Re: [PATCH v20 2/8] crash: add generic infrastructure for crash hotplug support

[Eric DeVolder]

On 3/20/23 03:13, Baoquan He wrote:
> On 03/17/23 at 05:21pm, Eric DeVolder wrote:
> ......
> > @@ -697,3 +700,137 @@ static int __init crash_save_vmcoreinfo_init(void)
> >   }
> >   
> >   subsys_initcall(crash_save_vmcoreinfo_init);
> > +
> > +#ifdef CONFIG_CRASH_HOTPLUG
> > +#undef pr_fmt
> > +#define pr_fmt(fmt) "crash hp: " fmt
> > +/*
> > + * 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.
> > + *
> > + * 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).
> > + */
> > +static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
> > +{
> > +	/* Obtain lock while changing crash information */
> > +	if (!kexec_trylock())
> > +		return;
> > +
> > +	/* Check kdump is loaded */
> > +	if (kexec_crash_image) {
>
> Here, what I mean is:
>
> 	/* Obtain lock while changing crash information */
> 	if (!kexec_trylock())
> 		return;
>
> 	/*If kdump is not loaded*/
> 	if (!kexec_crash_image)
> 		goto out;	
>
> Then we reduce one tab of indentation for the following code block, e.g
> the for loop block will have smaller pressure on breaking the 80 chars
> limitation.

Ah, yes, ok. I'll make that change. Do you prefer I post that soon, or give this v20 some more time?
eric

> > +		struct kimage *image = kexec_crash_image;
> > +
> > +		if (hp_action == KEXEC_CRASH_HP_ADD_CPU ||
> > +			hp_action == KEXEC_CRASH_HP_REMOVE_CPU)
> > +			pr_debug("hp_action %u, cpu %u\n", hp_action, cpu);
> > +		else
> > +			pr_debug("hp_action %u\n", hp_action);
> > +
> > +		/*
> > +		 * When the struct kimage is allocated, the elfcorehdr_index
> > +		 * is set to -1. 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 < 0) {
> > +			unsigned long mem;
> > +			unsigned char *ptr;
> > +			unsigned int n;
> > +
> > +			for (n = 0; n < image->nr_segments; n++) {
> > +				mem = image->segment[n].mem;
> > +				ptr = kmap_local_page(pfn_to_page(mem >> PAGE_SHIFT));
> > +				if (ptr) {
> > +					/* The segment containing elfcorehdr */
> > +					if (memcmp(ptr, ELFMAG, SELFMAG) == 0)
> > +						image->elfcorehdr_index = (int)n;
> > +					kunmap_local(ptr);
> > +				}
> > +			}
> > +		}
> > +
> > +		if (image->elfcorehdr_index < 0) {
> > +			pr_err("unable to locate elfcorehdr segment");
> > +			goto out;
> > +		}
> > +
> > +		/* Needed in order for the segments to be updated */
> > +		arch_kexec_unprotect_crashkres();
> > +
> > +		/* Differentiate between normal load and hotplug update */
> > +		image->hp_action = hp_action;
> > +
> > +		/* Now invoke arch-specific update handler */
> > +		arch_crash_handle_hotplug_event(image);
> > +
> > +		/* No longer handling a hotplug event */
> > +		image->hp_action = KEXEC_CRASH_HP_NONE;
> > +		image->elfcorehdr_updated = true;
> > +
> > +		/* Change back to read-only */
> > +		arch_kexec_protect_crashkres();
> > +	}
> > +
> > +out:
> > +	/* Release lock now that update complete */
> > +	kexec_unlock();
> > +}
> > +
> > +static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v)
> > +{
> > +	switch (val) {
> > +	case MEM_ONLINE:
> > +		crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_MEMORY,
> > +			KEXEC_CRASH_HP_INVALID_CPU);
> > +		break;
> > +
> > +	case MEM_OFFLINE:
> > +		crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_MEMORY,
> > +			KEXEC_CRASH_HP_INVALID_CPU);
> > +		break;
> > +	}
> > +	return NOTIFY_OK;
> > +}
> > +
> > +static struct notifier_block crash_memhp_nb = {
> > +	.notifier_call = crash_memhp_notifier,
> > +	.priority = 0
> > +};
> > +
> > +static int crash_cpuhp_online(unsigned int cpu)
> > +{
> > +	crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu);
> > +	return 0;
> > +}
> > +
> > +static int crash_cpuhp_offline(unsigned int cpu)
> > +{
> > +	crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu);
> > +	return 0;
> > +}
> > +
> > +static int __init crash_hotplug_init(void)
> > +{
> > +	int result = 0;
> > +
> > +	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
> > +		register_memory_notifier(&crash_memhp_nb);
> > +
> > +	if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
> > +		result = cpuhp_setup_state_nocalls(CPUHP_BP_PREPARE_DYN,
> > +			"crash/cpuhp", crash_cpuhp_online, crash_cpuhp_offline);
> > +	}
> > +
> > +	return result;
> > +}
> > +
> > +subsys_initcall(crash_hotplug_init);
> > +#endif
> > diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
> > index 3d578c6fefee..8296d019737c 100644
> > --- a/kernel/kexec_core.c
> > +++ b/kernel/kexec_core.c
> > @@ -277,6 +277,12 @@ struct kimage *do_kimage_alloc_init(void)
> >   	/* Initialize the list of unusable pages */
> >   	INIT_LIST_HEAD(&image->unusable_pages);
> >   
> > +#ifdef CONFIG_CRASH_HOTPLUG
> > +	image->hp_action = KEXEC_CRASH_HP_NONE;
> > +	image->elfcorehdr_index = -1;
> > +	image->elfcorehdr_updated = false;
> > +#endif
> > +
> >   	return image;
> >   }
> >   
> > --
> > 2.31.1