crash: memory and CPU hotplug sysfs attributes

Introduce the crash_hotplug attribute for memory and CPUs for use by
userspace.  These attributes directly facilitate the udev rule for
managing userspace re-loading of the crash kernel upon hot un/plug
changes.

For memory, expose the crash_hotplug attribute to the
/sys/devices/system/memory directory.  For example:

 # udevadm info --attribute-walk /sys/devices/system/memory/memory81
  looking at device '/devices/system/memory/memory81':
    KERNEL=="memory81"
    SUBSYSTEM=="memory"
    DRIVER==""
    ATTR{online}=="1"
    ATTR{phys_device}=="0"
    ATTR{phys_index}=="00000051"
    ATTR{removable}=="1"
    ATTR{state}=="online"
    ATTR{valid_zones}=="Movable"

  looking at parent device '/devices/system/memory':
    KERNELS=="memory"
    SUBSYSTEMS==""
    DRIVERS==""
    ATTRS{auto_online_blocks}=="offline"
    ATTRS{block_size_bytes}=="8000000"
    ATTRS{crash_hotplug}=="1"

For CPUs, expose the crash_hotplug attribute to the
/sys/devices/system/cpu directory. For example:

 # udevadm info --attribute-walk /sys/devices/system/cpu/cpu0
  looking at device '/devices/system/cpu/cpu0':
    KERNEL=="cpu0"
    SUBSYSTEM=="cpu"
    DRIVER=="processor"
    ATTR{crash_notes}=="277c38600"
    ATTR{crash_notes_size}=="368"
    ATTR{online}=="1"

  looking at parent device '/devices/system/cpu':
    KERNELS=="cpu"
    SUBSYSTEMS==""
    DRIVERS==""
    ATTRS{crash_hotplug}=="1"
    ATTRS{isolated}==""
    ATTRS{kernel_max}=="8191"
    ATTRS{nohz_full}=="  (null)"
    ATTRS{offline}=="4-7"
    ATTRS{online}=="0-3"
    ATTRS{possible}=="0-7"
    ATTRS{present}=="0-3"

With these sysfs attributes in place, it is possible to efficiently
instruct the udev rule to skip crash kernel reloading for kernels
configured with crash hotplug support.

For example, the following is the proposed udev rule change for RHEL
system 98-kexec.rules (as the first lines of the rule file):

 # The kernel updates the crash elfcorehdr for CPU and memory changes
 SUBSYSTEM=="cpu", ATTRS{crash_hotplug}=="1", GOTO="kdump_reload_end"
 SUBSYSTEM=="memory", ATTRS{crash_hotplug}=="1", GOTO="kdump_reload_end"

When examined in the context of 98-kexec.rules, the above rules test if
crash_hotplug is set, and if so, the userspace initiated
unload-then-reload of the crash kernel is skipped.

CPU and memory checks are separated in accordance with CONFIG_HOTPLUG_CPU
and CONFIG_MEMORY_HOTPLUG kernel config options.  If an architecture
supports, for example, memory hotplug but not CPU hotplug, then the
/sys/devices/system/memory/crash_hotplug attribute file is present, but
the /sys/devices/system/cpu/crash_hotplug attribute file will NOT be
present.  Thus the udev rule skips userspace processing of memory hot
un/plug events, but the udev rule will evaluate false for CPU events, thus
allowing userspace to process CPU hot un/plug events (ie the
unload-then-reload of the kdump capture kernel).

Link: https://lkml.kernel.org/r/20230814214446.6659-5-eric.devolder@oracle.com
Signed-off-by: Eric DeVolder <eric.devolder@oracle.com>
Reviewed-by: Sourabh Jain <sourabhjain@linux.ibm.com>
Acked-by: Hari Bathini <hbathini@linux.ibm.com>
Acked-by: Baoquan He <bhe@redhat.com>
Cc: Akhil Raj <lf32.dev@gmail.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Mimi Zohar <zohar@linux.ibm.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Weißschuh <linux@weissschuh.net>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory
index d8b0f80b9e33cf04938e4c6908c189a1115bbc1a..a95e0f17c35ade3a8c4623160773cf6060d16feb 100644 (file)
--- a/Documentation/ABI/testing/sysfs-devices-memory
+++ b/Documentation/ABI/testing/sysfs-devices-memory
@@ -110,3 +110,11 @@ Description:
                link is created for memory section 9 on node0.
 
                /sys/devices/system/node/node0/memory9 -> ../../memory/memory9
+
+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.

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index ecd585ca2d503853e3c2e8cdfa61551be999044e..31189da7ef57607efe8a8669079552061619d503 100644 (file)
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -686,3 +686,11 @@ Description:
                (RO) the list of CPUs that are isolated and don't
                participate in load balancing. These CPUs are set by
                boot parameter "isolcpus=".
+
+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.

diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst
index 1b02fe5807cc6c67c52da9da4592d488918db3f5..eb99d79223a3ebebb483c17b250cdd901fae58c8 100644 (file)
--- a/Documentation/admin-guide/mm/memory-hotplug.rst
+++ b/Documentation/admin-guide/mm/memory-hotplug.rst
@@ -291,6 +291,14 @@ The following files are currently defined:
                       Availability depends on the CONFIG_ARCH_MEMORY_PROBE
                       kernel configuration option.
 ``uevent``            read-write: generic udev file for device subsystems.
+``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.
+
+                      Availability depends on the CONFIG_MEMORY_HOTPLUG kernel
+                      configuration option.
 ====================== =========================================================
 
 .. note::

diff --git a/Documentation/core-api/cpu_hotplug.rst b/Documentation/core-api/cpu_hotplug.rst
index e6f5bc39cf5c632a220a7614d26e97f4ca57efe9..d6d470d7dda06a3e4e36a54c49fffe96e03d43cd 100644 (file)
--- a/Documentation/core-api/cpu_hotplug.rst
+++ b/Documentation/core-api/cpu_hotplug.rst
@@ -741,6 +741,24 @@ will receive all events. A script like::
 
 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.
+
+The availability depends on the CONFIG_HOTPLUG_CPU kernel configuration
+option.
+
+To skip userspace processing of CPU hot un/plug events for kdump
+(i.e. the unload-then-reload to obtain a current list of CPUs), this sysfs
+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.
+
 Kernel Inline Documentations Reference
 ======================================
 

diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index c1815b9dae68efc6810fce4560668f612d5a0db6..c9204d69e6160b4b5ec4308886dd2b5b2ae16828 100644 (file)
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -282,6 +282,16 @@ static ssize_t print_cpus_nohz_full(struct device *dev,
 static DEVICE_ATTR(nohz_full, 0444, print_cpus_nohz_full, NULL);
 #endif
 
+#ifdef CONFIG_CRASH_HOTPLUG
+static ssize_t crash_hotplug_show(struct device *dev,
+                                    struct device_attribute *attr,
+                                    char *buf)
+{
+       return sysfs_emit(buf, "%d\n", crash_hotplug_cpu_support());
+}
+static DEVICE_ATTR_ADMIN_RO(crash_hotplug);
+#endif
+
 static void cpu_device_release(struct device *dev)
 {
        /*
@@ -469,6 +479,9 @@ static struct attribute *cpu_root_attrs[] = {
 #ifdef CONFIG_NO_HZ_FULL
        &dev_attr_nohz_full.attr,
 #endif
+#ifdef CONFIG_CRASH_HOTPLUG
+       &dev_attr_crash_hotplug.attr,
+#endif
 #ifdef CONFIG_GENERIC_CPU_AUTOPROBE
        &dev_attr_modalias.attr,
 #endif

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index b456ac21361058d1c007bdfdca5b2eed996e57aa..15bb416e58cea807763986ad5c329870b5395ddf 100644 (file)
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -490,6 +490,16 @@ static ssize_t auto_online_blocks_store(struct device *dev,
 
 static DEVICE_ATTR_RW(auto_online_blocks);
 
+#ifdef CONFIG_CRASH_HOTPLUG
+#include <linux/kexec.h>
+static ssize_t crash_hotplug_show(struct device *dev,
+                                      struct device_attribute *attr, char *buf)
+{
+       return sysfs_emit(buf, "%d\n", crash_hotplug_memory_support());
+}
+static DEVICE_ATTR_RO(crash_hotplug);
+#endif
+
 /*
  * Some architectures will have custom drivers to do this, and
  * will not need to do it from userspace.  The fake hot-add code
@@ -889,6 +899,9 @@ static struct attribute *memory_root_attrs[] = {
 
        &dev_attr_block_size_bytes.attr,
        &dev_attr_auto_online_blocks.attr,
+#ifdef CONFIG_CRASH_HOTPLUG
+       &dev_attr_crash_hotplug.attr,
+#endif
        NULL
 };
 

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index df395f888915609462b867ccdc4f564ad785ef9a..172e9a5449286428389c24e72ee29e049bba0073 100644 (file)
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -486,6 +486,14 @@ static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) {
 static inline void arch_crash_handle_hotplug_event(struct kimage *image) { }
 #endif
 
+#ifndef crash_hotplug_cpu_support
+static inline int crash_hotplug_cpu_support(void) { return 0; }
+#endif
+
+#ifndef crash_hotplug_memory_support
+static inline int crash_hotplug_memory_support(void) { return 0; }
+#endif
+
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;