Linux 内存映射
下面引用两张网上找到的图片,总结了Linux kernel的内存管理机制。
总体来说linux线性地址分为
- 0-16MB DMA
- 16-896MB Normal
- 896-4096MB 高端内存 Highmem
其中: 896-1024MB 用来实现 固定映射、永久映射和高端内存的临时映射。
页描述符
struct page 用来记录每个页框状态之类的。
mem_map
数组,所有页描述符都存在这里。
struct page {
/* First double word block */
unsigned long flags; /* Atomic flags, some possibly
* updated asynchronously */
union {
struct address_space *mapping; /* If low bit clear, points to
* inode address_space, or NULL.
* If page mapped as anonymous
* memory, low bit is set, and
* it points to anon_vma object:
* see PAGE_MAPPING_ANON below.
*/
void *s_mem; /* slab first object */
};
/* Second double word */
struct {
union {
pgoff_t index; /* Our offset within mapping. */
void *freelist; /* sl[aou]b first free object */
bool pfmemalloc; /* If set by the page allocator,
* ALLOC_NO_WATERMARKS was set
* and the low watermark was not
* met implying that the system
* is under some pressure. The
* caller should try ensure
* this page is only used to
* free other pages.
*/
};
union {
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
/* Used for cmpxchg_double in slub */
unsigned long counters;
#else
/*
* Keep _count separate from slub cmpxchg_double data.
* As the rest of the double word is protected by
* slab_lock but _count is not.
*/
unsigned counters;
#endif
struct {
union {
/*
* Count of ptes mapped in
* mms, to show when page is
* mapped & limit reverse map
* searches.
*
* Used also for tail pages
* refcounting instead of
* _count. Tail pages cannot
* be mapped and keeping the
* tail page _count zero at
* all times guarantees
* get_page_unless_zero() will
* never succeed on tail
* pages.
*/
atomic_t _mapcount;
struct { /* SLUB */
unsigned inuse:16;
unsigned objects:15;
unsigned frozen:1;
};
int units; /* SLOB */
};
atomic_t _count; /* Usage count, see below. */
};
unsigned int active; /* SLAB */
};
};
/* Third double word block */
union {
struct list_head lru; /* Pageout list, eg. active_list
* protected by zone->lru_lock !
* Can be used as a generic list
* by the page owner.
*/
struct { /* slub per cpu partial pages */
struct page *next; /* Next partial slab */
#ifdef CONFIG_64BIT
int pages; /* Nr of partial slabs left */
int pobjects; /* Approximate # of objects */
#else
short int pages;
short int pobjects;
#endif
};
struct slab *slab_page; /* slab fields */
struct rcu_head rcu_head; /* Used by SLAB
* when destroying via RCU
*/
/* First tail page of compound page */
struct {
compound_page_dtor *compound_dtor;
unsigned long compound_order;
};
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
pgtable_t pmd_huge_pte; /* protected by page->ptl */
#endif
};
/* Remainder is not double word aligned */
union {
unsigned long private; /* Mapping-private opaque data:
* usually used for buffer_heads
* if PagePrivate set; used for
* swp_entry_t if PageSwapCache;
* indicates order in the buddy
* system if PG_buddy is set.
*/
#if USE_SPLIT_PTE_PTLOCKS
#if ALLOC_SPLIT_PTLOCKS
spinlock_t *ptl;
#else
spinlock_t ptl;
#endif
#endif
struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */
struct page *first_page; /* Compound tail pages */
};
#ifdef CONFIG_MEMCG
struct mem_cgroup *mem_cgroup;
#endif
/*
* On machines where all RAM is mapped into kernel address space,
* we can simply calculate the virtual address. On machines with
* highmem some memory is mapped into kernel virtual memory
* dynamically, so we need a place to store that address.
* Note that this field could be 16 bits on x86 ... ;)
*
* Architectures with slow multiplication can define
* WANT_PAGE_VIRTUAL in asm/page.h
*/
#if defined(WANT_PAGE_VIRTUAL)
void *virtual; /* Kernel virtual address (NULL if
not kmapped, ie. highmem) */
#endif /* WANT_PAGE_VIRTUAL */
#ifdef CONFIG_KMEMCHECK
/*
* kmemcheck wants to track the status of each byte in a page; this
* is a pointer to such a status block. NULL if not tracked.
*/
void *shadow;
#endif
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
int _last_cpupid;
#endif
}
重点关注下
__count 字段
页的应用计数器,如果为-1 表示空闲。>=0 分配了给一个或多个进程,或存放的内核数据结构。
flags
页的状态描述标志。
高端内存映射用到了
- 永久映射
- 固定映射
- 临时映射
先理解下pgd pud pmd pte
32 未linux内核 不开PAE的话只用到了 pgd 和 pte
#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
swapper_pg_dir + pgd_idx -> pte
*pte & 0xfffff000 就是页框的物理地址 //4kb对齐
反过来
物理地址| flags -> *pte
pte | flags -> *(swapper_pg_dir + pgd_idx)
这样就建立了映射
enum fixed_addresses是预留为了给固定映射预留空间。通过这个索引能快速找到映射的全局目录项。FIX_KMAP_BEGIN - FIX_KMAP_END就是为了完成临时映射预留的。
enum fixed_addresses {
#ifdef CONFIG_X86_32
FIX_HOLE,
#else
#ifdef CONFIG_X86_VSYSCALL_EMULATION
VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT,
#endif
#ifdef CONFIG_PARAVIRT_CLOCK
PVCLOCK_FIXMAP_BEGIN,
PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,
#endif
#endif
FIX_DBGP_BASE,
FIX_EARLYCON_MEM_BASE,
#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
FIX_OHCI1394_BASE,
#endif
#ifdef CONFIG_X86_LOCAL_APIC
FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */
#endif
#ifdef CONFIG_X86_IO_APIC
FIX_IO_APIC_BASE_0,
FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
#endif
FIX_RO_IDT, /* Virtual mapping for read-only IDT */
#ifdef CONFIG_X86_32
FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ //临时映射???
FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
#ifdef CONFIG_PCI_MMCONFIG
FIX_PCIE_MCFG,
#endif
#endif
#ifdef CONFIG_PARAVIRT
FIX_PARAVIRT_BOOTMAP,
#endif
FIX_TEXT_POKE1, /* reserve 2 pages for text_poke() */
FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
#ifdef CONFIG_X86_INTEL_MID
FIX_LNW_VRTC,
#endif
__end_of_permanent_fixed_addresses,
/*
* 512 temporary boot-time mappings, used by early_ioremap(),
* before ioremap() is functional.
*
* If necessary we round it up to the next 512 pages boundary so
* that we can have a single pgd entry and a single pte table:
*/
#define NR_FIX_BTMAPS 64
#define FIX_BTMAPS_SLOTS 8
#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
FIX_BTMAP_END =
(__end_of_permanent_fixed_addresses ^
(__end_of_permanent_fixed_addresses + TOTAL_FIX_BTMAPS - 1)) &
-PTRS_PER_PTE
? __end_of_permanent_fixed_addresses + TOTAL_FIX_BTMAPS -
(__end_of_permanent_fixed_addresses & (TOTAL_FIX_BTMAPS - 1))
: __end_of_permanent_fixed_addresses,
FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
#ifdef CONFIG_X86_32
FIX_WP_TEST,
#endif
#ifdef CONFIG_INTEL_TXT
FIX_TBOOT_BASE,
#endif
__end_of_fixed_addresses
};
通过这两个宏来实现线性地址与索引之间的转换
#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT))
#define __virt_to_fix(x) ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
永久映射
void *kmap(struct page *page)
{
might_sleep();
if (!PageHighMem(page))
return page_address(page);
return kmap_high(page);
}
void *kmap_high(struct page *page)
{
unsigned long vaddr;
/*
* For highmem pages, we can't trust "virtual" until
* after we have the lock.
*/
lock_kmap();
vaddr = (unsigned long)page_address(page);
if (!vaddr)
vaddr = map_new_virtual(page);
pkmap_count[PKMAP_NR(vaddr)]++;
BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2);
unlock_kmap();
return (void*) vaddr;
}
固定映射
临时映射
static void __init kmap_init(void)
{
unsigned long kmap_vstart;
/*
* Cache the first kmap pte:
*/
kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
kmap_pte = kmap_get_fixmap_pte(kmap_vstart);
kmap_prot = PAGE_KERNEL;
}
void *kmap_atomic(struct page *page)
{
return kmap_atomic_prot(page, kmap_prot);
}
void *kmap_atomic_prot(struct page *page, pgprot_t prot)
{
unsigned long vaddr;
int idx, type;
preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
type = kmap_atomic_idx_push();
idx = type + KM_TYPE_NR*smp_processor_id();
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); //线性地址 最后 1023项
BUG_ON(!pte_none(*(kmap_pte-idx)));
set_pte(kmap_pte-idx, mk_pte(page, prot));
arch_flush_lazy_mmu_mode();
return (void *)vaddr;
}
内核用到的机制
- 非一致内存访问 numa
- 伙伴系统
- slab系统
- 每页cpu高速缓存
- TLB
- 保留的页框池
- 内存池
- 非连续内存管理