From: Mike Rapoport <rppt@xxxxxxxxxxxxx> commit d3921cb8be29ce5668c64e23ffdaeec5f8c69399 upstream. There could be struct pages that are not backed by actual physical memory. This can happen when the actual memory bank is not a multiple of SECTION_SIZE or when an architecture does not register memory holes reserved by the firmware as memblock.memory. Such pages are currently initialized using init_unavailable_mem() function that iterates through PFNs in holes in memblock.memory and if there is a struct page corresponding to a PFN, the fields if this page are set to default values and the page is marked as Reserved. init_unavailable_mem() does not take into account zone and node the page belongs to and sets both zone and node links in struct page to zero. On a system that has firmware reserved holes in a zone above ZONE_DMA, for instance in a configuration below: # grep -A1 E820 /proc/iomem 7a17b000-7a216fff : Unknown E820 type 7a217000-7bffffff : System RAM unset zone link in struct page will trigger VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page); because there are pages in both ZONE_DMA32 and ZONE_DMA (unset zone link in struct page) in the same pageblock. Update init_unavailable_mem() to use zone constraints defined by an architecture to properly setup the zone link and use node ID of the adjacent range in memblock.memory to set the node link. Link: https://lkml.kernel.org/r/20210111194017.22696-3-rppt@xxxxxxxxxx Fixes: 73a6e474cb37 ("mm: memmap_init: iterate over memblock regions rather that check each PFN") Signed-off-by: Mike Rapoport <rppt@xxxxxxxxxxxxx> Reported-by: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Baoquan He <bhe@xxxxxxxxxx> Cc: Borislav Petkov <bp@xxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: "H. Peter Anvin" <hpa@xxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxxxxx> Cc: Mel Gorman <mgorman@xxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxxxx> Cc: Qian Cai <cai@xxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Vlastimil Babka <vbabka@xxxxxxx> Cc: <stable@xxxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- mm/page_alloc.c | 84 +++++++++++++++++++++++++++++++++----------------------- 1 file changed, 50 insertions(+), 34 deletions(-) --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7003,23 +7003,26 @@ void __init free_area_init_memoryless_no * Initialize all valid struct pages in the range [spfn, epfn) and mark them * PageReserved(). Return the number of struct pages that were initialized. */ -static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn) +static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn, + int zone, int nid) { - unsigned long pfn; + unsigned long pfn, zone_spfn, zone_epfn; u64 pgcnt = 0; + zone_spfn = arch_zone_lowest_possible_pfn[zone]; + zone_epfn = arch_zone_highest_possible_pfn[zone]; + + spfn = clamp(spfn, zone_spfn, zone_epfn); + epfn = clamp(epfn, zone_spfn, zone_epfn); + for (pfn = spfn; pfn < epfn; pfn++) { if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) { pfn = ALIGN_DOWN(pfn, pageblock_nr_pages) + pageblock_nr_pages - 1; continue; } - /* - * Use a fake node/zone (0) for now. Some of these pages - * (in memblock.reserved but not in memblock.memory) will - * get re-initialized via reserve_bootmem_region() later. - */ - __init_single_page(pfn_to_page(pfn), pfn, 0, 0); + + __init_single_page(pfn_to_page(pfn), pfn, zone, nid); __SetPageReserved(pfn_to_page(pfn)); pgcnt++; } @@ -7028,51 +7031,64 @@ static u64 __init init_unavailable_range } /* - * Only struct pages that are backed by physical memory are zeroed and - * initialized by going through __init_single_page(). But, there are some - * struct pages which are reserved in memblock allocator and their fields - * may be accessed (for example page_to_pfn() on some configuration accesses - * flags). We must explicitly initialize those struct pages. + * Only struct pages that correspond to ranges defined by memblock.memory + * are zeroed and initialized by going through __init_single_page() during + * memmap_init(). * - * This function also addresses a similar issue where struct pages are left - * uninitialized because the physical address range is not covered by - * memblock.memory or memblock.reserved. That could happen when memblock - * layout is manually configured via memmap=, or when the highest physical - * address (max_pfn) does not end on a section boundary. + * But, there could be struct pages that correspond to holes in + * memblock.memory. This can happen because of the following reasons: + * - phyiscal memory bank size is not necessarily the exact multiple of the + * arbitrary section size + * - early reserved memory may not be listed in memblock.memory + * - memory layouts defined with memmap= kernel parameter may not align + * nicely with memmap sections + * + * Explicitly initialize those struct pages so that: + * - PG_Reserved is set + * - zone link is set accorging to the architecture constrains + * - node is set to node id of the next populated region except for the + * trailing hole where last node id is used */ -static void __init init_unavailable_mem(void) +static void __init init_zone_unavailable_mem(int zone) { - phys_addr_t start, end; - u64 i, pgcnt; - phys_addr_t next = 0; + unsigned long start, end; + int i, nid; + u64 pgcnt; + unsigned long next = 0; /* - * Loop through unavailable ranges not covered by memblock.memory. + * Loop through holes in memblock.memory and initialize struct + * pages corresponding to these holes */ pgcnt = 0; - for_each_mem_range(i, &start, &end) { + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { if (next < start) - pgcnt += init_unavailable_range(PFN_DOWN(next), - PFN_UP(start)); + pgcnt += init_unavailable_range(next, start, zone, nid); next = end; } /* - * Early sections always have a fully populated memmap for the whole - * section - see pfn_valid(). If the last section has holes at the - * end and that section is marked "online", the memmap will be - * considered initialized. Make sure that memmap has a well defined - * state. + * Last section may surpass the actual end of memory (e.g. we can + * have 1Gb section and 512Mb of RAM pouplated). + * Make sure that memmap has a well defined state in this case. */ - pgcnt += init_unavailable_range(PFN_DOWN(next), - round_up(max_pfn, PAGES_PER_SECTION)); + end = round_up(max_pfn, PAGES_PER_SECTION); + pgcnt += init_unavailable_range(next, end, zone, nid); /* * Struct pages that do not have backing memory. This could be because * firmware is using some of this memory, or for some other reasons. */ if (pgcnt) - pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); + pr_info("Zone %s: zeroed struct page in unavailable ranges: %lld pages", zone_names[zone], pgcnt); +} + +static void __init init_unavailable_mem(void) +{ + int zone; + + for (zone = 0; zone < ZONE_MOVABLE; zone++) + init_zone_unavailable_mem(zone); } #else static inline void __init init_unavailable_mem(void)
