summaryrefslogtreecommitdiffstats
path: root/arch/arm64/kernel/machine_kexec.c
blob: a0b144cfaea716c0dda21d3d935147c3e0bcdb48 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * kexec for arm64
 *
 * Copyright (C) Linaro.
 * Copyright (C) Huawei Futurewei Technologies.
 */

#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/kernel.h>
#include <linux/kexec.h>
#include <linux/page-flags.h>
#include <linux/smp.h>

#include <asm/cacheflush.h>
#include <asm/cpu_ops.h>
#include <asm/daifflags.h>
#include <asm/memory.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/page.h>

#include "cpu-reset.h"

/* Global variables for the arm64_relocate_new_kernel routine. */
extern const unsigned char arm64_relocate_new_kernel[];
extern const unsigned long arm64_relocate_new_kernel_size;

/**
 * kexec_image_info - For debugging output.
 */
#define kexec_image_info(_i) _kexec_image_info(__func__, __LINE__, _i)
static void _kexec_image_info(const char *func, int line,
	const struct kimage *kimage)
{
	unsigned long i;

	pr_debug("%s:%d:\n", func, line);
	pr_debug("  kexec kimage info:\n");
	pr_debug("    type:        %d\n", kimage->type);
	pr_debug("    start:       %lx\n", kimage->start);
	pr_debug("    head:        %lx\n", kimage->head);
	pr_debug("    nr_segments: %lu\n", kimage->nr_segments);

	for (i = 0; i < kimage->nr_segments; i++) {
		pr_debug("      segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n",
			i,
			kimage->segment[i].mem,
			kimage->segment[i].mem + kimage->segment[i].memsz,
			kimage->segment[i].memsz,
			kimage->segment[i].memsz /  PAGE_SIZE);
	}
}

void machine_kexec_cleanup(struct kimage *kimage)
{
	/* Empty routine needed to avoid build errors. */
}

/**
 * machine_kexec_prepare - Prepare for a kexec reboot.
 *
 * Called from the core kexec code when a kernel image is loaded.
 * Forbid loading a kexec kernel if we have no way of hotplugging cpus or cpus
 * are stuck in the kernel. This avoids a panic once we hit machine_kexec().
 */
int machine_kexec_prepare(struct kimage *kimage)
{
	kexec_image_info(kimage);

	if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) {
		pr_err("Can't kexec: CPUs are stuck in the kernel.\n");
		return -EBUSY;
	}

	return 0;
}

/**
 * kexec_list_flush - Helper to flush the kimage list and source pages to PoC.
 */
static void kexec_list_flush(struct kimage *kimage)
{
	kimage_entry_t *entry;

	for (entry = &kimage->head; ; entry++) {
		unsigned int flag;
		void *addr;

		/* flush the list entries. */
		__flush_dcache_area(entry, sizeof(kimage_entry_t));

		flag = *entry & IND_FLAGS;
		if (flag == IND_DONE)
			break;

		addr = phys_to_virt(*entry & PAGE_MASK);

		switch (flag) {
		case IND_INDIRECTION:
			/* Set entry point just before the new list page. */
			entry = (kimage_entry_t *)addr - 1;
			break;
		case IND_SOURCE:
			/* flush the source pages. */
			__flush_dcache_area(addr, PAGE_SIZE);
			break;
		case IND_DESTINATION:
			break;
		default:
			BUG();
		}
	}
}

/**
 * kexec_segment_flush - Helper to flush the kimage segments to PoC.
 */
static void kexec_segment_flush(const struct kimage *kimage)
{
	unsigned long i;

	pr_debug("%s:\n", __func__);

	for (i = 0; i < kimage->nr_segments; i++) {
		pr_debug("  segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n",
			i,
			kimage->segment[i].mem,
			kimage->segment[i].mem + kimage->segment[i].memsz,
			kimage->segment[i].memsz,
			kimage->segment[i].memsz /  PAGE_SIZE);

		__flush_dcache_area(phys_to_virt(kimage->segment[i].mem),
			kimage->segment[i].memsz);
	}
}

/**
 * machine_kexec - Do the kexec reboot.
 *
 * Called from the core kexec code for a sys_reboot with LINUX_REBOOT_CMD_KEXEC.
 */
void machine_kexec(struct kimage *kimage)
{
	phys_addr_t reboot_code_buffer_phys;
	void *reboot_code_buffer;
	bool in_kexec_crash = (kimage == kexec_crash_image);
	bool stuck_cpus = cpus_are_stuck_in_kernel();

	/*
	 * New cpus may have become stuck_in_kernel after we loaded the image.
	 */
	BUG_ON(!in_kexec_crash && (stuck_cpus || (num_online_cpus() > 1)));
	WARN(in_kexec_crash && (stuck_cpus || smp_crash_stop_failed()),
		"Some CPUs may be stale, kdump will be unreliable.\n");

	reboot_code_buffer_phys = page_to_phys(kimage->control_code_page);
	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);

	kexec_image_info(kimage);

	/*
	 * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use
	 * after the kernel is shut down.
	 */
	memcpy(reboot_code_buffer, arm64_relocate_new_kernel,
		arm64_relocate_new_kernel_size);

	/* Flush the reboot_code_buffer in preparation for its execution. */
	__flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size);

	/*
	 * Although we've killed off the secondary CPUs, we don't update
	 * the online mask if we're handling a crash kernel and consequently
	 * need to avoid flush_icache_range(), which will attempt to IPI
	 * the offline CPUs. Therefore, we must use the __* variant here.
	 */
	__flush_icache_range((uintptr_t)reboot_code_buffer,
			     (uintptr_t)reboot_code_buffer +
			     arm64_relocate_new_kernel_size);

	/* Flush the kimage list and its buffers. */
	kexec_list_flush(kimage);

	/* Flush the new image if already in place. */
	if ((kimage != kexec_crash_image) && (kimage->head & IND_DONE))
		kexec_segment_flush(kimage);

	pr_info("Bye!\n");

	local_daif_mask();

	/*
	 * cpu_soft_restart will shutdown the MMU, disable data caches, then
	 * transfer control to the reboot_code_buffer which contains a copy of
	 * the arm64_relocate_new_kernel routine.  arm64_relocate_new_kernel
	 * uses physical addressing to relocate the new image to its final
	 * position and transfers control to the image entry point when the
	 * relocation is complete.
	 * In kexec case, kimage->start points to purgatory assuming that
	 * kernel entry and dtb address are embedded in purgatory by
	 * userspace (kexec-tools).
	 * In kexec_file case, the kernel starts directly without purgatory.
	 */
	cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start,
#ifdef CONFIG_KEXEC_FILE
						kimage->arch.dtb_mem);
#else
						0);
#endif

	BUG(); /* Should never get here. */
}

static void machine_kexec_mask_interrupts(void)
{
	unsigned int i;
	struct irq_desc *desc;

	for_each_irq_desc(i, desc) {
		struct irq_chip *chip;
		int ret;

		chip = irq_desc_get_chip(desc);
		if (!chip)
			continue;

		/*
		 * First try to remove the active state. If this
		 * fails, try to EOI the interrupt.
		 */
		ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);

		if (ret && irqd_irq_inprogress(&desc->irq_data) &&
		    chip->irq_eoi)
			chip->irq_eoi(&desc->irq_data);

		if (chip->irq_mask)
			chip->irq_mask(&desc->irq_data);

		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
			chip->irq_disable(&desc->irq_data);
	}
}

/**
 * machine_crash_shutdown - shutdown non-crashing cpus and save registers
 */
void machine_crash_shutdown(struct pt_regs *regs)
{
	local_irq_disable();

	/* shutdown non-crashing cpus */
	crash_smp_send_stop();

	/* for crashing cpu */
	crash_save_cpu(regs, smp_processor_id());
	machine_kexec_mask_interrupts();

	pr_info("Starting crashdump kernel...\n");
}

void arch_kexec_protect_crashkres(void)
{
	int i;

	kexec_segment_flush(kexec_crash_image);

	for (i = 0; i < kexec_crash_image->nr_segments; i++)
		set_memory_valid(
			__phys_to_virt(kexec_crash_image->segment[i].mem),
			kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 0);
}

void arch_kexec_unprotect_crashkres(void)
{
	int i;

	for (i = 0; i < kexec_crash_image->nr_segments; i++)
		set_memory_valid(
			__phys_to_virt(kexec_crash_image->segment[i].mem),
			kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 1);
}

#ifdef CONFIG_HIBERNATION
/*
 * To preserve the crash dump kernel image, the relevant memory segments
 * should be mapped again around the hibernation.
 */
void crash_prepare_suspend(void)
{
	if (kexec_crash_image)
		arch_kexec_unprotect_crashkres();
}

void crash_post_resume(void)
{
	if (kexec_crash_image)
		arch_kexec_protect_crashkres();
}

/*
 * crash_is_nosave
 *
 * Return true only if a page is part of reserved memory for crash dump kernel,
 * but does not hold any data of loaded kernel image.
 *
 * Note that all the pages in crash dump kernel memory have been initially
 * marked as Reserved as memory was allocated via memblock_reserve().
 *
 * In hibernation, the pages which are Reserved and yet "nosave" are excluded
 * from the hibernation iamge. crash_is_nosave() does thich check for crash
 * dump kernel and will reduce the total size of hibernation image.
 */

bool crash_is_nosave(unsigned long pfn)
{
	int i;
	phys_addr_t addr;

	if (!crashk_res.end)
		return false;

	/* in reserved memory? */
	addr = __pfn_to_phys(pfn);
	if ((addr < crashk_res.start) || (crashk_res.end < addr))
		return false;

	if (!kexec_crash_image)
		return true;

	/* not part of loaded kernel image? */
	for (i = 0; i < kexec_crash_image->nr_segments; i++)
		if (addr >= kexec_crash_image->segment[i].mem &&
				addr < (kexec_crash_image->segment[i].mem +
					kexec_crash_image->segment[i].memsz))
			return false;

	return true;
}

void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
{
	unsigned long addr;
	struct page *page;

	for (addr = begin; addr < end; addr += PAGE_SIZE) {
		page = phys_to_page(addr);
		free_reserved_page(page);
	}
}
#endif /* CONFIG_HIBERNATION */