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
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
|
/*
* Architecture specific (i386/x86_64) functions for kexec based crash dumps.
*
* Created by: Hariprasad Nellitheertha (hari@in.ibm.com)
*
* Copyright (C) IBM Corporation, 2004. All rights reserved.
* Copyright (C) Red Hat Inc., 2014. All rights reserved.
* Authors:
* Vivek Goyal <vgoyal@redhat.com>
*
*/
#define pr_fmt(fmt) "kexec: " fmt
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/smp.h>
#include <linux/reboot.h>
#include <linux/kexec.h>
#include <linux/delay.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <asm/processor.h>
#include <asm/hardirq.h>
#include <asm/nmi.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/e820/types.h>
#include <asm/io_apic.h>
#include <asm/hpet.h>
#include <linux/kdebug.h>
#include <asm/cpu.h>
#include <asm/reboot.h>
#include <asm/virtext.h>
#include <asm/intel_pt.h>
/* Alignment required for elf header segment */
#define ELF_CORE_HEADER_ALIGN 4096
/* This primarily represents number of split ranges due to exclusion */
#define CRASH_MAX_RANGES 16
struct crash_mem_range {
u64 start, end;
};
struct crash_mem {
unsigned int nr_ranges;
struct crash_mem_range ranges[CRASH_MAX_RANGES];
};
/* Misc data about ram ranges needed to prepare elf headers */
struct crash_elf_data {
struct kimage *image;
/*
* Total number of ram ranges we have after various adjustments for
* crash reserved region, etc.
*/
unsigned int max_nr_ranges;
/* Pointer to elf header */
void *ehdr;
/* Pointer to next phdr */
void *bufp;
struct crash_mem mem;
};
/* Used while preparing memory map entries for second kernel */
struct crash_memmap_data {
struct boot_params *params;
/* Type of memory */
unsigned int type;
};
/*
* This is used to VMCLEAR all VMCSs loaded on the
* processor. And when loading kvm_intel module, the
* callback function pointer will be assigned.
*
* protected by rcu.
*/
crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL;
EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss);
unsigned long crash_zero_bytes;
static inline void cpu_crash_vmclear_loaded_vmcss(void)
{
crash_vmclear_fn *do_vmclear_operation = NULL;
rcu_read_lock();
do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss);
if (do_vmclear_operation)
do_vmclear_operation();
rcu_read_unlock();
}
#if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
{
#ifdef CONFIG_X86_32
struct pt_regs fixed_regs;
if (!user_mode(regs)) {
crash_fixup_ss_esp(&fixed_regs, regs);
regs = &fixed_regs;
}
#endif
crash_save_cpu(regs, cpu);
/*
* VMCLEAR VMCSs loaded on all cpus if needed.
*/
cpu_crash_vmclear_loaded_vmcss();
/* Disable VMX or SVM if needed.
*
* We need to disable virtualization on all CPUs.
* Having VMX or SVM enabled on any CPU may break rebooting
* after the kdump kernel has finished its task.
*/
cpu_emergency_vmxoff();
cpu_emergency_svm_disable();
/*
* Disable Intel PT to stop its logging
*/
cpu_emergency_stop_pt();
disable_local_APIC();
}
void kdump_nmi_shootdown_cpus(void)
{
nmi_shootdown_cpus(kdump_nmi_callback);
disable_local_APIC();
}
/* Override the weak function in kernel/panic.c */
void crash_smp_send_stop(void)
{
static int cpus_stopped;
if (cpus_stopped)
return;
if (smp_ops.crash_stop_other_cpus)
smp_ops.crash_stop_other_cpus();
else
smp_send_stop();
cpus_stopped = 1;
}
#else
void crash_smp_send_stop(void)
{
/* There are no cpus to shootdown */
}
#endif
void native_machine_crash_shutdown(struct pt_regs *regs)
{
/* This function is only called after the system
* has panicked or is otherwise in a critical state.
* The minimum amount of code to allow a kexec'd kernel
* to run successfully needs to happen here.
*
* In practice this means shooting down the other cpus in
* an SMP system.
*/
/* The kernel is broken so disable interrupts */
local_irq_disable();
crash_smp_send_stop();
/*
* VMCLEAR VMCSs loaded on this cpu if needed.
*/
cpu_crash_vmclear_loaded_vmcss();
/* Booting kdump kernel with VMX or SVM enabled won't work,
* because (among other limitations) we can't disable paging
* with the virt flags.
*/
cpu_emergency_vmxoff();
cpu_emergency_svm_disable();
/*
* Disable Intel PT to stop its logging
*/
cpu_emergency_stop_pt();
#ifdef CONFIG_X86_IO_APIC
/* Prevent crash_kexec() from deadlocking on ioapic_lock. */
ioapic_zap_locks();
clear_IO_APIC();
#endif
lapic_shutdown();
restore_boot_irq_mode();
#ifdef CONFIG_HPET_TIMER
hpet_disable();
#endif
crash_save_cpu(regs, safe_smp_processor_id());
}
#ifdef CONFIG_KEXEC_FILE
static int get_nr_ram_ranges_callback(struct resource *res, void *arg)
{
unsigned int *nr_ranges = arg;
(*nr_ranges)++;
return 0;
}
/* Gather all the required information to prepare elf headers for ram regions */
static void fill_up_crash_elf_data(struct crash_elf_data *ced,
struct kimage *image)
{
unsigned int nr_ranges = 0;
ced->image = image;
walk_system_ram_res(0, -1, &nr_ranges,
get_nr_ram_ranges_callback);
ced->max_nr_ranges = nr_ranges;
/* Exclusion of crash region could split memory ranges */
ced->max_nr_ranges++;
/* If crashk_low_res is not 0, another range split possible */
if (crashk_low_res.end)
ced->max_nr_ranges++;
}
static int exclude_mem_range(struct crash_mem *mem,
unsigned long long mstart, unsigned long long mend)
{
int i, j;
unsigned long long start, end;
struct crash_mem_range temp_range = {0, 0};
for (i = 0; i < mem->nr_ranges; i++) {
start = mem->ranges[i].start;
end = mem->ranges[i].end;
if (mstart > end || mend < start)
continue;
/* Truncate any area outside of range */
if (mstart < start)
mstart = start;
if (mend > end)
mend = end;
/* Found completely overlapping range */
if (mstart == start && mend == end) {
mem->ranges[i].start = 0;
mem->ranges[i].end = 0;
if (i < mem->nr_ranges - 1) {
/* Shift rest of the ranges to left */
for (j = i; j < mem->nr_ranges - 1; j++) {
mem->ranges[j].start =
mem->ranges[j+1].start;
mem->ranges[j].end =
mem->ranges[j+1].end;
}
}
mem->nr_ranges--;
return 0;
}
if (mstart > start && mend < end) {
/* Split original range */
mem->ranges[i].end = mstart - 1;
temp_range.start = mend + 1;
temp_range.end = end;
} else if (mstart != start)
mem->ranges[i].end = mstart - 1;
else
mem->ranges[i].start = mend + 1;
break;
}
/* If a split happend, add the split to array */
if (!temp_range.end)
return 0;
/* Split happened */
if (i == CRASH_MAX_RANGES - 1) {
pr_err("Too many crash ranges after split\n");
return -ENOMEM;
}
/* Location where new range should go */
j = i + 1;
if (j < mem->nr_ranges) {
/* Move over all ranges one slot towards the end */
for (i = mem->nr_ranges - 1; i >= j; i--)
mem->ranges[i + 1] = mem->ranges[i];
}
mem->ranges[j].start = temp_range.start;
mem->ranges[j].end = temp_range.end;
mem->nr_ranges++;
return 0;
}
/*
* Look for any unwanted ranges between mstart, mend and remove them. This
* might lead to split and split ranges are put in ced->mem.ranges[] array
*/
static int elf_header_exclude_ranges(struct crash_elf_data *ced)
{
struct crash_mem *cmem = &ced->mem;
int ret = 0;
/* Exclude crashkernel region */
ret = exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
if (ret)
return ret;
if (crashk_low_res.end) {
ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
if (ret)
return ret;
}
return ret;
}
static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg)
{
struct crash_elf_data *ced = arg;
struct crash_mem *cmem = &ced->mem;
cmem->ranges[cmem->nr_ranges].start = res->start;
cmem->ranges[cmem->nr_ranges].end = res->end;
cmem->nr_ranges++;
return 0;
}
static int prepare_elf64_headers(struct crash_elf_data *ced, bool kernel_map,
void **addr, unsigned long *sz)
{
Elf64_Ehdr *ehdr;
Elf64_Phdr *phdr;
unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
unsigned char *buf, *bufp;
unsigned int cpu, i;
unsigned long long notes_addr;
struct crash_mem *cmem = &ced->mem;
unsigned long mstart, mend;
/* extra phdr for vmcoreinfo elf note */
nr_phdr = nr_cpus + 1;
nr_phdr += ced->max_nr_ranges;
/*
* kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
* area on x86_64 (ffffffff80000000 - ffffffffa0000000).
* I think this is required by tools like gdb. So same physical
* memory will be mapped in two elf headers. One will contain kernel
* text virtual addresses and other will have __va(physical) addresses.
*/
nr_phdr++;
elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);
buf = vzalloc(elf_sz);
if (!buf)
return -ENOMEM;
bufp = buf;
ehdr = (Elf64_Ehdr *)bufp;
bufp += sizeof(Elf64_Ehdr);
memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
ehdr->e_ident[EI_CLASS] = ELFCLASS64;
ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
ehdr->e_ident[EI_VERSION] = EV_CURRENT;
ehdr->e_ident[EI_OSABI] = ELF_OSABI;
memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
ehdr->e_type = ET_CORE;
ehdr->e_machine = ELF_ARCH;
ehdr->e_version = EV_CURRENT;
ehdr->e_phoff = sizeof(Elf64_Ehdr);
ehdr->e_ehsize = sizeof(Elf64_Ehdr);
ehdr->e_phentsize = sizeof(Elf64_Phdr);
/* Prepare one phdr of type PT_NOTE for each present cpu */
for_each_present_cpu(cpu) {
phdr = (Elf64_Phdr *)bufp;
bufp += sizeof(Elf64_Phdr);
phdr->p_type = PT_NOTE;
notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
phdr->p_offset = phdr->p_paddr = notes_addr;
phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
(ehdr->e_phnum)++;
}
/* Prepare one PT_NOTE header for vmcoreinfo */
phdr = (Elf64_Phdr *)bufp;
bufp += sizeof(Elf64_Phdr);
phdr->p_type = PT_NOTE;
phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
(ehdr->e_phnum)++;
/* Prepare PT_LOAD type program header for kernel text region */
if (kernel_map) {
phdr = (Elf64_Phdr *)bufp;
bufp += sizeof(Elf64_Phdr);
phdr->p_type = PT_LOAD;
phdr->p_flags = PF_R|PF_W|PF_X;
phdr->p_vaddr = (Elf64_Addr)_text;
phdr->p_filesz = phdr->p_memsz = _end - _text;
phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
(ehdr->e_phnum)++;
}
/* Go through all the ranges in cmem->ranges[] and prepare phdr */
for (i = 0; i < cmem->nr_ranges; i++) {
mstart = cmem->ranges[i].start;
mend = cmem->ranges[i].end;
phdr->p_type = PT_LOAD;
phdr->p_flags = PF_R|PF_W|PF_X;
phdr->p_offset = mstart;
phdr->p_paddr = mstart;
phdr->p_vaddr = (unsigned long long) __va(mstart);
phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
phdr->p_align = 0;
ehdr->e_phnum++;
phdr++;
pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
ehdr->e_phnum, phdr->p_offset);
}
*addr = buf;
*sz = elf_sz;
return 0;
}
/* Prepare elf headers. Return addr and size */
static int prepare_elf_headers(struct kimage *image, void **addr,
unsigned long *sz)
{
struct crash_elf_data *ced;
Elf64_Ehdr *ehdr;
Elf64_Phdr *phdr;
int ret, i;
ced = kzalloc(sizeof(*ced), GFP_KERNEL);
if (!ced)
return -ENOMEM;
fill_up_crash_elf_data(ced, image);
ret = walk_system_ram_res(0, -1, ced,
prepare_elf64_ram_headers_callback);
if (ret)
goto out;
/* Exclude unwanted mem ranges */
ret = elf_header_exclude_ranges(ced);
if (ret)
goto out;
/* By default prepare 64bit headers */
ret = prepare_elf64_headers(ced, IS_ENABLED(CONFIG_X86_64), addr, sz);
if (ret)
goto out;
/*
* If a range matches backup region, adjust offset to backup
* segment.
*/
ehdr = (Elf64_Ehdr *)*addr;
phdr = (Elf64_Phdr *)(ehdr + 1);
for (i = 0; i < ehdr->e_phnum; phdr++, i++)
if (phdr->p_type == PT_LOAD &&
phdr->p_paddr == image->arch.backup_src_start &&
phdr->p_memsz == image->arch.backup_src_sz) {
phdr->p_offset = image->arch.backup_load_addr;
break;
}
out:
kfree(ced);
return ret;
}
static int add_e820_entry(struct boot_params *params, struct e820_entry *entry)
{
unsigned int nr_e820_entries;
nr_e820_entries = params->e820_entries;
if (nr_e820_entries >= E820_MAX_ENTRIES_ZEROPAGE)
return 1;
memcpy(¶ms->e820_table[nr_e820_entries], entry,
sizeof(struct e820_entry));
params->e820_entries++;
return 0;
}
static int memmap_entry_callback(struct resource *res, void *arg)
{
struct crash_memmap_data *cmd = arg;
struct boot_params *params = cmd->params;
struct e820_entry ei;
ei.addr = res->start;
ei.size = resource_size(res);
ei.type = cmd->type;
add_e820_entry(params, &ei);
return 0;
}
static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem,
unsigned long long mstart,
unsigned long long mend)
{
unsigned long start, end;
int ret = 0;
cmem->ranges[0].start = mstart;
cmem->ranges[0].end = mend;
cmem->nr_ranges = 1;
/* Exclude Backup region */
start = image->arch.backup_load_addr;
end = start + image->arch.backup_src_sz - 1;
ret = exclude_mem_range(cmem, start, end);
if (ret)
return ret;
/* Exclude elf header region */
start = image->arch.elf_load_addr;
end = start + image->arch.elf_headers_sz - 1;
return exclude_mem_range(cmem, start, end);
}
/* Prepare memory map for crash dump kernel */
int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
{
int i, ret = 0;
unsigned long flags;
struct e820_entry ei;
struct crash_memmap_data cmd;
struct crash_mem *cmem;
cmem = vzalloc(sizeof(struct crash_mem));
if (!cmem)
return -ENOMEM;
memset(&cmd, 0, sizeof(struct crash_memmap_data));
cmd.params = params;
/* Add first 640K segment */
ei.addr = image->arch.backup_src_start;
ei.size = image->arch.backup_src_sz;
ei.type = E820_TYPE_RAM;
add_e820_entry(params, &ei);
/* Add ACPI tables */
cmd.type = E820_TYPE_ACPI;
flags = IORESOURCE_MEM | IORESOURCE_BUSY;
walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd,
memmap_entry_callback);
/* Add ACPI Non-volatile Storage */
cmd.type = E820_TYPE_NVS;
walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd,
memmap_entry_callback);
/* Add crashk_low_res region */
if (crashk_low_res.end) {
ei.addr = crashk_low_res.start;
ei.size = crashk_low_res.end - crashk_low_res.start + 1;
ei.type = E820_TYPE_RAM;
add_e820_entry(params, &ei);
}
/* Exclude some ranges from crashk_res and add rest to memmap */
ret = memmap_exclude_ranges(image, cmem, crashk_res.start,
crashk_res.end);
if (ret)
goto out;
for (i = 0; i < cmem->nr_ranges; i++) {
ei.size = cmem->ranges[i].end - cmem->ranges[i].start + 1;
/* If entry is less than a page, skip it */
if (ei.size < PAGE_SIZE)
continue;
ei.addr = cmem->ranges[i].start;
ei.type = E820_TYPE_RAM;
add_e820_entry(params, &ei);
}
out:
vfree(cmem);
return ret;
}
static int determine_backup_region(struct resource *res, void *arg)
{
struct kimage *image = arg;
image->arch.backup_src_start = res->start;
image->arch.backup_src_sz = resource_size(res);
/* Expecting only one range for backup region */
return 1;
}
int crash_load_segments(struct kimage *image)
{
int ret;
struct kexec_buf kbuf = { .image = image, .buf_min = 0,
.buf_max = ULONG_MAX, .top_down = false };
/*
* Determine and load a segment for backup area. First 640K RAM
* region is backup source
*/
ret = walk_system_ram_res(KEXEC_BACKUP_SRC_START, KEXEC_BACKUP_SRC_END,
image, determine_backup_region);
/* Zero or postive return values are ok */
if (ret < 0)
return ret;
/* Add backup segment. */
if (image->arch.backup_src_sz) {
kbuf.buffer = &crash_zero_bytes;
kbuf.bufsz = sizeof(crash_zero_bytes);
kbuf.memsz = image->arch.backup_src_sz;
kbuf.buf_align = PAGE_SIZE;
/*
* Ideally there is no source for backup segment. This is
* copied in purgatory after crash. Just add a zero filled
* segment for now to make sure checksum logic works fine.
*/
ret = kexec_add_buffer(&kbuf);
if (ret)
return ret;
image->arch.backup_load_addr = kbuf.mem;
pr_debug("Loaded backup region at 0x%lx backup_start=0x%lx memsz=0x%lx\n",
image->arch.backup_load_addr,
image->arch.backup_src_start, kbuf.memsz);
}
/* Prepare elf headers and add a segment */
ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz);
if (ret)
return ret;
image->arch.elf_headers = kbuf.buffer;
image->arch.elf_headers_sz = kbuf.bufsz;
kbuf.memsz = kbuf.bufsz;
kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
ret = kexec_add_buffer(&kbuf);
if (ret) {
vfree((void *)image->arch.elf_headers);
return ret;
}
image->arch.elf_load_addr = kbuf.mem;
pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
image->arch.elf_load_addr, kbuf.bufsz, kbuf.bufsz);
return ret;
}
#endif /* CONFIG_KEXEC_FILE */
|