1================================================================
2Documentation for Kdump - The kexec-based Crash Dumping Solution
3================================================================
4
5This document includes overview, setup, installation, and analysis
6information.
7
8Overview
9========
10
11Kdump uses kexec to quickly boot to a dump-capture kernel whenever a
12dump of the system kernel's memory needs to be taken (for example, when
13the system panics). The system kernel's memory image is preserved across
14the reboot and is accessible to the dump-capture kernel.
15
16You can use common commands, such as cp, scp or makedumpfile to copy
17the memory image to a dump file on the local disk, or across the network
18to a remote system.
19
20Kdump and kexec are currently supported on the x86, x86_64, ppc64,
21s390x, arm and arm64 architectures.
22
23When the system kernel boots, it reserves a small section of memory for
24the dump-capture kernel. This ensures that ongoing Direct Memory Access
25(DMA) from the system kernel does not corrupt the dump-capture kernel.
26The kexec -p command loads the dump-capture kernel into this reserved
27memory.
28
29On x86 machines, the first 640 KB of physical memory is needed for boot,
30regardless of where the kernel loads. For simpler handling, the whole
31low 1M is reserved to avoid any later kernel or device driver writing
32data into this area. Like this, the low 1M can be reused as system RAM
33by kdump kernel without extra handling.
34
35On PPC64 machines first 32KB of physical memory is needed for booting
36regardless of where the kernel is loaded and to support 64K page size
37kexec backs up the first 64KB memory.
38
39For s390x, when kdump is triggered, the crashkernel region is exchanged
40with the region [0, crashkernel region size] and then the kdump kernel
41runs in [0, crashkernel region size]. Therefore no relocatable kernel is
42needed for s390x.
43
44All of the necessary information about the system kernel's core image is
45encoded in the ELF format, and stored in a reserved area of memory
46before a crash. The physical address of the start of the ELF header is
47passed to the dump-capture kernel through the elfcorehdr= boot
48parameter. Optionally the size of the ELF header can also be passed
49when using the elfcorehdr=[size[KMG]@]offset[KMG] syntax.
50
51With the dump-capture kernel, you can access the memory image through
52/proc/vmcore. This exports the dump as an ELF-format file that you can
53write out using file copy commands such as cp or scp. You can also use
54makedumpfile utility to analyze and write out filtered contents with
55options, e.g with '-d 31' it will only write out kernel data. Further,
56you can use analysis tools such as the GNU Debugger (GDB) and the Crash
57tool to debug the dump file. This method ensures that the dump pages are
58correctly ordered.
59
60Setup and Installation
61======================
62
63Install kexec-tools
64-------------------
65
661) Login as the root user.
67
682) Download the kexec-tools user-space package from the following URL:
69
70http://kernel.org/pub/linux/utils/kernel/kexec/kexec-tools.tar.gz
71
72This is a symlink to the latest version.
73
74The latest kexec-tools git tree is available at:
75
76- git://git.kernel.org/pub/scm/utils/kernel/kexec/kexec-tools.git
77- http://www.kernel.org/pub/scm/utils/kernel/kexec/kexec-tools.git
78
79There is also a gitweb interface available at
80http://www.kernel.org/git/?p=utils/kernel/kexec/kexec-tools.git
81
82More information about kexec-tools can be found at
83http://horms.net/projects/kexec/
84
853) Unpack the tarball with the tar command, as follows::
86
87	tar xvpzf kexec-tools.tar.gz
88
894) Change to the kexec-tools directory, as follows::
90
91	cd kexec-tools-VERSION
92
935) Configure the package, as follows::
94
95	./configure
96
976) Compile the package, as follows::
98
99	make
100
1017) Install the package, as follows::
102
103	make install
104
105
106Build the system and dump-capture kernels
107-----------------------------------------
108There are two possible methods of using Kdump.
109
1101) Build a separate custom dump-capture kernel for capturing the
111   kernel core dump.
112
1132) Or use the system kernel binary itself as dump-capture kernel and there is
114   no need to build a separate dump-capture kernel. This is possible
115   only with the architectures which support a relocatable kernel. As
116   of today, i386, x86_64, ppc64, arm and arm64 architectures support
117   relocatable kernel.
118
119Building a relocatable kernel is advantageous from the point of view that
120one does not have to build a second kernel for capturing the dump. But
121at the same time one might want to build a custom dump capture kernel
122suitable to his needs.
123
124Following are the configuration setting required for system and
125dump-capture kernels for enabling kdump support.
126
127System kernel config options
128----------------------------
129
1301) Enable "kexec system call" or "kexec file based system call" in
131   "Processor type and features."::
132
133	CONFIG_KEXEC=y or CONFIG_KEXEC_FILE=y
134
135   And both of them will select KEXEC_CORE::
136
137	CONFIG_KEXEC_CORE=y
138
1392) Enable "sysfs file system support" in "Filesystem" -> "Pseudo
140   filesystems." This is usually enabled by default::
141
142	CONFIG_SYSFS=y
143
144   Note that "sysfs file system support" might not appear in the "Pseudo
145   filesystems" menu if "Configure standard kernel features (expert users)"
146   is not enabled in "General Setup." In this case, check the .config file
147   itself to ensure that sysfs is turned on, as follows::
148
149	grep 'CONFIG_SYSFS' .config
150
1513) Enable "Compile the kernel with debug info" in "Kernel hacking."::
152
153	CONFIG_DEBUG_INFO=Y
154
155   This causes the kernel to be built with debug symbols. The dump
156   analysis tools require a vmlinux with debug symbols in order to read
157   and analyze a dump file.
158
159Dump-capture kernel config options (Arch Independent)
160-----------------------------------------------------
161
1621) Enable "kernel crash dumps" support under "Processor type and
163   features"::
164
165	CONFIG_CRASH_DUMP=y
166
167   And this will select VMCORE_INFO and CRASH_RESERVE::
168	CONFIG_VMCORE_INFO=y
169	CONFIG_CRASH_RESERVE=y
170
1712) Enable "/proc/vmcore support" under "Filesystems" -> "Pseudo filesystems"::
172
173	CONFIG_PROC_VMCORE=y
174
175   (CONFIG_PROC_VMCORE is set by default when CONFIG_CRASH_DUMP is selected.)
176
177Dump-capture kernel config options (Arch Dependent, i386 and x86_64)
178--------------------------------------------------------------------
179
1801) On i386, enable high memory support under "Processor type and
181   features"::
182
183	CONFIG_HIGHMEM4G
184
1852) With CONFIG_SMP=y, usually nr_cpus=1 need specified on the kernel
186   command line when loading the dump-capture kernel because one
187   CPU is enough for kdump kernel to dump vmcore on most of systems.
188
189   However, you can also specify nr_cpus=X to enable multiple processors
190   in kdump kernel.
191
192   With CONFIG_SMP=n, the above things are not related.
193
1943) A relocatable kernel is suggested to be built by default. If not yet,
195   enable "Build a relocatable kernel" support under "Processor type and
196   features"::
197
198	CONFIG_RELOCATABLE=y
199
2004) Use a suitable value for "Physical address where the kernel is
201   loaded" (under "Processor type and features"). This only appears when
202   "kernel crash dumps" is enabled. A suitable value depends upon
203   whether kernel is relocatable or not.
204
205   If you are using a relocatable kernel use CONFIG_PHYSICAL_START=0x100000
206   This will compile the kernel for physical address 1MB, but given the fact
207   kernel is relocatable, it can be run from any physical address hence
208   kexec boot loader will load it in memory region reserved for dump-capture
209   kernel.
210
211   Otherwise it should be the start of memory region reserved for
212   second kernel using boot parameter "crashkernel=Y@X". Here X is
213   start of memory region reserved for dump-capture kernel.
214   Generally X is 16MB (0x1000000). So you can set
215   CONFIG_PHYSICAL_START=0x1000000
216
2175) Make and install the kernel and its modules. DO NOT add this kernel
218   to the boot loader configuration files.
219
220Dump-capture kernel config options (Arch Dependent, ppc64)
221----------------------------------------------------------
222
2231) Enable "Build a kdump crash kernel" support under "Kernel" options::
224
225	CONFIG_CRASH_DUMP=y
226
2272)   Enable "Build a relocatable kernel" support::
228
229	CONFIG_RELOCATABLE=y
230
231   Make and install the kernel and its modules.
232
233Dump-capture kernel config options (Arch Dependent, arm)
234----------------------------------------------------------
235
236-   To use a relocatable kernel,
237    Enable "AUTO_ZRELADDR" support under "Boot" options::
238
239	AUTO_ZRELADDR=y
240
241Dump-capture kernel config options (Arch Dependent, arm64)
242----------------------------------------------------------
243
244- Please note that kvm of the dump-capture kernel will not be enabled
245  on non-VHE systems even if it is configured. This is because the CPU
246  will not be reset to EL2 on panic.
247
248crashkernel syntax
249===========================
2501) crashkernel=size@offset
251
252   Here 'size' specifies how much memory to reserve for the dump-capture kernel
253   and 'offset' specifies the beginning of this reserved memory. For example,
254   "crashkernel=64M@16M" tells the system kernel to reserve 64 MB of memory
255   starting at physical address 0x01000000 (16MB) for the dump-capture kernel.
256
257   The crashkernel region can be automatically placed by the system
258   kernel at run time. This is done by specifying the base address as 0,
259   or omitting it all together::
260
261         crashkernel=256M@0
262
263   or::
264
265         crashkernel=256M
266
267   If the start address is specified, note that the start address of the
268   kernel will be aligned to a value (which is Arch dependent), so if the
269   start address is not then any space below the alignment point will be
270   wasted.
271
2722) range1:size1[,range2:size2,...][@offset]
273
274   While the "crashkernel=size[@offset]" syntax is sufficient for most
275   configurations, sometimes it's handy to have the reserved memory dependent
276   on the value of System RAM -- that's mostly for distributors that pre-setup
277   the kernel command line to avoid a unbootable system after some memory has
278   been removed from the machine.
279
280   The syntax is::
281
282       crashkernel=<range1>:<size1>[,<range2>:<size2>,...][@offset]
283       range=start-[end]
284
285   For example::
286
287       crashkernel=512M-2G:64M,2G-:128M
288
289   This would mean:
290
291       1) if the RAM is smaller than 512M, then don't reserve anything
292          (this is the "rescue" case)
293       2) if the RAM size is between 512M and 2G (exclusive), then reserve 64M
294       3) if the RAM size is larger than 2G, then reserve 128M
295
2963) crashkernel=size,high and crashkernel=size,low
297
298   If memory above 4G is preferred, crashkernel=size,high can be used to
299   fulfill that. With it, physical memory is allowed to be allocated from top,
300   so could be above 4G if system has more than 4G RAM installed. Otherwise,
301   memory region will be allocated below 4G if available.
302
303   When crashkernel=X,high is passed, kernel could allocate physical memory
304   region above 4G, low memory under 4G is needed in this case. There are
305   three ways to get low memory:
306
307      1) Kernel will allocate at least 256M memory below 4G automatically
308         if crashkernel=Y,low is not specified.
309      2) Let user specify low memory size instead.
310      3) Specified value 0 will disable low memory allocation::
311
312            crashkernel=0,low
313
3144) crashkernel=size,cma
315
316	Reserve additional crash kernel memory from CMA. This reservation is
317	usable by the first system's userspace memory and kernel movable
318	allocations (memory balloon, zswap). Pages allocated from this memory
319	range will not be included in the vmcore so this should not be used if
320	dumping of userspace memory is intended and it has to be expected that
321	some movable kernel pages may be missing from the dump.
322
323	A standard crashkernel reservation, as described above, is still needed
324	to hold the crash kernel and initrd.
325
326	This option increases the risk of a kdump failure: DMA transfers
327	configured by the first kernel may end up corrupting the second
328	kernel's memory.
329
330	This reservation method is intended for systems that can't afford to
331	sacrifice enough memory for standard crashkernel reservation and where
332	less reliable and possibly incomplete kdump is preferable to no kdump at
333	all.
334
335Boot into System Kernel
336-----------------------
3371) Update the boot loader (such as grub, yaboot, or lilo) configuration
338   files as necessary.
339
3402) Boot the system kernel with the boot parameter "crashkernel=Y@X".
341
342   On x86 and x86_64, use "crashkernel=Y[@X]". Most of the time, the
343   start address 'X' is not necessary, kernel will search a suitable
344   area. Unless an explicit start address is expected.
345
346   On ppc64, use "crashkernel=128M@32M".
347
348   On s390x, typically use "crashkernel=xxM". The value of xx is dependent
349   on the memory consumption of the kdump system. In general this is not
350   dependent on the memory size of the production system.
351
352   On arm, the use of "crashkernel=Y@X" is no longer necessary; the
353   kernel will automatically locate the crash kernel image within the
354   first 512MB of RAM if X is not given.
355
356   On arm64, use "crashkernel=Y[@X]".  Note that the start address of
357   the kernel, X if explicitly specified, must be aligned to 2MiB (0x200000).
358
359Load the Dump-capture Kernel
360============================
361
362After booting to the system kernel, dump-capture kernel needs to be
363loaded.
364
365Based on the architecture and type of image (relocatable or not), one
366can choose to load the uncompressed vmlinux or compressed bzImage/vmlinuz
367of dump-capture kernel. Following is the summary.
368
369For i386 and x86_64:
370
371	- Use bzImage/vmlinuz if kernel is relocatable.
372	- Use vmlinux if kernel is not relocatable.
373
374For ppc64:
375
376	- Use vmlinux
377
378For s390x:
379
380	- Use image or bzImage
381
382For arm:
383
384	- Use zImage
385
386For arm64:
387
388	- Use vmlinux or Image
389
390If you are using an uncompressed vmlinux image then use following command
391to load dump-capture kernel::
392
393   kexec -p <dump-capture-kernel-vmlinux-image> \
394   --initrd=<initrd-for-dump-capture-kernel> --args-linux \
395   --append="root=<root-dev> <arch-specific-options>"
396
397If you are using a compressed bzImage/vmlinuz, then use following command
398to load dump-capture kernel::
399
400   kexec -p <dump-capture-kernel-bzImage> \
401   --initrd=<initrd-for-dump-capture-kernel> \
402   --append="root=<root-dev> <arch-specific-options>"
403
404If you are using a compressed zImage, then use following command
405to load dump-capture kernel::
406
407   kexec --type zImage -p <dump-capture-kernel-bzImage> \
408   --initrd=<initrd-for-dump-capture-kernel> \
409   --dtb=<dtb-for-dump-capture-kernel> \
410   --append="root=<root-dev> <arch-specific-options>"
411
412If you are using an uncompressed Image, then use following command
413to load dump-capture kernel::
414
415   kexec -p <dump-capture-kernel-Image> \
416   --initrd=<initrd-for-dump-capture-kernel> \
417   --append="root=<root-dev> <arch-specific-options>"
418
419Following are the arch specific command line options to be used while
420loading dump-capture kernel.
421
422For i386 and x86_64:
423
424	"1 irqpoll nr_cpus=1 reset_devices"
425
426For ppc64:
427
428	"1 maxcpus=1 noirqdistrib reset_devices"
429
430For s390x:
431
432	"1 nr_cpus=1 cgroup_disable=memory"
433
434For arm:
435
436	"1 maxcpus=1 reset_devices"
437
438For arm64:
439
440	"1 nr_cpus=1 reset_devices"
441
442Notes on loading the dump-capture kernel:
443
444* By default, the ELF headers are stored in ELF64 format to support
445  systems with more than 4GB memory. On i386, kexec automatically checks if
446  the physical RAM size exceeds the 4 GB limit and if not, uses ELF32.
447  So, on non-PAE systems, ELF32 is always used.
448
449  The --elf32-core-headers option can be used to force the generation of ELF32
450  headers. This is necessary because GDB currently cannot open vmcore files
451  with ELF64 headers on 32-bit systems.
452
453* The "irqpoll" boot parameter reduces driver initialization failures
454  due to shared interrupts in the dump-capture kernel.
455
456* You must specify <root-dev> in the format corresponding to the root
457  device name in the output of mount command.
458
459* Boot parameter "1" boots the dump-capture kernel into single-user
460  mode without networking. If you want networking, use "3".
461
462* We generally don't have to bring up a SMP kernel just to capture the
463  dump. Hence generally it is useful either to build a UP dump-capture
464  kernel or specify maxcpus=1 option while loading dump-capture kernel.
465  Note, though maxcpus always works, you had better replace it with
466  nr_cpus to save memory if supported by the current ARCH, such as x86.
467
468* You should enable multi-cpu support in dump-capture kernel if you intend
469  to use multi-thread programs with it, such as parallel dump feature of
470  makedumpfile. Otherwise, the multi-thread program may have a great
471  performance degradation. To enable multi-cpu support, you should bring up an
472  SMP dump-capture kernel and specify maxcpus/nr_cpus options while loading it.
473
474* For s390x there are two kdump modes: If a ELF header is specified with
475  the elfcorehdr= kernel parameter, it is used by the kdump kernel as it
476  is done on all other architectures. If no elfcorehdr= kernel parameter is
477  specified, the s390x kdump kernel dynamically creates the header. The
478  second mode has the advantage that for CPU and memory hotplug, kdump has
479  not to be reloaded with kexec_load().
480
481* For s390x systems with many attached devices the "cio_ignore" kernel
482  parameter should be used for the kdump kernel in order to prevent allocation
483  of kernel memory for devices that are not relevant for kdump. The same
484  applies to systems that use SCSI/FCP devices. In that case the
485  "allow_lun_scan" zfcp module parameter should be set to zero before
486  setting FCP devices online.
487
488Kernel Panic
489============
490
491After successfully loading the dump-capture kernel as previously
492described, the system will reboot into the dump-capture kernel if a
493system crash is triggered.  Trigger points are located in panic(),
494die(), die_nmi() and in the sysrq handler (ALT-SysRq-c).
495
496The following conditions will execute a crash trigger point:
497
498If a hard lockup is detected and "NMI watchdog" is configured, the system
499will boot into the dump-capture kernel ( die_nmi() ).
500
501If die() is called, and it happens to be a thread with pid 0 or 1, or die()
502is called inside interrupt context or die() is called and panic_on_oops is set,
503the system will boot into the dump-capture kernel.
504
505On powerpc systems when a soft-reset is generated, die() is called by all cpus
506and the system will boot into the dump-capture kernel.
507
508For testing purposes, you can trigger a crash by using "ALT-SysRq-c",
509"echo c > /proc/sysrq-trigger" or write a module to force the panic.
510
511Write Out the Dump File
512=======================
513
514After the dump-capture kernel is booted, write out the dump file with
515the following command::
516
517   cp /proc/vmcore <dump-file>
518
519or use scp to write out the dump file between hosts on a network, e.g::
520
521   scp /proc/vmcore remote_username@remote_ip:<dump-file>
522
523You can also use makedumpfile utility to write out the dump file
524with specified options to filter out unwanted contents, e.g::
525
526   makedumpfile -l --message-level 1 -d 31 /proc/vmcore <dump-file>
527
528Analysis
529========
530
531Before analyzing the dump image, you should reboot into a stable kernel.
532
533You can do limited analysis using GDB on the dump file copied out of
534/proc/vmcore. Use the debug vmlinux built with -g and run the following
535command::
536
537   gdb vmlinux <dump-file>
538
539Stack trace for the task on processor 0, register display, and memory
540display work fine.
541
542Note: GDB cannot analyze core files generated in ELF64 format for x86.
543On systems with a maximum of 4GB of memory, you can generate
544ELF32-format headers using the --elf32-core-headers kernel option on the
545dump kernel.
546
547You can also use the Crash utility to analyze dump files in Kdump
548format. Crash is available at the following URL:
549
550   https://github.com/crash-utility/crash
551
552Crash document can be found at:
553   https://crash-utility.github.io/
554
555Trigger Kdump on WARN()
556=======================
557
558The kernel parameter, panic_on_warn, calls panic() in all WARN() paths.  This
559will cause a kdump to occur at the panic() call.  In cases where a user wants
560to specify this during runtime, /proc/sys/kernel/panic_on_warn can be set to 1
561to achieve the same behaviour.
562
563Trigger Kdump on add_taint()
564============================
565
566The kernel parameter panic_on_taint facilitates a conditional call to panic()
567from within add_taint() whenever the value set in this bitmask matches with the
568bit flag being set by add_taint().
569This will cause a kdump to occur at the add_taint()->panic() call.
570
571Write the dump file to encrypted disk volume
572============================================
573
574CONFIG_CRASH_DM_CRYPT can be enabled to support saving the dump file to an
575encrypted disk volume (only x86_64 supported for now). User space can interact
576with /sys/kernel/config/crash_dm_crypt_keys for setup,
577
5781. Tell the first kernel what logon keys are needed to unlock the disk volumes,
579    # Add key #1
580    mkdir /sys/kernel/config/crash_dm_crypt_keys/7d26b7b4-e342-4d2d-b660-7426b0996720
581    # Add key #1's description
582    echo cryptsetup:7d26b7b4-e342-4d2d-b660-7426b0996720 > /sys/kernel/config/crash_dm_crypt_keys/description
583
584    # how many keys do we have now?
585    cat /sys/kernel/config/crash_dm_crypt_keys/count
586    1
587
588    # Add key #2 in the same way
589
590    # how many keys do we have now?
591    cat /sys/kernel/config/crash_dm_crypt_keys/count
592    2
593
594    # To support CPU/memory hot-plugging, re-use keys already saved to reserved
595    # memory
596    echo true > /sys/kernel/config/crash_dm_crypt_key/reuse
597
5982. Load the dump-capture kernel
599
6003. After the dump-capture kerne get booted, restore the keys to user keyring
601   echo yes > /sys/kernel/crash_dm_crypt_keys/restore
602
603Contact
604=======
605
606- kexec@lists.infradead.org
607
608GDB macros
609==========
610
611.. include:: gdbmacros.txt
612   :literal:
613