Buddy(伙伴)系统分配器之分配page

/* The ALLOC_WMARK bits are used as an index to zone->watermark */
#define ALLOC_WMARK_MIN     WMARK_MIN
#define ALLOC_WMARK_LOW     WMARK_LOW
#define ALLOC_WMARK_HIGH    WMARK_HIGH
#define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */
 
/* Mask to get the watermark bits */
#define ALLOC_WMARK_MASK    (ALLOC_NO_WATERMARKS-1)

#ifdef CONFIG_MMU
#define ALLOC_OOM       0x08
#else
#define ALLOC_OOM       ALLOC_NO_WATERMARKS
#endif
 
#define ALLOC_HARDER         0x10 /* try to alloc harder */
#define ALLOC_HIGH       0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET         0x40 /* check for correct cpuset */
#define ALLOC_CMA        0x80 /* allow allocations from CMA areas */
#ifdef CONFIG_ZONE_DMA32
#define ALLOC_NOFRAGMENT    0x100 /* avoid mixing pageblock types */
#else
#define ALLOC_NOFRAGMENT      0x0
#endif
#define ALLOC_KSWAPD        0x200 /* allow waking of kswapd */

#define __GFP_DMA   ((__force gfp_t)___GFP_DMA)
#define __GFP_HIGHMEM   ((__force gfp_t)___GFP_HIGHMEM)
#define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32)
#define __GFP_MOVABLE   ((__force gfp_t)___GFP_MOVABLE)  /* ZONE_MOVABLE allowed */
#define __GFP_CMA   ((__force gfp_t)___GFP_CMA)
#define GFP_ZONEMASK    (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)
#define __GFP_NOFAIL    ((__force gfp_t)___GFP_NOFAIL)
#define __GFP_NORETRY   ((__force gfp_t)___GFP_NORETRY)

/*
 * Allocate a page from the given zone. Use pcplists for order-0 allocations.
 */
static inline
struct page *rmqueue(struct zone *preferred_zone, struct zone *zone, unsigned int order, gfp_t gfp_flags, unsigned int alloc_flags,int migratetype)
{
    unsigned long flags;
    struct page *page;
 
    if (likely(order == 0)) {
        page = rmqueue_pcplist(preferred_zone, zone, order,
                gfp_flags, migratetype, alloc_flags);
        goto out;
    }
 
    /*
     * We most definitely don't want callers attempting to
     * allocate greater than order-1 page units with __GFP_NOFAIL.
     */
    WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
    spin_lock_irqsave(&zone->lock, flags);
 
    do {
        page = NULL;
 
        if (alloc_flags & ALLOC_HARDER) {
            page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
            if (page)
                trace_mm_page_alloc_zone_locked(page, order, migratetype);
        }
 
        if (!page && migratetype == MIGRATE_MOVABLE &&
                gfp_flags & __GFP_CMA)
            page = __rmqueue_cma(zone, order);
 
        if (!page)
            page = __rmqueue(zone, order, migratetype, alloc_flags);
    } while (page && check_new_pages(page, order));
 
    spin_unlock(&zone->lock);
    if (!page)
        goto failed;
    __mod_zone_freepage_state(zone, -(1 << order),
                  get_pcppage_migratetype(page));
 
    __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
    zone_statistics(preferred_zone, zone);
    local_irq_restore(flags);
 
out:
    /* Separate test+clear to avoid unnecessary atomics */
    if (test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags)) {
        clear_bit(ZONE_BOOSTED_WATERMARK, &zone->flags);
        wakeup_kswapd(zone, 0, 0, zone_idx(zone));
    }
 
    VM_BUG_ON_PAGE(page && bad_range(zone, page), page);
    return page;
 
failed:
    local_irq_restore(flags);
    return NULL;
}

/*
 * Go through the free lists for the given migratetype and remove
 * the smallest available page from the freelists
 */
static __always_inline
struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
                        int migratetype)
{
    unsigned int current_order;
    struct free_area *area;
    struct page *page;
 
    /* Find a page of the appropriate size in the preferred list */
    for (current_order = order; current_order < MAX_ORDER; ++current_order) {
        area = &(zone->free_area[current_order]);
        page = list_first_entry_or_null(&area->free_list[migratetype],
                            struct page, lru);
        if (!page)
            continue;
        list_del(&page->lru);
        rmv_page_order(page);
        area->nr_free--;
        expand(zone, page, order, current_order, area, migratetype);
        set_pcppage_migratetype(page, migratetype);
        return page;
    }
 
    return NULL;
}

static inline void expand(struct zone *zone, struct page *page, int low, int high, struct free_area *area, int migratetype)
{
    unsigned long size = 1 << high;
 
    while (high > low) {
        area--;
        high--;
        size >>= 1;
        VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);
 
        /*
         * Mark as guard pages (or page), that will allow to
         * merge back to allocator when buddy will be freed.
         * Corresponding page table entries will not be touched,
         * pages will stay not present in virtual address space
         */
        if (set_page_guard(zone, &page[size], high, migratetype))
            continue;
 
        list_add(&page[size].lru, &area->free_list[migratetype]);
        area->nr_free++;
        set_page_order(&page[size], high);
    }
}