diff options
| -rw-r--r-- | Documentation/ABI/testing/sysfs-devices-memory | 6 | ||||
| -rw-r--r-- | Documentation/ABI/testing/sysfs-devices-system-cpu | 6 | ||||
| -rw-r--r-- | Documentation/admin-guide/mm/memory-hotplug.rst | 5 | ||||
| -rw-r--r-- | Documentation/core-api/cpu_hotplug.rst | 10 | ||||
| -rw-r--r-- | kernel/crash_core.c | 33 |
5 files changed, 35 insertions, 25 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory index a95e0f17c35a..cec65827e602 100644 --- a/Documentation/ABI/testing/sysfs-devices-memory +++ b/Documentation/ABI/testing/sysfs-devices-memory @@ -115,6 +115,6 @@ What: /sys/devices/system/memory/crash_hotplug Date: Aug 2023 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: - (RO) indicates whether or not the kernel directly supports - modifying the crash elfcorehdr for memory hot un/plug and/or - on/offline changes. + (RO) indicates whether or not the kernel updates relevant kexec + segments on memory hot un/plug and/or on/offline events, avoiding the + need to reload kdump kernel. diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index de725ca3be82..206079d3bd5b 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -704,9 +704,9 @@ What: /sys/devices/system/cpu/crash_hotplug Date: Aug 2023 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: - (RO) indicates whether or not the kernel directly supports - modifying the crash elfcorehdr for CPU hot un/plug and/or - on/offline changes. + (RO) indicates whether or not the kernel updates relevant kexec + segments on memory hot un/plug and/or on/offline events, avoiding the + need to reload kdump kernel. What: /sys/devices/system/cpu/enabled Date: Nov 2022 diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst index 098f14d83e99..cb2c080f400c 100644 --- a/Documentation/admin-guide/mm/memory-hotplug.rst +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -294,8 +294,9 @@ The following files are currently defined: ``crash_hotplug`` read-only: when changes to the system memory map occur due to hot un/plug of memory, this file contains '1' if the kernel updates the kdump capture kernel memory - map itself (via elfcorehdr), or '0' if userspace must update - the kdump capture kernel memory map. + map itself (via elfcorehdr and other relevant kexec + segments), or '0' if userspace must update the kdump + capture kernel memory map. Availability depends on the CONFIG_MEMORY_HOTPLUG kernel configuration option. diff --git a/Documentation/core-api/cpu_hotplug.rst b/Documentation/core-api/cpu_hotplug.rst index dcb0e379e5e8..a21dbf261be7 100644 --- a/Documentation/core-api/cpu_hotplug.rst +++ b/Documentation/core-api/cpu_hotplug.rst @@ -737,8 +737,9 @@ can process the event further. When changes to the CPUs in the system occur, the sysfs file /sys/devices/system/cpu/crash_hotplug contains '1' if the kernel -updates the kdump capture kernel list of CPUs itself (via elfcorehdr), -or '0' if userspace must update the kdump capture kernel list of CPUs. +updates the kdump capture kernel list of CPUs itself (via elfcorehdr and +other relevant kexec segment), or '0' if userspace must update the kdump +capture kernel list of CPUs. The availability depends on the CONFIG_HOTPLUG_CPU kernel configuration option. @@ -750,8 +751,9 @@ file can be used in a udev rule as follows: SUBSYSTEM=="cpu", ATTRS{crash_hotplug}=="1", GOTO="kdump_reload_end" For a CPU hot un/plug event, if the architecture supports kernel updates -of the elfcorehdr (which contains the list of CPUs), then the rule skips -the unload-then-reload of the kdump capture kernel. +of the elfcorehdr (which contains the list of CPUs) and other relevant +kexec segments, then the rule skips the unload-then-reload of the kdump +capture kernel. Kernel Inline Documentations Reference ====================================== diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 63cf89393c6e..c1048893f4b6 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -505,7 +505,7 @@ int crash_check_hotplug_support(void) crash_hotplug_lock(); /* Obtain lock while reading crash information */ if (!kexec_trylock()) { - pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n"); + pr_info("kexec_trylock() failed, kdump image may be inaccurate\n"); crash_hotplug_unlock(); return 0; } @@ -520,18 +520,25 @@ int crash_check_hotplug_support(void) } /* - * To accurately reflect hot un/plug changes of cpu and memory resources - * (including onling and offlining of those resources), the elfcorehdr - * (which is passed to the crash kernel via the elfcorehdr= parameter) - * must be updated with the new list of CPUs and memories. + * To accurately reflect hot un/plug changes of CPU and Memory resources + * (including onling and offlining of those resources), the relevant + * kexec segments must be updated with latest CPU and Memory resources. * - * In order to make changes to elfcorehdr, two conditions are needed: - * First, the segment containing the elfcorehdr must be large enough - * to permit a growing number of resources; the elfcorehdr memory size - * is based on NR_CPUS_DEFAULT and CRASH_MAX_MEMORY_RANGES. - * Second, purgatory must explicitly exclude the elfcorehdr from the - * list of segments it checks (since the elfcorehdr changes and thus - * would require an update to purgatory itself to update the digest). + * Architectures must ensure two things for all segments that need + * updating during hotplug events: + * + * 1. Segments must be large enough to accommodate a growing number of + * resources. + * 2. Exclude the segments from SHA verification. + * + * For example, on most architectures, the elfcorehdr (which is passed + * to the crash kernel via the elfcorehdr= parameter) must include the + * new list of CPUs and memory. To make changes to the elfcorehdr, it + * should be large enough to permit a growing number of CPU and Memory + * resources. One can estimate the elfcorehdr memory size based on + * NR_CPUS_DEFAULT and CRASH_MAX_MEMORY_RANGES. The elfcorehdr is + * excluded from SHA verification by default if the architecture + * supports crash hotplug. */ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu, void *arg) { @@ -540,7 +547,7 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu, crash_hotplug_lock(); /* Obtain lock while changing crash information */ if (!kexec_trylock()) { - pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n"); + pr_info("kexec_trylock() failed, kdump image may be inaccurate\n"); crash_hotplug_unlock(); return; } |