Re: kernel BUG at include/linux/mm.h:1020!

[Oscar Salvador <osalvador@suse.de>]

On Fri, Mar 22, 2019 at 09:55:16AM +0100, Oscar Salvador wrote:
> On Fri, Mar 22, 2019 at 12:54:01PM +0500, Mikhail Gavrilov wrote:
> > On Fri, 22 Mar 2019 at 12:39, Oscar Salvador <osalvador@suse.de> wrote:
> > >
> > > do you happen to have your config at hand?
> > > Could you share it please?
> > >
> > 
> > https://pastebin.com/4idrLvJQ
> 
> Thanks, could you boot up with below patch and send back the log please?

I mean to send back the log once you trigger the issue again.

> 
> diff --git a/mm/debug.c b/mm/debug.c
> index 1611cf00a137..31f71517b0fb 100644
> --- a/mm/debug.c
> +++ b/mm/debug.c
> @@ -54,7 +54,12 @@ void __dump_page(struct page *page, const char *reason)
>  	 * dump_page() when detected.
>  	 */
>  	if (page_poisoned) {
> -		pr_warn("page:%px is uninitialized and poisoned", page);
> +		unsigned long pfn = page_to_pfn(page);
> +		unsigned long section_nr = pfn_to_section_nr(pfn);
> +		bool online = online_section(__nr_to_section(section_nr));
> +
> +		pr_warn("page:%px (pfn: %lx section: %ld online: %d)is uninitialized and poisoned",
> +								page, pfn, section_nr, online);
>  		goto hex_only;
>  	}
>  
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 3eb01dedfb50..a7b54c5995a6 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -1324,6 +1324,7 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
>  {
>  	unsigned long start_pfn = PFN_DOWN(start);
>  	unsigned long end_pfn = PFN_UP(end);
> +	unsigned long __pfn = start_pfn;
>  
>  	for (; start_pfn < end_pfn; start_pfn++) {
>  		if (pfn_valid(start_pfn)) {
> @@ -1342,6 +1343,7 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
>  			__SetPageReserved(page);
>  		}
>  	}
> +	pr_info("%s: %lx - %lx init\n", __func__, __pfn, end_pfn - 1);
>  }
>  
>  static void __free_pages_ok(struct page *page, unsigned int order)
> @@ -1617,6 +1619,7 @@ static unsigned long  __init deferred_init_pages(int nid, int zid,
>  	unsigned long nr_pgmask = pageblock_nr_pages - 1;
>  	unsigned long nr_pages = 0;
>  	struct page *page = NULL;
> +	unsigned long start_pfn = pfn;
>  
>  	for (; pfn < end_pfn; pfn++) {
>  		if (!deferred_pfn_valid(nid, pfn, &nid_init_state)) {
> @@ -1631,6 +1634,8 @@ static unsigned long  __init deferred_init_pages(int nid, int zid,
>  		__init_single_page(page, pfn, zid, nid);
>  		nr_pages++;
>  	}
> +
> +	pr_info("%s: pfn: %lx - %lx init\n", __func__, start_pfn, end_pfn - 1);
>  	return (nr_pages);
>  }
>  
> @@ -5748,10 +5753,14 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
>  		 * function.  They do not exist on hotplugged memory.
>  		 */
>  		if (context == MEMMAP_EARLY) {
> -			if (!early_pfn_valid(pfn))
> +			if (!early_pfn_valid(pfn)) {
> +				pr_info("%s: skipping: %lx\n", __func__, pfn);
>  				continue;
> -			if (!early_pfn_in_nid(pfn, nid))
> +			}
> +			if (!early_pfn_in_nid(pfn, nid)) {
> +				pr_info("%s: skipping: %lx\n", __func__, pfn);
>  				continue;
> +			}
>  			if (overlap_memmap_init(zone, &pfn))
>  				continue;
>  			if (defer_init(nid, pfn, end_pfn))
> @@ -5780,6 +5789,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
>  			cond_resched();
>  		}
>  	}
> +	pr_info("%s: pfn: %lx - %lx init\n", __func__, start_pfn, end_pfn - 1);
>  }
>  
>  #ifdef CONFIG_ZONE_DEVICE
> @@ -5852,6 +5862,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
>  		}
>  	}
>  
> +	pr_info("%s: %lx - %lx init\n", __func__, start_pfn, end_pfn - 1);
>  	pr_info("%s initialised, %lu pages in %ums\n", dev_name(pgmap->dev),
>  		size, jiffies_to_msecs(jiffies - start));
>  }
> @@ -6651,6 +6662,8 @@ static void __init free_area_init_core(struct pglist_data *pgdat)
>  		setup_usemap(pgdat, zone, zone_start_pfn, size);
>  		init_currently_empty_zone(zone, zone_start_pfn, size);
>  		memmap_init(size, nid, j, zone_start_pfn);
> +		pr_info("%s: zone: %s zone: %lx - %lx\n",
> +			__func__, zone->name, zone_start_pfn, zone_end_pfn(zone));
>  	}
>  }
>  
> @@ -6765,6 +6778,8 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn)
>  		pgcnt++;
>  	}
>  
> +	pr_info("%s: %lx - %lx zeroed\n", __func__, spfn, epfn - 1);
> +
>  	return pgcnt;
>  }
> 
> -- 
> Oscar Salvador
> SUSE L3
> 

-- 
Oscar Salvador
SUSE L3