summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/machine_kexec_64.c
blob: 611acdf30096643a1d94bc3111b685e28d290453 (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
/*
 * PPC64 code to handle Linux booting another kernel.
 *
 * Copyright (C) 2004-2005, IBM Corp.
 *
 * Created by: Milton D Miller II
 *
 * This source code is licensed under the GNU General Public License,
 * Version 2.  See the file COPYING for more details.
 */


#include <linux/kexec.h>
#include <linux/smp.h>
#include <linux/thread_info.h>
#include <linux/init_task.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/cpu.h>
#include <linux/hardirq.h>

#include <asm/page.h>
#include <asm/current.h>
#include <asm/machdep.h>
#include <asm/cacheflush.h>
#include <asm/paca.h>
#include <asm/mmu.h>
#include <asm/sections.h>	/* _end */
#include <asm/prom.h>
#include <asm/smp.h>
#include <asm/hw_breakpoint.h>

int default_machine_kexec_prepare(struct kimage *image)
{
	int i;
	unsigned long begin, end;	/* limits of segment */
	unsigned long low, high;	/* limits of blocked memory range */
	struct device_node *node;
	const unsigned long *basep;
	const unsigned int *sizep;

	if (!ppc_md.hpte_clear_all)
		return -ENOENT;

	/*
	 * Since we use the kernel fault handlers and paging code to
	 * handle the virtual mode, we must make sure no destination
	 * overlaps kernel static data or bss.
	 */
	for (i = 0; i < image->nr_segments; i++)
		if (image->segment[i].mem < __pa(_end))
			return -ETXTBSY;

	/*
	 * For non-LPAR, we absolutely can not overwrite the mmu hash
	 * table, since we are still using the bolted entries in it to
	 * do the copy.  Check that here.
	 *
	 * It is safe if the end is below the start of the blocked
	 * region (end <= low), or if the beginning is after the
	 * end of the blocked region (begin >= high).  Use the
	 * boolean identity !(a || b)  === (!a && !b).
	 */
	if (htab_address) {
		low = __pa(htab_address);
		high = low + htab_size_bytes;

		for (i = 0; i < image->nr_segments; i++) {
			begin = image->segment[i].mem;
			end = begin + image->segment[i].memsz;

			if ((begin < high) && (end > low))
				return -ETXTBSY;
		}
	}

	/* We also should not overwrite the tce tables */
	for_each_node_by_type(node, "pci") {
		basep = of_get_property(node, "linux,tce-base", NULL);
		sizep = of_get_property(node, "linux,tce-size", NULL);
		if (basep == NULL || sizep == NULL)
			continue;

		low = *basep;
		high = low + (*sizep);

		for (i = 0; i < image->nr_segments; i++) {
			begin = image->segment[i].mem;
			end = begin + image->segment[i].memsz;

			if ((begin < high) && (end > low))
				return -ETXTBSY;
		}
	}

	return 0;
}

#define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE)

static void copy_segments(unsigned long ind)
{
	unsigned long entry;
	unsigned long *ptr;
	void *dest;
	void *addr;

	/*
	 * We rely on kexec_load to create a lists that properly
	 * initializes these pointers before they are used.
	 * We will still crash if the list is wrong, but at least
	 * the compiler will be quiet.
	 */
	ptr = NULL;
	dest = NULL;

	for (entry = ind; !(entry & IND_DONE); entry = *ptr++) {
		addr = __va(entry & PAGE_MASK);

		switch (entry & IND_FLAGS) {
		case IND_DESTINATION:
			dest = addr;
			break;
		case IND_INDIRECTION:
			ptr = addr;
			break;
		case IND_SOURCE:
			copy_page(dest, addr);
			dest += PAGE_SIZE;
		}
	}
}

void kexec_copy_flush(struct kimage *image)
{
	long i, nr_segments = image->nr_segments;
	struct  kexec_segment ranges[KEXEC_SEGMENT_MAX];

	/* save the ranges on the stack to efficiently flush the icache */
	memcpy(ranges, image->segment, sizeof(ranges));

	/*
	 * After this call we may not use anything allocated in dynamic
	 * memory, including *image.
	 *
	 * Only globals and the stack are allowed.
	 */
	copy_segments(image->head);

	/*
	 * we need to clear the icache for all dest pages sometime,
	 * including ones that were in place on the original copy
	 */
	for (i = 0; i < nr_segments; i++)
		flush_icache_range((unsigned long)__va(ranges[i].mem),
			(unsigned long)__va(ranges[i].mem + ranges[i].memsz));
}

#ifdef CONFIG_SMP

static int kexec_all_irq_disabled = 0;

static void kexec_smp_down(void *arg)
{
	local_irq_disable();
	hard_irq_disable();

	mb(); /* make sure our irqs are disabled before we say they are */
	get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
	while(kexec_all_irq_disabled == 0)
		cpu_relax();
	mb(); /* make sure all irqs are disabled before this */
	hw_breakpoint_disable();
	/*
	 * Now every CPU has IRQs off, we can clear out any pending
	 * IPIs and be sure that no more will come in after this.
	 */
	if (ppc_md.kexec_cpu_down)
		ppc_md.kexec_cpu_down(0, 1);

	kexec_smp_wait();
	/* NOTREACHED */
}

static void kexec_prepare_cpus_wait(int wait_state)
{
	int my_cpu, i, notified=-1;

	hw_breakpoint_disable();
	my_cpu = get_cpu();
	/* Make sure each CPU has at least made it to the state we need.
	 *
	 * FIXME: There is a (slim) chance of a problem if not all of the CPUs
	 * are correctly onlined.  If somehow we start a CPU on boot with RTAS
	 * start-cpu, but somehow that CPU doesn't write callin_cpu_map[] in
	 * time, the boot CPU will timeout.  If it does eventually execute
	 * stuff, the secondary will start up (paca[].cpu_start was written) and
	 * get into a peculiar state.  If the platform supports
	 * smp_ops->take_timebase(), the secondary CPU will probably be spinning
	 * in there.  If not (i.e. pseries), the secondary will continue on and
	 * try to online itself/idle/etc. If it survives that, we need to find
	 * these possible-but-not-online-but-should-be CPUs and chaperone them
	 * into kexec_smp_wait().
	 */
	for_each_online_cpu(i) {
		if (i == my_cpu)
			continue;

		while (paca[i].kexec_state < wait_state) {
			barrier();
			if (i != notified) {
				printk(KERN_INFO "kexec: waiting for cpu %d "
				       "(physical %d) to enter %i state\n",
				       i, paca[i].hw_cpu_id, wait_state);
				notified = i;
			}
		}
	}
	mb();
}

/*
 * We need to make sure each present CPU is online.  The next kernel will scan
 * the device tree and assume primary threads are online and query secondary
 * threads via RTAS to online them if required.  If we don't online primary
 * threads, they will be stuck.  However, we also online secondary threads as we
 * may be using 'cede offline'.  In this case RTAS doesn't see the secondary
 * threads as offline -- and again, these CPUs will be stuck.
 *
 * So, we online all CPUs that should be running, including secondary threads.
 */
static void wake_offline_cpus(void)
{
	int cpu = 0;

	for_each_present_cpu(cpu) {
		if (!cpu_online(cpu)) {
			printk(KERN_INFO "kexec: Waking offline cpu %d.\n",
			       cpu);
			cpu_up(cpu);
		}
	}
}

static void kexec_prepare_cpus(void)
{
	wake_offline_cpus();
	smp_call_function(kexec_smp_down, NULL, /* wait */0);
	local_irq_disable();
	hard_irq_disable();

	mb(); /* make sure IRQs are disabled before we say they are */
	get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;

	kexec_prepare_cpus_wait(KEXEC_STATE_IRQS_OFF);
	/* we are sure every CPU has IRQs off at this point */
	kexec_all_irq_disabled = 1;

	/* after we tell the others to go down */
	if (ppc_md.kexec_cpu_down)
		ppc_md.kexec_cpu_down(0, 0);

	/*
	 * Before removing MMU mappings make sure all CPUs have entered real
	 * mode:
	 */
	kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE);

	put_cpu();
}

#else /* ! SMP */

static void kexec_prepare_cpus(void)
{
	/*
	 * move the secondarys to us so that we can copy
	 * the new kernel 0-0x100 safely
	 *
	 * do this if kexec in setup.c ?
	 *
	 * We need to release the cpus if we are ever going from an
	 * UP to an SMP kernel.
	 */
	smp_release_cpus();
	if (ppc_md.kexec_cpu_down)
		ppc_md.kexec_cpu_down(0, 0);
	local_irq_disable();
	hard_irq_disable();
}

#endif /* SMP */

/*
 * kexec thread structure and stack.
 *
 * We need to make sure that this is 16384-byte aligned due to the
 * way process stacks are handled.  It also must be statically allocated
 * or allocated as part of the kimage, because everything else may be
 * overwritten when we copy the kexec image.  We piggyback on the
 * "init_task" linker section here to statically allocate a stack.
 *
 * We could use a smaller stack if we don't care about anything using
 * current, but that audit has not been performed.
 */
static union thread_union kexec_stack __init_task_data =
	{ };

/*
 * For similar reasons to the stack above, the kexecing CPU needs to be on a
 * static PACA; we switch to kexec_paca.
 */
struct paca_struct kexec_paca;

/* Our assembly helper, in kexec_stub.S */
extern void kexec_sequence(void *newstack, unsigned long start,
			   void *image, void *control,
			   void (*clear_all)(void)) __noreturn;

/* too late to fail here */
void default_machine_kexec(struct kimage *image)
{
	/* prepare control code if any */

	/*
        * If the kexec boot is the normal one, need to shutdown other cpus
        * into our wait loop and quiesce interrupts.
        * Otherwise, in the case of crashed mode (crashing_cpu >= 0),
        * stopping other CPUs and collecting their pt_regs is done before
        * using debugger IPI.
        */

	if (crashing_cpu == -1)
		kexec_prepare_cpus();

	pr_debug("kexec: Starting switchover sequence.\n");

	/* switch to a staticly allocated stack.  Based on irq stack code.
	 * We setup preempt_count to avoid using VMX in memcpy.
	 * XXX: the task struct will likely be invalid once we do the copy!
	 */
	kexec_stack.thread_info.task = current_thread_info()->task;
	kexec_stack.thread_info.flags = 0;
	kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET;
	kexec_stack.thread_info.cpu = current_thread_info()->cpu;

	/* We need a static PACA, too; copy this CPU's PACA over and switch to
	 * it.  Also poison per_cpu_offset to catch anyone using non-static
	 * data.
	 */
	memcpy(&kexec_paca, get_paca(), sizeof(struct paca_struct));
	kexec_paca.data_offset = 0xedeaddeadeeeeeeeUL;
	paca = (struct paca_struct *)RELOC_HIDE(&kexec_paca, 0) -
		kexec_paca.paca_index;
	setup_paca(&kexec_paca);

	/* XXX: If anyone does 'dynamic lppacas' this will also need to be
	 * switched to a static version!
	 */

	/* Some things are best done in assembly.  Finding globals with
	 * a toc is easier in C, so pass in what we can.
	 */
	kexec_sequence(&kexec_stack, image->start, image,
			page_address(image->control_code_page),
			ppc_md.hpte_clear_all);
	/* NOTREACHED */
}

/* Values we need to export to the second kernel via the device tree. */
static unsigned long htab_base;

static struct property htab_base_prop = {
	.name = "linux,htab-base",
	.length = sizeof(unsigned long),
	.value = &htab_base,
};

static struct property htab_size_prop = {
	.name = "linux,htab-size",
	.length = sizeof(unsigned long),
	.value = &htab_size_bytes,
};

static int __init export_htab_values(void)
{
	struct device_node *node;
	struct property *prop;

	/* On machines with no htab htab_address is NULL */
	if (!htab_address)
		return -ENODEV;

	node = of_find_node_by_path("/chosen");
	if (!node)
		return -ENODEV;

	/* remove any stale propertys so ours can be found */
	prop = of_find_property(node, htab_base_prop.name, NULL);
	if (prop)
		of_remove_property(node, prop);
	prop = of_find_property(node, htab_size_prop.name, NULL);
	if (prop)
		of_remove_property(node, prop);

	htab_base = __pa(htab_address);
	of_add_property(node, &htab_base_prop);
	of_add_property(node, &htab_size_prop);

	of_node_put(node);
	return 0;
}
late_initcall(export_htab_values);