From 330d48105245abfb8c9ca491dc53ea500657217a Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 13 Jun 2019 15:21:39 -0300 Subject: docs: admin-guide: add kdump documentation into it The Kdump documentation describes procedures with admins use in order to solve issues on their systems. Signed-off-by: Mauro Carvalho Chehab --- Documentation/admin-guide/bug-hunting.rst | 4 +- Documentation/admin-guide/index.rst | 1 + Documentation/admin-guide/kdump/gdbmacros.txt | 264 ++++++++++++ Documentation/admin-guide/kdump/index.rst | 20 + Documentation/admin-guide/kdump/kdump.rst | 534 ++++++++++++++++++++++++ Documentation/admin-guide/kdump/vmcoreinfo.rst | 488 ++++++++++++++++++++++ Documentation/admin-guide/kernel-parameters.txt | 6 +- 7 files changed, 1312 insertions(+), 5 deletions(-) create mode 100644 Documentation/admin-guide/kdump/gdbmacros.txt create mode 100644 Documentation/admin-guide/kdump/index.rst create mode 100644 Documentation/admin-guide/kdump/kdump.rst create mode 100644 Documentation/admin-guide/kdump/vmcoreinfo.rst (limited to 'Documentation/admin-guide') diff --git a/Documentation/admin-guide/bug-hunting.rst b/Documentation/admin-guide/bug-hunting.rst index b761aa2a51d2..44b8a4edd348 100644 --- a/Documentation/admin-guide/bug-hunting.rst +++ b/Documentation/admin-guide/bug-hunting.rst @@ -90,9 +90,9 @@ the disk is not available then you have three options: run a null modem to a second machine and capture the output there using your favourite communication program. Minicom works well. -(3) Use Kdump (see Documentation/kdump/kdump.rst), +(3) Use Kdump (see Documentation/admin-guide/kdump/kdump.rst), extract the kernel ring buffer from old memory with using dmesg - gdbmacro in Documentation/kdump/gdbmacros.txt. + gdbmacro in Documentation/admin-guide/kdump/gdbmacros.txt. Finding the bug's location -------------------------- diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst index 6fcc83aaa9b6..5b63182ceb5f 100644 --- a/Documentation/admin-guide/index.rst +++ b/Documentation/admin-guide/index.rst @@ -39,6 +39,7 @@ problems and bugs in particular. ramoops dynamic-debug-howto init + kdump/index perf/index This is the beginning of a section with information of interest to diff --git a/Documentation/admin-guide/kdump/gdbmacros.txt b/Documentation/admin-guide/kdump/gdbmacros.txt new file mode 100644 index 000000000000..220d0a80ca2c --- /dev/null +++ b/Documentation/admin-guide/kdump/gdbmacros.txt @@ -0,0 +1,264 @@ +# +# This file contains a few gdb macros (user defined commands) to extract +# useful information from kernel crashdump (kdump) like stack traces of +# all the processes or a particular process and trapinfo. +# +# These macros can be used by copying this file in .gdbinit (put in home +# directory or current directory) or by invoking gdb command with +# --command= option +# +# Credits: +# Alexander Nyberg +# V Srivatsa +# Maneesh Soni +# + +define bttnobp + set $tasks_off=((size_t)&((struct task_struct *)0)->tasks) + set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next) + set $init_t=&init_task + set $next_t=(((char *)($init_t->tasks).next) - $tasks_off) + set var $stacksize = sizeof(union thread_union) + while ($next_t != $init_t) + set $next_t=(struct task_struct *)$next_t + printf "\npid %d; comm %s:\n", $next_t.pid, $next_t.comm + printf "===================\n" + set var $stackp = $next_t.thread.sp + set var $stack_top = ($stackp & ~($stacksize - 1)) + $stacksize + + while ($stackp < $stack_top) + if (*($stackp) > _stext && *($stackp) < _sinittext) + info symbol *($stackp) + end + set $stackp += 4 + end + set $next_th=(((char *)$next_t->thread_group.next) - $pid_off) + while ($next_th != $next_t) + set $next_th=(struct task_struct *)$next_th + printf "\npid %d; comm %s:\n", $next_t.pid, $next_t.comm + printf "===================\n" + set var $stackp = $next_t.thread.sp + set var $stack_top = ($stackp & ~($stacksize - 1)) + stacksize + + while ($stackp < $stack_top) + if (*($stackp) > _stext && *($stackp) < _sinittext) + info symbol *($stackp) + end + set $stackp += 4 + end + set $next_th=(((char *)$next_th->thread_group.next) - $pid_off) + end + set $next_t=(char *)($next_t->tasks.next) - $tasks_off + end +end +document bttnobp + dump all thread stack traces on a kernel compiled with !CONFIG_FRAME_POINTER +end + +define btthreadstack + set var $pid_task = $arg0 + + printf "\npid %d; comm %s:\n", $pid_task.pid, $pid_task.comm + printf "task struct: " + print $pid_task + printf "===================\n" + set var $stackp = $pid_task.thread.sp + set var $stacksize = sizeof(union thread_union) + set var $stack_top = ($stackp & ~($stacksize - 1)) + $stacksize + set var $stack_bot = ($stackp & ~($stacksize - 1)) + + set $stackp = *((unsigned long *) $stackp) + while (($stackp < $stack_top) && ($stackp > $stack_bot)) + set var $addr = *(((unsigned long *) $stackp) + 1) + info symbol $addr + set $stackp = *((unsigned long *) $stackp) + end +end +document btthreadstack + dump a thread stack using the given task structure pointer +end + + +define btt + set $tasks_off=((size_t)&((struct task_struct *)0)->tasks) + set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next) + set $init_t=&init_task + set $next_t=(((char *)($init_t->tasks).next) - $tasks_off) + while ($next_t != $init_t) + set $next_t=(struct task_struct *)$next_t + btthreadstack $next_t + + set $next_th=(((char *)$next_t->thread_group.next) - $pid_off) + while ($next_th != $next_t) + set $next_th=(struct task_struct *)$next_th + btthreadstack $next_th + set $next_th=(((char *)$next_th->thread_group.next) - $pid_off) + end + set $next_t=(char *)($next_t->tasks.next) - $tasks_off + end +end +document btt + dump all thread stack traces on a kernel compiled with CONFIG_FRAME_POINTER +end + +define btpid + set var $pid = $arg0 + set $tasks_off=((size_t)&((struct task_struct *)0)->tasks) + set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next) + set $init_t=&init_task + set $next_t=(((char *)($init_t->tasks).next) - $tasks_off) + set var $pid_task = 0 + + while ($next_t != $init_t) + set $next_t=(struct task_struct *)$next_t + + if ($next_t.pid == $pid) + set $pid_task = $next_t + end + + set $next_th=(((char *)$next_t->thread_group.next) - $pid_off) + while ($next_th != $next_t) + set $next_th=(struct task_struct *)$next_th + if ($next_th.pid == $pid) + set $pid_task = $next_th + end + set $next_th=(((char *)$next_th->thread_group.next) - $pid_off) + end + set $next_t=(char *)($next_t->tasks.next) - $tasks_off + end + + btthreadstack $pid_task +end +document btpid + backtrace of pid +end + + +define trapinfo + set var $pid = $arg0 + set $tasks_off=((size_t)&((struct task_struct *)0)->tasks) + set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next) + set $init_t=&init_task + set $next_t=(((char *)($init_t->tasks).next) - $tasks_off) + set var $pid_task = 0 + + while ($next_t != $init_t) + set $next_t=(struct task_struct *)$next_t + + if ($next_t.pid == $pid) + set $pid_task = $next_t + end + + set $next_th=(((char *)$next_t->thread_group.next) - $pid_off) + while ($next_th != $next_t) + set $next_th=(struct task_struct *)$next_th + if ($next_th.pid == $pid) + set $pid_task = $next_th + end + set $next_th=(((char *)$next_th->thread_group.next) - $pid_off) + end + set $next_t=(char *)($next_t->tasks.next) - $tasks_off + end + + printf "Trapno %ld, cr2 0x%lx, error_code %ld\n", $pid_task.thread.trap_no, \ + $pid_task.thread.cr2, $pid_task.thread.error_code + +end +document trapinfo + Run info threads and lookup pid of thread #1 + 'trapinfo ' will tell you by which trap & possibly + address the kernel panicked. +end + +define dump_log_idx + set $idx = $arg0 + if ($argc > 1) + set $prev_flags = $arg1 + else + set $prev_flags = 0 + end + set $msg = ((struct printk_log *) (log_buf + $idx)) + set $prefix = 1 + set $newline = 1 + set $log = log_buf + $idx + sizeof(*$msg) + + # prev & LOG_CONT && !(msg->flags & LOG_PREIX) + if (($prev_flags & 8) && !($msg->flags & 4)) + set $prefix = 0 + end + + # msg->flags & LOG_CONT + if ($msg->flags & 8) + # (prev & LOG_CONT && !(prev & LOG_NEWLINE)) + if (($prev_flags & 8) && !($prev_flags & 2)) + set $prefix = 0 + end + # (!(msg->flags & LOG_NEWLINE)) + if (!($msg->flags & 2)) + set $newline = 0 + end + end + + if ($prefix) + printf "[%5lu.%06lu] ", $msg->ts_nsec / 1000000000, $msg->ts_nsec % 1000000000 + end + if ($msg->text_len != 0) + eval "printf \"%%%d.%ds\", $log", $msg->text_len, $msg->text_len + end + if ($newline) + printf "\n" + end + if ($msg->dict_len > 0) + set $dict = $log + $msg->text_len + set $idx = 0 + set $line = 1 + while ($idx < $msg->dict_len) + if ($line) + printf " " + set $line = 0 + end + set $c = $dict[$idx] + if ($c == '\0') + printf "\n" + set $line = 1 + else + if ($c < ' ' || $c >= 127 || $c == '\\') + printf "\\x%02x", $c + else + printf "%c", $c + end + end + set $idx = $idx + 1 + end + printf "\n" + end +end +document dump_log_idx + Dump a single log given its index in the log buffer. The first + parameter is the index into log_buf, the second is optional and + specified the previous log buffer's flags, used for properly + formatting continued lines. +end + +define dmesg + set $i = log_first_idx + set $end_idx = log_first_idx + set $prev_flags = 0 + + while (1) + set $msg = ((struct printk_log *) (log_buf + $i)) + if ($msg->len == 0) + set $i = 0 + else + dump_log_idx $i $prev_flags + set $i = $i + $msg->len + set $prev_flags = $msg->flags + end + if ($i == $end_idx) + loop_break + end + end +end +document dmesg + print the kernel ring buffer +end diff --git a/Documentation/admin-guide/kdump/index.rst b/Documentation/admin-guide/kdump/index.rst new file mode 100644 index 000000000000..8e2ebd0383cd --- /dev/null +++ b/Documentation/admin-guide/kdump/index.rst @@ -0,0 +1,20 @@ + +================================================================ +Documentation for Kdump - The kexec-based Crash Dumping Solution +================================================================ + +This document includes overview, setup and installation, and analysis +information. + +.. toctree:: + :maxdepth: 1 + + kdump + vmcoreinfo + +.. only:: subproject and html + + Indices + ======= + + * :ref:`genindex` diff --git a/Documentation/admin-guide/kdump/kdump.rst b/Documentation/admin-guide/kdump/kdump.rst new file mode 100644 index 000000000000..ac7e131d2935 --- /dev/null +++ b/Documentation/admin-guide/kdump/kdump.rst @@ -0,0 +1,534 @@ +================================================================ +Documentation for Kdump - The kexec-based Crash Dumping Solution +================================================================ + +This document includes overview, setup and installation, and analysis +information. + +Overview +======== + +Kdump uses kexec to quickly boot to a dump-capture kernel whenever a +dump of the system kernel's memory needs to be taken (for example, when +the system panics). The system kernel's memory image is preserved across +the reboot and is accessible to the dump-capture kernel. + +You can use common commands, such as cp and scp, to copy the +memory image to a dump file on the local disk, or across the network to +a remote system. + +Kdump and kexec are currently supported on the x86, x86_64, ppc64, ia64, +s390x, arm and arm64 architectures. + +When the system kernel boots, it reserves a small section of memory for +the dump-capture kernel. This ensures that ongoing Direct Memory Access +(DMA) from the system kernel does not corrupt the dump-capture kernel. +The kexec -p command loads the dump-capture kernel into this reserved +memory. + +On x86 machines, the first 640 KB of physical memory is needed to boot, +regardless of where the kernel loads. Therefore, kexec backs up this +region just before rebooting into the dump-capture kernel. + +Similarly on PPC64 machines first 32KB of physical memory is needed for +booting regardless of where the kernel is loaded and to support 64K page +size kexec backs up the first 64KB memory. + +For s390x, when kdump is triggered, the crashkernel region is exchanged +with the region [0, crashkernel region size] and then the kdump kernel +runs in [0, crashkernel region size]. Therefore no relocatable kernel is +needed for s390x. + +All of the necessary information about the system kernel's core image is +encoded in the ELF format, and stored in a reserved area of memory +before a crash. The physical address of the start of the ELF header is +passed to the dump-capture kernel through the elfcorehdr= boot +parameter. Optionally the size of the ELF header can also be passed +when using the elfcorehdr=[size[KMG]@]offset[KMG] syntax. + + +With the dump-capture kernel, you can access the memory image through +/proc/vmcore. This exports the dump as an ELF-format file that you can +write out using file copy commands such as cp or scp. Further, you can +use analysis tools such as the GNU Debugger (GDB) and the Crash tool to +debug the dump file. This method ensures that the dump pages are correctly +ordered. + + +Setup and Installation +====================== + +Install kexec-tools +------------------- + +1) Login as the root user. + +2) Download the kexec-tools user-space package from the following URL: + +http://kernel.org/pub/linux/utils/kernel/kexec/kexec-tools.tar.gz + +This is a symlink to the latest version. + +The latest kexec-tools git tree is available at: + +- git://git.kernel.org/pub/scm/utils/kernel/kexec/kexec-tools.git +- http://www.kernel.org/pub/scm/utils/kernel/kexec/kexec-tools.git + +There is also a gitweb interface available at +http://www.kernel.org/git/?p=utils/kernel/kexec/kexec-tools.git + +More information about kexec-tools can be found at +http://horms.net/projects/kexec/ + +3) Unpack the tarball with the tar command, as follows:: + + tar xvpzf kexec-tools.tar.gz + +4) Change to the kexec-tools directory, as follows:: + + cd kexec-tools-VERSION + +5) Configure the package, as follows:: + + ./configure + +6) Compile the package, as follows:: + + make + +7) Install the package, as follows:: + + make install + + +Build the system and dump-capture kernels +----------------------------------------- +There are two possible methods of using Kdump. + +1) Build a separate custom dump-capture kernel for capturing the + kernel core dump. + +2) Or use the system kernel binary itself as dump-capture kernel and there is + no need to build a separate dump-capture kernel. This is possible + only with the architectures which support a relocatable kernel. As + of today, i386, x86_64, ppc64, ia64, arm and arm64 architectures support + relocatable kernel. + +Building a relocatable kernel is advantageous from the point of view that +one does not have to build a second kernel for capturing the dump. But +at the same time one might want to build a custom dump capture kernel +suitable to his needs. + +Following are the configuration setting required for system and +dump-capture kernels for enabling kdump support. + +System kernel config options +---------------------------- + +1) Enable "kexec system call" in "Processor type and features.":: + + CONFIG_KEXEC=y + +2) Enable "sysfs file system support" in "Filesystem" -> "Pseudo + filesystems." This is usually enabled by default:: + + CONFIG_SYSFS=y + + Note that "sysfs file system support" might not appear in the "Pseudo + filesystems" menu if "Configure standard kernel features (for small + systems)" is not enabled in "General Setup." In this case, check the + .config file itself to ensure that sysfs is turned on, as follows:: + + grep 'CONFIG_SYSFS' .config + +3) Enable "Compile the kernel with debug info" in "Kernel hacking.":: + + CONFIG_DEBUG_INFO=Y + + This causes the kernel to be built with debug symbols. The dump + analysis tools require a vmlinux with debug symbols in order to read + and analyze a dump file. + +Dump-capture kernel config options (Arch Independent) +----------------------------------------------------- + +1) Enable "kernel crash dumps" support under "Processor type and + features":: + + CONFIG_CRASH_DUMP=y + +2) Enable "/proc/vmcore support" under "Filesystems" -> "Pseudo filesystems":: + + CONFIG_PROC_VMCORE=y + + (CONFIG_PROC_VMCORE is set by default when CONFIG_CRASH_DUMP is selected.) + +Dump-capture kernel config options (Arch Dependent, i386 and x86_64) +-------------------------------------------------------------------- + +1) On i386, enable high memory support under "Processor type and + features":: + + CONFIG_HIGHMEM64G=y + + or:: + + CONFIG_HIGHMEM4G + +2) On i386 and x86_64, disable symmetric multi-processing support + under "Processor type and features":: + + CONFIG_SMP=n + + (If CONFIG_SMP=y, then specify maxcpus=1 on the kernel command line + when loading the dump-capture kernel, see section "Load the Dump-capture + Kernel".) + +3) If one wants to build and use a relocatable kernel, + Enable "Build a relocatable kernel" support under "Processor type and + features":: + + CONFIG_RELOCATABLE=y + +4) Use a suitable value for "Physical address where the kernel is + loaded" (under "Processor type and features"). This only appears when + "kernel crash dumps" is enabled. A suitable value depends upon + whether kernel is relocatable or not. + + If you are using a relocatable kernel use CONFIG_PHYSICAL_START=0x100000 + This will compile the kernel for physical address 1MB, but given the fact + kernel is relocatable, it can be run from any physical address hence + kexec boot loader will load it in memory region reserved for dump-capture + kernel. + + Otherwise it should be the start of memory region reserved for + second kernel using boot parameter "crashkernel=Y@X". Here X is + start of memory region reserved for dump-capture kernel. + Generally X is 16MB (0x1000000). So you can set + CONFIG_PHYSICAL_START=0x1000000 + +5) Make and install the kernel and its modules. DO NOT add this kernel + to the boot loader configuration files. + +Dump-capture kernel config options (Arch Dependent, ppc64) +---------------------------------------------------------- + +1) Enable "Build a kdump crash kernel" support under "Kernel" options:: + + CONFIG_CRASH_DUMP=y + +2) Enable "Build a relocatable kernel" support:: + + CONFIG_RELOCATABLE=y + + Make and install the kernel and its modules. + +Dump-capture kernel config options (Arch Dependent, ia64) +---------------------------------------------------------- + +- No specific options are required to create a dump-capture kernel + for ia64, other than those specified in the arch independent section + above. This means that it is possible to use the system kernel + as a dump-capture kernel if desired. + + The crashkernel region can be automatically placed by the system + kernel at run time. This is done by specifying the base address as 0, + or omitting it all together:: + + crashkernel=256M@0 + + or:: + + crashkernel=256M + + If the start address is specified, note that the start address of the + kernel will be aligned to 64Mb, so if the start address is not then + any space below the alignment point will be wasted. + +Dump-capture kernel config options (Arch Dependent, arm) +---------------------------------------------------------- + +- To use a relocatable kernel, + Enable "AUTO_ZRELADDR" support under "Boot" options:: + + AUTO_ZRELADDR=y + +Dump-capture kernel config options (Arch Dependent, arm64) +---------------------------------------------------------- + +- Please note that kvm of the dump-capture kernel will not be enabled + on non-VHE systems even if it is configured. This is because the CPU + will not be reset to EL2 on panic. + +Extended crashkernel syntax +=========================== + +While the "crashkernel=size[@offset]" syntax is sufficient for most +configurations, sometimes it's handy to have the reserved memory dependent +on the value of System RAM -- that's mostly for distributors that pre-setup +the kernel command line to avoid a unbootable system after some memory has +been removed from the machine. + +The syntax is:: + + crashkernel=:[,:,...][@offset] + range=start-[end] + +For example:: + + crashkernel=512M-2G:64M,2G-:128M + +This would mean: + + 1) if the RAM is smaller than 512M, then don't reserve anything + (this is the "rescue" case) + 2) if the RAM size is between 512M and 2G (exclusive), then reserve 64M + 3) if the RAM size is larger than 2G, then reserve 128M + + + +Boot into System Kernel +======================= + +1) Update the boot loader (such as grub, yaboot, or lilo) configuration + files as necessary. + +2) Boot the system kernel with the boot parameter "crashkernel=Y@X", + where Y specifies how much memory to reserve for the dump-capture kernel + and X specifies the beginning of this reserved memory. For example, + "crashkernel=64M@16M" tells the system kernel to reserve 64 MB of memory + starting at physical address 0x01000000 (16MB) for the dump-capture kernel. + + On x86 and x86_64, use "crashkernel=64M@16M". + + On ppc64, use "crashkernel=128M@32M". + + On ia64, 256M@256M is a generous value that typically works. + The region may be automatically placed on ia64, see the + dump-capture kernel config option notes above. + If use sparse memory, the size should be rounded to GRANULE boundaries. + + On s390x, typically use "crashkernel=xxM". The value of xx is dependent + on the memory consumption of the kdump system. In general this is not + dependent on the memory size of the production system. + + On arm, the use of "crashkernel=Y@X" is no longer necessary; the + kernel will automatically locate the crash kernel image within the + first 512MB of RAM if X is not given. + + On arm64, use "crashkernel=Y[@X]". Note that the start address of + the kernel, X if explicitly specified, must be aligned to 2MiB (0x200000). + +Load the Dump-capture Kernel +============================ + +After booting to the system kernel, dump-capture kernel needs to be +loaded. + +Based on the architecture and type of image (relocatable or not), one +can choose to load the uncompressed vmlinux or compressed bzImage/vmlinuz +of dump-capture kernel. Following is the summary. + +For i386 and x86_64: + + - Use vmlinux if kernel is not relocatable. + - Use bzImage/vmlinuz if kernel is relocatable. + +For ppc64: + + - Use vmlinux + +For ia64: + + - Use vmlinux or vmlinuz.gz + +For s390x: + + - Use image or bzImage + +For arm: + + - Use zImage + +For arm64: + + - Use vmlinux or Image + +If you are using an uncompressed vmlinux image then use following command +to load dump-capture kernel:: + + kexec -p \ + --initrd= --args-linux \ + --append="root= " + +If you are using a compressed bzImage/vmlinuz, then use following command +to load dump-capture kernel:: + + kexec -p \ + --initrd= \ + --append="root= " + +If you are using a compressed zImage, then use following command +to load dump-capture kernel:: + + kexec --type zImage -p \ + --initrd= \ + --dtb= \ + --append="root= " + +If you are using an uncompressed Image, then use following command +to load dump-capture kernel:: + + kexec -p \ + --initrd= \ + --append="root= " + +Please note, that --args-linux does not need to be specified for ia64. +It is planned to make this a no-op on that architecture, but for now +it should be omitted + +Following are the arch specific command line options to be used while +loading dump-capture kernel. + +For i386, x86_64 and ia64: + + "1 irqpoll maxcpus=1 reset_devices" + +For ppc64: + + "1 maxcpus=1 noirqdistrib reset_devices" + +For s390x: + + "1 maxcpus=1 cgroup_disable=memory" + +For arm: + + "1 maxcpus=1 reset_devices" + +For arm64: + + "1 maxcpus=1 reset_devices" + +Notes on loading the dump-capture kernel: + +* By default, the ELF headers are stored in ELF64 format to support + systems with more than 4GB memory. On i386, kexec automatically checks if + the physical RAM size exceeds the 4 GB limit and if not, uses ELF32. + So, on non-PAE systems, ELF32 is always used. + + The --elf32-core-headers option can be used to force the generation of ELF32 + headers. This is necessary because GDB currently cannot open vmcore files + with ELF64 headers on 32-bit systems. + +* The "irqpoll" boot parameter reduces driver initialization failures + due to shared interrupts in the dump-capture kernel. + +* You must specify in the format corresponding to the root + device name in the output of mount command. + +* Boot parameter "1" boots the dump-capture kernel into single-user + mode without networking. If you want networking, use "3". + +* We generally don't have to bring up a SMP kernel just to capture the + dump. Hence generally it is useful either to build a UP dump-capture + kernel or specify maxcpus=1 option while loading dump-capture kernel. + Note, though maxcpus always works, you had better replace it with + nr_cpus to save memory if supported by the current ARCH, such as x86. + +* You should enable multi-cpu support in dump-capture kernel if you intend + to use multi-thread programs with it, such as parallel dump feature of + makedumpfile. Otherwise, the multi-thread program may have a great + performance degradation. To enable multi-cpu support, you should bring up an + SMP dump-capture kernel and specify maxcpus/nr_cpus, disable_cpu_apicid=[X] + options while loading it. + +* For s390x there are two kdump modes: If a ELF header is specified with + the elfcorehdr= kernel parameter, it is used by the kdump kernel as it + is done on all other architectures. If no elfcorehdr= kernel parameter is + specified, the s390x kdump kernel dynamically creates the header. The + second mode has the advantage that for CPU and memory hotplug, kdump has + not to be reloaded with kexec_load(). + +* For s390x systems with many attached devices the "cio_ignore" kernel + parameter should be used for the kdump kernel in order to prevent allocation + of kernel memory for devices that are not relevant for kdump. The same + applies to systems that use SCSI/FCP devices. In that case the + "allow_lun_scan" zfcp module parameter should be set to zero before + setting FCP devices online. + +Kernel Panic +============ + +After successfully loading the dump-capture kernel as previously +described, the system will reboot into the dump-capture kernel if a +system crash is triggered. Trigger points are located in panic(), +die(), die_nmi() and in the sysrq handler (ALT-SysRq-c). + +The following conditions will execute a crash trigger point: + +If a hard lockup is detected and "NMI watchdog" is configured, the system +will boot into the dump-capture kernel ( die_nmi() ). + +If die() is called, and it happens to be a thread with pid 0 or 1, or die() +is called inside interrupt context or die() is called and panic_on_oops is set, +the system will boot into the dump-capture kernel. + +On powerpc systems when a soft-reset is generated, die() is called by all cpus +and the system will boot into the dump-capture kernel. + +For testing purposes, you can trigger a crash by using "ALT-SysRq-c", +"echo c > /proc/sysrq-trigger" or write a module to force the panic. + +Write Out the Dump File +======================= + +After the dump-capture kernel is booted, write out the dump file with +the following command:: + + cp /proc/vmcore + + +Analysis +======== + +Before analyzing the dump image, you should reboot into a stable kernel. + +You can do limited analysis using GDB on the dump file copied out of +/proc/vmcore. Use the debug vmlinux built with -g and run the following +command:: + + gdb vmlinux + +Stack trace for the task on processor 0, register display, and memory +display work fine. + +Note: GDB cannot analyze core files generated in ELF64 format for x86. +On systems with a maximum of 4GB of memory, you can generate +ELF32-format headers using the --elf32-core-headers kernel option on the +dump kernel. + +You can also use the Crash utility to analyze dump files in Kdump +format. Crash is available on Dave Anderson's site at the following URL: + + http://people.redhat.com/~anderson/ + +Trigger Kdump on WARN() +======================= + +The kernel parameter, panic_on_warn, calls panic() in all WARN() paths. This +will cause a kdump to occur at the panic() call. In cases where a user wants +to specify this during runtime, /proc/sys/kernel/panic_on_warn can be set to 1 +to achieve the same behaviour. + +Contact +======= + +- Vivek Goyal (vgoyal@redhat.com) +- Maneesh Soni (maneesh@in.ibm.com) + +GDB macros +========== + +.. include:: gdbmacros.txt + :literal: diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst new file mode 100644 index 000000000000..007a6b86e0ee --- /dev/null +++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst @@ -0,0 +1,488 @@ +========== +VMCOREINFO +========== + +What is it? +=========== + +VMCOREINFO is a special ELF note section. It contains various +information from the kernel like structure size, page size, symbol +values, field offsets, etc. These data are packed into an ELF note +section and used by user-space tools like crash and makedumpfile to +analyze a kernel's memory layout. + +Common variables +================ + +init_uts_ns.name.release +------------------------ + +The version of the Linux kernel. Used to find the corresponding source +code from which the kernel has been built. For example, crash uses it to +find the corresponding vmlinux in order to process vmcore. + +PAGE_SIZE +--------- + +The size of a page. It is the smallest unit of data used by the memory +management facilities. It is usually 4096 bytes of size and a page is +aligned on 4096 bytes. Used for computing page addresses. + +init_uts_ns +----------- + +The UTS namespace which is used to isolate two specific elements of the +system that relate to the uname(2) system call. It is named after the +data structure used to store information returned by the uname(2) system +call. + +User-space tools can get the kernel name, host name, kernel release +number, kernel version, architecture name and OS type from it. + +node_online_map +--------------- + +An array node_states[N_ONLINE] which represents the set of online nodes +in a system, one bit position per node number. Used to keep track of +which nodes are in the system and online. + +swapper_pg_dir +-------------- + +The global page directory pointer of the kernel. Used to translate +virtual to physical addresses. + +_stext +------ + +Defines the beginning of the text section. In general, _stext indicates +the kernel start address. Used to convert a virtual address from the +direct kernel map to a physical address. + +vmap_area_list +-------------- + +Stores the virtual area list. makedumpfile gets the vmalloc start value +from this variable and its value is necessary for vmalloc translation. + +mem_map +------- + +Physical addresses are translated to struct pages by treating them as +an index into the mem_map array. Right-shifting a physical address +PAGE_SHIFT bits converts it into a page frame number which is an index +into that mem_map array. + +Used to map an address to the corresponding struct page. + +contig_page_data +---------------- + +Makedumpfile gets the pglist_data structure from this symbol, which is +used to describe the memory layout. + +User-space tools use this to exclude free pages when dumping memory. + +mem_section|(mem_section, NR_SECTION_ROOTS)|(mem_section, section_mem_map) +-------------------------------------------------------------------------- + +The address of the mem_section array, its length, structure size, and +the section_mem_map offset. + +It exists in the sparse memory mapping model, and it is also somewhat +similar to the mem_map variable, both of them are used to translate an +address. + +page +---- + +The size of a page structure. struct page is an important data structure +and it is widely used to compute contiguous memory. + +pglist_data +----------- + +The size of a pglist_data structure. This value is used to check if the +pglist_data structure is valid. It is also used for checking the memory +type. + +zone +---- + +The size of a zone structure. This value is used to check if the zone +structure has been found. It is also used for excluding free pages. + +free_area +--------- + +The size of a free_area structure. It indicates whether the free_area +structure is valid or not. Useful when excluding free pages. + +list_head +--------- + +The size of a list_head structure. Used when iterating lists in a +post-mortem analysis session. + +nodemask_t +---------- + +The size of a nodemask_t type. Used to compute the number of online +nodes. + +(page, flags|_refcount|mapping|lru|_mapcount|private|compound_dtor|compound_order|compound_head) +------------------------------------------------------------------------------------------------- + +User-space tools compute their values based on the offset of these +variables. The variables are used when excluding unnecessary pages. + +(pglist_data, node_zones|nr_zones|node_mem_map|node_start_pfn|node_spanned_pages|node_id) +----------------------------------------------------------------------------------------- + +On NUMA machines, each NUMA node has a pg_data_t to describe its memory +layout. On UMA machines there is a single pglist_data which describes the +whole memory. + +These values are used to check the memory type and to compute the +virtual address for memory map. + +(zone, free_area|vm_stat|spanned_pages) +--------------------------------------- + +Each node is divided into a number of blocks called zones which +represent ranges within memory. A zone is described by a structure zone. + +User-space tools compute required values based on the offset of these +variables. + +(free_area, free_list) +---------------------- + +Offset of the free_list's member. This value is used to compute the number +of free pages. + +Each zone has a free_area structure array called free_area[MAX_ORDER]. +The free_list represents a linked list of free page blocks. + +(list_head, next|prev) +---------------------- + +Offsets of the list_head's members. list_head is used to define a +circular linked list. User-space tools need these in order to traverse +lists. + +(vmap_area, va_start|list) +-------------------------- + +Offsets of the vmap_area's members. They carry vmalloc-specific +information. Makedumpfile gets the start address of the vmalloc region +from this. + +(zone.free_area, MAX_ORDER) +--------------------------- + +Free areas descriptor. User-space tools use this value to iterate the +free_area ranges. MAX_ORDER is used by the zone buddy allocator. + +log_first_idx +------------- + +Index of the first record stored in the buffer log_buf. Used by +user-space tools to read the strings in the log_buf. + +log_buf +------- + +Console output is written to the ring buffer log_buf at index +log_first_idx. Used to get the kernel log. + +log_buf_len +----------- + +log_buf's length. + +clear_idx +--------- + +The index that the next printk() record to read after the last clear +command. It indicates the first record after the last SYSLOG_ACTION +_CLEAR, like issued by 'dmesg -c'. Used by user-space tools to dump +the dmesg log. + +log_next_idx +------------ + +The index of the next record to store in the buffer log_buf. Used to +compute the index of the current buffer position. + +printk_log +---------- + +The size of a structure printk_log. Used to compute the size of +messages, and extract dmesg log. It encapsulates header information for +log_buf, such as timestamp, syslog level, etc. + +(printk_log, ts_nsec|len|text_len|dict_len) +------------------------------------------- + +It represents field offsets in struct printk_log. User space tools +parse it and check whether the values of printk_log's members have been +changed. + +(free_area.free_list, MIGRATE_TYPES) +------------------------------------ + +The number of migrate types for pages. The free_list is described by the +array. Used by tools to compute the number of free pages. + +NR_FREE_PAGES +------------- + +On linux-2.6.21 or later, the number of free pages is in +vm_stat[NR_FREE_PAGES]. Used to get the number of free pages. + +PG_lru|PG_private|PG_swapcache|PG_swapbacked|PG_slab|PG_hwpoision|PG_head_mask +------------------------------------------------------------------------------ + +Page attributes. These flags are used to filter various unnecessary for +dumping pages. + +PAGE_BUDDY_MAPCOUNT_VALUE(~PG_buddy)|PAGE_OFFLINE_MAPCOUNT_VALUE(~PG_offline) +----------------------------------------------------------------------------- + +More page attributes. These flags are used to filter various unnecessary for +dumping pages. + + +HUGETLB_PAGE_DTOR +----------------- + +The HUGETLB_PAGE_DTOR flag denotes hugetlbfs pages. Makedumpfile +excludes these pages. + +x86_64 +====== + +phys_base +--------- + +Used to convert the virtual address of an exported kernel symbol to its +corresponding physical address. + +init_top_pgt +------------ + +Used to walk through the whole page table and convert virtual addresses +to physical addresses. The init_top_pgt is somewhat similar to +swapper_pg_dir, but it is only used in x86_64. + +pgtable_l5_enabled +------------------ + +User-space tools need to know whether the crash kernel was in 5-level +paging mode. + +node_data +--------- + +This is a struct pglist_data array and stores all NUMA nodes +information. Makedumpfile gets the pglist_data structure from it. + +(node_data, MAX_NUMNODES) +------------------------- + +The maximum number of nodes in system. + +KERNELOFFSET +------------ + +The kernel randomization offset. Used to compute the page offset. If +KASLR is disabled, this value is zero. + +KERNEL_IMAGE_SIZE +----------------- + +Currently unused by Makedumpfile. Used to compute the module virtual +address by Crash. + +sme_mask +-------- + +AMD-specific with SME support: it indicates the secure memory encryption +mask. Makedumpfile tools need to know whether the crash kernel was +encrypted. If SME is enabled in the first kernel, the crash kernel's +page table entries (pgd/pud/pmd/pte) contain the memory encryption +mask. This is used to remove the SME mask and obtain the true physical +address. + +Currently, sme_mask stores the value of the C-bit position. If needed, +additional SME-relevant info can be placed in that variable. + +For example:: + + [ misc ][ enc bit ][ other misc SME info ] + 0000_0000_0000_0000_1000_0000_0000_0000_0000_0000_..._0000 + 63 59 55 51 47 43 39 35 31 27 ... 3 + +x86_32 +====== + +X86_PAE +------- + +Denotes whether physical address extensions are enabled. It has the cost +of a higher page table lookup overhead, and also consumes more page +table space per process. Used to check whether PAE was enabled in the +crash kernel when converting virtual addresses to physical addresses. + +ia64 +==== + +pgdat_list|(pgdat_list, MAX_NUMNODES) +------------------------------------- + +pg_data_t array storing all NUMA nodes information. MAX_NUMNODES +indicates the number of the nodes. + +node_memblk|(node_memblk, NR_NODE_MEMBLKS) +------------------------------------------ + +List of node memory chunks. Filled when parsing the SRAT table to obtain +information about memory nodes. NR_NODE_MEMBLKS indicates the number of +node memory chunks. + +These values are used to compute the number of nodes the crashed kernel used. + +node_memblk_s|(node_memblk_s, start_paddr)|(node_memblk_s, size) +---------------------------------------------------------------- + +The size of a struct node_memblk_s and the offsets of the +node_memblk_s's members. Used to compute the number of nodes. + +PGTABLE_3|PGTABLE_4 +------------------- + +User-space tools need to know whether the crash kernel was in 3-level or +4-level paging mode. Used to distinguish the page table. + +ARM64 +===== + +VA_BITS +------- + +The maximum number of bits for virtual addresses. Used to compute the +virtual memory ranges. + +kimage_voffset +-------------- + +The offset between the kernel virtual and physical mappings. Used to +translate virtual to physical addresses. + +PHYS_OFFSET +----------- + +Indicates the physical address of the start of memory. Similar to +kimage_voffset, which is used to translate virtual to physical +addresses. + +KERNELOFFSET +------------ + +The kernel randomization offset. Used to compute the page offset. If +KASLR is disabled, this value is zero. + +arm +=== + +ARM_LPAE +-------- + +It indicates whether the crash kernel supports large physical address +extensions. Used to translate virtual to physical addresses. + +s390 +==== + +lowcore_ptr +----------- + +An array with a pointer to the lowcore of every CPU. Used to print the +psw and all registers information. + +high_memory +----------- + +Used to get the vmalloc_start address from the high_memory symbol. + +(lowcore_ptr, NR_CPUS) +---------------------- + +The maximum number of CPUs. + +powerpc +======= + + +node_data|(node_data, MAX_NUMNODES) +----------------------------------- + +See above. + +contig_page_data +---------------- + +See above. + +vmemmap_list +------------ + +The vmemmap_list maintains the entire vmemmap physical mapping. Used +to get vmemmap list count and populated vmemmap regions info. If the +vmemmap address translation information is stored in the crash kernel, +it is used to translate vmemmap kernel virtual addresses. + +mmu_vmemmap_psize +----------------- + +The size of a page. Used to translate virtual to physical addresses. + +mmu_psize_defs +-------------- + +Page size definitions, i.e. 4k, 64k, or 16M. + +Used to make vtop translations. + +vmemmap_backing|(vmemmap_backing, list)|(vmemmap_backing, phys)|(vmemmap_backing, virt_addr) +-------------------------------------------------------------------------------------------- + +The vmemmap virtual address space management does not have a traditional +page table to track which virtual struct pages are backed by a physical +mapping. The virtual to physical mappings are tracked in a simple linked +list format. + +User-space tools need to know the offset of list, phys and virt_addr +when computing the count of vmemmap regions. + +mmu_psize_def|(mmu_psize_def, shift) +------------------------------------ + +The size of a struct mmu_psize_def and the offset of mmu_psize_def's +member. + +Used in vtop translations. + +sh +== + +node_data|(node_data, MAX_NUMNODES) +----------------------------------- + +See above. + +X2TLB +----- + +Indicates whether the crashed kernel enabled SH extended mode. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 4821175a3769..e645b3ab4b6f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -708,14 +708,14 @@ [KNL, x86_64] select a region under 4G first, and fall back to reserve region above 4G when '@offset' hasn't been specified. - See Documentation/kdump/kdump.rst for further details. + See Documentation/admin-guide/kdump/kdump.rst for further details. crashkernel=range1:size1[,range2:size2,...][@offset] [KNL] Same as above, but depends on the memory in the running system. The syntax of range is start-[end] where start and end are both a memory unit (amount[KMG]). See also - Documentation/kdump/kdump.rst for an example. + Documentation/admin-guide/kdump/kdump.rst for an example. crashkernel=size[KMG],high [KNL, x86_64] range could be above 4G. Allow kernel @@ -1207,7 +1207,7 @@ Specifies physical address of start of kernel core image elf header and optionally the size. Generally kexec loader will pass this option to capture kernel. - See Documentation/kdump/kdump.rst for details. + See Documentation/admin-guide/kdump/kdump.rst for details. enable_mtrr_cleanup [X86] The kernel tries to adjust MTRR layout from continuous -- cgit v1.2.3