linux-4.4.1/free_hot_cold_page() の履歴(No.1)

• 履歴一覧
• 差分 を表示
• 現在との差分 を表示
• ソース を表示
• linux-4.4.1/free_hot_cold_page() へ行く。
  • 1 (2016-03-14 (月) 11:02:14)

参照元†

• linux-4.4.1/__free_pages()
• linux-4.4.1/buffered_rmqueue()

説明†

• パス: linux-4.4.1/mm/page_alloc.c

• FIXME: これは何？
  • 説明

引数†

• struct page *page
  • [[linux-4.4.1/]]
• bool cold

返り値†

• なし

参考†

実装†

/*
 * Free a 0-order page
 * cold == true ? free a cold page : free a hot page
 */
void free_hot_cold_page(struct page *page, bool cold)
{
        struct zone *zone = page_zone(page);
        struct per_cpu_pages *pcp;
        unsigned long flags;
        unsigned long pfn = page_to_pfn(page);
        int migratetype;

• • linux-4.4.1/zone
  • linux-4.4.1/page_zone()
  • linux-4.4.1/per_cpu_pages
  • linux-4.4.1/page_to_pfn()

        if (!free_pages_prepare(page, 0))
                return;

• • linux-4.4.1/free_pages_prepare()

        migratetype = get_pfnblock_migratetype(page, pfn);
        set_pcppage_migratetype(page, migratetype);
        local_irq_save(flags);
        __count_vm_event(PGFREE);

• • linux-4.4.1/get_pnfblock_migratetype()
  • linux-4.4.1/set_pcppage_migratetype()
  • linux-4.4.1/local_irq_save()
  • linux-4.4.1/__count_vm_event()

        /*
         * We only track unmovable, reclaimable and movable on pcp lists.
         * Free ISOLATE pages back to the allocator because they are being
         * offlined but treat RESERVE as movable pages so we can get those
         * areas back if necessary. Otherwise, we may have to free
         * excessively into the page allocator
         */
        if (migratetype >= MIGRATE_PCPTYPES) {
                if (unlikely(is_migrate_isolate(migratetype))) {
                        free_one_page(zone, page, pfn, 0, migratetype);
                        goto out;

• • linux-4.4.1/MIGRATE_PCPTYPES
  • linux-4.4.1/unlikely()
  • linux-4.4.1/is_migrate_isolate()
  • linux-4.4.1/free_one_page()

                }
                migratetype = MIGRATE_MOVABLE;

• • linux-4.4.1/MIGRATE_MOVABLE

        }

        pcp = &this_cpu_ptr(zone->pageset)->pcp;
        if (!cold)
                list_add(&page->lru, &pcp->lists[migratetype]);
        else
                list_add_tail(&page->lru, &pcp->lists[migratetype]);

• • linux-4.4.1/this_cpu_ptr()
  • linux-4.4.1/list_add()
  • linux-4.4.1/list_add_tail()

        pcp->count++;
        if (pcp->count >= pcp->high) {
                unsigned long batch = READ_ONCE(pcp->batch);
                free_pcppages_bulk(zone, batch, pcp);
                pcp->count -= batch;
        }

out:
        local_irq_restore(flags);
}

コメント†