diff options
Diffstat (limited to 'mm/mm_init.c')
| -rw-r--r-- | mm/mm_init.c | 165 |
1 files changed, 60 insertions, 105 deletions
diff --git a/mm/mm_init.c b/mm/mm_init.c index 3ec04933f7fd..75c3bd42799b 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -29,6 +29,7 @@ #include <linux/cma.h> #include <linux/crash_dump.h> #include <linux/execmem.h> +#include <linux/vmstat.h> #include "internal.h" #include "slab.h" #include "shuffle.h" @@ -53,7 +54,6 @@ void __init mminit_verify_zonelist(void) struct zonelist *zonelist; int i, listid, zoneid; - BUILD_BUG_ON(MAX_ZONELISTS > 2); for (i = 0; i < MAX_ZONELISTS * MAX_NR_ZONES; i++) { /* Identify the zone and nodelist */ @@ -363,7 +363,7 @@ static void __init find_zone_movable_pfns_for_nodes(void) nid = memblock_get_region_node(r); - usable_startpfn = PFN_DOWN(r->base); + usable_startpfn = memblock_region_memory_base_pfn(r); zone_movable_pfn[nid] = zone_movable_pfn[nid] ? min(usable_startpfn, zone_movable_pfn[nid]) : usable_startpfn; @@ -568,7 +568,7 @@ void __meminit __init_single_page(struct page *page, unsigned long pfn, mm_zero_struct_page(page); set_page_links(page, zone, nid, pfn); init_page_count(page); - page_mapcount_reset(page); + atomic_set(&page->_mapcount, -1); page_cpupid_reset_last(page); page_kasan_tag_reset(page); @@ -676,6 +676,14 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn) if (early_page_ext_enabled()) return false; + + /* Always populate low zones for address-constrained allocations */ + if (end_pfn < pgdat_end_pfn(NODE_DATA(nid))) + return false; + + if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX) + return true; + /* * prev_end_pfn static that contains the end of previous zone * No need to protect because called very early in boot before smp_init. @@ -685,12 +693,6 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn) nr_initialised = 0; } - /* Always populate low zones for address-constrained allocations */ - if (end_pfn < pgdat_end_pfn(NODE_DATA(nid))) - return false; - - if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX) - return true; /* * We start only with one section of pages, more pages are added as * needed until the rest of deferred pages are initialized. @@ -758,9 +760,6 @@ void __meminit reserve_bootmem_region(phys_addr_t start, init_reserved_page(start_pfn, nid); - /* Avoid false-positive PageTail() */ - INIT_LIST_HEAD(&page->lru); - /* * no need for atomic set_bit because the struct * page is not visible yet so nobody should @@ -892,8 +891,14 @@ void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone page = pfn_to_page(pfn); __init_single_page(page, pfn, zone, nid); - if (context == MEMINIT_HOTPLUG) - __SetPageReserved(page); + if (context == MEMINIT_HOTPLUG) { +#ifdef CONFIG_ZONE_DEVICE + if (zone == ZONE_DEVICE) + __SetPageReserved(page); + else +#endif + __SetPageOffline(page); + } /* * Usually, we want to mark the pageblock MIGRATE_MOVABLE, @@ -1618,6 +1623,8 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat) panic("Failed to allocate %ld bytes for node %d memory map\n", size, pgdat->node_id); pgdat->node_mem_map = map + offset; + mod_node_early_perpage_metadata(pgdat->node_id, + DIV_ROUND_UP(size, PAGE_SIZE)); pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", __func__, pgdat->node_id, (unsigned long)pgdat, (unsigned long)pgdat->node_mem_map); @@ -1913,8 +1920,8 @@ unsigned long __init node_map_pfn_alignment(void) } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT -static void __init deferred_free_range(unsigned long pfn, - unsigned long nr_pages) +static void __init deferred_free_pages(unsigned long pfn, + unsigned long nr_pages) { struct page *page; unsigned long i; @@ -1928,7 +1935,7 @@ static void __init deferred_free_range(unsigned long pfn, if (nr_pages == MAX_ORDER_NR_PAGES && IS_MAX_ORDER_ALIGNED(pfn)) { for (i = 0; i < nr_pages; i += pageblock_nr_pages) set_pageblock_migratetype(page + i, MIGRATE_MOVABLE); - __free_pages_core(page, MAX_PAGE_ORDER); + __free_pages_core(page, MAX_PAGE_ORDER, MEMINIT_EARLY); return; } @@ -1938,7 +1945,7 @@ static void __init deferred_free_range(unsigned long pfn, for (i = 0; i < nr_pages; i++, page++, pfn++) { if (pageblock_aligned(pfn)) set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_core(page, 0); + __free_pages_core(page, 0, MEMINIT_EARLY); } } @@ -1953,90 +1960,47 @@ static inline void __init pgdat_init_report_one_done(void) } /* - * Returns true if page needs to be initialized or freed to buddy allocator. - * - * We check if a current MAX_PAGE_ORDER block is valid by only checking the - * validity of the head pfn. - */ -static inline bool __init deferred_pfn_valid(unsigned long pfn) -{ - if (IS_MAX_ORDER_ALIGNED(pfn) && !pfn_valid(pfn)) - return false; - return true; -} - -/* - * Free pages to buddy allocator. Try to free aligned pages in - * MAX_ORDER_NR_PAGES sizes. - */ -static void __init deferred_free_pages(unsigned long pfn, - unsigned long end_pfn) -{ - unsigned long nr_free = 0; - - for (; pfn < end_pfn; pfn++) { - if (!deferred_pfn_valid(pfn)) { - deferred_free_range(pfn - nr_free, nr_free); - nr_free = 0; - } else if (IS_MAX_ORDER_ALIGNED(pfn)) { - deferred_free_range(pfn - nr_free, nr_free); - nr_free = 1; - } else { - nr_free++; - } - } - /* Free the last block of pages to allocator */ - deferred_free_range(pfn - nr_free, nr_free); -} - -/* * Initialize struct pages. We minimize pfn page lookups and scheduler checks * by performing it only once every MAX_ORDER_NR_PAGES. * Return number of pages initialized. */ -static unsigned long __init deferred_init_pages(struct zone *zone, - unsigned long pfn, - unsigned long end_pfn) +static unsigned long __init deferred_init_pages(struct zone *zone, + unsigned long pfn, unsigned long end_pfn) { int nid = zone_to_nid(zone); - unsigned long nr_pages = 0; + unsigned long nr_pages = end_pfn - pfn; int zid = zone_idx(zone); - struct page *page = NULL; + struct page *page = pfn_to_page(pfn); - for (; pfn < end_pfn; pfn++) { - if (!deferred_pfn_valid(pfn)) { - page = NULL; - continue; - } else if (!page || IS_MAX_ORDER_ALIGNED(pfn)) { - page = pfn_to_page(pfn); - } else { - page++; - } + for (; pfn < end_pfn; pfn++, page++) __init_single_page(page, pfn, zid, nid); - nr_pages++; - } return nr_pages; } /* - * This function is meant to pre-load the iterator for the zone init. - * Specifically it walks through the ranges until we are caught up to the - * first_init_pfn value and exits there. If we never encounter the value we - * return false indicating there are no valid ranges left. + * This function is meant to pre-load the iterator for the zone init from + * a given point. + * Specifically it walks through the ranges starting with initial index + * passed to it until we are caught up to the first_init_pfn value and + * exits there. If we never encounter the value we return false indicating + * there are no valid ranges left. */ static bool __init deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone, unsigned long *spfn, unsigned long *epfn, unsigned long first_init_pfn) { - u64 j; + u64 j = *i; + + if (j == 0) + __next_mem_pfn_range_in_zone(&j, zone, spfn, epfn); /* * Start out by walking through the ranges in this zone that have * already been initialized. We don't need to do anything with them * so we just need to flush them out of the system. */ - for_each_free_mem_pfn_range_in_zone(j, zone, spfn, epfn) { + for_each_free_mem_pfn_range_in_zone_from(j, zone, spfn, epfn) { if (*epfn <= first_init_pfn) continue; if (*spfn < first_init_pfn) @@ -2093,7 +2057,7 @@ deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn, break; t = min(mo_pfn, epfn); - deferred_free_pages(spfn, t); + deferred_free_pages(spfn, t - spfn); if (mo_pfn <= epfn) break; @@ -2108,7 +2072,7 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn, { unsigned long spfn, epfn; struct zone *zone = arg; - u64 i; + u64 i = 0; deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn); @@ -2122,11 +2086,10 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn, } } -/* An arch may override for more concurrency. */ -__weak int __init +static unsigned int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask) { - return 1; + return max(cpumask_weight(node_cpumask), 1U); } /* Initialise remaining memory on a node */ @@ -2138,8 +2101,8 @@ static int __init deferred_init_memmap(void *data) unsigned long first_init_pfn, flags; unsigned long start = jiffies; struct zone *zone; - int zid, max_threads; - u64 i; + int max_threads; + u64 i = 0; /* Bind memory initialisation thread to a local node if possible */ if (!cpumask_empty(cpumask)) @@ -2165,27 +2128,18 @@ static int __init deferred_init_memmap(void *data) */ pgdat_resize_unlock(pgdat, &flags); - /* Only the highest zone is deferred so find it */ - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - zone = pgdat->node_zones + zid; - if (first_init_pfn < zone_end_pfn(zone)) - break; - } - - /* If the zone is empty somebody else may have cleared out the zone */ - if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, - first_init_pfn)) - goto zone_empty; + /* Only the highest zone is deferred */ + zone = pgdat->node_zones + pgdat->nr_zones - 1; max_threads = deferred_page_init_max_threads(cpumask); - while (spfn < epfn) { - unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION); + while (deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, first_init_pfn)) { + first_init_pfn = ALIGN(epfn, PAGES_PER_SECTION); struct padata_mt_job job = { .thread_fn = deferred_init_memmap_chunk, .fn_arg = zone, .start = spfn, - .size = epfn_align - spfn, + .size = first_init_pfn - spfn, .align = PAGES_PER_SECTION, .min_chunk = PAGES_PER_SECTION, .max_threads = max_threads, @@ -2193,12 +2147,10 @@ static int __init deferred_init_memmap(void *data) }; padata_do_multithreaded(&job); - deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, - epfn_align); } -zone_empty: + /* Sanity check that the next zone really is unpopulated */ - WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone)); + WARN_ON(pgdat->nr_zones < MAX_NR_ZONES && populated_zone(++zone)); pr_info("node %d deferred pages initialised in %ums\n", pgdat->node_id, jiffies_to_msecs(jiffies - start)); @@ -2225,7 +2177,7 @@ bool __init deferred_grow_zone(struct zone *zone, unsigned int order) unsigned long first_deferred_pfn = pgdat->first_deferred_pfn; unsigned long spfn, epfn, flags; unsigned long nr_pages = 0; - u64 i; + u64 i = 0; /* Only the last zone may have deferred pages */ if (zone_end_pfn(zone) != pgdat_end_pfn(pgdat)) @@ -2322,6 +2274,7 @@ void set_zone_contiguous(struct zone *zone) zone->contiguous = true; } +static void __init mem_init_print_info(void); void __init page_alloc_init_late(void) { struct zone *zone; @@ -2348,6 +2301,8 @@ void __init page_alloc_init_late(void) files_maxfiles_init(); #endif + /* Accounting of total+free memory is stable at this point. */ + mem_init_print_info(); buffer_init(); /* Discard memblock private memory */ @@ -2514,7 +2469,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, } } - __free_pages_core(page, order); + __free_pages_core(page, order, MEMINIT_EARLY); } DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc); @@ -2694,6 +2649,7 @@ static void __init mem_init_print_info(void) void __init mm_core_init(void) { /* Initializations relying on SMP setup */ + BUILD_BUG_ON(MAX_ZONELISTS > 2); build_all_zonelists(NULL); page_alloc_init_cpuhp(); @@ -2708,7 +2664,6 @@ void __init mm_core_init(void) kmsan_init_shadow(); stack_depot_early_init(); mem_init(); - mem_init_print_info(); kmem_cache_init(); /* * page_owner must be initialized after buddy is ready, and also after |