page cache 在linux vfs 中是比较重要的一层,其功能就不详细介绍了。主要介绍了几个关键性函数,容易帮助了解page cache里的整体逻辑和流程
先看一下page 的结构体
- /*
- * Each physical page in the system has a struct page associated with
- * it to keep track of whatever it is we are using the page for at the
- * moment. Note that we have no way to track which tasks are using
- * a page.
- */
- struct page {
- unsigned long flags; /* Atomic flags, some possibly
- * updated asynchronously */
- atomic_t _count; /* Usage count, see below. */
- atomic_t _mapcount; /* Count of ptes mapped in mms,
- * to show when page is mapped
- * & limit reverse map searches.
- */
- union {
- struct {
- 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.
- */
- 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.
- */
- };
- #if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
- spinlock_t ptl;
- #endif
- };
- pgoff_t index; /* Our offset within mapping. */
- struct list_head lru; /* Pageout list, eg. active_list
- * protected by zone->lru_lock !
- */
- /*
- * 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 */
- };
page_cache_get() 主要是调用函数get_page
- static inline void get_page(struct page *page)
- {
- if (unlikely(PageCompound(page)))
- page = (struct page *)page_private(page);
- atomic_inc(&page->_count);
- }
主要page里的计数器+1,表示page引用的reference 次数
page_cache_release() 的核心函数 put_page_testzero
- static inline int put_page_testzero(struct page *page)
- {
- BUG_ON(atomic_read(&page->_count) == 0);
- return atomic_dec_and_test(&page->_count);
- }
显然是page的计数器-1, page的引用被释放
page 的flags 参数, 在page 的结构体里定义了flags参数,用bit位来标识page的状态,定义在page-flags.h文件里
这是在32位机 和 64位 系统的关于flags 定义
32 bit -------------------------------| FIELDS | FLAGS |
64 bit | FIELDS | ?????? FLAGS |
63 32 0
从bit0-bit19是常用的,其他位保留给了mapping zone, node and SPARSEMEM
- #define PG_locked 0 /* Page is locked. Don't touch. */
- #define PG_error 1
- #define PG_referenced 2
- #define PG_uptodate 3
- #define PG_dirty 4
- #define PG_lru 5
- #define PG_active 6
- #define PG_slab 7 /* slab debug (Suparna wants this) */
- #define PG_checked 8 /* kill me in 2.5.<early>. */
- #define PG_arch_1 9
- #define PG_reserved 10
- #define PG_private 11 /* Has something at ->private */
- #define PG_writeback 12 /* Page is under writeback */
- #define PG_nosave 13 /* Used for system suspend/resume */
- #define PG_compound 14 /* Part of a compound page */
- #define PG_swapcache 15 /* Swap page: swp_entry_t in private */
- #define PG_mappedtodisk 16 /* Has blocks allocated on-disk */
- #define PG_reclaim 17 /* To be reclaimed asap */
- #define PG_nosave_free 18 /* Free, should not be written */
- #define PG_buddy 19 /* Page is free, on buddy lists */
SetPageUptodate 原子设置bit PG_uptodate 状态为1,表示改页被更新
#define SetPageUptodate(page) set_bit(PG_uptodate, &(page)->flags)
ClearPageUptodate 原子设置bit PG_uptodate 状态为0,表示页没有被更新
#define ClearPageUptodate(page) clear_bit(PG_uptodate, &(page)->flags)
TestSetPageLocked 设置原子设置page locked状态,并返回改变前的原来状态
- #define TestSetPageLocked(page) \
- test_and_set_bit(PG_locked, &(page)->flags)
__lock_page 函数
- void fastcall __lock_page(struct page *page)
- {
- DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
- __wait_on_bit_lock(page_waitqueue(page), &wait, sync_page,
- TASK_UNINTERRUPTIBLE);
- }
- EXPORT_SYMBOL(__lock_page);
将当前进程设置成Task_uninterruptible状态,并将进程挂载到 wait对队列中,如果PG_Locked的状态为1时,触发sync_page的方法,只有在sync_page方法中才会调用schedule()调度当前进程,直到PG_locked的状态为0,注意当执行完__wait_on_bit_lock 的时候PG_locked仍然是1,因为__wait_on_bit_lock是用test_and_set_bit来进行while条件判断的,最后将进程设置成 TASK_RUNNING 状态,把该进程从wait 队列中移除。
unlock_page 函数
- void fastcall unlock_page(struct page *page)
- {
- smp_mb__before_clear_bit();
- if (!TestClearPageLocked(page))
- BUG();
- smp_mb__after_clear_bit();
- wake_up_page(page, PG_locked);
- }
- EXPORT_SYMBOL(unlock_page);
设置PG_Locked 的状态是0,遍历等待队列,执行唤醒函数
- static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, int sync, void *key)
- {
- struct list_head *tmp, *next;
- list_for_each_safe(tmp, next, &q->task_list) {
- wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list);
- unsigned flags = curr->flags;
- if (curr->func(curr, mode, sync, key) &&
- (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
- break;
- }
- }
其中func的定义是
- .func = autoremove_wake_function,
在autoremove_wake_function里,调用sched.c 的default_wake_function -> try_to_wake_up
将等待队列里的线程状态置为 TASK_RUNNING 并放置到运行队列中去