From: Mike Rapoport <rppt@xxxxxxxxxxxxx> commit 122e093c1734361dedb64f65c99b93e28e4624f4 upstream. On systems with memory nodes sorted in descending order, for instance Dell Precision WorkStation T5500, the struct pages for higher PFNs and respectively lower nodes, could be overwritten by the initialization of struct pages corresponding to the holes in the memory sections. For example for the below memory layout [ 0.245624] Early memory node ranges [ 0.248496] node 1: [mem 0x0000000000001000-0x0000000000090fff] [ 0.251376] node 1: [mem 0x0000000000100000-0x00000000dbdf8fff] [ 0.254256] node 1: [mem 0x0000000100000000-0x0000001423ffffff] [ 0.257144] node 0: [mem 0x0000001424000000-0x0000002023ffffff] the range 0x1424000000 - 0x1428000000 in the beginning of node 0 starts in the middle of a section and will be considered as a hole during the initialization of the last section in node 1. The wrong initialization of the memory map causes panic on boot when CONFIG_DEBUG_VM is enabled. Reorder loop order of the memory map initialization so that the outer loop will always iterate over populated memory regions in the ascending order and the inner loop will select the zone corresponding to the PFN range. This way initialization of the struct pages for the memory holes will be always done for the ranges that are actually not populated. [akpm@xxxxxxxxxxxxxxxxxxxx: coding style fixes] Link: https://lkml.kernel.org/r/YNXlMqBbL+tBG7yq@xxxxxxxxxx Link: https://bugzilla.kernel.org/show_bug.cgi?id=213073 Link: https://lkml.kernel.org/r/20210624062305.10940-1-rppt@xxxxxxxxxx Fixes: 0740a50b9baa ("mm/page_alloc.c: refactor initialization of struct page for holes in memory layout") Signed-off-by: Mike Rapoport <rppt@xxxxxxxxxxxxx> Cc: Boris Petkov <bp@xxxxxxxxx> Cc: Robert Shteynfeld <robert.shteynfeld@xxxxxxxxx> Cc: Baoquan He <bhe@xxxxxxxxxx> Cc: Vlastimil Babka <vbabka@xxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> 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 | 100 +++++++++++++++++++++++++++++++++----------------------- 1 file changed, 60 insertions(+), 40 deletions(-) --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6129,7 +6129,7 @@ void __ref memmap_init_zone_device(struc return; /* - * The call to memmap_init_zone should have already taken care + * The call to memmap_init should have already taken care * of the pages reserved for the memmap, so we can just jump to * the end of that region and start processing the device pages. */ @@ -6194,7 +6194,7 @@ static void __meminit zone_init_free_lis /* * Only struct pages that correspond to ranges defined by memblock.memory * are zeroed and initialized by going through __init_single_page() during - * memmap_init_zone(). + * memmap_init_zone_range(). * * But, there could be struct pages that correspond to holes in * memblock.memory. This can happen because of the following reasons: @@ -6213,9 +6213,9 @@ static void __meminit zone_init_free_lis * zone/node above the hole except for the trailing pages in the last * section that will be appended to the zone/node below. */ -static u64 __meminit init_unavailable_range(unsigned long spfn, - unsigned long epfn, - int zone, int node) +static void __init init_unavailable_range(unsigned long spfn, + unsigned long epfn, + int zone, int node) { unsigned long pfn; u64 pgcnt = 0; @@ -6231,58 +6231,77 @@ static u64 __meminit init_unavailable_ra pgcnt++; } - return pgcnt; + if (pgcnt) + pr_info("On node %d, zone %s: %lld pages in unavailable ranges", + node, zone_names[zone], pgcnt); } #else -static inline u64 init_unavailable_range(unsigned long spfn, unsigned long epfn, - int zone, int node) +static inline void init_unavailable_range(unsigned long spfn, + unsigned long epfn, + int zone, int node) { - return 0; } #endif -void __meminit __weak memmap_init(unsigned long size, int nid, - unsigned long zone, - unsigned long range_start_pfn) +static void __init memmap_init_zone_range(struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long *hole_pfn) +{ + unsigned long zone_start_pfn = zone->zone_start_pfn; + unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages; + int nid = zone_to_nid(zone), zone_id = zone_idx(zone); + + start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn); + end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn); + + if (start_pfn >= end_pfn) + return; + + memmap_init_zone(end_pfn - start_pfn, nid, zone_id, start_pfn, + zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); + + if (*hole_pfn < start_pfn) + init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid); + + *hole_pfn = end_pfn; +} + +void __init __weak memmap_init(void) { - static unsigned long hole_pfn; unsigned long start_pfn, end_pfn; - unsigned long range_end_pfn = range_start_pfn + size; - int i; - u64 pgcnt = 0; + unsigned long hole_pfn = 0; + int i, j, zone_id, nid; - for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { - start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn); - end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + struct pglist_data *node = NODE_DATA(nid); - if (end_pfn > start_pfn) { - size = end_pfn - start_pfn; - memmap_init_zone(size, nid, zone, start_pfn, range_end_pfn, - MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); - } + for (j = 0; j < MAX_NR_ZONES; j++) { + struct zone *zone = node->node_zones + j; - if (hole_pfn < start_pfn) - pgcnt += init_unavailable_range(hole_pfn, start_pfn, - zone, nid); - hole_pfn = end_pfn; + if (!populated_zone(zone)) + continue; + + memmap_init_zone_range(zone, start_pfn, end_pfn, + &hole_pfn); + zone_id = j; + } } #ifdef CONFIG_SPARSEMEM /* - * Initialize the hole in the range [zone_end_pfn, section_end]. - * If zone boundary falls in the middle of a section, this hole - * will be re-initialized during the call to this function for the - * higher zone. + * Initialize the memory map for hole in the range [memory_end, + * section_end]. + * Append the pages in this hole to the highest zone in the last + * node. + * The call to init_unavailable_range() is outside the ifdef to + * silence the compiler warining about zone_id set but not used; + * for FLATMEM it is a nop anyway */ - end_pfn = round_up(range_end_pfn, PAGES_PER_SECTION); + end_pfn = round_up(end_pfn, PAGES_PER_SECTION); if (hole_pfn < end_pfn) - pgcnt += init_unavailable_range(hole_pfn, end_pfn, - zone, nid); #endif - - if (pgcnt) - pr_info(" %s zone: %llu pages in unavailable ranges\n", - zone_names[zone], pgcnt); + init_unavailable_range(hole_pfn, end_pfn, zone_id, nid); } static int zone_batchsize(struct zone *zone) @@ -6981,7 +7000,6 @@ static void __init free_area_init_core(s set_pageblock_order(); 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); } } @@ -7507,6 +7525,8 @@ void __init free_area_init(unsigned long node_set_state(nid, N_MEMORY); check_for_memory(pgdat, nid); } + + memmap_init(); } static int __init cmdline_parse_core(char *p, unsigned long *core,
