This patch introduces a generic crash hot plug/unplug infrastructure
for CPU and memory changes. Upon CPU and memory changes, a generic
crash_hotplug_handler() obtains the appropriate lock, does some
important house keeping and then dispatches the hot plug/unplug event
to the architecture specific arch_crash_hotplug_handler(), and when
that handler returns, the lock is released.
This patch modifies crash_core.c to implement a subsys_initcall()
function that installs handlers for hot plug/unplug events. If CPU
hotplug is enabled, then cpuhp_setup_state() is invoked to register a
handler for CPU changes. Similarly, if memory hotplug is enabled, then
register_memory_notifier() is invoked to install a handler for memory
changes. These handlers in turn invoke the common generic handler
crash_hotplug_handler().
On the CPU side, cpuhp_setup_state_nocalls() is invoked with parameter
CPUHP_AP_ONLINE_DYN. While this works, when a CPU is being unplugged,
the CPU still shows up in foreach_present_cpu() during the regeneration
of the new CPU list, thus the need to explicitly check and exclude the
soon-to-be offlined CPU in crash_prepare_elf64_headers().
On the memory side, each un/plugged memory block passes through the
handler. For example, if a 1GiB DIMM is hotplugged, that generate 8
memory events, one for each 128MiB memblock.
Signed-off-by: Eric DeVolder <[email protected]>
---
kernel/crash_core.c | 104 ++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 104 insertions(+)
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 0ff06d0698ad..524470e18883 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -10,12 +10,16 @@
#include <linux/utsname.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
+#include <linux/memory.h>
+#include <linux/cpuhotplug.h>
#include <asm/page.h>
#include <asm/sections.h>
#include <crypto/sha1.h>
+#include "kexec_internal.h"
+
/* vmcoreinfo stuff */
unsigned char *vmcoreinfo_data;
size_t vmcoreinfo_size;
@@ -521,5 +525,105 @@ void unmap_crash_pages(void **ptr)
*ptr = NULL;
}
}
+
+void __weak arch_crash_hotplug_handler(struct kimage *image,
+ unsigned int hp_action, unsigned long a, unsigned long b)
+{
+ pr_warn("crash hp: %s not implemented", __func__);
+}
+
+static void crash_hotplug_handler(unsigned int hp_action,
+ unsigned long a, unsigned long b)
+{
+ /* Obtain lock while changing crash information */
+ if (!mutex_trylock(&kexec_mutex))
+ return;
+
+ /* Check kdump is loaded */
+ if (kexec_crash_image) {
+ pr_debug("crash hp: hp_action %u, a %lu, b %lu", hp_action,
+ a, b);
+
+ /* Needed in order for the segments to be updated */
+ arch_kexec_unprotect_crashkres();
+
+ /* Flag to differentiate between normal load and hotplug */
+ kexec_crash_image->hotplug_event = true;
+
+ /* Now invoke arch-specific update handler */
+ arch_crash_hotplug_handler(kexec_crash_image, hp_action, a, b);
+
+ /* No longer handling a hotplug event */
+ kexec_crash_image->hotplug_event = false;
+
+ /* Change back to read-only */
+ arch_kexec_protect_crashkres();
+ }
+
+ /* Release lock now that update complete */
+ mutex_unlock(&kexec_mutex);
+}
+
+#if defined(CONFIG_MEMORY_HOTPLUG)
+static int crash_memhp_notifier(struct notifier_block *nb,
+ unsigned long val, void *v)
+{
+ struct memory_notify *mhp = v;
+ unsigned long start, end;
+
+ start = mhp->start_pfn << PAGE_SHIFT;
+ end = ((mhp->start_pfn + mhp->nr_pages) << PAGE_SHIFT) - 1;
+
+ switch (val) {
+ case MEM_ONLINE:
+ crash_hotplug_handler(KEXEC_CRASH_HP_ADD_MEMORY,
+ start, end-start);
+ break;
+
+ case MEM_OFFLINE:
+ crash_hotplug_handler(KEXEC_CRASH_HP_REMOVE_MEMORY,
+ start, end-start);
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block crash_memhp_nb = {
+ .notifier_call = crash_memhp_notifier,
+ .priority = 0
+};
#endif
+#if defined(CONFIG_HOTPLUG_CPU)
+static int crash_cpuhp_online(unsigned int cpu)
+{
+ crash_hotplug_handler(KEXEC_CRASH_HP_ADD_CPU, cpu, 0);
+ return 0;
+}
+
+static int crash_cpuhp_offline(unsigned int cpu)
+{
+ crash_hotplug_handler(KEXEC_CRASH_HP_REMOVE_CPU, cpu, 0);
+ return 0;
+}
+#endif
+
+static int __init crash_hotplug_init(void)
+{
+ int result = 0;
+
+#if defined(CONFIG_MEMORY_HOTPLUG)
+ register_memory_notifier(&crash_memhp_nb);
+#endif
+
+#if defined(CONFIG_HOTPLUG_CPU)
+ result = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+ "crash/cpuhp",
+ crash_cpuhp_online, crash_cpuhp_offline);
+#endif
+
+ return result;
+}
+
+subsys_initcall(crash_hotplug_init);
+#endif /* CONFIG_CRASH_HOTPLUG */
--
2.27.0
On 02/09/22 at 02:57pm, Eric DeVolder wrote:
> This patch introduces a generic crash hot plug/unplug infrastructure
> for CPU and memory changes. Upon CPU and memory changes, a generic
> crash_hotplug_handler() obtains the appropriate lock, does some
> important house keeping and then dispatches the hot plug/unplug event
> to the architecture specific arch_crash_hotplug_handler(), and when
> that handler returns, the lock is released.
>
> This patch modifies crash_core.c to implement a subsys_initcall()
> function that installs handlers for hot plug/unplug events. If CPU
> hotplug is enabled, then cpuhp_setup_state() is invoked to register a
> handler for CPU changes. Similarly, if memory hotplug is enabled, then
> register_memory_notifier() is invoked to install a handler for memory
> changes. These handlers in turn invoke the common generic handler
> crash_hotplug_handler().
>
> On the CPU side, cpuhp_setup_state_nocalls() is invoked with parameter
> CPUHP_AP_ONLINE_DYN. While this works, when a CPU is being unplugged,
> the CPU still shows up in foreach_present_cpu() during the regeneration
> of the new CPU list, thus the need to explicitly check and exclude the
> soon-to-be offlined CPU in crash_prepare_elf64_headers().
>
> On the memory side, each un/plugged memory block passes through the
> handler. For example, if a 1GiB DIMM is hotplugged, that generate 8
> memory events, one for each 128MiB memblock.
This looks good to me. As I commented in patch 3, these both may need be
merged.
>
> Signed-off-by: Eric DeVolder <[email protected]>
> ---
> kernel/crash_core.c | 104 ++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 104 insertions(+)
>
> diff --git a/kernel/crash_core.c b/kernel/crash_core.c
> index 0ff06d0698ad..524470e18883 100644
> --- a/kernel/crash_core.c
> +++ b/kernel/crash_core.c
> @@ -10,12 +10,16 @@
> #include <linux/utsname.h>
> #include <linux/vmalloc.h>
> #include <linux/highmem.h>
> +#include <linux/memory.h>
> +#include <linux/cpuhotplug.h>
>
> #include <asm/page.h>
> #include <asm/sections.h>
>
> #include <crypto/sha1.h>
>
> +#include "kexec_internal.h"
> +
> /* vmcoreinfo stuff */
> unsigned char *vmcoreinfo_data;
> size_t vmcoreinfo_size;
> @@ -521,5 +525,105 @@ void unmap_crash_pages(void **ptr)
> *ptr = NULL;
> }
> }
> +
> +void __weak arch_crash_hotplug_handler(struct kimage *image,
> + unsigned int hp_action, unsigned long a, unsigned long b)
> +{
> + pr_warn("crash hp: %s not implemented", __func__);
> +}
> +
> +static void crash_hotplug_handler(unsigned int hp_action,
> + unsigned long a, unsigned long b)
> +{
> + /* Obtain lock while changing crash information */
> + if (!mutex_trylock(&kexec_mutex))
> + return;
> +
> + /* Check kdump is loaded */
> + if (kexec_crash_image) {
> + pr_debug("crash hp: hp_action %u, a %lu, b %lu", hp_action,
> + a, b);
> +
> + /* Needed in order for the segments to be updated */
> + arch_kexec_unprotect_crashkres();
> +
> + /* Flag to differentiate between normal load and hotplug */
> + kexec_crash_image->hotplug_event = true;
> +
> + /* Now invoke arch-specific update handler */
> + arch_crash_hotplug_handler(kexec_crash_image, hp_action, a, b);
> +
> + /* No longer handling a hotplug event */
> + kexec_crash_image->hotplug_event = false;
> +
> + /* Change back to read-only */
> + arch_kexec_protect_crashkres();
> + }
> +
> + /* Release lock now that update complete */
> + mutex_unlock(&kexec_mutex);
> +}
> +
> +#if defined(CONFIG_MEMORY_HOTPLUG)
> +static int crash_memhp_notifier(struct notifier_block *nb,
> + unsigned long val, void *v)
> +{
> + struct memory_notify *mhp = v;
> + unsigned long start, end;
> +
> + start = mhp->start_pfn << PAGE_SHIFT;
> + end = ((mhp->start_pfn + mhp->nr_pages) << PAGE_SHIFT) - 1;
> +
> + switch (val) {
> + case MEM_ONLINE:
> + crash_hotplug_handler(KEXEC_CRASH_HP_ADD_MEMORY,
> + start, end-start);
> + break;
> +
> + case MEM_OFFLINE:
> + crash_hotplug_handler(KEXEC_CRASH_HP_REMOVE_MEMORY,
> + start, end-start);
> + break;
> + }
> + return NOTIFY_OK;
> +}
> +
> +static struct notifier_block crash_memhp_nb = {
> + .notifier_call = crash_memhp_notifier,
> + .priority = 0
> +};
> #endif
>
> +#if defined(CONFIG_HOTPLUG_CPU)
> +static int crash_cpuhp_online(unsigned int cpu)
> +{
> + crash_hotplug_handler(KEXEC_CRASH_HP_ADD_CPU, cpu, 0);
> + return 0;
> +}
> +
> +static int crash_cpuhp_offline(unsigned int cpu)
> +{
> + crash_hotplug_handler(KEXEC_CRASH_HP_REMOVE_CPU, cpu, 0);
> + return 0;
> +}
> +#endif
> +
> +static int __init crash_hotplug_init(void)
> +{
> + int result = 0;
> +
> +#if defined(CONFIG_MEMORY_HOTPLUG)
> + register_memory_notifier(&crash_memhp_nb);
> +#endif
> +
> +#if defined(CONFIG_HOTPLUG_CPU)
> + result = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
> + "crash/cpuhp",
> + crash_cpuhp_online, crash_cpuhp_offline);
> +#endif
> +
> + return result;
> +}
> +
> +subsys_initcall(crash_hotplug_init);
> +#endif /* CONFIG_CRASH_HOTPLUG */
> --
> 2.27.0
>
On 2/22/22 21:59, Baoquan He wrote:
> On 02/09/22 at 02:57pm, Eric DeVolder wrote:
>> This patch introduces a generic crash hot plug/unplug infrastructure
>> for CPU and memory changes. Upon CPU and memory changes, a generic
>> crash_hotplug_handler() obtains the appropriate lock, does some
>> important house keeping and then dispatches the hot plug/unplug event
>> to the architecture specific arch_crash_hotplug_handler(), and when
>> that handler returns, the lock is released.
>>
>> This patch modifies crash_core.c to implement a subsys_initcall()
>> function that installs handlers for hot plug/unplug events. If CPU
>> hotplug is enabled, then cpuhp_setup_state() is invoked to register a
>> handler for CPU changes. Similarly, if memory hotplug is enabled, then
>> register_memory_notifier() is invoked to install a handler for memory
>> changes. These handlers in turn invoke the common generic handler
>> crash_hotplug_handler().
>>
>> On the CPU side, cpuhp_setup_state_nocalls() is invoked with parameter
>> CPUHP_AP_ONLINE_DYN. While this works, when a CPU is being unplugged,
>> the CPU still shows up in foreach_present_cpu() during the regeneration
>> of the new CPU list, thus the need to explicitly check and exclude the
>> soon-to-be offlined CPU in crash_prepare_elf64_headers().
>>
>> On the memory side, each un/plugged memory block passes through the
>> handler. For example, if a 1GiB DIMM is hotplugged, that generate 8
>> memory events, one for each 128MiB memblock.
>
> This looks good to me. As I commented in patch 3, these both may need be
> merged.
OK, merged with 3.
eric
>
>>
>> Signed-off-by: Eric DeVolder <[email protected]>
>> ---
>> kernel/crash_core.c | 104 ++++++++++++++++++++++++++++++++++++++++++++
>> 1 file changed, 104 insertions(+)
>>
>> diff --git a/kernel/crash_core.c b/kernel/crash_core.c
>> index 0ff06d0698ad..524470e18883 100644
>> --- a/kernel/crash_core.c
>> +++ b/kernel/crash_core.c
>> @@ -10,12 +10,16 @@
>> #include <linux/utsname.h>
>> #include <linux/vmalloc.h>
>> #include <linux/highmem.h>
>> +#include <linux/memory.h>
>> +#include <linux/cpuhotplug.h>
>>
>> #include <asm/page.h>
>> #include <asm/sections.h>
>>
>> #include <crypto/sha1.h>
>>
>> +#include "kexec_internal.h"
>> +
>> /* vmcoreinfo stuff */
>> unsigned char *vmcoreinfo_data;
>> size_t vmcoreinfo_size;
>> @@ -521,5 +525,105 @@ void unmap_crash_pages(void **ptr)
>> *ptr = NULL;
>> }
>> }
>> +
>> +void __weak arch_crash_hotplug_handler(struct kimage *image,
>> + unsigned int hp_action, unsigned long a, unsigned long b)
>> +{
>> + pr_warn("crash hp: %s not implemented", __func__);
>> +}
>> +
>> +static void crash_hotplug_handler(unsigned int hp_action,
>> + unsigned long a, unsigned long b)
>> +{
>> + /* Obtain lock while changing crash information */
>> + if (!mutex_trylock(&kexec_mutex))
>> + return;
>> +
>> + /* Check kdump is loaded */
>> + if (kexec_crash_image) {
>> + pr_debug("crash hp: hp_action %u, a %lu, b %lu", hp_action,
>> + a, b);
>> +
>> + /* Needed in order for the segments to be updated */
>> + arch_kexec_unprotect_crashkres();
>> +
>> + /* Flag to differentiate between normal load and hotplug */
>> + kexec_crash_image->hotplug_event = true;
>> +
>> + /* Now invoke arch-specific update handler */
>> + arch_crash_hotplug_handler(kexec_crash_image, hp_action, a, b);
>> +
>> + /* No longer handling a hotplug event */
>> + kexec_crash_image->hotplug_event = false;
>> +
>> + /* Change back to read-only */
>> + arch_kexec_protect_crashkres();
>> + }
>> +
>> + /* Release lock now that update complete */
>> + mutex_unlock(&kexec_mutex);
>> +}
>> +
>> +#if defined(CONFIG_MEMORY_HOTPLUG)
>> +static int crash_memhp_notifier(struct notifier_block *nb,
>> + unsigned long val, void *v)
>> +{
>> + struct memory_notify *mhp = v;
>> + unsigned long start, end;
>> +
>> + start = mhp->start_pfn << PAGE_SHIFT;
>> + end = ((mhp->start_pfn + mhp->nr_pages) << PAGE_SHIFT) - 1;
>> +
>> + switch (val) {
>> + case MEM_ONLINE:
>> + crash_hotplug_handler(KEXEC_CRASH_HP_ADD_MEMORY,
>> + start, end-start);
>> + break;
>> +
>> + case MEM_OFFLINE:
>> + crash_hotplug_handler(KEXEC_CRASH_HP_REMOVE_MEMORY,
>> + start, end-start);
>> + break;
>> + }
>> + return NOTIFY_OK;
>> +}
>> +
>> +static struct notifier_block crash_memhp_nb = {
>> + .notifier_call = crash_memhp_notifier,
>> + .priority = 0
>> +};
>> #endif
>>
>> +#if defined(CONFIG_HOTPLUG_CPU)
>> +static int crash_cpuhp_online(unsigned int cpu)
>> +{
>> + crash_hotplug_handler(KEXEC_CRASH_HP_ADD_CPU, cpu, 0);
>> + return 0;
>> +}
>> +
>> +static int crash_cpuhp_offline(unsigned int cpu)
>> +{
>> + crash_hotplug_handler(KEXEC_CRASH_HP_REMOVE_CPU, cpu, 0);
>> + return 0;
>> +}
>> +#endif
>> +
>> +static int __init crash_hotplug_init(void)
>> +{
>> + int result = 0;
>> +
>> +#if defined(CONFIG_MEMORY_HOTPLUG)
>> + register_memory_notifier(&crash_memhp_nb);
>> +#endif
>> +
>> +#if defined(CONFIG_HOTPLUG_CPU)
>> + result = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
>> + "crash/cpuhp",
>> + crash_cpuhp_online, crash_cpuhp_offline);
>> +#endif
>> +
>> + return result;
>> +}
>> +
>> +subsys_initcall(crash_hotplug_init);
>> +#endif /* CONFIG_CRASH_HOTPLUG */
>> --
>> 2.27.0
>>
>