linux伙伴系统接口alloc_page分析1

#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)

#define alloc_pages(gfp_mask, order) \
        alloc_pages_node(numa_node_id(), gfp_mask, order)

static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
                        unsigned int order)
{
    /* Unknown node is current node */
    /*如果没有指定node ，则从当前node分配*/
    if (nid < 0)
        nid = numa_node_id();

    return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
}

static inline struct page *
__alloc_pages(gfp_t gfp_mask, unsigned int order,
        struct zonelist *zonelist)
{
    return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL);
}

struct per_cpu_pageset {
    struct per_cpu_pages pcp;
#ifdef CONFIG_NUMA
    s8 expire;
#endif
#ifdef CONFIG_SMP
    s8 stat_threshold;
    s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
#endif
};

struct per_cpu_pages {
    int count;        /* number of pages in the list */
    int high;        /* high watermark, emptying needed */
    int batch;        /* chunk size for buddy add/remove */

    /* Lists of pages, one per migrate type stored on the pcp-lists */
    /*链表数组，每个迁移类型维护一个数组*/
    /*MIGRATE_UNMOVABLE,
    MIGRATE_RECLAIMABLE,
    MIGRATE_MOVABLE,
    MIGRATE_PCPTYPES,    // the number of types on the pcp lists 
    MIGRATE_RESERVE*/
    struct list_head lists[MIGRATE_PCPTYPES];
};

    if (likely(order == 0)) {
        struct per_cpu_pages *pcp;
        struct list_head *list;

        local_irq_save(flags);
        /*页框高速缓存*/
        pcp = &this_cpu_ptr(zone->pageset)->pcp;
        /*获取缓存链表*/
        list = &pcp->lists[migratetype];
        /*如果链表为空*/
        if (list_empty(list)) {
            /*尝试从伙伴系统填充链表*/
            pcp->count += rmqueue_bulk(zone, 0,
                    pcp->batch, list,
                    migratetype, cold);
            /*如果依然为空，则失败*/
            if (unlikely(list_empty(list)))
                goto failed;
        }
        /*list是双链表，如果cold为真就从表尾部分配，否则从表头分配*/
        if (cold)
            page = list_entry(list->prev, struct page, lru);
        else
            page = list_entry(list->next, struct page, lru);
        /*页面从链表删除*/
        list_del(&page->lru);
        pcp->count--;
    }

static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
    struct zonelist *zonelist, enum zone_type high_zoneidx,
    nodemask_t *nodemask, struct zone *preferred_zone,
    int migratetype)
{
    const gfp_t wait = gfp_mask & __GFP_WAIT;
    struct page *page = NULL;
    int alloc_flags;
    unsigned long pages_reclaimed = 0;
    unsigned long did_some_progress;
    bool sync_migration = false;
    bool deferred_compaction = false;
    bool contended_compaction = false;

    /*
     * In the slowpath, we sanity check order to avoid ever trying to
     * reclaim >= MAX_ORDER areas which will never succeed. Callers may
     * be using allocators in order of preference for an area that is
     * too large.
     */
    if (order >= MAX_ORDER) {
        WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN));
        return NULL;
    }

    /*
     * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
     * __GFP_NOWARN set) should not cause reclaim since the subsystem
     * (f.e. slab) using GFP_THISNODE may choose to trigger reclaim
     * using a larger set of nodes after it has established that the
     * allowed per node queues are empty and that nodes are
     * over allocated.
     */
    if (IS_ENABLED(CONFIG_NUMA) &&
            (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
        goto nopage;
    /*到这一步如果允许启用kswapd线程，则唤醒所有的kswapd*/
restart:
    if (!(gfp_mask & __GFP_NO_KSWAPD))
        wake_all_kswapd(order, zonelist, high_zoneidx,
                        zone_idx(preferred_zone));

    /*
     * OK, we‘re below the kswapd watermark and have kicked background
     * reclaim. Now things get more complex, so set up alloc_flags according
     * to how we want to proceed.
     */
    alloc_flags = gfp_to_alloc_flags(gfp_mask);

    /*
     * Find the true preferred zone if the allocation is unconstrained by
     * cpusets.
     */
     /*如果没哟没有指定cpuset，则选取最优的zonelist*/
    if (!(alloc_flags & ALLOC_CPUSET) && !nodemask)
        first_zones_zonelist(zonelist, high_zoneidx, NULL,
                    &preferred_zone);

rebalance:
    /* This is the last chance, in general, before the goto nopage. */
    /*尝试分配页面*/
    page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
            high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
            preferred_zone, migratetype);
    if (page)
        goto got_pg;
    /*如果允许不管区域的watermark*/
    /* Allocate without watermarks if the context allows */
    if (alloc_flags & ALLOC_NO_WATERMARKS) {
        /*
         * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
         * the allocation is high priority and these type of
         * allocations are system rather than user orientated
         */
        zonelist = node_zonelist(numa_node_id(), gfp_mask);
        /*高优先级的内存分配，遍历整个zonelist*/
        page = __alloc_pages_high_priority(gfp_mask, order,
                zonelist, high_zoneidx, nodemask,
                preferred_zone, migratetype);
        if (page) {
            goto got_pg;
        }
    }

    /* Atomic allocations - we can‘t balance anything */
    if (!wait)
        goto nopage;

    /* Avoid recursion of direct reclaim */
    if (current->flags & PF_MEMALLOC)
        goto nopage;

    /* Avoid allocations with no watermarks from looping endlessly */
    if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
        goto nopage;

    /*
     * Try direct compaction. The first pass is asynchronous. Subsequent
     * attempts after direct reclaim are synchronous
     */
    page = __alloc_pages_direct_compact(gfp_mask, order,
                    zonelist, high_zoneidx,
                    nodemask,
                    alloc_flags, preferred_zone,
                    migratetype, sync_migration,
                    &contended_compaction,
                    &deferred_compaction,
                    &did_some_progress);
    if (page)
        goto got_pg;
    sync_migration = true;

    /*
     * If compaction is deferred for high-order allocations, it is because
     * sync compaction recently failed. In this is the case and the caller
     * requested a movable allocation that does not heavily disrupt the
     * system then fail the allocation instead of entering direct reclaim.
     */
    if ((deferred_compaction || contended_compaction) &&
                        (gfp_mask & __GFP_NO_KSWAPD))
        goto nopage;

    /* Try direct reclaim and then allocating */
    /*如果压缩后仍然没哟u可用的，就对页面进行回收*/
    page = __alloc_pages_direct_reclaim(gfp_mask, order,
                    zonelist, high_zoneidx,
                    nodemask,
                    alloc_flags, preferred_zone,
                    migratetype, &did_some_progress);
    if (page)
        goto got_pg;

    /*
     * If we failed to make any progress reclaiming, then we are
     * running out of options and have to consider going OOM
     */
    if (!did_some_progress) {
        if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
            if (oom_killer_disabled)
                goto nopage;
            /* Coredumps can quickly deplete all memory reserves */
            if ((current->flags & PF_DUMPCORE) &&
                !(gfp_mask & __GFP_NOFAIL))
                goto nopage;
            page = __alloc_pages_may_oom(gfp_mask, order,
                    zonelist, high_zoneidx,
                    nodemask, preferred_zone,
                    migratetype);
            if (page)
                goto got_pg;

            if (!(gfp_mask & __GFP_NOFAIL)) {
                /*
                 * The oom killer is not called for high-order
                 * allocations that may fail, so if no progress
                 * is being made, there are no other options and
                 * retrying is unlikely to help.
                 */
                if (order > PAGE_ALLOC_COSTLY_ORDER)
                    goto nopage;
                /*
                 * The oom killer is not called for lowmem
                 * allocations to prevent needlessly killing
                 * innocent tasks.
                 */
                if (high_zoneidx < ZONE_NORMAL)
                    goto nopage;
            }

            goto restart;
        }
    }

    /* Check if we should retry the allocation */
    pages_reclaimed += did_some_progress;
    if (should_alloc_retry(gfp_mask, order, did_some_progress,
                        pages_reclaimed)) {
        /* Wait for some write requests to complete then retry */
        wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
        goto rebalance;
    } else {
        /*
         * High-order allocations do not necessarily loop after
         * direct reclaim and reclaim/compaction depends on compaction
         * being called after reclaim so call directly if necessary
         */
        page = __alloc_pages_direct_compact(gfp_mask, order,
                    zonelist, high_zoneidx,
                    nodemask,
                    alloc_flags, preferred_zone,
                    migratetype, sync_migration,
                    &contended_compaction,
                    &deferred_compaction,
                    &did_some_progress);
        if (page)
            goto got_pg;
    }

nopage:
    warn_alloc_failed(gfp_mask, order, NULL);
    return page;
got_pg:
    if (kmemcheck_enabled)
        kmemcheck_pagealloc_alloc(page, order, gfp_mask);

    return page;
}

for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
                                nodemask) {
        int status;

        status = compact_zone_order(zone, order, gfp_mask, sync,
                        contended);
        rc = max(status, rc);

        /* If a normal allocation would succeed, stop compacting */
        if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0,
                      alloc_flags))
            break;
    }

static unsigned long compact_zone_order(struct zone *zone,
                 int order, gfp_t gfp_mask,
                 bool sync, bool *contended)
{
    unsigned long ret;
    /*压缩控制器*/
    struct compact_control cc = {
        .nr_freepages = 0,
        .nr_migratepages = 0,
        .order = order,
        .migratetype = allocflags_to_migratetype(gfp_mask),
        .zone = zone,
        .sync = sync,
    };
    INIT_LIST_HEAD(&cc.freepages);
    INIT_LIST_HEAD(&cc.migratepages);
    /*执行压缩*/
    ret = compact_zone(zone, &cc);

    VM_BUG_ON(!list_empty(&cc.freepages));
    VM_BUG_ON(!list_empty(&cc.migratepages));

    *contended = cc.contended;
    return ret;
}

struct compact_control {
    struct list_head freepages;    /* List of free pages to migrate to */
    struct list_head migratepages;    /* List of pages being migrated */
    unsigned long nr_freepages;    /* Number of isolated free pages */
    unsigned long nr_migratepages;    /* Number of pages to migrate */
    unsigned long free_pfn;        /* isolate_freepages search base */
    unsigned long migrate_pfn;    /* isolate_migratepages search base */
    bool sync;            /* Synchronous migration */
    bool ignore_skip_hint;        /* Scan blocks even if marked skip */
    bool finished_update_free;    /* True when the zone cached pfns are
                     * no longer being updated
                     */
    bool finished_update_migrate;

    int order;            /* order a direct compactor needs */
    int migratetype;        /* MOVABLE, RECLAIMABLE etc */
    struct zone *zone;
    bool contended;            /* True if a lock was contended */
};

/*
 * compact_control is used to track pages being migrated and the free pages
 * they are being migrated to during memory compaction. The free_pfn starts
 * at the end of a zone and migrate_pfn begins at the start. Movable pages
 * are moved to the end of a zone during a compaction run and the run
 * completes when free_pfn <= migrate_pfn
 */

cc->migrate_pfn = zone->compact_cached_migrate_pfn;
    cc->free_pfn = zone->compact_cached_free_pfn;
    if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
        cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
        zone->compact_cached_free_pfn = cc->free_pfn;
    }
    if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) {
        cc->migrate_pfn = start_pfn;
        zone->compact_cached_migrate_pfn = cc->migrate_pfn;
    }

while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
        unsigned long nr_migrate, nr_remaining;
        int err;

        switch (isolate_migratepages(zone, cc)) {
        case ISOLATE_ABORT:
            ret = COMPACT_PARTIAL;
            putback_movable_pages(&cc->migratepages);
            cc->nr_migratepages = 0;
            goto out;
        case ISOLATE_NONE:
            continue;
        case ISOLATE_SUCCESS:
            ;
        }

        nr_migrate = cc->nr_migratepages;
        err = migrate_pages(&cc->migratepages, compaction_alloc,
                (unsigned long)cc,
                cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC,
                MR_COMPACTION);
        update_nr_listpages(cc);
        nr_remaining = cc->nr_migratepages;

        trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
                        nr_remaining);

        /* Release isolated pages not migrated */
        if (err) {
            putback_movable_pages(&cc->migratepages);
            cc->nr_migratepages = 0;
            if (err == -ENOMEM) {
                ret = COMPACT_PARTIAL;
                goto out;
            }
        }
    }