linux内存管理——内存初始化1—物理内存初始化
备注:
1. Kernel版本:5.4.95
2. 使用工具:Source Insight 4.0
1 linux物理内存的组织形式
Linux把物理内存划分为三个层次来管理
层次 | 描述 |
---|---|
存储节点(Node) | CPU被划分为多个节点(node), 内存则被分簇, 每个CPU对应一个本地物理内存, 即一个CPU-node对应一个内存簇bank,即每个内存簇被认为是一个节点 |
管理区(Zone) | 每个物理内存节点node被划分为多个内存管理区域, 用于表示不同范围的内存, 内核可以使用不同的映射方式映射物理内存 |
页面(Page) | 内存被细分为多个页面帧, 页面是最基本的页面分配的单位 |
物理内存初始化是随着Linux内核初始化进行的,同时内存管理也是其他很多其他功能的基础。和内核中各种模块耦合在一起。在进行初始化之前,了解Linux内存管理框架图有助于对内存管理有个大概的映像。
首先,需要知道整个用户和内核空间是如何划分的(3:1、2:2),然后从Node->Zone->Page的层级进行初始化,直到内存达到可用状态。关于Nodes、Zones、Pages三者之间的关系,《ULVMM》 Figure 2.1介绍,虽然zone_mem_map一层已经被替代,但是仍然反映了他们之间的层级树形关系。pg_data_t对应一个Node,node_zones包含了不同Zone;Zone下又定义了per_cpu_pageset,将page和cpu绑定。
- 首先, 内存被划分为结点. 每个节点关联到系统中的一个处理器, 内核中表示为pg_data_t的实例. 系统中每个节点被链接到一个以NULL结尾的pgdat_list链表中<而其中的每个节点利用pg_data_tnode_next字段链接到下一节.而对于PC这种UMA结构的机器来说, 只使用了一个成为contig_page_data的静态pg_data_t结构.
- 接着各个节点又被划分为内存管理区域, 一个管理区域通过struct zone_struct描述, 其被定义为zone_t, 用以表示内存的某个范围, 低端范围的16MB被描述为ZONE_DMA, 某些工业标准体系结构中的(ISA)设备需要用到它, 然后是可直接映射到内核的普通内存域ZONE_NORMAL,最后是超出了内核段的物理地址域ZONE_HIGHMEM, 被称为高端内存. 是系统中预留的可用内存空间, 不能被内核直接映射.
- 最后页帧(page frame)代表了系统内存的最小单位, 堆内存中的每个页都会创建一个struct page的一个实例. 传统上,把内存视为连续的字节,即内存为字节数组,内存单元的编号(地址)可作为字节数组的索引. 分页管理时,将若干字节视为一页,比如4K byte. 此时,内存变成了连续的页,即内存为页数组,每一页物理内存叫页帧,以页为单位对内存进行编号,该编号可作为页数组的索引,又称为页帧号.
在一个单独的节点内,任一给定CPU访问页面所需的时间都是相同的。然而,对不同的CPU,这个时间可能就不同。对每个CPU而言,内核都试图把耗时节点的访问次数减到最少这就要小心地选择CPU最常引用的内核数据结构的存放位置.
1.1 内存节点node
在LINUX中引入一个数据结构struct pglist_data ,来描述一个node,定义在include/linux/mmzone.h 文件中。
//include/linux/mmzone.h
/*
* On NUMA machines, each NUMA node would have a pg_data_t to describe
* it's memory layout. On UMA machines there is a single pglist_data which
* describes the whole memory.
*
* Memory statistics and page replacement data structures are maintained on a
* per-zone basis.
*/
struct bootmem_data;
typedef struct pglist_data {
struct zone node_zones[MAX_NR_ZONES];
struct zonelist node_zonelists[MAX_ZONELISTS];
int nr_zones;
#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */
struct page *node_mem_map;
#ifdef CONFIG_PAGE_EXTENSION
struct page_ext *node_page_ext;
#endif
#endif
#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
/*
* Must be held any time you expect node_start_pfn,
* node_present_pages, node_spanned_pages or nr_zones to stay constant.
* Also synchronizes pgdat->first_deferred_pfn during deferred page
* init.
*
* pgdat_resize_lock() and pgdat_resize_unlock() are provided to
* manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG
* or CONFIG_DEFERRED_STRUCT_PAGE_INIT.
*
* Nests above zone->lock and zone->span_seqlock
*/
spinlock_t node_size_lock;
#endif
unsigned long node_start_pfn;
unsigned long node_present_pages; /* total number of physical pages */
unsigned long node_spanned_pages; /* total size of physical page
range, including holes */
int node_id;
wait_queue_head_t kswapd_wait;
wait_queue_head_t pfmemalloc_wait;
struct task_struct *kswapd; /* Protected by
mem_hotplug_begin/end() */
int kswapd_order;
enum zone_type kswapd_classzone_idx;
int kswapd_failures; /* Number of 'reclaimed == 0' runs */
#ifdef CONFIG_COMPACTION
int kcompactd_max_order;
enum zone_type kcompactd_classzone_idx;
wait_queue_head_t kcompactd_wait;
struct task_struct *kcompactd;
#endif
/*
* This is a per-node reserve of pages that are not available
* to userspace allocations.
*/
unsigned long totalreserve_pages;
#ifdef CONFIG_NUMA
/*
* zone reclaim becomes active if more unmapped pages exist.
*/
unsigned long min_unmapped_pages;
unsigned long min_slab_pages;
#endif /* CONFIG_NUMA */
/* Write-intensive fields used by page reclaim */
ZONE_PADDING(_pad1_)
spinlock_t lru_lock;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
* If memory initialisation on large machines is deferred then this
* is the first PFN that needs to be initialised.
*/
unsigned long first_deferred_pfn;
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
struct deferred_split deferred_split_queue;
#endif
/* Fields commonly accessed by the page reclaim scanner */
struct lruvec lruvec;
unsigned long flags;
ZONE_PADDING(_pad2_)
/* Per-node vmstats */
struct per_cpu_nodestat __percpu *per_cpu_nodestats;
atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS];
} pg_data_t;
1.2 物理内存区域zone
Linux内核对不同区域的内存需要采用不同的管理方式和映射方式,
为了解决这些制约条件,Linux使用了三种区:
ZONE_DMA : 这个区包含的页用来执行DMA操作。
ZONE_NOMAL : 这个区包含的都是能正常映射的页。
ZONE_HIGHEM : 这个区包”高端内存”,其中的页能不永久地映射到内核地址空间
而为了兼容一些设备的热插拔支持以及内存碎片化的处理, 内核也引入一些逻辑上的内存区.
ZONE_MOVABLE : 内核定义了一个伪内存域ZONE_MOVABLE, 在防止物理内存碎片的机制memory migration中需要使用该内存域. 供防止物理内存碎片的极致使用
ZONE_DEVICE : 为支持热插拔设备而分配的Non Volatile Memory非易失性内存
内核将每个簇所对应的node又被分成的称为管理区(zone)的块,它们各自描述在内存中的范围。一个管理区(zone)由struct zone结构体来描述,在linux-5.4.95之前的内核中是用typedef struct zone_struct zone_t数据结构来描述)
//include/linux/mmzone.h
struct zone {
/* Read-mostly fields */
/* zone watermarks, access with *_wmark_pages(zone) macros */
unsigned long _watermark[NR_WMARK];
unsigned long watermark_boost;
unsigned long nr_reserved_highatomic;
/*
* We don't know if the memory that we're going to allocate will be
* freeable or/and it will be released eventually, so to avoid totally
* wasting several GB of ram we must reserve some of the lower zone
* memory (otherwise we risk to run OOM on the lower zones despite
* there being tons of freeable ram on the higher zones). This array is
* recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl
* changes.
*/
long lowmem_reserve[MAX_NR_ZONES];
#ifdef CONFIG_NUMA
int node;
#endif
struct pglist_data *zone_pgdat;
struct per_cpu_pageset __percpu *pageset;
#ifndef CONFIG_SPARSEMEM
/*
* Flags for a pageblock_nr_pages block. See pageblock-flags.h.
* In SPARSEMEM, this map is stored in struct mem_section
*/
unsigned long *pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
unsigned long zone_start_pfn;
/*
* spanned_pages is the total pages spanned by the zone, including
* holes, which is calculated as:
* spanned_pages = zone_end_pfn - zone_start_pfn;
*
* present_pages is physical pages existing within the zone, which
* is calculated as:
* present_pages = spanned_pages - absent_pages(pages in holes);
*
* managed_pages is present pages managed by the buddy system, which
* is calculated as (reserved_pages includes pages allocated by the
* bootmem allocator):
* managed_pages = present_pages - reserved_pages;
*
* So present_pages may be used by memory hotplug or memory power
* management logic to figure out unmanaged pages by checking
* (present_pages - managed_pages). And managed_pages should be used
* by page allocator and vm scanner to calculate all kinds of watermarks
* and thresholds.
*
* Locking rules:
*
* zone_start_pfn and spanned_pages are protected by span_seqlock.
* It is a seqlock because it has to be read outside of zone->lock,
* and it is done in the main allocator path. But, it is written
* quite infrequently.
*
* The span_seq lock is declared along with zone->lock because it is
* frequently read in proximity to zone->lock. It's good to
* give them a chance of being in the same cacheline.
*
* Write access to present_pages at runtime should be protected by
* mem_hotplug_begin/end(). Any reader who can't tolerant drift of
* present_pages should get_online_mems() to get a stable value.
*/
atomic_long_t managed_pages;
unsigned long spanned_pages;
unsigned long present_pages;
const char *name;
#ifdef CONFIG_MEMORY_ISOLATION
/*
* Number of isolated pageblock. It is used to solve incorrect
* freepage counting problem due to racy retrieving migratetype
* of pageblock. Protected by zone->lock.
*/
unsigned long nr_isolate_pageblock;
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/* see spanned/present_pages for more description */
seqlock_t span_seqlock;
#endif
int initialized;
/* Write-intensive fields used from the page allocator */
ZONE_PADDING(_pad1_)
/* free areas of different sizes */
struct free_area free_area[MAX_ORDER];
/* zone flags, see below */
unsigned long flags;
/* Primarily protects free_area */
spinlock_t lock;
/* Write-intensive fields used by compaction and vmstats. */
ZONE_PADDING(_pad2_)
/*
* When free pages are below this point, additional steps are taken
* when reading the number of free pages to avoid per-cpu counter
* drift allowing watermarks to be breached
*/
unsigned long percpu_drift_mark;
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* pfn where compaction free scanner should start */
unsigned long compact_cached_free_pfn;
/* pfn where async and sync compaction migration scanner should start */
unsigned long compact_cached_migrate_pfn[2];
unsigned long compact_init_migrate_pfn;
unsigned long compact_init_free_pfn;
#endif
#ifdef CONFIG_COMPACTION
/*
* On compaction failure, 1<<compact_defer_shift compactions
* are skipped before trying again. The number attempted since
* last failure is tracked with compact_considered.
*/
unsigned int compact_considered;
unsigned int compact_defer_shift;
int compact_order_failed;
#endif
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* Set to true when the PG_migrate_skip bits should be cleared */
bool compact_blockskip_flush;
#endif
bool contiguous;
ZONE_PADDING(_pad3_)
/* Zone statistics */
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
} ____cacheline_internodealigned_in_smp;
2 内核空间与用户空间的划分
这样配置的结果就是生成的autoconf.h定义了#define CONFIG_PAGE_OFFSET 0xC0000000。
在arch/arm/include/asm/memory.h中,可以看出PAGE_OFFSET是用户空间和内核空间的分水岭。也是用内核空间的起始点。
#define PLAT_PHYS_OFFSET UL(CONFIG_PHYS_OFFSET)
#define PHYS_OFFSET PLAT_PHYS_OFFSET
#define PHYS_PFN_OFFSET ((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT))
static inline phys_addr_t __virt_to_phys_nodebug(unsigned long x)
{
return (phys_addr_t)x - PAGE_OFFSET + PHYS_OFFSET;
}
static inline unsigned long __phys_to_virt(phys_addr_t x)
{
return x - PHYS_OFFSET + PAGE_OFFSET;
}
3 物理内存初始化流程
3.1 初始化流程框图
3.2 物理内存的获取及memblock
3.2.1 物理内存的获取
后面的一切初始化以及内存管理都是基于物理内存,所以首先要获取物理内存的物理地址和大小。通过DTS获取物理内存属性,然后解析并添加到memblock子系统中。
arch/arm/boot/dts/arobot-*.dts:
memory {
device_type = "memory";
reg = <0x10000000 0x4000000>; //64MB
};
根据上面的dts,在start_kernel–>setup_arch–>setup_machine_fdt–>early_init_dt_scan_nodes–>of_scan_flat_dt(遍历Nodes)–>early_init_dt_scan_memory(初始化单个内存Node)。结果是从DTS解析出base size分别是0x10000000 0x4000000。
/**
* early_init_dt_scan_memory - Look for and parse memory nodes
*/
int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
int depth, void *data)
{
const char *type = of_get_flat_dt_prop(node, "device_type", NULL); //device_type = "memory"
const __be32 *reg, *endp;
int l;
bool hotpluggable;
/* We are scanning "memory" nodes only */
if (type == NULL || strcmp(type, "memory") != 0)
return 0;
reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l);
if (reg == NULL)
reg = of_get_flat_dt_prop(node, "reg", &l);//reg = <0x10000000 0x0400_0000> //64MB
if (reg == NULL)
return 0;
endp = reg + (l / sizeof(__be32));
hotpluggable = of_get_flat_dt_prop(node, "hotpluggable", NULL);
pr_debug("memory scan node %s, reg size %d,\n", uname, l);
while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) {
u64 base, size;
base = dt_mem_next_cell(dt_root_addr_cells, ®);//0x1000_0000
size = dt_mem_next_cell(dt_root_size_cells, ®);//0x0400_0000
if (size == 0)
continue;
pr_debug(" - %llx , %llx\n", (unsigned long long)base,
(unsigned long long)size);
early_init_dt_add_memory_arch(base, size);
if (!hotpluggable)
continue;
if (early_init_dt_mark_hotplug_memory_arch(base, size))
pr_warn("failed to mark hotplug range 0x%llx - 0x%llx\n",
base, base + size);
}
return 0;
}
3.2.2 add memory
#ifndef MIN_MEMBLOCK_ADDR
#define MIN_MEMBLOCK_ADDR __pa(PAGE_OFFSET)//物理基地址(0x1000_0000)
#endif
#ifndef MAX_MEMBLOCK_ADDR
#define MAX_MEMBLOCK_ADDR ((phys_addr_t)~0)//32bit,MAX_MEMBLOCK_ADDR = 0xffff_ffff
#endif
void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
{
const u64 phys_offset = MIN_MEMBLOCK_ADDR;
//size<PAGE_SIZE(4K),该memory则无效,并报warn
if (size < PAGE_SIZE - (base & ~PAGE_MASK)) {
pr_warn("Ignoring memory block 0x%llx - 0x%llx\n",
base, base + size);
return;
}
//base = PAGE_ALIGN,即4K对齐
if (!PAGE_ALIGNED(base)) {
size -= PAGE_SIZE - (base & ~PAGE_MASK);
base = PAGE_ALIGN(base);
}
size &= PAGE_MASK;
//大于0xffff_ffff,则报warn
if (base > MAX_MEMBLOCK_ADDR) {
pr_warning("Ignoring memory block 0x%llx - 0x%llx\n",
base, base + size);
return;
}
//最大地址大于0xffff_ffff,则取小于0xffff_ffff,其余舍弃
if (base + size - 1 > MAX_MEMBLOCK_ADDR) {
pr_warning("Ignoring memory range 0x%llx - 0x%llx\n",
((u64)MAX_MEMBLOCK_ADDR) + 1, base + size);
size = MAX_MEMBLOCK_ADDR - base + 1;
}
//base + size < MIN_MEMBLOCK_ADDR,直接报warn,并退出
if (base + size < phys_offset) {
pr_warning("Ignoring memory block 0x%llx - 0x%llx\n",
base, base + size);
return;
}
//base < MIN_MEMBLOCK_ADDR,则丢弃小于MIN_MEMBLOCK_ADDR部分
if (base < phys_offset) {
pr_warning("Ignoring memory range 0x%llx - 0x%llx\n",
base, phys_offset);
size -= phys_offset - base;
base = phys_offset;
}
//添加memory
memblock_add(base, size);
}
/**
* memblock_add - add new memblock region
* @base: base address of the new region
* @size: size of the new region
*
* Add new memblock region [@base, @base + @size) to the "memory"
* type. See memblock_add_range() description for mode details
*
* Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
memblock_dbg("memblock_add: [%pa-%pa] %pS\n",
&base, &end, (void *)_RET_IP_);
return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0);
}
memblock的定义:
//include/linux/memblock.h
/**
* struct memblock_type - collection of memory regions of certain type
* @cnt: number of regions
* @max: size of the allocated array
* @total_size: size of all regions
* @regions: array of regions
* @name: the memory type symbolic name
*/
struct memblock_type {
unsigned long cnt;
unsigned long max;
phys_addr_t total_size;
struct memblock_region *regions;
char *name;
};
/**
* struct memblock - memblock allocator metadata
* @bottom_up: is bottom up direction?
* @current_limit: physical address of the current allocation limit
* @memory: usabe memory regions
* @reserved: reserved memory regions
* @physmem: all physical memory
*/
struct memblock {
bool bottom_up; /* is bottom up direction? */
phys_addr_t current_limit;
struct memblock_type memory; //添加物理内存区域
struct memblock_type reserved; //添加预留内存保存区域
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
struct memblock_type physmem;
#endif
};
struct memblock memblock __initdata_memblock = {
.memory.regions = memblock_memory_init_regions,
.memory.cnt = 1, /* empty dummy entry */
.memory.max = INIT_MEMBLOCK_REGIONS,
.memory.name = "memory",
.reserved.regions = memblock_reserved_init_regions,
.reserved.cnt = 1, /* empty dummy entry */
.reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS,
.reserved.name = "reserved",
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
.physmem.regions = memblock_physmem_init_regions,
.physmem.cnt = 1, /* empty dummy entry */
.physmem.max = INIT_PHYSMEM_REGIONS,
.physmem.name = "physmem",
#endif
.bottom_up = false,
.current_limit = MEMBLOCK_ALLOC_ANYWHERE,
};
/**
* memblock_add - add new memblock region
* @base: base address of the new region
* @size: size of the new region
*
* Add new memblock region [@base, @base + @size) to the "memory"
* type. See memblock_add_range() description for mode details
*
* Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
memblock_dbg("memblock_add: [%pa-%pa] %pS\n",
&base, &end, (void *)_RET_IP_);
return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0);
}
图中的左侧是函数的执行流程图,执行效果是右侧部分。右侧部分画的是一个典型的情况,实际的情况可能有多种,但是核心的逻辑都是对插入的region进行判断,如果出现了物理地址范围重叠的部分,那就进行split操作,最终对具有相同flag的region进行merge操作。
/**
* memblock_add_range - add new memblock region
* @type: memblock type to add new region into
* @base: base address of the new region
* @size: size of the new region
* @nid: nid of the new region
* @flags: flags of the new region
*
* Add new memblock region [@base, @base + @size) into @type. The new region
* is allowed to overlap with existing ones - overlaps don't affect already
* existing regions. @type is guaranteed to be minimal (all neighbouring
* compatible regions are merged) after the addition.
*
* Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_add_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size,
int nid, enum memblock_flags flags)
{
bool insert = false;
phys_addr_t obase = base;
phys_addr_t end = base + memblock_cap_size(base, &size);
int idx, nr_new;
struct memblock_region *rgn;
if (!size)
return 0;
/* special case for empty array */
if (type->regions[0].size == 0) {
WARN_ON(type->cnt != 1 || type->total_size);
type->regions[0].base = base;
type->regions[0].size = size;
type->regions[0].flags = flags;
memblock_set_region_node(&type->regions[0], nid);
type->total_size = size;
return 0;
}
repeat:
/*
* The following is executed twice. Once with %false @insert and
* then with %true. The first counts the number of regions needed
* to accommodate the new area. The second actually inserts them.
*/
base = obase;
nr_new = 0;
for_each_memblock_type(idx, type, rgn) {
phys_addr_t rbase = rgn->base;
phys_addr_t rend = rbase + rgn->size;
if (rbase >= end)
break;
if (rend <= base)
continue;
/*
* @rgn overlaps. If it separates the lower part of new
* area, insert that portion.
*/
if (rbase > base) {
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
WARN_ON(nid != memblock_get_region_node(rgn));
#endif
WARN_ON(flags != rgn->flags);
nr_new++;
if (insert)
memblock_insert_region(type, idx++, base,
rbase - base, nid,
flags);
}
/* area below @rend is dealt with, forget about it */
base = min(rend, end);
}
/* insert the remaining portion */
if (base < end) {
nr_new++;
if (insert)
memblock_insert_region(type, idx, base, end - base,
nid, flags);
}
if (!nr_new)
return 0;
/*
* If this was the first round, resize array and repeat for actual
* insertions; otherwise, merge and return.
*/
if (!insert) {
while (type->cnt + nr_new > type->max)
if (memblock_double_array(type, obase, size) < 0)
return -ENOMEM;
insert = true;
goto repeat;
} else {
memblock_merge_regions(type);
return 0;
}
}
3.3 early_mem init
3.3.1 DTB fixmap
boot会将kernel image和dtb拷贝到内存中,并且将dtb物理地址告知kernel,kernel需要从该物理地址上读取到dtb文件并解析,才能得到最终的内存信息,dtb的物理地址需要映射到虚拟地址上才能访问,但是这个时候paging_init还没有调用,也就是说物理地址的映射还没有完成,那该怎么办呢?没错,Fixed map机制出现了。
简单来说,Fixed map指的是虚拟地址中的一段区域,在该区域中所有的线性地址是在编译阶段就确定好的,这些虚拟地址需要在boot阶段去映射到物理地址上。来看看虚拟地址空间:
Virtual kernel memory layout:
vector : 0xffff0000 - 0xffff1000 ( 4 kB)
fixmap : 0xffc00000 - 0xfff00000 (3072 kB)
vmalloc : 0xc4000000 - 0xff800000 ( 952 MB)
lowmem : 0xc0000000 - 0xc3e80000 ( 62 MB)
modules : 0xbf000000 - 0xc0000000 ( 16 MB)
.text : 0x(ptrval) - 0x(ptrval) (5088 kB)
.init : 0x(ptrval) - 0x(ptrval) (1024 kB)
.data : 0x(ptrval) - 0x(ptrval) ( 149 kB)
.bss : 0x(ptrval) - 0x(ptrval) ( 224 kB)
fixmap : 0xffc00000 - 0xfff00000 (3072 kB)描述的就是fixed map的区域。
从图中可以看出,如果要访问DTB所在的物理地址,那么需要将该物理地址映射到Fixed map中的区域,然后访问该区域中的虚拟地址即可。像访问IO空间也是一样的道理,下文也会讲述到。那么来看看early_fixmap_init函数的关键代码吧:
#define FIXADDR_START 0xffc00000UL
#define FIXADDR_END 0xfff00000UL
#define FIXADDR_TOP (FIXADDR_END - PAGE_SIZE)
static inline pmd_t * __init fixmap_pmd(unsigned long addr)
{
//根据传入的虚拟地址addr,计算得到pgd table中的某个entry,并返回其虚拟地址。
pgd_t *pgd = pgd_offset_k(addr);
//根据传入的虚拟地址addr,计算得到pud table中的某个entry,并返回其虚拟地址。
pud_t *pud = pud_offset(pgd, addr);
//根据传入的虚拟地址addr,计算得到pmd table中的某个entry,并返回其虚拟地址。
pmd_t *pmd = pmd_offset(pud, addr);
return pmd;
}
void __init early_fixmap_init(void)
{
pmd_t *pmd;
/*
* The early fixmap range spans multiple pmds, for which
* we are not prepared:
*/
BUILD_BUG_ON((__fix_to_virt(__end_of_early_ioremap_region) >> PMD_SHIFT)
!= FIXADDR_TOP >> PMD_SHIFT);
//根据传入的虚拟地址,计算得到pmd table中的某个entry,并返回其虚拟地址
pmd = fixmap_pmd(FIXADDR_TOP);//FIXADDR_TOP = 0xfff00000UL - 0x1000
//将pte table的物理地址填充到pmd entry中
pmd_populate_kernel(&init_mm, pmd, bm_pte);
pte_offset_fixmap = pte_offset_early_fixmap;
}
事实上,early_fixmap_init只是建立了一个映射的框架,具体的物理地址和虚拟地址的映射没有去填充,这个是由使用者具体在使用时再去填充对应的pte entry。比如像fixmap_remap_fdt()函数,就是典型的填充pte entry的过程,完成最后的一步映射,然后才能读取dtb文件。
3.3.2 early_ioremap_init
对于一些硬件需要在内存管理系统起来之前就要工作的,我们就可以使用这种机制来映射内存给这些硬件driver使用。各个模块在使用完early ioremap的地址后,需要尽快把这段映射的虚拟地址释放掉,这样才能反复被其他模块继续申请使用。
static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata;
void __init early_ioremap_setup(void)
{
int i;
for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
if (WARN_ON(prev_map[i]))
break;
for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i);
}
/*
* Must be called after early_fixmap_init
*/
void __init early_ioremap_init(void)
{
early_ioremap_setup();
}
3.3.4 early_mm_init
void __init early_mm_init(const struct machine_desc *mdesc)
{
build_mem_type_table();//根据不同的arm架构,设置mem_types表
early_paging_init(mdesc);
}
根据不同的cpu架构初始化PMD页表属性:
mem_types的定义:
//arch/arm/mm/mm.h
struct mem_type {
pteval_t prot_pte; //二级页表的属性
pteval_t prot_pte_s2;
pmdval_t prot_l1; //二级映射中的一级页表属性
pmdval_t prot_sect; //一级页表属性,只一级映射
unsigned int domain; //映射的页框所属的domain
};
//arch/arm/mm/mmu.c
static struct mem_type mem_types[] __ro_after_init = {
[MT_DEVICE] = { /* Strongly ordered / ARMv6 shared device */
.prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED |
L_PTE_SHARED,
.prot_pte_s2 = s2_policy(PROT_PTE_S2_DEVICE) |
s2_policy(L_PTE_S2_MT_DEV_SHARED) |
L_PTE_SHARED,
.prot_l1 = PMD_TYPE_TABLE,
.prot_sect = PROT_SECT_DEVICE | PMD_SECT_S,
.domain = DOMAIN_IO,
},
[MT_DEVICE_NONSHARED] = { /* ARMv6 non-shared device */
.prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_NONSHARED,
.prot_l1 = PMD_TYPE_TABLE,
.prot_sect = PROT_SECT_DEVICE,
.domain = DOMAIN_IO,
},
[MT_DEVICE_CACHED] = { /* ioremap_cached */
.prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_CACHED,
.prot_l1 = PMD_TYPE_TABLE,
.prot_sect = PROT_SECT_DEVICE | PMD_SECT_WB,
.domain = DOMAIN_IO,
},
[MT_DEVICE_WC] = { /* ioremap_wc */
.prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_WC,
.prot_l1 = PMD_TYPE_TABLE,
.prot_sect = PROT_SECT_DEVICE,
.domain = DOMAIN_IO,
},
[MT_UNCACHED] = {
.prot_pte = PROT_PTE_DEVICE,
.prot_l1 = PMD_TYPE_TABLE,
.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN,
.domain = DOMAIN_IO,
},
[MT_CACHECLEAN] = {
.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN,
.domain = DOMAIN_KERNEL,
},
#ifndef CONFIG_ARM_LPAE
[MT_MINICLEAN] = {
.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN | PMD_SECT_MINICACHE,
.domain = DOMAIN_KERNEL,
},
#endif
[MT_LOW_VECTORS] = {
.prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
L_PTE_RDONLY,
.prot_l1 = PMD_TYPE_TABLE,
.domain = DOMAIN_VECTORS,
},
[MT_HIGH_VECTORS] = {
.prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
L_PTE_USER | L_PTE_RDONLY,
.prot_l1 = PMD_TYPE_TABLE,
.domain = DOMAIN_VECTORS,
},
[MT_MEMORY_RWX] = {
.prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
.prot_l1 = PMD_TYPE_TABLE,
.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
.domain = DOMAIN_KERNEL,
},
[MT_MEMORY_RW] = {
.prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
L_PTE_XN,
.prot_l1 = PMD_TYPE_TABLE,
.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
.domain = DOMAIN_KERNEL,
},
[MT_ROM] = {
.prot_sect = PMD_TYPE_SECT,
.domain = DOMAIN_KERNEL,
},
[MT_MEMORY_RWX_NONCACHED] = {
.prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
L_PTE_MT_BUFFERABLE,
.prot_l1 = PMD_TYPE_TABLE,
.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
.domain = DOMAIN_KERNEL,
},
[MT_MEMORY_RW_DTCM] = {
.prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
L_PTE_XN,
.prot_l1 = PMD_TYPE_TABLE,
.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN,
.domain = DOMAIN_KERNEL,
},
[MT_MEMORY_RWX_ITCM] = {
.prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
.prot_l1 = PMD_TYPE_TABLE,
.domain = DOMAIN_KERNEL,
},
[MT_MEMORY_RW_SO] = {
.prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
L_PTE_MT_UNCACHED | L_PTE_XN,
.prot_l1 = PMD_TYPE_TABLE,
.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_S |
PMD_SECT_UNCACHED | PMD_SECT_XN,
.domain = DOMAIN_KERNEL,
},
[MT_MEMORY_DMA_READY] = {
.prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
L_PTE_XN,
.prot_l1 = PMD_TYPE_TABLE,
.domain = DOMAIN_KERNEL,
},
};
cache_policies的定义:
//arch/arm/mm/mmu.c
static struct cachepolicy cache_policies[] __initdata = {
{
.policy = "uncached",
.cr_mask = CR_W|CR_C,
.pmd = PMD_SECT_UNCACHED,
.pte = L_PTE_MT_UNCACHED,
.pte_s2 = s2_policy(L_PTE_S2_MT_UNCACHED),
}, {
.policy = "buffered",
.cr_mask = CR_C,
.pmd = PMD_SECT_BUFFERED,
.pte = L_PTE_MT_BUFFERABLE,
.pte_s2 = s2_policy(L_PTE_S2_MT_UNCACHED),
}, {
.policy = "writethrough",
.cr_mask = 0,
.pmd = PMD_SECT_WT,
.pte = L_PTE_MT_WRITETHROUGH,
.pte_s2 = s2_policy(L_PTE_S2_MT_WRITETHROUGH),
}, {
.policy = "writeback",
.cr_mask = 0,
.pmd = PMD_SECT_WB,
.pte = L_PTE_MT_WRITEBACK,
.pte_s2 = s2_policy(L_PTE_S2_MT_WRITEBACK),
}, {
.policy = "writealloc",
.cr_mask = 0,
.pmd = PMD_SECT_WBWA,
.pte = L_PTE_MT_WRITEALLOC,
.pte_s2 = s2_policy(L_PTE_S2_MT_WRITEBACK),
}
};
/*
* Adjust the PMD section entries according to the CPU in use.
*/
static void __init build_mem_type_table(void)
{
struct cachepolicy *cp;
unsigned int cr = get_cr();
pteval_t user_pgprot, kern_pgprot, vecs_pgprot;
pteval_t hyp_device_pgprot, s2_pgprot, s2_device_pgprot;
int cpu_arch = cpu_architecture();
int i;
if (cpu_arch < CPU_ARCH_ARMv6) {
#if defined(CONFIG_CPU_DCACHE_DISABLE)
if (cachepolicy > CPOLICY_BUFFERED)
cachepolicy = CPOLICY_BUFFERED;
#elif defined(CONFIG_CPU_DCACHE_WRITETHROUGH)
if (cachepolicy > CPOLICY_WRITETHROUGH)
cachepolicy = CPOLICY_WRITETHROUGH;
#endif
}
if (cpu_arch < CPU_ARCH_ARMv5) {
if (cachepolicy >= CPOLICY_WRITEALLOC)
cachepolicy = CPOLICY_WRITEBACK;
ecc_mask = 0;
}
if (is_smp()) {
if (cachepolicy != CPOLICY_WRITEALLOC) {
pr_warn("Forcing write-allocate cache policy for SMP\n");
cachepolicy = CPOLICY_WRITEALLOC;
}
if (!(initial_pmd_value & PMD_SECT_S)) {
pr_warn("Forcing shared mappings for SMP\n");
initial_pmd_value |= PMD_SECT_S;
}
}
/*
* Strip out features not present on earlier architectures.
* Pre-ARMv5 CPUs don't have TEX bits. Pre-ARMv6 CPUs or those
* without extended page tables don't have the 'Shared' bit.
*/
if (cpu_arch < CPU_ARCH_ARMv5)
for (i = 0; i < ARRAY_SIZE(mem_types); i++)
mem_types[i].prot_sect &= ~PMD_SECT_TEX(7);
if ((cpu_arch < CPU_ARCH_ARMv6 || !(cr & CR_XP)) && !cpu_is_xsc3())
for (i = 0; i < ARRAY_SIZE(mem_types); i++)
mem_types[i].prot_sect &= ~PMD_SECT_S;
/*
* ARMv5 and lower, bit 4 must be set for page tables (was: cache
* "update-able on write" bit on ARM610). However, Xscale and
* Xscale3 require this bit to be cleared.
*/
if (cpu_is_xscale_family()) {
for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
mem_types[i].prot_sect &= ~PMD_BIT4;
mem_types[i].prot_l1 &= ~PMD_BIT4;
}
} else if (cpu_arch < CPU_ARCH_ARMv6) {
for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
if (mem_types[i].prot_l1)
mem_types[i].prot_l1 |= PMD_BIT4;
if (mem_types[i].prot_sect)
mem_types[i].prot_sect |= PMD_BIT4;
}
}
/*
* Mark the device areas according to the CPU/architecture.
*/
if (cpu_is_xsc3() || (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP))) {
if (!cpu_is_xsc3()) {
/*
* Mark device regions on ARMv6+ as execute-never
* to prevent speculative instruction fetches.
*/
mem_types[MT_DEVICE].prot_sect |= PMD_SECT_XN;
mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_XN;
mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_XN;
mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_XN;
/* Also setup NX memory mapping */
mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_XN;
}
if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) {
/*
* For ARMv7 with TEX remapping,
* - shared device is SXCB=1100
* - nonshared device is SXCB=0100
* - write combine device mem is SXCB=0001
* (Uncached Normal memory)
*/
mem_types[MT_DEVICE].prot_sect |= PMD_SECT_TEX(1);
mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_TEX(1);
mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_BUFFERABLE;
} else if (cpu_is_xsc3()) {
/*
* For Xscale3,
* - shared device is TEXCB=00101
* - nonshared device is TEXCB=01000
* - write combine device mem is TEXCB=00100
* (Inner/Outer Uncacheable in xsc3 parlance)
*/
mem_types[MT_DEVICE].prot_sect |= PMD_SECT_TEX(1) | PMD_SECT_BUFFERED;
mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_TEX(2);
mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_TEX(1);
} else {
/*
* For ARMv6 and ARMv7 without TEX remapping,
* - shared device is TEXCB=00001
* - nonshared device is TEXCB=01000
* - write combine device mem is TEXCB=00100
* (Uncached Normal in ARMv6 parlance).
*/
mem_types[MT_DEVICE].prot_sect |= PMD_SECT_BUFFERED;
mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_TEX(2);
mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_TEX(1);
}
} else {
/*
* On others, write combining is "Uncached/Buffered"
*/
mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_BUFFERABLE;
}
/*
* Now deal with the memory-type mappings
*/
cp = &cache_policies[cachepolicy];
vecs_pgprot = kern_pgprot = user_pgprot = cp->pte;
s2_pgprot = cp->pte_s2;
hyp_device_pgprot = mem_types[MT_DEVICE].prot_pte;
s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2;
#ifndef CONFIG_ARM_LPAE
/*
* We don't use domains on ARMv6 (since this causes problems with
* v6/v7 kernels), so we must use a separate memory type for user
* r/o, kernel r/w to map the vectors page.
*/
if (cpu_arch == CPU_ARCH_ARMv6)
vecs_pgprot |= L_PTE_MT_VECTORS;
/*
* Check is it with support for the PXN bit
* in the Short-descriptor translation table format descriptors.
*/
if (cpu_arch == CPU_ARCH_ARMv7 &&
(read_cpuid_ext(CPUID_EXT_MMFR0) & 0xF) >= 4) {
user_pmd_table |= PMD_PXNTABLE;
}
#endif
/*
* ARMv6 and above have extended page tables.
*/
if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) {
#ifndef CONFIG_ARM_LPAE
/*
* Mark cache clean areas and XIP ROM read only
* from SVC mode and no access from userspace.
*/
mem_types[MT_ROM].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
#endif
/*
* If the initial page tables were created with the S bit
* set, then we need to do the same here for the same
* reasons given in early_cachepolicy().
*/
if (initial_pmd_value & PMD_SECT_S) {
user_pgprot |= L_PTE_SHARED;
kern_pgprot |= L_PTE_SHARED;
vecs_pgprot |= L_PTE_SHARED;
s2_pgprot |= L_PTE_SHARED;
mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S;
mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED;
mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
mem_types[MT_MEMORY_RWX].prot_sect |= PMD_SECT_S;
mem_types[MT_MEMORY_RWX].prot_pte |= L_PTE_SHARED;
mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_S;
mem_types[MT_MEMORY_RW].prot_pte |= L_PTE_SHARED;
mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED;
mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_S;
mem_types[MT_MEMORY_RWX_NONCACHED].prot_pte |= L_PTE_SHARED;
}
}
/*
* Non-cacheable Normal - intended for memory areas that must
* not cause dirty cache line writebacks when used
*/
if (cpu_arch >= CPU_ARCH_ARMv6) {
if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) {
/* Non-cacheable Normal is XCB = 001 */
mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |=
PMD_SECT_BUFFERED;
} else {
/* For both ARMv6 and non-TEX-remapping ARMv7 */
mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |=
PMD_SECT_TEX(1);
}
} else {
mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE;
}
#ifdef CONFIG_ARM_LPAE
/*
* Do not generate access flag faults for the kernel mappings.
*/
for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
mem_types[i].prot_pte |= PTE_EXT_AF;
if (mem_types[i].prot_sect)
mem_types[i].prot_sect |= PMD_SECT_AF;
}
kern_pgprot |= PTE_EXT_AF;
vecs_pgprot |= PTE_EXT_AF;
/*
* Set PXN for user mappings
*/
user_pgprot |= PTE_EXT_PXN;
#endif
for (i = 0; i < 16; i++) {
pteval_t v = pgprot_val(protection_map[i]);
protection_map[i] = __pgprot(v | user_pgprot);
}
mem_types[MT_LOW_VECTORS].prot_pte |= vecs_pgprot;
mem_types[MT_HIGH_VECTORS].prot_pte |= vecs_pgprot;
pgprot_user = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | user_pgprot);
pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG |
L_PTE_DIRTY | kern_pgprot);
pgprot_s2 = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | s2_pgprot);
pgprot_s2_device = __pgprot(s2_device_pgprot);
pgprot_hyp_device = __pgprot(hyp_device_pgprot);
mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask;
mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
mem_types[MT_MEMORY_RWX].prot_sect |= ecc_mask | cp->pmd;
mem_types[MT_MEMORY_RWX].prot_pte |= kern_pgprot;
mem_types[MT_MEMORY_RW].prot_sect |= ecc_mask | cp->pmd;
mem_types[MT_MEMORY_RW].prot_pte |= kern_pgprot;
mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot;
mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= ecc_mask;
mem_types[MT_ROM].prot_sect |= cp->pmd;
switch (cp->pmd) {
case PMD_SECT_WT:
mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_WT;
break;
case PMD_SECT_WB:
case PMD_SECT_WBWA:
mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_WB;
break;
}
pr_info("Memory policy: %sData cache %s\n",
ecc_mask ? "ECC enabled, " : "", cp->policy);
for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
struct mem_type *t = &mem_types[i];
if (t->prot_l1)
t->prot_l1 |= PMD_DOMAIN(t->domain);
if (t->prot_sect)
t->prot_sect |= PMD_DOMAIN(t->domain);
}
}
以上数组中的内容最终会填入页表项中:
3.4 arm_memblock_init
void __init arm_memblock_init(const struct machine_desc *mdesc)
{
/* Register the kernel text, kernel data and initrd with memblock. */
//__pa(x) __virt_to_phys((unsigned long)(x)),将虚拟地址转成物理地址
//KERNEL_START:内核镜像起始地址:0xc000_8000
//KERNEL_END:内核镜像终止地址,KERNEL_END - KERNEL_START为内核镜像大小
memblock_reserve(__pa(KERNEL_START), KERNEL_END - KERNEL_START);
//预留initrd文件系统所需的内存,具体用法请参照initrd的用法
arm_initrd_init();
//预留PGD页表的内存
arm_mm_memblock_reserve();
/* reserve any platform specific memblock areas */
if (mdesc->reserve)
mdesc->reserve();
//预留dtb的内存
early_init_fdt_reserve_self();
//预留dtb内所配置的预留内存
early_init_fdt_scan_reserved_mem();
/* reserve memory for DMA contiguous allocations */
//预留dma 所需使用到的物理连续内存 arm_dma_limit为0xffff_ffff
//#ifdef CONFIG_ZONE_DMA
//extern phys_addr_t arm_dma_limit;
//extern unsigned long arm_dma_pfn_limit;
//#else
//#define arm_dma_limit ((phys_addr_t)~0)
//#define arm_dma_pfn_limit (~0ul >> PAGE_SHIFT)
//#endif
dma_contiguous_reserve(arm_dma_limit);
arm_memblock_steal_permitted = false;
memblock_dump_all();
}
3.4.1 kernel镜像内存
//arch/arm/include/asm/memory.h
#ifdef CONFIG_XIP_KERNEL
#define KERNEL_START _sdata
#else
#define KERNEL_START _stext
#endif
#define KERNEL_END _end
SECTIONS
{
......
//_stext,_end等在vmlinux.lds.S中定义,如下:
. = PAGE_OFFSET + TEXT_OFFSET;//PAGE_OFFSET = 0xc000_0000,TEXT_OFFSET = 0x8000
.head.text : {
_text = .;
HEAD_TEXT
}
#ifdef CONFIG_STRICT_KERNEL_RWX
. = ALIGN(1<<SECTION_SHIFT);
#endif
#ifdef CONFIG_ARM_MPU
. = ALIGN(PMSAv8_MINALIGN);
#endif
.text : { /* Real text segment */
_stext = .; /* Text and read-only data */
ARM_TEXT
}
......
_end = .;
STABS_DEBUG
}
3.4.2 initrd内存
static void __init arm_initrd_init(void)
{
#ifdef CONFIG_BLK_DEV_INITRD
phys_addr_t start;
unsigned long size;
initrd_start = initrd_end = 0;
if (!phys_initrd_size)
return;
/*
* Round the memory region to page boundaries as per free_initrd_mem()
* This allows us to detect whether the pages overlapping the initrd
* are in use, but more importantly, reserves the entire set of pages
* as we don't want these pages allocated for other purposes.
*/
start = round_down(phys_initrd_start, PAGE_SIZE);
size = phys_initrd_size + (phys_initrd_start - start);
size = round_up(size, PAGE_SIZE);
if (!memblock_is_region_memory(start, size)) {
pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region - disabling initrd\n",
(u64)start, size);
return;
}
if (memblock_is_region_reserved(start, size)) {
pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region - disabling initrd\n",
(u64)start, size);
return;
}
memblock_reserve(start, size);
/* Now convert initrd to virtual addresses */
initrd_start = __phys_to_virt(phys_initrd_start);
initrd_end = initrd_start + phys_initrd_size;
#endif
}
3.4.3 PGD页表内存
//arch/arm/kernel/head.S
#define KERNEL_RAM_VADDR (PAGE_OFFSET + TEXT_OFFSET)
#ifdef CONFIG_ARM_LPAE
/* LPAE requires an additional page for the PGD */
#define PG_DIR_SIZE 0x5000
#define PMD_ORDER 3
#else
#define PG_DIR_SIZE 0x4000
#define PMD_ORDER 2
#endif
.equ swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE
.equ为伪指令,意义为:定义swapper_pg_dir为KERNEL_RAM_VADDR - PG_DIR_SIZE
由上可知,PGD页表的首地址为0xc000_0000 + 0x8000 - 0x4000
//arch/arm/mm/mmu.c
/*
* Reserve the special regions of memory
*/
void __init arm_mm_memblock_reserve(void)
{
/*
* Reserve the page tables. These are already in use,
* and can only be in node 0.
*/
memblock_reserve(__pa(swapper_pg_dir), SWAPPER_PG_DIR_SIZE);
#ifdef CONFIG_SA1111
/*
* Because of the SA1111 DMA bug, we want to preserve our
* precious DMA-able memory...
*/
memblock_reserve(PHYS_OFFSET, __pa(swapper_pg_dir) - PHYS_OFFSET);
#endif
}
3.4.4 FDT内存
int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
phys_addr_t size, bool nomap)
{
if (nomap)
return memblock_remove(base, size);
return memblock_reserve(base, size);
}
/**
* early_init_fdt_reserve_self() - reserve the memory used by the FDT blob
*/
void __init early_init_fdt_reserve_self(void)
{
if (!initial_boot_params)
return;
/* Reserve the dtb region */
early_init_dt_reserve_memory_arch(__pa(initial_boot_params),
fdt_totalsize(initial_boot_params),
false);
}
initial_boot_params初始化流程
boot—>r2(boot_args)—>__atags_pointer(arch/arm/kernel/head-common.S)—>setup_arch(arch/arm/kernel/setup.c)—>setup_machine_fdt(arch/arm/kernel/devtree.c)—>early_init_dt_verify(drivers/of/fdt.c)
bool __init early_init_dt_verify(void *params)
{
if (!params)
return false;
/* check device tree validity */
if (fdt_check_header(params))
return false;
/* Setup flat device-tree pointer */
initial_boot_params = params;
of_fdt_crc32 = crc32_be(~0, initial_boot_params,
fdt_totalsize(initial_boot_params));
return true;
}
FDT保留内存的初始化
/**
* early_init_fdt_scan_reserved_mem() - create reserved memory regions
*
* This function grabs memory from early allocator for device exclusive use
* defined in device tree structures. It should be called by arch specific code
* once the early allocator (i.e. memblock) has been fully activated.
*/
void __init early_init_fdt_scan_reserved_mem(void)
{
int n;
u64 base, size;
if (!initial_boot_params)
return;
/* Process header /memreserve/ fields */
for (n = 0; ; n++) {
fdt_get_mem_rsv(initial_boot_params, n, &base, &size);
if (!size)
break;
early_init_dt_reserve_memory_arch(base, size, false);
}
of_scan_flat_dt(__fdt_scan_reserved_mem, NULL);
fdt_init_reserved_mem();
}
获取dtb中"reserved-memory"信息:
//解析dtb中"reserved-memory"的设备节点,获取"reserved-memory"信息
/**
* fdt_scan_reserved_mem() - scan a single FDT node for reserved memory
*/
static int __init __fdt_scan_reserved_mem(unsigned long node, const char *uname,
int depth, void *data)
{
static int found;
int err;
if (!found && depth == 1 && strcmp(uname, "reserved-memory") == 0) {
if (__reserved_mem_check_root(node) != 0) {
pr_err("Reserved memory: unsupported node format, ignoring\n");
/* break scan */
return 1;
}
found = 1;
/* scan next node */
return 0;
} else if (!found) {
/* scan next node */
return 0;
} else if (found && depth < 2) {
/* scanning of /reserved-memory has been finished */
return 1;
}
if (!of_fdt_device_is_available(initial_boot_params, node))
return 0;
err = __reserved_mem_reserve_reg(node, uname);
if (err == -ENOENT && of_get_flat_dt_prop(node, "size", NULL))
fdt_reserved_mem_save_node(node, uname, 0, 0);
/* scan next node */
return 0;
}
fdt_init_reserved_mem:
//include/linux/of_reserved_mem.h
struct reserved_mem {
const char *name;
unsigned long fdt_node;
unsigned long phandle;
const struct reserved_mem_ops *ops;
phys_addr_t base;
phys_addr_t size;
void *priv;
};
struct reserved_mem_ops {
int (*device_init)(struct reserved_mem *rmem,
struct device *dev);
void (*device_release)(struct reserved_mem *rmem,
struct device *dev);
};
//drivers/of/of_reserved_mem.c
#define MAX_RESERVED_REGIONS 32
static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS];
//drivers/of/of_reserved_mem.c
/**
* fdt_init_reserved_mem - allocate and init all saved reserved memory regions
*/
void __init fdt_init_reserved_mem(void)
{
int i;
/* check for overlapping reserved regions */
__rmem_check_for_overlap();
for (i = 0; i < reserved_mem_count; i++) {
struct reserved_mem *rmem = &reserved_mem[i];
unsigned long node = rmem->fdt_node;
int len;
const __be32 *prop;
int err = 0;
int nomap;
nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;
prop = of_get_flat_dt_prop(node, "phandle", &len);
if (!prop)
prop = of_get_flat_dt_prop(node, "linux,phandle", &len);
if (prop)
rmem->phandle = of_read_number(prop, len/4);
if (rmem->size == 0)
err = __reserved_mem_alloc_size(node, rmem->name,
&rmem->base, &rmem->size);
if (err == 0) {
err = __reserved_mem_init_node(rmem);
if (err != 0 && err != -ENOENT) {
pr_info("node %s compatible matching fail\n",
rmem->name);
memblock_free(rmem->base, rmem->size);
if (nomap)
memblock_add(rmem->base, rmem->size);
}
}
}
}
3.4.5 dma cma内存
//kernel/dma/contiguous.c
#ifdef CONFIG_CMA_SIZE_MBYTES
#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
#else
#define CMA_SIZE_MBYTES 0
#endif
static const phys_addr_t size_bytes = (phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
static phys_addr_t size_cmdline = -1;
static phys_addr_t base_cmdline;
static phys_addr_t limit_cmdline;
//kernel/dma/contiguous.c
/**
* dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
* @limit: End address of the reserved memory (optional, 0 for any).
*
* This function reserves memory from early allocator. It should be
* called by arch specific code once the early allocator (memblock or bootmem)
* has been activated and all other subsystems have already allocated/reserved
* memory.
*/
void __init dma_contiguous_reserve(phys_addr_t limit)
{
phys_addr_t selected_size = 0;
phys_addr_t selected_base = 0;
phys_addr_t selected_limit = limit;
bool fixed = false;
pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
if (size_cmdline != -1) {
selected_size = size_cmdline;
selected_base = base_cmdline;
selected_limit = min_not_zero(limit_cmdline, limit);
if (base_cmdline + size_cmdline == limit_cmdline)
fixed = true;
} else {
#ifdef CONFIG_CMA_SIZE_SEL_MBYTES
selected_size = size_bytes;
#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE)
selected_size = cma_early_percent_memory();
#elif defined(CONFIG_CMA_SIZE_SEL_MIN)
selected_size = min(size_bytes, cma_early_percent_memory());
#elif defined(CONFIG_CMA_SIZE_SEL_MAX)
selected_size = max(size_bytes, cma_early_percent_memory());
#endif
}
if (selected_size && !dma_contiguous_default_area) {
pr_debug("%s: reserving %ld MiB for global area\n", __func__,
(unsigned long)selected_size / SZ_1M);
dma_contiguous_reserve_area(selected_size, selected_base,
selected_limit,
&dma_contiguous_default_area,
fixed);
}
}
/**
* dma_contiguous_reserve_area() - reserve custom contiguous area
* @size: Size of the reserved area (in bytes),
* @base: Base address of the reserved area optional, use 0 for any
* @limit: End address of the reserved memory (optional, 0 for any).
* @res_cma: Pointer to store the created cma region.
* @fixed: hint about where to place the reserved area
*
* This function reserves memory from early allocator. It should be
* called by arch specific code once the early allocator (memblock or bootmem)
* has been activated and all other subsystems have already allocated/reserved
* memory. This function allows to create custom reserved areas for specific
* devices.
*
* If @fixed is true, reserve contiguous area at exactly @base. If false,
* reserve in range from @base to @limit.
*/
int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
phys_addr_t limit, struct cma **res_cma,
bool fixed)
{
int ret;
ret = cma_declare_contiguous(base, size, limit, 0, 0, fixed,
"reserved", res_cma);
if (ret)
return ret;
/* Architecture specific contiguous memory fixup. */
dma_contiguous_early_fixup(cma_get_base(*res_cma),
cma_get_size(*res_cma));
return 0;
}