aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/kexec.c
blob: bc933c0db9bf019aefa7c5bc7061bc2541fb2a00 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * kexec.c - kexec_load system call
 * Copyright (C) 2002-2004 Eric Biederman  <ebiederm@xmission.com>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/security.h>
#include <linux/kexec.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/syscalls.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>

#include "kexec_internal.h"

static int copy_user_segment_list(struct kimage *image,
				  unsigned long nr_segments,
				  struct kexec_segment __user *segments)
{
	int ret;
	size_t segment_bytes;

	/* Read in the segments */
	image->nr_segments = nr_segments;
	segment_bytes = nr_segments * sizeof(*segments);
	ret = copy_from_user(image->segment, segments, segment_bytes);
	if (ret)
		ret = -EFAULT;

	return ret;
}

static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
			     unsigned long nr_segments,
			     struct kexec_segment __user *segments,
			     unsigned long flags)
{
	int ret;
	struct kimage *image;
	bool kexec_on_panic = flags & KEXEC_ON_CRASH;

	if (kexec_on_panic) {
		/* Verify we have a valid entry point */
		if ((entry < phys_to_boot_phys(crashk_res.start)) ||
		    (entry > phys_to_boot_phys(crashk_res.end)))
			return -EADDRNOTAVAIL;
	}

	/* Allocate and initialize a controlling structure */
	image = do_kimage_alloc_init();
	if (!image)
		return -ENOMEM;

	image->start = entry;

	ret = copy_user_segment_list(image, nr_segments, segments);
	if (ret)
		goto out_free_image;

	if (kexec_on_panic) {
		/* Enable special crash kernel control page alloc policy. */
		image->control_page = crashk_res.start;
		image->type = KEXEC_TYPE_CRASH;
	}

	ret = sanity_check_segment_list(image);
	if (ret)
		goto out_free_image;

	/*
	 * Find a location for the control code buffer, and add it
	 * the vector of segments so that it's pages will also be
	 * counted as destination pages.
	 */
	ret = -ENOMEM;
	image->control_code_page = kimage_alloc_control_pages(image,
					   get_order(KEXEC_CONTROL_PAGE_SIZE));
	if (!image->control_code_page) {
		pr_err("Could not allocate control_code_buffer\n");
		goto out_free_image;
	}

	if (!kexec_on_panic) {
		image->swap_page = kimage_alloc_control_pages(image, 0);
		if (!image->swap_page) {
			pr_err("Could not allocate swap buffer\n");
			goto out_free_control_pages;
		}
	}

	*rimage = image;
	return 0;
out_free_control_pages:
	kimage_free_page_list(&image->control_pages);
out_free_image:
	kfree(image);
	return ret;
}

static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
		struct kexec_segment __user *segments, unsigned long flags)
{
	struct kimage **dest_image, *image;
	unsigned long i;
	int ret;

	if (flags & KEXEC_ON_CRASH) {
		dest_image = &kexec_crash_image;
		if (kexec_crash_image)
			arch_kexec_unprotect_crashkres();
	} else {
		dest_image = &kexec_image;
	}

	if (nr_segments == 0) {
		/* Uninstall image */
		kimage_free(xchg(dest_image, NULL));
		return 0;
	}
	if (flags & KEXEC_ON_CRASH) {
		/*
		 * Loading another kernel to switch to if this one
		 * crashes.  Free any current crash dump kernel before
		 * we corrupt it.
		 */
		kimage_free(xchg(&kexec_crash_image, NULL));
	}

	ret = kimage_alloc_init(&image, entry, nr_segments, segments, flags);
	if (ret)
		return ret;

	if (flags & KEXEC_PRESERVE_CONTEXT)
		image->preserve_context = 1;

	ret = machine_kexec_prepare(image);
	if (ret)
		goto out;

	/*
	 * Some architecture(like S390) may touch the crash memory before
	 * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
	 */
	ret = kimage_crash_copy_vmcoreinfo(image);
	if (ret)
		goto out;

	for (i = 0; i < nr_segments; i++) {
		ret = kimage_load_segment(image, &image->segment[i]);
		if (ret)
			goto out;
	}

	kimage_terminate(image);

	/* Install the new kernel and uninstall the old */
	image = xchg(dest_image, image);

out:
	if ((flags & KEXEC_ON_CRASH) && kexec_crash_image)
		arch_kexec_protect_crashkres();

	kimage_free(image);
	return ret;
}

/*
 * Exec Kernel system call: for obvious reasons only root may call it.
 *
 * This call breaks up into three pieces.
 * - A generic part which loads the new kernel from the current
 *   address space, and very carefully places the data in the
 *   allocated pages.
 *
 * - A generic part that interacts with the kernel and tells all of
 *   the devices to shut down.  Preventing on-going dmas, and placing
 *   the devices in a consistent state so a later kernel can
 *   reinitialize them.
 *
 * - A machine specific part that includes the syscall number
 *   and then copies the image to it's final destination.  And
 *   jumps into the image at entry.
 *
 * kexec does not sync, or unmount filesystems so if you need
 * that to happen you need to do that yourself.
 */

static inline int kexec_load_check(unsigned long nr_segments,
				   unsigned long flags)
{
	int result;

	/* We only trust the superuser with rebooting the system. */
	if (!capable(CAP_SYS_BOOT) || kexec_load_disabled)
		return -EPERM;

	/* Permit LSMs and IMA to fail the kexec */
	result = security_kernel_load_data(LOADING_KEXEC_IMAGE);
	if (result < 0)
		return result;

	/*
	 * kexec can be used to circumvent module loading restrictions, so
	 * prevent loading in that case
	 */
	result = security_locked_down(LOCKDOWN_KEXEC);
	if (result)
		return result;

	/*
	 * Verify we have a legal set of flags
	 * This leaves us room for future extensions.
	 */
	if ((flags & KEXEC_FLAGS) != (flags & ~KEXEC_ARCH_MASK))
		return -EINVAL;

	/* Put an artificial cap on the number
	 * of segments passed to kexec_load.
	 */
	if (nr_segments > KEXEC_SEGMENT_MAX)
		return -EINVAL;

	return 0;
}

SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
		struct kexec_segment __user *, segments, unsigned long, flags)
{
	int result;

	result = kexec_load_check(nr_segments, flags);
	if (result)
		return result;

	/* Verify we are on the appropriate architecture */
	if (((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH) &&
		((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT))
		return -EINVAL;

	/* Because we write directly to the reserved memory
	 * region when loading crash kernels we need a mutex here to
	 * prevent multiple crash  kernels from attempting to load
	 * simultaneously, and to prevent a crash kernel from loading
	 * over the top of a in use crash kernel.
	 *
	 * KISS: always take the mutex.
	 */
	if (!mutex_trylock(&kexec_mutex))
		return -EBUSY;

	result = do_kexec_load(entry, nr_segments, segments, flags);

	mutex_unlock(&kexec_mutex);

	return result;
}

#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry,
		       compat_ulong_t, nr_segments,
		       struct compat_kexec_segment __user *, segments,
		       compat_ulong_t, flags)
{
	struct compat_kexec_segment in;
	struct kexec_segment out, __user *ksegments;
	unsigned long i, result;

	result = kexec_load_check(nr_segments, flags);
	if (result)
		return result;

	/* Don't allow clients that don't understand the native
	 * architecture to do anything.
	 */
	if ((flags & KEXEC_ARCH_MASK) == KEXEC_ARCH_DEFAULT)
		return -EINVAL;

	ksegments = compat_alloc_user_space(nr_segments * sizeof(out));
	for (i = 0; i < nr_segments; i++) {
		result = copy_from_user(&in, &segments[i], sizeof(in));
		if (result)
			return -EFAULT;

		out.buf   = compat_ptr(in.buf);
		out.bufsz = in.bufsz;
		out.mem   = in.mem;
		out.memsz = in.memsz;

		result = copy_to_user(&ksegments[i], &out, sizeof(out));
		if (result)
			return -EFAULT;
	}

	/* Because we write directly to the reserved memory
	 * region when loading crash kernels we need a mutex here to
	 * prevent multiple crash  kernels from attempting to load
	 * simultaneously, and to prevent a crash kernel from loading
	 * over the top of a in use crash kernel.
	 *
	 * KISS: always take the mutex.
	 */
	if (!mutex_trylock(&kexec_mutex))
		return -EBUSY;

	result = do_kexec_load(entry, nr_segments, ksegments, flags);

	mutex_unlock(&kexec_mutex);

	return result;
}
#endif