内存管理（八）：zone的初始化
linux版本：4.14.74
硬件：ARMV8 A53
1 zone概念
物理内存可以分为内存区域zone，内核定义的对zone类型的定义如下
enum zone_type {
#ifdef CONFIG_ZONE_DMA
/*
* ZONE_DMA is used when there are devices that are not able
* to do DMA to all of addressable memory (ZONE_NORMAL). Then we
* carve out the portion of memory that is needed for these devices.
* The range is arch specific.
*
* Some examples
*
* Architecture Limit
* ---------------------------
* parisc, ia64, sparc <4G
* s390 <2G
* arm Various
* alpha Unlimited or 0-16MB.
*
* i386, x86_64 and multiple other arches
* <16M.
*/
ZONE_DMA,
#endif
#ifdef CONFIG_ZONE_DMA32
/*
* x86_64 needs two ZONE_DMAs because it supports devices that are
* only able to do DMA to the lower 16M but also 32 bit devices that
* can only do DMA areas below 4G.
*/
ZONE_DMA32,
#endif
/*
* Normal addressable memory is in ZONE_NORMAL. DMA operations can be
* performed on pages in ZONE_NORMAL if the DMA devices support
* transfers to all addressable memory.
*/
ZONE_NORMAL,
#ifdef CONFIG_HIGHMEM
/*
* A memory area that is only addressable by the kernel through
* mapping portions into its own address space. This is for example
* used by i386 to allow the kernel to address the memory beyond
* 900MB. The kernel will set up special mappings (page
* table entries on i386) for each page that the kernel needs to
* access.
*/
ZONE_HIGHMEM,
#endif
ZONE_MOVABLE,
#ifdef CONFIG_ZONE_DEVICE
ZONE_DEVICE,
#endif
__MAX_NR_ZONES
};
- ZONE DMA: DMA区域。有些设备不能直接访问所有内存，需要使用DMA区域，如旧的ISA总线只能访问16MB一下的内存
- DMA32区域：64位系统，如果既要支持只能访问16MB一下内存的设备，又要支持只能访问4GB以下内存的32位设备，那么必须使用DMA32区域
- 普通区域：直接映射到内核虚拟地址空间的内存区域
- 高端内存区域，32bit时代的产物，64bit内核虚拟地址空间非常大，完全够用了，不再需要这块区域
- 可移动区域，它是一个伪内存区域，用来防止内存碎片。
- 设备区域，为了支持永久内存热插拔增加的内存区域
内存区域用一个结构体zone描述
struct zone {
/* Read-mostly fields */
/* zone watermarks, access with *_wmark_pages(zone) macros */
unsigned long watermark[NR_WMARK]; /*页分配器使用的水线*/
...
long lowmem_reserve[MAX_NR_ZONES]; //页分配器使用，当前区域保留多少
//页不能借给高的区域类型
struct pglist_data *zone_pgdat; //指向内存节点的pglist_data实例
struct per_cpu_pageset __percpu *pageset; //每处理器页集合
...
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
unsigned long zone_start_pfn; //当前区域的起始物理页号
unsigned long managed_pages; //伙伴分配器管理的物理页的数量
unsigned long spanned_pages; //当前区域跨越的总页数，包括空洞
unsigned long present_pages; //当前区域存在的物理页的数量，不包括空洞
const char *name; //区域名称
/* free areas of different sizes */
/*不同长度的空闲区域*/
struct free_area free_area[MAX_ORDER];
...
} ____cacheline_internodealigned_in_smp;
2 zone 初始化
bootmem_init中将调用zone_sizes_init函数进行zone初始化
void __init bootmem_init(void)
{
unsigned long min, max;
min = PFN_UP(memblock_start_of_DRAM());
max = PFN_DOWN(memblock_end_of_DRAM());
early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
max_pfn = max_low_pfn = max;
arm64_numa_init();
/*
* Sparsemem tries to allocate bootmem in memory_present(), so must be
* done after the fixed reservations.
*/
arm64_memory_present();
sparse_init();
zone_sizes_init(min, max);
memblock_dump_all();
}
static void __init zone_sizes_init(unsigned long min, unsigned long max)
{
struct memblock_region *reg;
unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
unsigned long max_dma = min;
memset(zone_size, 0, sizeof(zone_size));
/* 4GB maximum for 32-bit only capable devices */
/****1***/
#ifdef CONFIG_ZONE_DMA
max_dma = PFN_DOWN(arm64_dma_phys_limit);
zone_size[ZONE_DMA] = max_dma - min;
#endif
zone_size[ZONE_NORMAL] = max - max_dma;
memcpy(zhole_size, zone_size, sizeof(zhole_size));
for_each_memblock(memory, reg) {
unsigned long start = memblock_region_memory_base_pfn(reg);
unsigned long end = memblock_region_memory_end_pfn(reg);
if (start >= max)
continue;
#ifdef CONFIG_ZONE_DMA
if (start < max_dma) {
unsigned long dma_end = min(end, max_dma);
zhole_size[ZONE_DMA] -= dma_end - start;
}
#endif
if (end > max_dma) {
unsigned long normal_end = min(end, max);
unsigned long normal_start = max(start, max_dma);
zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
}
}
/****2*****/
free_area_init_node(0, zone_size, min, zhole_size);
}
- 是否定义了DMA区域，我的项目中定义了这个区域，并且这个区域最大支持4G大小，而项目中的内存最大也不超过4G，所以实际上只有这一个区域，normal区域也不复存在了
- 对pglist字段初始化，管理zone区域
void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
unsigned long node_start_pfn, unsigned long *zholes_size)
{
pg_data_t *pgdat = NODE_DATA(nid);
unsigned long start_pfn = 0;
unsigned long end_pfn = 0;
/* pg_data_t should be reset to zero when it's allocated */
WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
pgdat->node_id = nid;
pgdat->node_start_pfn = node_start_pfn;
pgdat->per_cpu_nodestats = NULL;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid,
(u64)start_pfn << PAGE_SHIFT,
end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0);
#else
start_pfn = node_start_pfn;
#endif
/******1*****/
calculate_node_totalpages(pgdat, start_pfn, end_pfn,
zones_size, zholes_size);
alloc_node_mem_map(pgdat);
#ifdef CONFIG_FLAT_NODE_MEM_MAP
printk(KERN_DEBUG "free_area_init_node: node %d, pgdat %08lx, node_mem_map %08lx\n",
nid, (unsigned long)pgdat,
(unsigned long)pgdat->node_mem_map);
#endif
reset_deferred_meminit(pgdat);
/***2****/
free_area_init_core(pgdat);
}
- 计算当前zone的page数量，包括spanned_pages(总页数)，present_pages（不包含空洞的总页数），并对node的总页数进行累加
- 继续对pgdat初始化
/*
* Set up the zone data structures:
* - mark all pages reserved
* - mark all memory queues empty
* - clear the memory bitmaps
*
* NOTE: pgdat should get zeroed by caller.
*/
static void __paginginit free_area_init_core(struct pglist_data *pgdat)
{
enum zone_type j;
int nid = pgdat->node_id;
pgdat_resize_init(pgdat);
#ifdef CONFIG_NUMA_BALANCING
spin_lock_init(&pgdat->numabalancing_migrate_lock);
pgdat->numabalancing_migrate_nr_pages = 0;
pgdat->numabalancing_migrate_next_window = jiffies;
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
spin_lock_init(&pgdat->split_queue_lock);
INIT_LIST_HEAD(&pgdat->split_queue);
pgdat->split_queue_len = 0;
#endif
init_waitqueue_head(&pgdat->kswapd_wait);
init_waitqueue_head(&pgdat->pfmemalloc_wait);
#ifdef CONFIG_COMPACTION
init_waitqueue_head(&pgdat->kcompactd_wait);
#endif
pgdat_page_ext_init(pgdat);
spin_lock_init(&pgdat->lru_lock);
lruvec_init(node_lruvec(pgdat));
pgdat->per_cpu_nodestats = &boot_nodestats;
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, freesize, memmap_pages;
unsigned long zone_start_pfn = zone->zone_start_pfn;
size = zone->spanned_pages;
realsize = freesize = zone->present_pages;
/*
* Adjust freesize so that it accounts for how much memory
* is used by this zone for memmap. This affects the watermark
* and per-cpu initialisations
*/
/******1*****/
memmap_pages = calc_memmap_size(size, realsize);
if (!is_highmem_idx(j)) {
if (freesize >= memmap_pages) {
freesize -= memmap_pages;
if (memmap_pages)
printk(KERN_DEBUG
" %s zone: %lu pages used for memmap\n",
zone_names[j], memmap_pages);
} else
pr_warn(" %s zone: %lu pages exceeds freesize %lu\n",
zone_names[j], memmap_pages, freesize);
}
/* Account for reserved pages */
if (j == 0 && freesize > dma_reserve) {
freesize -= dma_reserve;
printk(KERN_DEBUG " %s zone: %lu pages reserved\n",
zone_names[0], dma_reserve);
}
if (!is_highmem_idx(j))
nr_kernel_pages += freesize;
/* Charge for highmem memmap if there are enough kernel pages */
else if (nr_kernel_pages > memmap_pages * 2)
nr_kernel_pages -= memmap_pages;
nr_all_pages += freesize;
/*
* Set an approximate value for lowmem here, it will be adjusted
* when the bootmem allocator frees pages into the buddy system.
* And all highmem pages will be managed by the buddy system.
*/
zone->managed_pages = is_highmem_idx(j) ? realsize : freesize;
#ifdef CONFIG_NUMA
zone->node = nid;
#endif
zone->name = zone_names[j];
zone->zone_pgdat = pgdat;
spin_lock_init(&zone->lock);
zone_seqlock_init(zone);
zone_pcp_init(zone);
if (!size)
continue;
set_pageblock_order();
setup_usemap(pgdat, zone, zone_start_pfn, size);
init_currently_empty_zone(zone, zone_start_pfn, size);
memmap_init(size, nid, j, zone_start_pfn);
}
}
- 一个struct page结构体大小64字节，存储这个区域中可用的页数（present_pages）需要多少struct page，这些struct page总共会占用多少页大小
参考文件
《Linux内核深度解析》