filemap.c

ARM 嵌入式 系统 设计与实例开发 实验教材 二源码

/*
 *	linux/mm/filemap.c
 *
 * Copyright (C) 1994-1999  Linus Torvalds
 */

/*
 * This file handles the generic file mmap semantics used by
 * most "normal" filesystems (but you don't /have/ to use this:
 * the NFS filesystem used to do this differently, for example)
 */
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/locks.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/smp_lock.h>
#include <linux/blkdev.h>
#include <linux/file.h>
#include <linux/swapctl.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/iobuf.h>
#include <linux/compiler.h>

#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/mman.h>

#include <linux/highmem.h>

/*
 * Shared mappings implemented 30.11.1994. It's not fully working yet,
 * though.
 *
 * Shared mappings now work. 15.8.1995  Bruno.
 *
 * finished 'unifying' the page and buffer cache and SMP-threaded the
 * page-cache, 21.05.1999, Ingo Molnar <[e-mail]>
 *
 * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <[e-mail]>
 */

atomic_t page_cache_size = ATOMIC_INIT(0);
unsigned int page_hash_bits;
struct page **page_hash_table;

int vm_max_readahead = 31;
int vm_min_readahead = 3;
EXPORT_SYMBOL(vm_max_readahead);
EXPORT_SYMBOL(vm_min_readahead);


spinlock_t pagecache_lock __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED;
/*
 * NOTE: to avoid deadlocking you must never acquire the pagemap_lru_lock 
 *	with the pagecache_lock held.
 *
 * Ordering:
 *	swap_lock ->
 *		pagemap_lru_lock ->
 *			pagecache_lock
 */
spinlock_t pagemap_lru_lock __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED;

#define CLUSTER_PAGES		(1 << page_cluster)
#define CLUSTER_OFFSET(x)	(((x) >> page_cluster) << page_cluster)

static void FASTCALL(add_page_to_hash_queue(struct page * page, struct page **p));
static void add_page_to_hash_queue(struct page * page, struct page **p)
{
	struct page *next = *p;

	*p = page;
	page->next_hash = next;
	page->pprev_hash = p;
	if (next)
		next->pprev_hash = &page->next_hash;
	if (page->buffers)
		PAGE_BUG(page);
	atomic_inc(&page_cache_size);
}

static inline void add_page_to_inode_queue(struct address_space *mapping, struct page * page)
{
	struct list_head *head = &mapping->clean_pages;

	mapping->nrpages++;
	list_add(&page->list, head);
	page->mapping = mapping;
}

static inline void remove_page_from_inode_queue(struct page * page)
{
	struct address_space * mapping = page->mapping;

	mapping->nrpages--;
	list_del(&page->list);
	page->mapping = NULL;
}

static inline void remove_page_from_hash_queue(struct page * page)
{
	struct page *next = page->next_hash;
	struct page **pprev = page->pprev_hash;

	if (next)
		next->pprev_hash = pprev;
	*pprev = next;
	page->pprev_hash = NULL;
	atomic_dec(&page_cache_size);
}

/*
 * Remove a page from the page cache and free it. Caller has to make
 * sure the page is locked and that nobody else uses it - or that usage
 * is safe.
 */
void __remove_inode_page(struct page *page)
{
	if (PageDirty(page)) BUG();
	remove_page_from_inode_queue(page);
	remove_page_from_hash_queue(page);
}

void remove_inode_page(struct page *page)
{
	if (!PageLocked(page))
		PAGE_BUG(page);

	spin_lock(&pagecache_lock);
	__remove_inode_page(page);
	spin_unlock(&pagecache_lock);
}

static inline int sync_page(struct page *page)
{
	struct address_space *mapping = page->mapping;

	if (mapping && mapping->a_ops && mapping->a_ops->sync_page)
		return mapping->a_ops->sync_page(page);
	return 0;
}

/*
 * Add a page to the dirty page list.
 */
void set_page_dirty(struct page *page)
{
	if (!test_and_set_bit(PG_dirty, &page->flags)) {
		struct address_space *mapping = page->mapping;

		if (mapping) {
			spin_lock(&pagecache_lock);
			list_del(&page->list);
			list_add(&page->list, &mapping->dirty_pages);
			spin_unlock(&pagecache_lock);

			if (mapping->host)
				mark_inode_dirty_pages(mapping->host);
		}
	}
}

/**
 * invalidate_inode_pages - Invalidate all the unlocked pages of one inode
 * @inode: the inode which pages we want to invalidate
 *
 * This function only removes the unlocked pages, if you want to
 * remove all the pages of one inode, you must call truncate_inode_pages.
 */

void invalidate_inode_pages(struct inode * inode)
{
	struct list_head *head, *curr;
	struct page * page;

	head = &inode->i_mapping->clean_pages;

	spin_lock(&pagemap_lru_lock);
	spin_lock(&pagecache_lock);
	curr = head->next;

	while (curr != head) {
		page = list_entry(curr, struct page, list);
		curr = curr->next;

		/* We cannot invalidate something in dirty.. */
		if (PageDirty(page))
			continue;

		/* ..or locked */
		if (TryLockPage(page))
			continue;

		if (page->buffers && !try_to_free_buffers(page, 0))
			goto unlock;

		if (page_count(page) != 1)
			goto unlock;

		__lru_cache_del(page);
		__remove_inode_page(page);
		UnlockPage(page);
		page_cache_release(page);
		continue;
unlock:
		UnlockPage(page);
		continue;
	}

	spin_unlock(&pagecache_lock);
	spin_unlock(&pagemap_lru_lock);
}

static int do_flushpage(struct page *page, unsigned long offset)
{
	int (*flushpage) (struct page *, unsigned long);
	flushpage = page->mapping->a_ops->flushpage;
	if (flushpage)
		return (*flushpage)(page, offset);
	return block_flushpage(page, offset);
}

static inline void truncate_partial_page(struct page *page, unsigned partial)
{
	memclear_highpage_flush(page, partial, PAGE_CACHE_SIZE-partial);
	if (page->buffers)
		do_flushpage(page, partial);
}

static void truncate_complete_page(struct page *page)
{
	/* Leave it on the LRU if it gets converted into anonymous buffers */
	if (!page->buffers || do_flushpage(page, 0))
		lru_cache_del(page);

	/*
	 * We remove the page from the page cache _after_ we have
	 * destroyed all buffer-cache references to it. Otherwise some
	 * other process might think this inode page is not in the
	 * page cache and creates a buffer-cache alias to it causing
	 * all sorts of fun problems ...  
	 */
	ClearPageDirty(page);
	ClearPageUptodate(page);
	remove_inode_page(page);
	page_cache_release(page);
}

static int FASTCALL(truncate_list_pages(struct list_head *, unsigned long, unsigned *));
static int truncate_list_pages(struct list_head *head, unsigned long start, unsigned *partial)
{
	struct list_head *curr;
	struct page * page;
	int unlocked = 0;

 restart:
	curr = head->prev;
	while (curr != head) {
		unsigned long offset;

		page = list_entry(curr, struct page, list);
		offset = page->index;

		/* Is one of the pages to truncate? */
		if ((offset >= start) || (*partial && (offset + 1) == start)) {
			int failed;

			page_cache_get(page);
			failed = TryLockPage(page);

			list_del(head);
			if (!failed)
				/* Restart after this page */
				list_add_tail(head, curr);
			else
				/* Restart on this page */
				list_add(head, curr);

			spin_unlock(&pagecache_lock);
			unlocked = 1;

 			if (!failed) {
				if (*partial && (offset + 1) == start) {
					truncate_partial_page(page, *partial);
					*partial = 0;
				} else 
					truncate_complete_page(page);

				UnlockPage(page);
			} else
 				wait_on_page(page);

			page_cache_release(page);

			if (current->need_resched) {
				__set_current_state(TASK_RUNNING);
				schedule();
			}

			spin_lock(&pagecache_lock);
			goto restart;
		}
		curr = curr->prev;
	}
	return unlocked;
}


/**
 * truncate_inode_pages - truncate *all* the pages from an offset
 * @mapping: mapping to truncate
 * @lstart: offset from with to truncate
 *
 * Truncate the page cache at a set offset, removing the pages
 * that are beyond that offset (and zeroing out partial pages).
 * If any page is locked we wait for it to become unlocked.
 */
void truncate_inode_pages(struct address_space * mapping, loff_t lstart) 
{
	unsigned long start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
	int unlocked;

	spin_lock(&pagecache_lock);
	do {
		unlocked = truncate_list_pages(&mapping->clean_pages, start, &partial);
		unlocked |= truncate_list_pages(&mapping->dirty_pages, start, &partial);
		unlocked |= truncate_list_pages(&mapping->locked_pages, start, &partial);
	} while (unlocked);
	/* Traversed all three lists without dropping the lock */
	spin_unlock(&pagecache_lock);
}

static inline int invalidate_this_page2(struct page * page,
					struct list_head * curr,
					struct list_head * head)
{
	int unlocked = 1;

	/*
	 * The page is locked and we hold the pagecache_lock as well
	 * so both page_count(page) and page->buffers stays constant here.
	 */
	if (page_count(page) == 1 + !!page->buffers) {
		/* Restart after this page */
		list_del(head);
		list_add_tail(head, curr);

		page_cache_get(page);
		spin_unlock(&pagecache_lock);
		truncate_complete_page(page);
	} else {
		if (page->buffers) {
			/* Restart after this page */
			list_del(head);
			list_add_tail(head, curr);

			page_cache_get(page);
			spin_unlock(&pagecache_lock);
			block_invalidate_page(page);
		} else
			unlocked = 0;

		ClearPageDirty(page);
		ClearPageUptodate(page);
	}

	return unlocked;
}

static int FASTCALL(invalidate_list_pages2(struct list_head *));
static int invalidate_list_pages2(struct list_head *head)
{
	struct list_head *curr;
	struct page * page;
	int unlocked = 0;

 restart:
	curr = head->prev;
	while (curr != head) {
		page = list_entry(curr, struct page, list);

		if (!TryLockPage(page)) {
			int __unlocked;

			__unlocked = invalidate_this_page2(page, curr, head);
			UnlockPage(page);
			unlocked |= __unlocked;
			if (!__unlocked) {
				curr = curr->prev;
				continue;
			}
		} else {
			/* Restart on this page */
			list_del(head);
			list_add(head, curr);

			page_cache_get(page);
			spin_unlock(&pagecache_lock);
			unlocked = 1;
			wait_on_page(page);
		}

		page_cache_release(page);
		if (current->need_resched) {
			__set_current_state(TASK_RUNNING);
			schedule();
		}

		spin_lock(&pagecache_lock);
		goto restart;
	}
	return unlocked;
}

/**
 * invalidate_inode_pages2 - Clear all the dirty bits around if it can't
 * free the pages because they're mapped.
 * @mapping: the address_space which pages we want to invalidate
 */
void invalidate_inode_pages2(struct address_space * mapping)
{
	int unlocked;

	spin_lock(&pagecache_lock);
	do {
		unlocked = invalidate_list_pages2(&mapping->clean_pages);
		unlocked |= invalidate_list_pages2(&mapping->dirty_pages);
		unlocked |= invalidate_list_pages2(&mapping->locked_pages);
	} while (unlocked);
	spin_unlock(&pagecache_lock);
}

static inline struct page * __find_page_nolock(struct address_space *mapping, unsigned long offset, struct page *page)
{
	goto inside;

	for (;;) {
		page = page->next_hash;
inside:
		if (!page)
			goto not_found;
		if (page->mapping != mapping)
			continue;
		if (page->index == offset)
			break;
	}

not_found:
	return page;
}

static int do_buffer_fdatasync(struct list_head *head, unsigned long start, unsigned long end, int (*fn)(struct page *))
{
	struct list_head *curr;
	struct page *page;
	int retval = 0;

	spin_lock(&pagecache_lock);
	curr = head->next;
	while (curr != head) {
		page = list_entry(curr, struct page, list);
		curr = curr->next;
		if (!page->buffers)
			continue;
		if (page->index >= end)
			continue;
		if (page->index < start)
			continue;

		page_cache_get(page);
		spin_unlock(&pagecache_lock);
		lock_page(page);

		/* The buffers could have been free'd while we waited for the page lock */
		if (page->buffers)
			retval |= fn(page);

		UnlockPage(page);
		spin_lock(&pagecache_lock);
		curr = page->list.next;
		page_cache_release(page);
	}
	spin_unlock(&pagecache_lock);

	return retval;
}

/*
 * Two-stage data sync: first start the IO, then go back and
 * collect the information..
 */
int generic_buffer_fdatasync(struct inode *inode, unsigned long start_idx, unsigned long end_idx)
{
	int retval;

	/* writeout dirty buffers on pages from both clean and dirty lists */
	retval = do_buffer_fdatasync(&inode->i_mapping->dirty_pages, start_idx, end_idx, writeout_one_page);
	retval |= do_buffer_fdatasync(&inode->i_mapping->clean_pages, start_idx, end_idx, writeout_one_page);
	retval |= do_buffer_fdatasync(&inode->i_mapping->locked_pages, start_idx, end_idx, writeout_one_page);

	/* now wait for locked buffers on pages from both clean and dirty lists */
	retval |= do_buffer_fdatasync(&inode->i_mapping->dirty_pages, start_idx, end_idx, waitfor_one_page);
	retval |= do_buffer_fdatasync(&inode->i_mapping->clean_pages, start_idx, end_idx, waitfor_one_page);
	retval |= do_buffer_fdatasync(&inode->i_mapping->locked_pages, start_idx, end_idx, waitfor_one_page);

	return retval;
}

/*
 * In-memory filesystems have to fail their