diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b1e3483249c311dedf43e9379318befcb291dbc2..0c47af9e97c6e65358474f313a6dd8aa6408d86c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1344,7 +1344,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, { int migratetype = 0; int batch_free = 0; - int prefetch_nr = 0; + int prefetch_nr = READ_ONCE(pcp->batch); bool isolated_pageblocks; struct page *page, *tmp; LIST_HEAD(head); @@ -1395,8 +1395,10 @@ static void free_pcppages_bulk(struct zone *zone, int count, * avoid excessive prefetching due to large count, only * prefetch buddy for the first pcp->batch nr of pages. */ - if (prefetch_nr++ < pcp->batch) + if (prefetch_nr) { prefetch_buddy(page); + prefetch_nr--; + } } while (--count && --batch_free && !list_empty(list)); } @@ -3197,10 +3199,8 @@ static void free_unref_page_commit(struct page *page, unsigned long pfn) pcp = &this_cpu_ptr(zone->pageset)->pcp; list_add(&page->lru, &pcp->lists[migratetype]); pcp->count++; - if (pcp->count >= pcp->high) { - unsigned long batch = READ_ONCE(pcp->batch); - free_pcppages_bulk(zone, batch, pcp); - } + if (pcp->count >= READ_ONCE(pcp->high)) + free_pcppages_bulk(zone, READ_ONCE(pcp->batch), pcp); } /* @@ -3385,7 +3385,7 @@ static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, do { if (list_empty(list)) { pcp->count += rmqueue_bulk(zone, 0, - pcp->batch, list, + READ_ONCE(pcp->batch), list, migratetype, alloc_flags); if (unlikely(list_empty(list))) return NULL; @@ -6270,13 +6270,16 @@ static int zone_batchsize(struct zone *zone) } /* - * pcp->high and pcp->batch values are related and dependent on one another: - * ->batch must never be higher then ->high. - * The following function updates them in a safe manner without read side - * locking. + * pcp->high and pcp->batch values are related and generally batch is lower + * than high. They are also related to pcp->count such that count is lower + * than high, and as soon as it reaches high, the pcplist is flushed. * - * Any new users of pcp->batch and pcp->high should ensure they can cope with - * those fields changing asynchronously (acording to the above rule). + * However, guaranteeing these relations at all times would require e.g. write + * barriers here but also careful usage of read barriers at the read side, and + * thus be prone to error and bad for performance. Thus the update only prevents + * store tearing. Any new users of pcp->batch and pcp->high should ensure they + * can cope with those fields changing asynchronously, and fully trust only the + * pcp->count field on the local CPU with interrupts disabled. * * mutex_is_locked(&pcp_batch_high_lock) required when calling this function * outside of boot time (or some other assurance that no concurrent updaters @@ -6285,15 +6288,8 @@ static int zone_batchsize(struct zone *zone) static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, unsigned long batch) { - /* start with a fail safe value for batch */ - pcp->batch = 1; - smp_wmb(); - - /* Update high, then batch, in order */ - pcp->high = high; - smp_wmb(); - - pcp->batch = batch; + WRITE_ONCE(pcp->batch, batch); + WRITE_ONCE(pcp->high, high); } static void pageset_init(struct per_cpu_pageset *p)