[PATCH v12 3/7] crash: add generic infrastructure for crash hotplug support

[Sourabh Jain]

Hello Eric,

On 10/09/22 02:35, Eric DeVolder wrote:
> CPU and memory change notifications are received in order to
> regenerate the elfcorehdr.
>
> To support cpu hotplug, a callback is registered to capture the
> CPUHP_AP_ONLINE_DYN online and offline events via
> cpuhp_setup_state_nocalls().
>
> To support memory hotplug, a notifier is registered to capture the
> MEM_ONLINE and MEM_OFFLINE events via register_memory_notifier().
>
> The cpu callback and memory notifiers call handle_hotplug_event()
> which performs needed tasks and then dispatches the event to the
> architecture specific arch_crash_handle_hotplug_event(). During the
> process, the kexec_mutex is held.
>
> Signed-off-by: Eric DeVolder <eric.devolder at oracle.com>
> Acked-by: Baoquan He <bhe at redhat.com>
> ---
>   include/linux/crash_core.h |   8 +++
>   include/linux/kexec.h      |  26 +++++++
>   kernel/crash_core.c        | 134 +++++++++++++++++++++++++++++++++++++
>   3 files changed, 168 insertions(+)
>
> diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
> index de62a722431e..a270f8660538 100644
> --- a/include/linux/crash_core.h
> +++ b/include/linux/crash_core.h
> @@ -84,4 +84,12 @@ int parse_crashkernel_high(char *cmdline, unsigned long long system_ram,
>   int parse_crashkernel_low(char *cmdline, unsigned long long system_ram,
>   		unsigned long long *crash_size, unsigned long long *crash_base);
>   
> +#define KEXEC_CRASH_HP_REMOVE_CPU		0
> +#define KEXEC_CRASH_HP_ADD_CPU			1
> +#define KEXEC_CRASH_HP_REMOVE_MEMORY		2
> +#define KEXEC_CRASH_HP_ADD_MEMORY		3
> +#define KEXEC_CRASH_HP_INVALID_CPU		-1U
> +
> +struct kimage;
> +
>   #endif /* LINUX_CRASH_CORE_H */
> diff --git a/include/linux/kexec.h b/include/linux/kexec.h
> index 4eefa631e0ae..9597b41136ec 100644
> --- a/include/linux/kexec.h
> +++ b/include/linux/kexec.h
> @@ -374,6 +374,13 @@ struct kimage {
>   	struct purgatory_info purgatory_info;
>   #endif
>   
> +#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_MEMORY_HOTPLUG)
> +	bool hotplug_event;
> +	unsigned int offlinecpu;
> +	bool elfcorehdr_index_valid;
> +	int elfcorehdr_index;
> +#endif
> +
>   #ifdef CONFIG_IMA_KEXEC
>   	/* Virtual address of IMA measurement buffer for kexec syscall */
>   	void *ima_buffer;
> @@ -503,6 +510,25 @@ static inline int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, g
>   static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { }
>   #endif
>   
> +#ifndef arch_map_crash_pages
> +static inline void *arch_map_crash_pages(unsigned long paddr,
> +		unsigned long size)
> +{
> +	return NULL;
> +}
> +#endif
> +
> +#ifndef arch_unmap_crash_pages
> +static inline void arch_unmap_crash_pages(void **ptr) { }
> +#endif
> +
> +#ifndef arch_crash_handle_hotplug_event
> +static inline void arch_crash_handle_hotplug_event(struct kimage *image,
> +		unsigned int hp_action)
> +{
> +}
> +#endif
> +
>   #else /* !CONFIG_KEXEC_CORE */
>   struct pt_regs;
>   struct task_struct;
> diff --git a/kernel/crash_core.c b/kernel/crash_core.c
> index 8c648fd5897a..4b15d91f0b21 100644
> --- a/kernel/crash_core.c
> +++ b/kernel/crash_core.c
> @@ -11,6 +11,8 @@
>   #include <linux/vmalloc.h>
>   #include <linux/sizes.h>
>   #include <linux/kexec.h>
> +#include <linux/memory.h>
> +#include <linux/cpuhotplug.h>
>   
>   #include <asm/page.h>
>   #include <asm/sections.h>
> @@ -18,6 +20,7 @@
>   #include <crypto/sha1.h>
>   
>   #include "kallsyms_internal.h"
> +#include "kexec_internal.h"
>   
>   /* vmcoreinfo stuff */
>   unsigned char *vmcoreinfo_data;
> @@ -612,3 +615,134 @@ static int __init crash_save_vmcoreinfo_init(void)
>   }
>   
>   subsys_initcall(crash_save_vmcoreinfo_init);
> +
> +#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_MEMORY_HOTPLUG)
> +/*
> + * To accurately reflect hot un/plug changes, the elfcorehdr (which
> + * is passed to the crash kernel via the elfcorehdr= parameter)
> + * must be updated with the new list of CPUs and memories.
> + *
> + * 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 is
> + * typically based on CONFIG_NR_CPUS and CONFIG_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).
> + */
> +static void handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
> +{
> +	/* Obtain lock while changing crash information */
> +	mutex_lock(&kexec_mutex);
> +
> +	/* Check kdump is loaded */
> +	if (kexec_crash_image) {
> +		struct kimage *image = kexec_crash_image;
> +
> +		if (hp_action == KEXEC_CRASH_HP_ADD_CPU ||
> +			hp_action == KEXEC_CRASH_HP_REMOVE_CPU)
> +			pr_debug("crash hp: hp_action %u, cpu %u\n", hp_action, cpu);
> +		else
> +			pr_debug("crash hp: hp_action %u\n", hp_action);
> +
> +		/*
> +		 * When the struct kimage is allocated, it is wiped to zero, so
> +		 * the elfcorehdr_index_valid defaults to false. Find the
> +		 * segment containing the elfcorehdr, if not already found.
> +		 * This works for both the kexec_load and kexec_file_load paths.
> +		 */
> +		if (!image->elfcorehdr_index_valid) {
> +			unsigned char *ptr;
> +			unsigned long mem, memsz;
> +			unsigned int n;
> +
> +			for (n = 0; n < image->nr_segments; n++) {
> +				mem = image->segment[n].mem;
> +				memsz = image->segment[n].memsz;
> +				ptr = arch_map_crash_pages(mem, memsz);
> +				if (ptr) {
> +					/* The segment containing elfcorehdr */
> +					if (memcmp(ptr, ELFMAG, SELFMAG) == 0) {
> +						image->elfcorehdr_index = (int)n;
> +						image->elfcorehdr_index_valid = true;
> +					}
> +				}
> +				arch_unmap_crash_pages((void **)&ptr);
> +			}
> +		}
> +
> +		if (!image->elfcorehdr_index_valid) {
> +			pr_err("crash hp: unable to locate elfcorehdr segment");
> +			goto out;
> +		}
> +
> +		/* Needed in order for the segments to be updated */
> +		arch_kexec_unprotect_crashkres();
> +
> +		/* Flag to differentiate between normal load and hotplug */
> +		image->hotplug_event = true;
> +
> +		/* Now invoke arch-specific update handler */
> +		arch_crash_handle_hotplug_event(image, hp_action);
> +
> +		/* No longer handling a hotplug event */
> +		image->hotplug_event = false;
> +
> +		/* Change back to read-only */
> +		arch_kexec_protect_crashkres();
> +	}
> +
> +out:
> +	/* Release lock now that update complete */
> +	mutex_unlock(&kexec_mutex);
> +}
> +
> +static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v)
> +{
> +	switch (val) {
> +	case MEM_ONLINE:
> +		handle_hotplug_event(KEXEC_CRASH_HP_ADD_MEMORY, 0);
> +		break;
> +
> +	case MEM_OFFLINE:
> +		handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_MEMORY, 0);
> +		break;
> +	}
> +	return NOTIFY_OK;

Can we pass v (memory_notify) argument to 
arch_crash_handle_hotplug_event function
via handle_hotplug_event?

Because the way memory hotplug is handled on PowerPC, it is hard to 
update the elfcorehdr
without memory_notify args.

On PowePC memblock data structure is used to prepare elfcorehdr for 
kdump. Since the notifier
used for memory hotplug crash handler get initiated before the memblock 
data structure update
happens (as depicted below), the newly prepared elfcorehdr still holds 
the old memory regions.
So if the system crash with obsolete elfcorehdr, makedumpfile failed to 
collect vmcore.

Sequence of actions done on PowerPC to server the memory hotplug:

  Initiate memory hot remove
           |
           v
  offline pages
           |
           v
  initiate memory notify call chain
  for MEM_OFFLINE event.
  (same is used for crash update)
           |
           v
  prepare new elfcorehdr for kdump using
  memblock data structure
           |
           v
  update memblock data structure

How passing memory_notify to arch crash hotplug handler will help?

memory_notify holds the start PFN and page count, with that we can get
the base address and size of hot unplugged memory and can use the same
to avoid hot unplugged memeory region to get added in the elfcorehdr..

Thanks,
Sourabh Jain