Viro committed
531
void do_coredump(const siginfo_t *siginfo)
532
533
534
535
536
537
538
539
540
541
{
	struct core_state core_state;
	struct core_name cn;
	struct mm_struct *mm = current->mm;
	struct linux_binfmt * binfmt;
	const struct cred *old_cred;
	struct cred *cred;
	int retval = 0;
	int ispipe;
	struct files_struct *displaced;
542
543
	/* require nonrelative corefile path and be extra careful */
	bool need_suid_safe = false;
544
	bool core_dumped = false;
545
546
	static atomic_t core_dump_count = ATOMIC_INIT(0);
	struct coredump_params cprm = {
547
		.siginfo = siginfo,
548
		.regs = signal_pt_regs(),
549
550
551
552
553
554
555
556
557
		.limit = rlimit(RLIMIT_CORE),
		/*
		 * We must use the same mm->flags while dumping core to avoid
		 * inconsistency of bit flags, since this flag is not protected
		 * by any locks.
		 */
		.mm_flags = mm->flags,
	};

558
	audit_core_dumps(siginfo->si_signo);
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574

	binfmt = mm->binfmt;
	if (!binfmt || !binfmt->core_dump)
		goto fail;
	if (!__get_dumpable(cprm.mm_flags))
		goto fail;

	cred = prepare_creds();
	if (!cred)
		goto fail;
	/*
	 * We cannot trust fsuid as being the "true" uid of the process
	 * nor do we know its entire history. We only know it was tainted
	 * so we dump it as root in mode 2, and only into a controlled
	 * environment (pipe handler or fully qualified path).
	 */
575
	if (__get_dumpable(cprm.mm_flags) == SUID_DUMP_ROOT) {
576
577
		/* Setuid core dump mode */
		cred->fsuid = GLOBAL_ROOT_UID;	/* Dump root private */
578
		need_suid_safe = true;
579
580
	}

581
	retval = coredump_wait(siginfo->si_signo, &core_state);
582
583
584
585
586
	if (retval < 0)
		goto fail_creds;

	old_cred = override_creds(cred);

587
	ispipe = format_corename(&cn, &cprm);
588

589
	if (ispipe) {
590
591
		int dump_count;
		char **helper_argv;
592
		struct subprocess_info *sub_info;
593
594
595
596

		if (ispipe < 0) {
			printk(KERN_WARNING "format_corename failed\n");
			printk(KERN_WARNING "Aborting core\n");
597
			goto fail_unlock;
598
599
600
601
602
603
604
		}

		if (cprm.limit == 1) {
			/* See umh_pipe_setup() which sets RLIMIT_CORE = 1.
			 *
			 * Normally core limits are irrelevant to pipes, since
			 * we're not writing to the file system, but we use
Bastien Nocera's avatar
Bastien Nocera committed
605
			 * cprm.limit of 1 here as a special value, this is a
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
			 * consistent way to catch recursive crashes.
			 * We can still crash if the core_pattern binary sets
			 * RLIM_CORE = !1, but it runs as root, and can do
			 * lots of stupid things.
			 *
			 * Note that we use task_tgid_vnr here to grab the pid
			 * of the process group leader.  That way we get the
			 * right pid if a thread in a multi-threaded
			 * core_pattern process dies.
			 */
			printk(KERN_WARNING
				"Process %d(%s) has RLIMIT_CORE set to 1\n",
				task_tgid_vnr(current), current->comm);
			printk(KERN_WARNING "Aborting core\n");
			goto fail_unlock;
		}
		cprm.limit = RLIM_INFINITY;

		dump_count = atomic_inc_return(&core_dump_count);
		if (core_pipe_limit && (core_pipe_limit < dump_count)) {
			printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n",
			       task_tgid_vnr(current), current->comm);
			printk(KERN_WARNING "Skipping core dump\n");
			goto fail_dropcount;
		}

632
		helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL);
633
634
635
636
637
638
		if (!helper_argv) {
			printk(KERN_WARNING "%s failed to allocate memory\n",
			       __func__);
			goto fail_dropcount;
		}

639
640
641
642
643
644
645
646
		retval = -ENOMEM;
		sub_info = call_usermodehelper_setup(helper_argv[0],
						helper_argv, NULL, GFP_KERNEL,
						umh_pipe_setup, NULL, &cprm);
		if (sub_info)
			retval = call_usermodehelper_exec(sub_info,
							  UMH_WAIT_EXEC);

647
648
		argv_free(helper_argv);
		if (retval) {
649
			printk(KERN_INFO "Core dump to |%s pipe failed\n",
650
651
			       cn.corename);
			goto close_fail;
652
		}
653
654
	} else {
		struct inode *inode;
655
656
		int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW |
				 O_LARGEFILE | O_EXCL;
657
658
659
660

		if (cprm.limit < binfmt->min_coredump)
			goto fail_unlock;

661
		if (need_suid_safe && cn.corename[0] != '/') {
662
663
664
665
666
667
668
			printk(KERN_WARNING "Pid %d(%s) can only dump core "\
				"to fully qualified path!\n",
				task_tgid_vnr(current), current->comm);
			printk(KERN_WARNING "Skipping core dump\n");
			goto fail_unlock;
		}

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
		/*
		 * Unlink the file if it exists unless this is a SUID
		 * binary - in that case, we're running around with root
		 * privs and don't want to unlink another user's coredump.
		 */
		if (!need_suid_safe) {
			mm_segment_t old_fs;

			old_fs = get_fs();
			set_fs(KERNEL_DS);
			/*
			 * If it doesn't exist, that's fine. If there's some
			 * other problem, we'll catch it at the filp_open().
			 */
			(void) sys_unlink((const char __user *)cn.corename);
			set_fs(old_fs);
		}

		/*
		 * There is a race between unlinking and creating the
		 * file, but if that causes an EEXIST here, that's
		 * fine - another process raced with us while creating
		 * the corefile, and the other process won. To userspace,
		 * what matters is that at least one of the two processes
		 * writes its coredump successfully, not which one.
		 */
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
		if (need_suid_safe) {
			/*
			 * Using user namespaces, normal user tasks can change
			 * their current->fs->root to point to arbitrary
			 * directories. Since the intention of the "only dump
			 * with a fully qualified path" rule is to control where
			 * coredumps may be placed using root privileges,
			 * current->fs->root must not be used. Instead, use the
			 * root directory of init_task.
			 */
			struct path root;

			task_lock(&init_task);
			get_fs_root(init_task.fs, &root);
			task_unlock(&init_task);
			cprm.file = file_open_root(root.dentry, root.mnt,
				cn.corename, open_flags, 0600);
			path_put(&root);
		} else {
			cprm.file = filp_open(cn.corename, open_flags, 0600);
		}
716
717
718
		if (IS_ERR(cprm.file))
			goto fail_unlock;

Al Viro's avatar
Al Viro committed
719
		inode = file_inode(cprm.file);
720
721
722
723
724
725
726
727
728
729
730
		if (inode->i_nlink > 1)
			goto close_fail;
		if (d_unhashed(cprm.file->f_path.dentry))
			goto close_fail;
		/*
		 * AK: actually i see no reason to not allow this for named
		 * pipes etc, but keep the previous behaviour for now.
		 */
		if (!S_ISREG(inode->i_mode))
			goto close_fail;
		/*
731
732
733
734
		 * Don't dump core if the filesystem changed owner or mode
		 * of the file during file creation. This is an issue when
		 * a process dumps core while its cwd is e.g. on a vfat
		 * filesystem.
735
736
737
		 */
		if (!uid_eq(inode->i_uid, current_fsuid()))
			goto close_fail;
738
739
		if ((inode->i_mode & 0677) != 0600)
			goto close_fail;
Al Viro's avatar
Al Viro committed
740
		if (!(cprm.file->f_mode & FMODE_CAN_WRITE))
741
742
743
744
745
746
747
748
749
750
751
			goto close_fail;
		if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
			goto close_fail;
	}

	/* get us an unshared descriptor table; almost always a no-op */
	retval = unshare_files(&displaced);
	if (retval)
		goto close_fail;
	if (displaced)
		put_files_struct(displaced);
752
753
754
755
756
	if (!dump_interrupted()) {
		file_start_write(cprm.file);
		core_dumped = binfmt->core_dump(&cprm);
		file_end_write(cprm.file);
	}
757
758
759
760
761
762
763
764
765
766
	if (ispipe && core_pipe_limit)
		wait_for_dump_helpers(cprm.file);
close_fail:
	if (cprm.file)
		filp_close(cprm.file, NULL);
fail_dropcount:
	if (ispipe)
		atomic_dec(&core_dump_count);
fail_unlock:
	kfree(cn.corename);
767
	coredump_finish(mm, core_dumped);
768
769
770
771
772
773
774
775
776
777
778
779
	revert_creds(old_cred);
fail_creds:
	put_cred(cred);
fail:
	return;
}

/*
 * Core dumping helper functions.  These are the only things you should
 * do on a core-file: use only these functions to write out all the
 * necessary info.
 */
Al Viro's avatar
Al Viro committed
780
781
782
int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
{
	struct file *file = cprm->file;
783
784
	loff_t pos = file->f_pos;
	ssize_t n;
Al Viro's avatar
Al Viro committed
785
786
	if (cprm->written + nr > cprm->limit)
		return 0;
787
788
789
	while (nr) {
		if (dump_interrupted())
			return 0;
790
		n = __kernel_write(file, addr, nr, &pos);
791
792
793
794
795
796
		if (n <= 0)
			return 0;
		file->f_pos = pos;
		cprm->written += n;
		nr -= n;
	}
Al Viro's avatar
Al Viro committed
797
798
799
800
	return 1;
}
EXPORT_SYMBOL(dump_emit);

801
int dump_skip(struct coredump_params *cprm, size_t nr)
802
{
803
804
	static char zeroes[PAGE_SIZE];
	struct file *file = cprm->file;
805
	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
806
807
		if (cprm->written + nr > cprm->limit)
			return 0;
808
		if (dump_interrupted() ||
809
		    file->f_op->llseek(file, nr, SEEK_CUR) < 0)
810
			return 0;
811
812
		cprm->written += nr;
		return 1;
813
	} else {
814
815
816
817
		while (nr > PAGE_SIZE) {
			if (!dump_emit(cprm, zeroes, PAGE_SIZE))
				return 0;
			nr -= PAGE_SIZE;
818
		}
819
		return dump_emit(cprm, zeroes, nr);
820
821
	}
}
822
EXPORT_SYMBOL(dump_skip);
Al Viro's avatar
Al Viro committed
823
824
825
826
827

int dump_align(struct coredump_params *cprm, int align)
{
	unsigned mod = cprm->written & (align - 1);
	if (align & (align - 1))
Al Viro's avatar
Al Viro committed
828
829
		return 0;
	return mod ? dump_skip(cprm, align - mod) : 1;
Al Viro's avatar
Al Viro committed
830
831
}
EXPORT_SYMBOL(dump_align);