diff options
Diffstat (limited to 'mm/page_alloc.c')
| -rw-r--r-- | mm/page_alloc.c | 200 |
1 files changed, 114 insertions, 86 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d4096f4a5c1f..c7dd9c86e353 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -293,7 +293,7 @@ int page_group_by_mobility_disabled __read_mostly; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* - * Determine how many pages need to be initialized durig early boot + * Determine how many pages need to be initialized during early boot * (non-deferred initialization). * The value of first_deferred_pfn will be set later, once non-deferred pages * are initialized, but for now set it ULONG_MAX. @@ -344,7 +344,7 @@ static inline bool update_defer_init(pg_data_t *pgdat, unsigned long pfn, unsigned long zone_end, unsigned long *nr_initialised) { - /* Always populate low zones for address-contrained allocations */ + /* Always populate low zones for address-constrained allocations */ if (zone_end < pgdat_end_pfn(pgdat)) return true; (*nr_initialised)++; @@ -1177,9 +1177,10 @@ static void free_one_page(struct zone *zone, } static void __meminit __init_single_page(struct page *page, unsigned long pfn, - unsigned long zone, int nid) + unsigned long zone, int nid, bool zero) { - mm_zero_struct_page(page); + if (zero) + mm_zero_struct_page(page); set_page_links(page, zone, nid, pfn); init_page_count(page); page_mapcount_reset(page); @@ -1194,9 +1195,9 @@ static void __meminit __init_single_page(struct page *page, unsigned long pfn, } static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone, - int nid) + int nid, bool zero) { - return __init_single_page(pfn_to_page(pfn), pfn, zone, nid); + return __init_single_page(pfn_to_page(pfn), pfn, zone, nid, zero); } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -1217,7 +1218,7 @@ static void __meminit init_reserved_page(unsigned long pfn) if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone)) break; } - __init_single_pfn(pfn, zid, nid); + __init_single_pfn(pfn, zid, nid, true); } #else static inline void init_reserved_page(unsigned long pfn) @@ -1457,92 +1458,87 @@ static inline void __init pgdat_init_report_one_done(void) } /* - * Helper for deferred_init_range, free the given range, reset the counters, and - * return number of pages freed. + * Returns true if page needs to be initialized or freed to buddy allocator. + * + * First we check if pfn is valid on architectures where it is possible to have + * holes within pageblock_nr_pages. On systems where it is not possible, this + * function is optimized out. + * + * Then, we check if a current large page is valid by only checking the validity + * of the head pfn. + * + * Finally, meminit_pfn_in_nid is checked on systems where pfns can interleave + * within a node: a pfn is between start and end of a node, but does not belong + * to this memory node. */ -static inline unsigned long __init __def_free(unsigned long *nr_free, - unsigned long *free_base_pfn, - struct page **page) +static inline bool __init +deferred_pfn_valid(int nid, unsigned long pfn, + struct mminit_pfnnid_cache *nid_init_state) { - unsigned long nr = *nr_free; + if (!pfn_valid_within(pfn)) + return false; + if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn)) + return false; + if (!meminit_pfn_in_nid(pfn, nid, nid_init_state)) + return false; + return true; +} - deferred_free_range(*free_base_pfn, nr); - *free_base_pfn = 0; - *nr_free = 0; - *page = NULL; +/* + * Free pages to buddy allocator. Try to free aligned pages in + * pageblock_nr_pages sizes. + */ +static void __init deferred_free_pages(int nid, int zid, unsigned long pfn, + unsigned long end_pfn) +{ + struct mminit_pfnnid_cache nid_init_state = { }; + unsigned long nr_pgmask = pageblock_nr_pages - 1; + unsigned long nr_free = 0; - return nr; + for (; pfn < end_pfn; pfn++) { + if (!deferred_pfn_valid(nid, pfn, &nid_init_state)) { + deferred_free_range(pfn - nr_free, nr_free); + nr_free = 0; + } else if (!(pfn & nr_pgmask)) { + deferred_free_range(pfn - nr_free, nr_free); + nr_free = 1; + cond_resched(); + } else { + nr_free++; + } + } + /* Free the last block of pages to allocator */ + deferred_free_range(pfn - nr_free, nr_free); } -static unsigned long __init deferred_init_range(int nid, int zid, - unsigned long start_pfn, - unsigned long end_pfn) +/* + * Initialize struct pages. We minimize pfn page lookups and scheduler checks + * by performing it only once every pageblock_nr_pages. + * Return number of pages initialized. + */ +static unsigned long __init deferred_init_pages(int nid, int zid, + unsigned long pfn, + unsigned long end_pfn) { struct mminit_pfnnid_cache nid_init_state = { }; unsigned long nr_pgmask = pageblock_nr_pages - 1; - unsigned long free_base_pfn = 0; unsigned long nr_pages = 0; - unsigned long nr_free = 0; struct page *page = NULL; - unsigned long pfn; - /* - * First we check if pfn is valid on architectures where it is possible - * to have holes within pageblock_nr_pages. On systems where it is not - * possible, this function is optimized out. - * - * Then, we check if a current large page is valid by only checking the - * validity of the head pfn. - * - * meminit_pfn_in_nid is checked on systems where pfns can interleave - * within a node: a pfn is between start and end of a node, but does not - * belong to this memory node. - * - * Finally, we minimize pfn page lookups and scheduler checks by - * performing it only once every pageblock_nr_pages. - * - * We do it in two loops: first we initialize struct page, than free to - * buddy allocator, becuse while we are freeing pages we can access - * pages that are ahead (computing buddy page in __free_one_page()). - */ - for (pfn = start_pfn; pfn < end_pfn; pfn++) { - if (!pfn_valid_within(pfn)) + for (; pfn < end_pfn; pfn++) { + if (!deferred_pfn_valid(nid, pfn, &nid_init_state)) { + page = NULL; continue; - if ((pfn & nr_pgmask) || pfn_valid(pfn)) { - if (meminit_pfn_in_nid(pfn, nid, &nid_init_state)) { - if (page && (pfn & nr_pgmask)) - page++; - else - page = pfn_to_page(pfn); - __init_single_page(page, pfn, zid, nid); - cond_resched(); - } - } - } - - page = NULL; - for (pfn = start_pfn; pfn < end_pfn; pfn++) { - if (!pfn_valid_within(pfn)) { - nr_pages += __def_free(&nr_free, &free_base_pfn, &page); - } else if (!(pfn & nr_pgmask) && !pfn_valid(pfn)) { - nr_pages += __def_free(&nr_free, &free_base_pfn, &page); - } else if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) { - nr_pages += __def_free(&nr_free, &free_base_pfn, &page); - } else if (page && (pfn & nr_pgmask)) { - page++; - nr_free++; - } else { - nr_pages += __def_free(&nr_free, &free_base_pfn, &page); + } else if (!page || !(pfn & nr_pgmask)) { page = pfn_to_page(pfn); - free_base_pfn = pfn; - nr_free = 1; cond_resched(); + } else { + page++; } + __init_single_page(page, pfn, zid, nid, true); + nr_pages++; } - /* Free the last block of pages to allocator */ - nr_pages += __def_free(&nr_free, &free_base_pfn, &page); - - return nr_pages; + return (nr_pages); } /* Initialise remaining memory on a node */ @@ -1582,10 +1578,21 @@ static int __init deferred_init_memmap(void *data) } first_init_pfn = max(zone->zone_start_pfn, first_init_pfn); + /* + * Initialize and free pages. We do it in two loops: first we initialize + * struct page, than free to buddy allocator, because while we are + * freeing pages we can access pages that are ahead (computing buddy + * page in __free_one_page()). + */ + for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) { + spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa)); + epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa)); + nr_pages += deferred_init_pages(nid, zid, spfn, epfn); + } for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) { spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa)); epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa)); - nr_pages += deferred_init_range(nid, zid, spfn, epfn); + deferred_free_pages(nid, zid, spfn, epfn); } /* Sanity check that the next zone really is unpopulated */ @@ -2507,10 +2514,6 @@ void drain_all_pages(struct zone *zone) if (WARN_ON_ONCE(!mm_percpu_wq)) return; - /* Workqueues cannot recurse */ - if (current->flags & PF_WQ_WORKER) - return; - /* * Do not drain if one is already in progress unless it's specific to * a zone. Such callers are primarily CMA and memory hotplug and need @@ -2688,6 +2691,7 @@ void free_unref_page_list(struct list_head *list) { struct page *page, *next; unsigned long flags, pfn; + int batch_count = 0; /* Prepare pages for freeing */ list_for_each_entry_safe(page, next, list, lru) { @@ -2704,6 +2708,16 @@ void free_unref_page_list(struct list_head *list) set_page_private(page, 0); trace_mm_page_free_batched(page); free_unref_page_commit(page, pfn); + + /* + * Guard against excessive IRQ disabled times when we get + * a large list of pages to free. + */ + if (++batch_count == SWAP_CLUSTER_MAX) { + local_irq_restore(flags); + batch_count = 0; + local_irq_save(flags); + } } local_irq_restore(flags); } @@ -3384,7 +3398,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, if (gfp_mask & __GFP_THISNODE) goto out; - /* Exhausted what can be done so it's blamo time */ + /* Exhausted what can be done so it's blame time */ if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) { *did_some_progress = 1; @@ -4265,7 +4279,7 @@ unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order) struct page *page; /* - * __get_free_pages() returns a 32-bit address, which cannot represent + * __get_free_pages() returns a virtual address, which cannot represent * a highmem page */ VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0); @@ -5386,15 +5400,20 @@ not_early: * can be created for invalid pages (for alignment) * check here not to call set_pageblock_migratetype() against * pfn out of zone. + * + * Please note that MEMMAP_HOTPLUG path doesn't clear memmap + * because this is done early in sparse_add_one_section */ if (!(pfn & (pageblock_nr_pages - 1))) { struct page *page = pfn_to_page(pfn); - __init_single_page(page, pfn, zone, nid); + __init_single_page(page, pfn, zone, nid, + context != MEMMAP_HOTPLUG); set_pageblock_migratetype(page, MIGRATE_MOVABLE); cond_resched(); } else { - __init_single_pfn(pfn, zone, nid); + __init_single_pfn(pfn, zone, nid, + context != MEMMAP_HOTPLUG); } } } @@ -6253,6 +6272,8 @@ void __paginginit zero_resv_unavail(void) pgcnt = 0; for_each_resv_unavail_range(i, &start, &end) { for (pfn = PFN_DOWN(start); pfn < PFN_UP(end); pfn++) { + if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) + continue; mm_zero_struct_page(pfn_to_page(pfn)); pgcnt++; } @@ -7656,11 +7677,18 @@ int alloc_contig_range(unsigned long start, unsigned long end, /* * In case of -EBUSY, we'd like to know which page causes problem. - * So, just fall through. We will check it in test_pages_isolated(). + * So, just fall through. test_pages_isolated() has a tracepoint + * which will report the busy page. + * + * It is possible that busy pages could become available before + * the call to test_pages_isolated, and the range will actually be + * allocated. So, if we fall through be sure to clear ret so that + * -EBUSY is not accidentally used or returned to caller. */ ret = __alloc_contig_migrate_range(&cc, start, end); if (ret && ret != -EBUSY) goto done; + ret =0; /* * Pages from [start, end) are within a MAX_ORDER_NR_PAGES |