根据git的合入记录，CMA（Contiguous Memory Allocator，连续内存分配器）是在内核3.5的版本引入，由三星的工程师开发实现的，用于DMA映射框架下提升连续大块内存的申请。
其实现主要是在系统引导时获取内存，并将内存设置为MIGRATE_CMA迁移类型，然后再将内存归还给系统。内核分配内存时，在CMA管理内存中仅允许申请可移动类型内存页面（movable pages），例如DMA映射时不使用的页面缓存。而通过dma_alloc_from_contiguous()申请大块连续内存时，将会把这些可移动页面从CMA管理区中迁移出去，以便腾出足够的连续内存空间满足申请需要。由此，实现了任何时刻只要系统中有足够的内存空间，便可以申请得到大块连续内存。
先由其初始化开始分析，于/drivers/base/dma-contiguous.c代码文件中，可以找到其初始化函数cma_init_reserved_areas()，其通过core_initcall()注册到系统初始化中。
先看一下cma_init_reserved_areas()实现：
【file:/drivers/base/dma-contiguous.c】
static int __init cma_init_reserved_areas(void)
{
int i;
for (i = 0; i < cma_area_count; i++) {
int ret = cma_activate_area(&cma_areas[i]);
if (ret)
return ret;
}
return 0;
}
其主要是通过遍历cma_areas的CMA管理区信息，调用cma_activate_area()将各个区进行初始化。其中cma_areas信息来自于DMA初始化时：start_kernel()->setup_arch()-> dma_contiguous_reserve()读取来自cmdline的信息，然后通过dma_contiguous_reserve_area()进行内存预留和cma_areas内存信息设置。具体这里不做深入分析。
而继续cma_activate_area()的实现：
【file:/drivers/base/dma-contiguous.c】
static int __init cma_activate_area(struct cma *cma)
{
int bitmap_size = BITS_TO_LONGS(cma->count) * sizeof(long);
unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
unsigned i = cma->count >> pageblock_order;
struct zone *zone;
cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
if (!cma->bitmap)
return -ENOMEM;
WARN_ON_ONCE(!pfn_valid(pfn));
zone = page_zone(pfn_to_page(pfn));
do {
unsigned j;
base_pfn = pfn;
for (j = pageblock_nr_pages; j; --j, pfn++) {
WARN_ON_ONCE(!pfn_valid(pfn));
if (page_zone(pfn_to_page(pfn)) != zone)
return -EINVAL;
}
init_cma_reserved_pageblock(pfn_to_page(base_pfn));
} while (--i);
return 0;
}
该函数主要是对CMA管理区进行初始化，先是kzalloc()申请位图，然后以最高阶pageblock_order的页面数量pageblock_nr_pages为单位对该区的内存页面进行检验，确保该数量单位的内存页面都合法且同处于一个内存管理区，也就是保证至少有一个最高阶的pageblock_nr_pages数量的内存块会被初始化，如果不够该数量，则返回-EINVAL错误。
而里面具体初始化页面的函数为init_cma_reserved_pageblock()：
【file:/drivers/base/dma-contiguous.c】
/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
void __init init_cma_reserved_pageblock(struct page *page)
{
unsigned i = pageblock_nr_pages;
struct page *p = page;
do {
__ClearPageReserved(p);
set_page_count(p, 0);
} while (++p, --i);
set_pageblock_migratetype(page, MIGRATE_CMA);
if (pageblock_order >= MAX_ORDER) {
i = pageblock_nr_pages;
p = page;
do {
set_page_refcounted(p);
__free_pages(p, MAX_ORDER - 1);
p += MAX_ORDER_NR_PAGES;
} while (i -= MAX_ORDER_NR_PAGES);
} else {
set_page_refcounted(page);
__free_pages(page, pageblock_order);
}
adjust_managed_page_count(page, pageblock_nr_pages);
}
该函数先是set_page_count()将页面计数初始化，接着set_pageblock_migratetype()将页面设置为MIGRATE_CMA类型，然后set_page_refcounted()重置页面引用计数后通过__free_pages()将内存释放至伙伴管理算法中，最终是挂到了zone->free_area[order].free_list[MIGRATE_CMA]（这里的order是pageblock_order或MAX_ORDER-1），最后通过adjust_managed_page_count()修改内存管理页面数量。
初始化基本上就这样了。
而CMA的内存分配则是通过dma_generic_alloc_coherent()进行分配的。
【file:/arch/x86/kernel/pci-dma.c】
void *dma_generic_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_addr, gfp_t flag,
struct dma_attrs *attrs)
{
unsigned long dma_mask;
struct page *page;
unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
dma_addr_t addr;
dma_mask = dma_alloc_coherent_mask(dev, flag);
flag |= __GFP_ZERO;
again:
page = NULL;
/* CMA can be used only in the context which permits sleeping */
if (flag & __GFP_WAIT)
page = dma_alloc_from_contiguous(dev, count, get_order(size));
/* fallback */
if (!page)
page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
if (!page)
return NULL;
addr = page_to_phys(page);
if (addr + size > dma_mask) {
__free_pages(page, get_order(size));
if (dma_mask < DMA_BIT_MASK(32) && !(flag & GFP_DMA)) {
flag = (flag & ~GFP_DMA32) | GFP_DMA;
goto again;
}
return NULL;
}
*dma_addr = addr;
return page_address(page);
}
如果希望从CMA管理区中获取内存，则分配标志flag需允许分配时休眠__GFP_WAIT。进而将通过dma_alloc_from_contiguous()获取到内存。
dma_alloc_from_contiguous()实现：
【file:/drivers/base/dma-contiguous.c】
/**
* dma_alloc_from_contiguous() - allocate pages from contiguous area
* @dev: Pointer to device for which the allocation is performed.
* @count: Requested number of pages.
* @align: Requested alignment of pages (in PAGE_SIZE order).
*
* This function allocates memory buffer for specified device. It uses
* device specific contiguous memory area if available or the default
* global one. Requires architecture specific get_dev_cma_area() helper
* function.
*/
struct page *dma_alloc_from_contiguous(struct device *dev, int count,
unsigned int align)
{
unsigned long mask, pfn, pageno, start = 0;
struct cma *cma = dev_get_cma_area(dev);
struct page *page = NULL;
int ret;
if (!cma || !cma->count)
return NULL;
if (align > CONFIG_CMA_ALIGNMENT)
align = CONFIG_CMA_ALIGNMENT;
pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma,
count, align);
if (!count)
return NULL;
mask = (1 << align) - 1;
mutex_lock(&cma_mutex);
for (;;) {
pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count,
start, count, mask);
if (pageno >= cma->count)
break;
pfn = cma->base_pfn + pageno;
ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
if (ret == 0) {
bitmap_set(cma->bitmap, pageno, count);
page = pfn_to_page(pfn);
break;
} else if (ret != -EBUSY) {
break;
}
pr_debug("%s(): memory range at %p is busy, retrying\n",
__func__, pfn_to_page(pfn));
/* try again with a bit different memory target */
start = pageno + mask + 1;
}
mutex_unlock(&cma_mutex);
pr_debug("%s(): returned %p\n", __func__, page);
return page;
}
该函数通过dev_get_cma_area()获得设备使用的CMA管理区，然后通过bitmap_find_next_zero_area()查找到CMA管理区中合适大小的未被分配的页面空间，接着调用alloc_contig_range()尝试去分配该查找到的页面空间，如果查找到，则使用bitmap_set()将该空间的bitmap位图进行置位表示已被使用，完了pfn_to_page()通过页框号去得首页面的结构并返回。
其中bitmap_find_next_zero_area()的实现：
【file:/lib/bitmap.c】
/*
* bitmap_find_next_zero_area - find a contiguous aligned zero area
* @map: The address to base the search on
* @size: The bitmap size in bits
* @start: The bitnumber to start searching at
* @nr: The number of zeroed bits we're looking for
* @align_mask: Alignment mask for zero area
*
* The @align_mask should be one less than a power of 2; the effect is that
* the bit offset of all zero areas this function finds is multiples of that
* power of 2. A @align_mask of 0 means no alignment is required.
*/
unsigned long bitmap_find_next_zero_area(unsigned long *map,
unsigned long size,
unsigned long start,
unsigned int nr,
unsigned long align_mask)
{
unsigned long index, end, i;
again:
index = find_next_zero_bit(map, size, start);
/* Align allocation */
index = __ALIGN_MASK(index, align_mask);
end = index + nr;
if (end > size)
return end;
i = find_next_bit(map, end, index);
if (i < end) {
start = i + 1;
goto again;
}
return index;
}
该函数通过find_next_zero_bit()和find_next_bit()往返查找bit位置0与置1之间的空间，以期找到足够大的空间以实现空间分配的查找。
而alloc_contig_range()的实现：
【file:/mm/page_alloc.c】
/**
* alloc_contig_range() -- tries to allocate given range of pages
* @start: start PFN to allocate
* @end: one-past-the-last PFN to allocate
* @migratetype: migratetype of the underlaying pageblocks (either
* #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks
* in range must have the same migratetype and it must
* be either of the two.
*
* The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
* aligned, however it's the caller's responsibility to guarantee that
* we are the only thread that changes migrate type of pageblocks the
* pages fall in.
*
* The PFN range must belong to a single zone.
*
* Returns zero on success or negative error code. On success all
* pages which PFN is in [start, end) are allocated for the caller and
* need to be freed with free_contig_range().
*/
int alloc_contig_range(unsigned long start, unsigned long end,
unsigned migratetype)
{
unsigned long outer_start, outer_end;
int ret = 0, order;
struct compact_control cc = {
.nr_migratepages = 0,
.order = -1,
.zone = page_zone(pfn_to_page(start)),
.sync = true,
.ignore_skip_hint = true,
};
INIT_LIST_HEAD(&cc.migratepages);
/*
* What we do here is we mark all pageblocks in range as
* MIGRATE_ISOLATE. Because pageblock and max order pages may
* have different sizes, and due to the way page allocator
* work, we align the range to biggest of the two pages so
* that page allocator won't try to merge buddies from
* different pageblocks and change MIGRATE_ISOLATE to some
* other migration type.
*
* Once the pageblocks are marked as MIGRATE_ISOLATE, we
* migrate the pages from an unaligned range (ie. pages that
* we are interested in). This will put all the pages in
* range back to page allocator as MIGRATE_ISOLATE.
*
* When this is done, we take the pages in range from page
* allocator removing them from the buddy system. This way
* page allocator will never consider using them.
*
* This lets us mark the pageblocks back as
* MIGRATE_CMA/MIGRATE_MOVABLE so that free pages in the
* aligned range but not in the unaligned, original range are
* put back to page allocator so that buddy can use them.
*/
ret = start_isolate_page_range(pfn_max_align_down(start),
pfn_max_align_up(end), migratetype,
false);
if (ret)
return ret;
ret = __alloc_contig_migrate_range(&cc, start, end);
if (ret)
goto done;
/*
* Pages from [start, end) are within a MAX_ORDER_NR_PAGES
* aligned blocks that are marked as MIGRATE_ISOLATE. What's
* more, all pages in [start, end) are free in page allocator.
* What we are going to do is to allocate all pages from
* [start, end) (that is remove them from page allocator).
*
* The only problem is that pages at the beginning and at the
* end of interesting range may be not aligned with pages that
* page allocator holds, ie. they can be part of higher order
* pages. Because of this, we reserve the bigger range and
* once this is done free the pages we are not interested in.
*
* We don't have to hold zone->lock here because the pages are
* isolated thus they won't get removed from buddy.
*/
lru_add_drain_all();
drain_all_pages();
order = 0;
outer_start = start;
while (!PageBuddy(pfn_to_page(outer_start))) {
if (++order >= MAX_ORDER) {
ret = -EBUSY;
goto done;
}
outer_start &= ~0UL << order;
}
/* Make sure the range is really isolated. */
if (test_pages_isolated(outer_start, end, false)) {
pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n",
outer_start, end);
ret = -EBUSY;
goto done;
}
/* Grab isolated pages from freelists. */
outer_end = isolate_freepages_range(&cc, outer_start, end);
if (!outer_end) {
ret = -EBUSY;
goto done;
}
/* Free head and tail (if any) */
if (start != outer_start)
free_contig_range(outer_start, start - outer_start);
if (end != outer_end)
free_contig_range(end, outer_end - end);
done:
undo_isolate_page_range(pfn_max_align_down(start),
pfn_max_align_up(end), migratetype);
return ret;
}
该函数主要是用于分配指定页面号的连续内存空间，其特点是内存块不需要页面块或者内存页面阶对齐，而且需要由调用者保证单线程操作，所以在dma_alloc_from_contiguous()调用时是加了互斥锁做保护的，此外被分配的空间不允许跨内存管理区。
为了深入了解其动作，深入分析一下其调用的几个函数，先看一下start_isolate_page_range()：
【file:/mm/page_isolation.c】
/*
* start_isolate_page_range() -- make page-allocation-type of range of pages
* to be MIGRATE_ISOLATE.
* @start_pfn: The lower PFN of the range to be isolated.
* @end_pfn: The upper PFN of the range to be isolated.
* @migratetype: migrate type to set in error recovery.
*
* Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
* the range will never be allocated. Any free pages and pages freed in the
* future will not be allocated again.
*
* start_pfn/end_pfn must be aligned to pageblock_order.
* Returns 0 on success and -EBUSY if any part of range cannot be isolated.
*/
int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
unsigned migratetype, bool skip_hwpoisoned_pages)
{
unsigned long pfn;
unsigned long undo_pfn;
struct page *page;
BUG_ON((start_pfn) & (pageblock_nr_pages - 1));
BUG_ON((end_pfn) & (pageblock_nr_pages - 1));
for (pfn = start_pfn;
pfn < end_pfn;
pfn += pageblock_nr_pages) {
page = __first_valid_page(pfn, pageblock_nr_pages);
if (page &&
set_migratetype_isolate(page, skip_hwpoisoned_pages)) {
undo_pfn = pfn;
goto undo;
}
}
return 0;
undo:
for (pfn = start_pfn;
pfn < undo_pfn;
pfn += pageblock_nr_pages)
unset_migratetype_isolate(pfn_to_page(pfn), migratetype);
return -EBUSY;
}
将页面类型设置为MIGRATE_ISOLATE意味着指定范围的空闲页面将不会被分配，值得注意的时候，这里的迁移类型变更和前面分析的页面迁移是一致的，都是基于pageblock_nr_pages为基数的页面个数做迁移的。
而里面调用的set_migratetype_isolate()：
【file:/mm/page_isolation.c】
int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages)
{
struct zone *zone;
unsigned long flags, pfn;
struct memory_isolate_notify arg;
int notifier_ret;
int ret = -EBUSY;
zone = page_zone(page);
spin_lock_irqsave(&zone->lock, flags);
pfn = page_to_pfn(page);
arg.start_pfn = pfn;
arg.nr_pages = pageblock_nr_pages;
arg.pages_found = 0;
/*
* It may be possible to isolate a pageblock even if the
* migratetype is not MIGRATE_MOVABLE. The memory isolation
* notifier chain is used by balloon drivers to return the
* number of pages in a range that are held by the balloon
* driver to shrink memory. If all the pages are accounted for
* by balloons, are free, or on the LRU, isolation can continue.
* Later, for example, when memory hotplug notifier runs, these
* pages reported as "can be isolated" should be isolated(freed)
* by the balloon driver through the memory notifier chain.
*/
notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
notifier_ret = notifier_to_errno(notifier_ret);
if (notifier_ret)
goto out;
/*
* FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
* We just check MOVABLE pages.
*/
if (!has_unmovable_pages(zone, page, arg.pages_found,
skip_hwpoisoned_pages))
ret = 0;
/*
* immobile means "not-on-lru" paes. If immobile is larger than
* removable-by-driver pages reported by notifier, we'll fail.
*/
out:
if (!ret) {
unsigned long nr_pages;
int migratetype = get_pageblock_migratetype(page);
set_pageblock_migratetype(page, MIGRATE_ISOLATE);
nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE);
__mod_zone_freepage_state(zone, -nr_pages, migratetype);
}
spin_unlock_irqrestore(&zone->lock, flags);
if (!ret)
drain_all_pages();
return ret;
}
由该函数可以看到，将页面设置为MIGRATE_ISOLATE类型时，其确保该空间范围内不存在不可以移动页面，同时其设置完页面类型后，通过move_freepages_block会将其从原来的页面类型链表中移除并挂入到MIGRATE_ISOLATE类型的链表中，移入MIGRATE_ISOLATE类型的页面将不会被分配出去。
start_isolate_page_range()完了如果没有异常状况会返回0，继而是调用__alloc_contig_migrate_range()：
【file:/mm/page_isolation.c】
/* [start, end) must belong to a single zone. */
static int __alloc_contig_migrate_range(struct compact_control *cc,
unsigned long start, unsigned long end)
{
/* This function is based on compact_zone() from compaction.c. */
unsigned long nr_reclaimed;
unsigned long pfn = start;
unsigned int tries = 0;
int ret = 0;
migrate_prep();
while (pfn < end || !list_empty(&cc->migratepages)) {
if (fatal_signal_pending(current)) {
ret = -EINTR;
break;
}
if (list_empty(&cc->migratepages)) {
cc->nr_migratepages = 0;
pfn = isolate_migratepages_range(cc->zone, cc,
pfn, end, true);
if (!pfn) {
ret = -EINTR;
break;
}
tries = 0;
} else if (++tries == 5) {
ret = ret < 0 ? ret : -EBUSY;
break;
}
nr_reclaimed = reclaim_clean_pages_from_list(cc->zone,
&cc->migratepages);
cc->nr_migratepages -= nr_reclaimed;
ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
0, MIGRATE_SYNC, MR_CMA);
}
if (ret < 0) {
putback_movable_pages(&cc->migratepages);
return ret;
}
return 0;
}
该函数中调用的migrate_prep()主要是为了将LRU链表进行清空，以便内存页面更好地隔离出来。
其余的则主要是while循环处理非空闲的页，其中主要涉及函数有isolate_migratepages_range()、reclaim_clean_pages_from_list()和migrate_pages()。
先看一下isolate_migratepages_range()的实现：
【file:/mm/compaction.c】
/**
* isolate_migratepages_range() - isolate all migrate-able pages in range.
* @zone: Zone pages are in.
* @cc: Compaction control structure.
* @low_pfn: The first PFN of the range.
* @end_pfn: The one-past-the-last PFN of the range.
* @unevictable: true if it allows to isolate unevictable pages
*
* Isolate all pages that can be migrated from the range specified by
* [low_pfn, end_pfn). Returns zero if there is a fatal signal
* pending), otherwise PFN of the first page that was not scanned
* (which may be both less, equal to or more then end_pfn).
*
* Assumes that cc->migratepages is empty and cc->nr_migratepages is
* zero.
*
* Apart from cc->migratepages and cc->nr_migratetypes this function
* does not modify any cc's fields, in particular it does not modify
* (or read for that matter) cc->migrate_pfn.
*/
unsigned long
isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
unsigned long low_pfn, unsigned long end_pfn, bool unevictable)
{
unsigned long last_pageblock_nr = 0, pageblock_nr;
unsigned long nr_scanned = 0, nr_isolated = 0;
struct list_head *migratelist = &cc->migratepages;
isolate_mode_t mode = 0;
struct lruvec *lruvec;
unsigned long flags;
bool locked = false;
struct page *page = NULL, *valid_page = NULL;
bool skipped_async_unsuitable = false;
/*
* Ensure that there are not too many pages isolated from the LRU
* list by either parallel reclaimers or compaction. If there are,
* delay for some time until fewer pages are isolated
*/
while (unlikely(too_many_isolated(zone))) {
/* async migration should just abort */
if (!cc->sync)
return 0;
congestion_wait(BLK_RW_ASYNC, HZ/10);
if (fatal_signal_pending(current))
return 0;
}
/* Time to isolate some pages for migration */
cond_resched();
for (; low_pfn < end_pfn; low_pfn++) {
/* give a chance to irqs before checking need_resched() */
if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) {
if (should_release_lock(&zone->lru_lock)) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
locked = false;
}
}
/*
* migrate_pfn does not necessarily start aligned to a
* pageblock. Ensure that pfn_valid is called when moving
* into a new MAX_ORDER_NR_PAGES range in case of large
* memory holes within the zone
*/
if ((low_pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
if (!pfn_valid(low_pfn)) {
low_pfn += MAX_ORDER_NR_PAGES - 1;
continue;
}
}
if (!pfn_valid_within(low_pfn))
continue;
nr_scanned++;
/*
* Get the page and ensure the page is within the same zone.
* See the comment in isolate_freepages about overlapping
* nodes. It is deliberate that the new zone lock is not taken
* as memory compaction should not move pages between nodes.
*/
page = pfn_to_page(low_pfn);
if (page_zone(page) != zone)
continue;
if (!valid_page)
valid_page = page;
/* If isolation recently failed, do not retry */
pageblock_nr = low_pfn >> pageblock_order;
if (!isolation_suitable(cc, page))
goto next_pageblock;
/*
* Skip if free. page_order cannot be used without zone->lock
* as nothing prevents parallel allocations or buddy merging.
*/
if (PageBuddy(page))
continue;
/*
* For async migration, also only scan in MOVABLE blocks. Async
* migration is optimistic to see if the minimum amount of work
* satisfies the allocation
*/
if (!cc->sync && last_pageblock_nr != pageblock_nr &&
!migrate_async_suitable(get_pageblock_migratetype(page))) {
cc->finished_update_migrate = true;
skipped_async_unsuitable = true;
goto next_pageblock;
}
/*
* Check may be lockless but that's ok as we recheck later.
* It's possible to migrate LRU pages and balloon pages
* Skip any other type of page
*/
if (!PageLRU(page)) {
if (unlikely(balloon_page_movable(page))) {
if (locked && balloon_page_isolate(page)) {
/* Successfully isolated */
cc->finished_update_migrate = true;
list_add(&page->lru, migratelist);
cc->nr_migratepages++;
nr_isolated++;
goto check_compact_cluster;
}
}
continue;
}
/*
* PageLRU is set. lru_lock normally excludes isolation
* splitting and collapsing (collapsing has already happened
* if PageLRU is set) but the lock is not necessarily taken
* here and it is wasteful to take it just to check transhuge.
* Check TransHuge without lock and skip the whole pageblock if
* it's either a transhuge or hugetlbfs page, as calling
* compound_order() without preventing THP from splitting the
* page underneath us may return surprising results.
*/
if (PageTransHuge(page)) {
if (!locked)
goto next_pageblock;
low_pfn += (1 << compound_order(page)) - 1;
continue;
}
/* Check if it is ok to still hold the lock */
locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
locked, cc);
if (!locked || fatal_signal_pending(current))
break;
/* Recheck PageLRU and PageTransHuge under lock */
if (!PageLRU(page))
continue;
if (PageTransHuge(page)) {
low_pfn += (1 << compound_order(page)) - 1;
continue;
}
if (!cc->sync)
mode |= ISOLATE_ASYNC_MIGRATE;
if (unevictable)
mode |= ISOLATE_UNEVICTABLE;
lruvec = mem_cgroup_page_lruvec(page, zone);
/* Try isolate the page */
if (__isolate_lru_page(page, mode) != 0)
continue;
VM_BUG_ON_PAGE(PageTransCompound(page), page);
/* Successfully isolated */
cc->finished_update_migrate = true;
del_page_from_lru_list(page, lruvec, page_lru(page));
list_add(&page->lru, migratelist);
cc->nr_migratepages++;
nr_isolated++;
check_compact_cluster:
/* Avoid isolating too much */
if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
++low_pfn;
break;
}
continue;
next_pageblock:
low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
last_pageblock_nr = pageblock_nr;
}
acct_isolated(zone, locked, cc);
if (locked)
spin_unlock_irqrestore(&zone->lru_lock, flags);
/*
* Update the pageblock-skip information and cached scanner pfn,
* if the whole pageblock was scanned without isolating any page.
* This is not done when pageblock was skipped due to being unsuitable
* for async compaction, so that eventual sync compaction can try.
*/
if (low_pfn == end_pfn && !skipped_async_unsuitable)
update_pageblock_skip(cc, valid_page, nr_isolated, true);
trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
count_compact_events(COMPACTMIGRATE_SCANNED, nr_scanned);
if (nr_isolated)
count_compact_events(COMPACTISOLATED, nr_isolated);
return low_pfn;
}
该函数主要是将low_pfn到end_pfn范围内，可用移动的内存页隔离出来，挂到cc->migratepages链表上。为后面的内存迁移做准备。
接着再看reclaim_clean_pages_from_list()：
【file:/mm/vmscan.c】
unsigned long reclaim_clean_pages_from_list(struct zone *zone,
struct list_head *page_list)
{
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.priority = DEF_PRIORITY,
.may_unmap = 1,
};
unsigned long ret, dummy1, dummy2, dummy3, dummy4, dummy5;
struct page *page, *next;
LIST_HEAD(clean_pages);
list_for_each_entry_safe(page, next, page_list, lru) {
if (page_is_file_cache(page) && !PageDirty(page) &&
!isolated_balloon_page(page)) {
ClearPageActive(page);
list_move(&page->lru, &clean_pages);
}
}
ret = shrink_page_list(&clean_pages, zone, &sc,
TTU_UNMAP|TTU_IGNORE_ACCESS,
&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
list_splice(&clean_pages, page_list);
__mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
return ret;
}
该函数则主要是将文件缓存、干净的以及非隔离的气球页进行直接回收。
继而分析migrate_pages()：
【file:/mm/migrate.c】
/*
* migrate_pages - migrate the pages specified in a list, to the free pages
* supplied as the target for the page migration
*
* @from: The list of pages to be migrated.
* @get_new_page: The function used to allocate free pages to be used
* as the target of the page migration.
* @private: Private data to be passed on to get_new_page()
* @mode: The migration mode that specifies the constraints for
* page migration, if any.
* @reason: The reason for page migration.
*
* The function returns after 10 attempts or if no pages are movable any more
* because the list has become empty or no retryable pages exist any more.
* The caller should call putback_lru_pages() to return pages to the LRU
* or free list only if ret != 0.
*
* Returns the number of pages that were not migrated, or an error code.
*/
int migrate_pages(struct list_head *from, new_page_t get_new_page,
unsigned long private, enum migrate_mode mode, int reason)
{
int retry = 1;
int nr_failed = 0;
int nr_succeeded = 0;
int pass = 0;
struct page *page;
struct page *page2;
int swapwrite = current->flags & PF_SWAPWRITE;
int rc;
if (!swapwrite)
current->flags |= PF_SWAPWRITE;
for(pass = 0; pass < 10 && retry; pass++) {
retry = 0;
list_for_each_entry_safe(page, page2, from, lru) {
cond_resched();
if (PageHuge(page))
rc = unmap_and_move_huge_page(get_new_page,
private, page, pass > 2, mode);
else
rc = unmap_and_move(get_new_page, private,
page, pass > 2, mode);
switch(rc) {
case -ENOMEM:
goto out;
case -EAGAIN:
retry++;
break;
case MIGRATEPAGE_SUCCESS:
nr_succeeded++;
break;
default:
/*
* Permanent failure (-EBUSY, -ENOSYS, etc.):
* unlike -EAGAIN case, the failed page is
* removed from migration page list and not
* retried in the next outer loop.
*/
nr_failed++;
break;
}
}
}
rc = nr_failed + retry;
out:
if (nr_succeeded)
count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
if (nr_failed)
count_vm_events(PGMIGRATE_FAIL, nr_failed);
trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason);
if (!swapwrite)
current->flags &= ~PF_SWAPWRITE;
return rc;
}
该函数主要实现的是页面迁移操作。其中核心函数是unmap_and_move()，其用于申请新页面，将老页面移过去再进行映射，以实现老页面得以回收。由此可知__alloc_contig_migrate_range()函数主要工作是将页面进行隔离然后再进行分离。
最后回到alloc_contig_range()函数，其从__alloc_contig_migrate_range()返回后，将再次调用lru_add_drain_all()，这里应该是为了防止__alloc_contig_migrate_range()中间休眠时，LRU链表被添加上页面了。而drain_all_pages()则是将每CPU中缓存的页面进行释放，这些页面将会根据其标记释放至MIGRATE_ISOLATE空闲列表中。接着再是test_pages_isolated()，用于检查确保该范围内的页面已经被隔离；isolate_freepages_range()则是将指定范围的空闲页面隔离出来；最后undo_isolate_page_range()则是将所有的标记为隔离的页面重新标记为MIGRATE_CMA，至此所需的连续内存页面已经分配到了，无需在乎其迁移属性了，便更改回去。
另外CMA管理内存的释放为：
【file:/mm/page_alloc.c】
void free_contig_range(unsigned long pfn, unsigned nr_pages)
{
unsigned int count = 0;
for (; nr_pages--; pfn++) {
struct page *page = pfn_to_page(pfn);
count += page_count(page) != 1;
__free_page(page);
}
WARN(count != 0, "%d pages are still in use!\n", count);
}
再次回归到__free_page()，这就便不再深入了。
原本无意于分析CMA的，一时好奇琢磨了一下，但已琢磨至此，遂记之，但有部分细节存在疑惑有待深入，因涉及面广，待后期深入分析后再进行细化。如有理解错误之处，望不吝指正。