Re: [Bug 206401] kernel panic on Hyper-V after 5 minutes due to memory hot-add

[Oscar Salvador <osalvador@suse.de>]

On Mon, Feb 17, 2020 at 02:46:27PM +0900, kkabe@vega.pgw.jp wrote:
> ===========================================
> struct page * __meminit populate_section_memmap(unsigned long pfn,
>                 unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
> {
>         struct page *page, *ret;
>         unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
> 
>         page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
>         if (page) {
>                 goto got_map_page;
>         }
> pr_info("%s: alloc_pages() returned 0x%p (should be 0), reverting to vmalloc(memmap_size=%lu)\n", __func__, page, memmap_size);
> BUG_ON(page != 0);
> 
>         ret = vmalloc(memmap_size);
> pr_info("%s: vmalloc(%lu) returned 0x%p\n", __func__, memmap_size, ret);
>         if (ret) {
>                 goto got_map_ptr;
>         }
> 
>         return NULL;
> got_map_page:
>         ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
> pr_info("%s: allocated struct page *page=0x%p\n", __func__, page);
> got_map_ptr:
> 
> pr_info("%s: returning struct page * =0x%p\n", __func__, ret);
>         return ret;
> }

Could you please replace %p with %px. Wih the first, pointers are hashed so it is trickier
to get an overview of the meaning.

David could be right about ZONE_NORMAL vs ZONE_HIGHMEM.
IIUC, default_kernel_zone_for_pfn and default_zone_for_pfn seem to only deal with
(ZONE_DMA,ZONE_NORMAL] or ZONE_MOVABLE.
Although I really fail to see how this could cause the crash.

Could you also please capture /proc/zoneinfo before and after hotplugging memory?

And add this delta on top of your debugging patch?

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0a54ffac8c68..2b9c821d7cf0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -574,6 +574,7 @@ EXPORT_SYMBOL_GPL(restore_online_page_callback);
 
 void generic_online_page(struct page *page, unsigned int order)
 {
+       pr_info("generic_online_page: page: %px order: %u\n", page, order);
        kernel_map_pages(page, 1 << order, 1);
        __free_pages_core(page, order);
        totalram_pages_add(1UL << order);
@@ -774,6 +775,8 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
        zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages);
        move_pfn_range_to_zone(zone, pfn, nr_pages, NULL);
 
+       pr_info("%s: pfn: %lx - %lx (zone: %s)\n", __func__, pfn, pfn + nr_pages, zone->name);
+
        arg.start_pfn = pfn;
        arg.nr_pages = nr_pages;
        node_states_check_changes_online(nr_pages, zone, &arg);


-- 
Oscar Salvador
SUSE L3