vmscan.c

ARM 嵌入式 系统 设计与实例开发 实验教材 二源码

/*
 *  linux/mm/vmscan.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Swap reorganised 29.12.95, Stephen Tweedie.
 *  kswapd added: 7.1.96  sct
 *  Removed kswapd_ctl limits, and swap out as many pages as needed
 *  to bring the system back to freepages.high: 2.4.97, Rik van Riel.
 *  Zone aware kswapd started 02/00, Kanoj Sarcar ([e-mail]).
 *  Multiqueue VM started 5.8.00, Rik van Riel.
 */

#include <linux/slab.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/swapctl.h>
#include <linux/smp_lock.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/file.h>
#include <linux/compiler.h>

#include <asm/pgalloc.h>

/*
 * The "priority" of VM scanning is how much of the queues we
 * will scan in one go. A value of 6 for DEF_PRIORITY implies
 * that we'll scan 1/64th of the queues ("queue_length >> 6")
 * during a normal aging round.
 */
#define DEF_PRIORITY (6)

/*
 * The swap-out function returns 1 if it successfully
 * scanned all the pages it was asked to (`count').
 * It returns zero if it couldn't do anything,
 *
 * rss may decrease because pages are shared, but this
 * doesn't count as having freed a page.
 */

/* mm->page_table_lock is held. mmap_sem is not held */
static inline int try_to_swap_out(struct mm_struct * mm, struct vm_area_struct* vma, unsigned long address, pte_t * page_table, struct page *page, zone_t * classzone)
{
	pte_t pte;
	swp_entry_t entry;

	/* Don't look at this pte if it's been accessed recently. */
	if ((vma->vm_flags & VM_LOCKED) || ptep_test_and_clear_young(page_table)) {
		mark_page_accessed(page);
		return 0;
	}

	/* Don't bother unmapping pages that are active */
	if (PageActive(page))
		return 0;

	/* Don't bother replenishing zones not under pressure.. */
	if (!memclass(page->zone, classzone))
		return 0;

	if (TryLockPage(page))
		return 0;

	/* From this point on, the odds are that we're going to
	 * nuke this pte, so read and clear the pte.  This hook
	 * is needed on CPUs which update the accessed and dirty
	 * bits in hardware.
	 */
	flush_cache_page(vma, address);
	pte = ptep_get_and_clear(page_table);
	flush_tlb_page(vma, address);

	if (pte_dirty(pte))
		set_page_dirty(page);

	/*
	 * Is the page already in the swap cache? If so, then
	 * we can just drop our reference to it without doing
	 * any IO - it's already up-to-date on disk.
	 */
	if (PageSwapCache(page)) {
		entry.val = page->index;
		swap_duplicate(entry);
set_swap_pte:
		set_pte(page_table, swp_entry_to_pte(entry));
drop_pte:
		mm->rss--;
		UnlockPage(page);
		memc_clear(vma->vm_mm, page);
		{
			int freeable = page_count(page) - !!page->buffers <= 2;
			page_cache_release(page);
			return freeable;
		}
	}

	/*
	 * Is it a clean page? Then it must be recoverable
	 * by just paging it in again, and we can just drop
	 * it..  or if it's dirty but has backing store,
	 * just mark the page dirty and drop it.
	 *
	 * However, this won't actually free any real
	 * memory, as the page will just be in the page cache
	 * somewhere, and as such we should just continue
	 * our scan.
	 *
	 * Basically, this just makes it possible for us to do
	 * some real work in the future in "refill_inactive()".
	 */
	if (page->mapping)
		goto drop_pte;
	if (!PageDirty(page))
		goto drop_pte;

	/*
	 * Anonymous buffercache pages can be left behind by
	 * concurrent truncate and pagefault.
	 */
	if (page->buffers)
		goto preserve;

	/*
	 * This is a dirty, swappable page.  First of all,
	 * get a suitable swap entry for it, and make sure
	 * we have the swap cache set up to associate the
	 * page with that swap entry.
	 */
	for (;;) {
		entry = get_swap_page();
		if (!entry.val)
			break;
		/* Add it to the swap cache and mark it dirty
		 * (adding to the page cache will clear the dirty
		 * and uptodate bits, so we need to do it again)
		 */
		if (add_to_swap_cache(page, entry) == 0) {
			SetPageUptodate(page);
			set_page_dirty(page);
			goto set_swap_pte;
		}
		/* Raced with "speculative" read_swap_cache_async */
		swap_free(entry);
	}

	/* No swap space left */
preserve:
	set_pte(page_table, pte);
	UnlockPage(page);
	return 0;
}

/* mm->page_table_lock is held. mmap_sem is not held */
static inline int swap_out_pmd(struct mm_struct * mm, struct vm_area_struct * vma, pmd_t *dir, unsigned long address, unsigned long end, int count, zone_t * classzone)
{
	pte_t * pte;
	unsigned long pmd_end;

	if (pmd_none(*dir))
		return count;
	if (pmd_bad(*dir)) {
		pmd_ERROR(*dir);
		pmd_clear(dir);
		return count;
	}
	
	pte = pte_offset(dir, address);
	
	pmd_end = (address + PMD_SIZE) & PMD_MASK;
	if (end > pmd_end)
		end = pmd_end;

	do {
		if (pte_present(*pte)) {
			struct page *page = pte_page(*pte);

			if (VALID_PAGE(page) && !PageReserved(page)) {
				count -= try_to_swap_out(mm, vma, address, pte, page, classzone);
				if (!count) {
					address += PAGE_SIZE;
					break;
				}
			}
		}
		address += PAGE_SIZE;
		pte++;
	} while (address && (address < end));
	mm->swap_address = address;
	return count;
}

/* mm->page_table_lock is held. mmap_sem is not held */
static inline int swap_out_pgd(struct mm_struct * mm, struct vm_area_struct * vma, pgd_t *dir, unsigned long address, unsigned long end, int count, zone_t * classzone)
{
	pmd_t * pmd;
	unsigned long pgd_end;

	if (pgd_none(*dir))
		return count;
	if (pgd_bad(*dir)) {
		pgd_ERROR(*dir);
		pgd_clear(dir);
		return count;
	}

	pmd = pmd_offset(dir, address);

	pgd_end = (address + PGDIR_SIZE) & PGDIR_MASK;	
	if (pgd_end && (end > pgd_end))
		end = pgd_end;
	
	do {
		count = swap_out_pmd(mm, vma, pmd, address, end, count, classzone);
		if (!count)
			break;
		address = (address + PMD_SIZE) & PMD_MASK;
		pmd++;
	} while (address && (address < end));
	return count;
}

/* mm->page_table_lock is held. mmap_sem is not held */
static inline int swap_out_vma(struct mm_struct * mm, struct vm_area_struct * vma, unsigned long address, int count, zone_t * classzone)
{
	pgd_t *pgdir;
	unsigned long end;

	/* Don't swap out areas which are reserved */
	if (vma->vm_flags & VM_RESERVED)
		return count;

	pgdir = pgd_offset(mm, address);

	end = vma->vm_end;
	if (address >= end)
		BUG();
	do {
		count = swap_out_pgd(mm, vma, pgdir, address, end, count, classzone);
		if (!count)
			break;
		address = (address + PGDIR_SIZE) & PGDIR_MASK;
		pgdir++;
	} while (address && (address < end));
	return count;
}

/* Placeholder for swap_out(): may be updated by fork.c:mmput() */
struct mm_struct *swap_mm = &init_mm;

/*
 * Returns remaining count of pages to be swapped out by followup call.
 */
static inline int swap_out_mm(struct mm_struct * mm, int count, int * mmcounter, zone_t * classzone)
{
	unsigned long address;
	struct vm_area_struct* vma;

	/*
	 * Find the proper vm-area after freezing the vma chain 
	 * and ptes.
	 */
	spin_lock(&mm->page_table_lock);
	address = mm->swap_address;
	if (address == TASK_SIZE || swap_mm != mm) {
		/* We raced: don't count this mm but try again */
		++*mmcounter;
		goto out_unlock;
	}
	vma = find_vma(mm, address);
	if (vma) {
		if (address < vma->vm_start)
			address = vma->vm_start;

		for (;;) {
			count = swap_out_vma(mm, vma, address, count, classzone);
			vma = vma->vm_next;
			if (!vma)
				break;
			if (!count)
				goto out_unlock;
			address = vma->vm_start;
		}
	}
	/* Indicate that we reached the end of address space */
	mm->swap_address = TASK_SIZE;

out_unlock:
	spin_unlock(&mm->page_table_lock);
	return count;
}

static int FASTCALL(swap_out(unsigned int priority, unsigned int gfp_mask, zone_t * classzone));
static int swap_out(unsigned int priority, unsigned int gfp_mask, zone_t * classzone)
{
	int counter, nr_pages = SWAP_CLUSTER_MAX;
	struct mm_struct *mm;

	counter = mmlist_nr;
	do {
		if (unlikely(current->need_resched)) {
			__set_current_state(TASK_RUNNING);
			schedule();
		}

		spin_lock(&mmlist_lock);
		mm = swap_mm;
		while (mm->swap_address == TASK_SIZE || mm == &init_mm) {
			mm->swap_address = 0;
			mm = list_entry(mm->mmlist.next, struct mm_struct, mmlist);
			if (mm == swap_mm)
				goto empty;
			swap_mm = mm;
		}

		/* Make sure the mm doesn't disappear when we drop the lock.. */
		atomic_inc(&mm->mm_users);
		spin_unlock(&mmlist_lock);

		nr_pages = swap_out_mm(mm, nr_pages, &counter, classzone);

		mmput(mm);

		if (!nr_pages)
			return 1;
	} while (--counter >= 0);

	return 0;

empty:
	spin_unlock(&mmlist_lock);
	return 0;
}

static int FASTCALL(shrink_cache(int nr_pages, zone_t * classzone, unsigned int gfp_mask, int priority));
static int shrink_cache(int nr_pages, zone_t * classzone, unsigned int gfp_mask, int priority)
{
	struct list_head * entry;
	int max_scan = nr_inactive_pages / priority;
	int max_mapped = min((nr_pages << (10 - priority)), max_scan / 10);

	spin_lock(&pagemap_lru_lock);
	while (--max_scan >= 0 && (entry = inactive_list.prev) != &inactive_list) {
		struct page * page;

		if (unlikely(current->need_resched)) {
			spin_unlock(&pagemap_lru_lock);
			__set_current_state(TASK_RUNNING);
			schedule();
			spin_lock(&pagemap_lru_lock);
			continue;
		}

		page = list_entry(entry, struct page, lru);

		if (unlikely(!PageLRU(page)))
			BUG();
		if (unlikely(PageActive(page)))
			BUG();

		list_del(entry);
		list_add(entry, &inactive_list);

		/*
		 * Zero page counts can happen because we unlink the pages
		 * _after_ decrementing the usage count..
		 */
		if (unlikely(!page_count(page)))
			continue;

		if (!memclass(page->zone, classzone))
			continue;

		/* Racy check to avoid trylocking when not worthwhile */
		if (!page->buffers && (page_count(page) != 1 || !page->mapping))
			goto page_mapped;

		/*
		 * The page is locked. IO in progress?
		 * Move it to the back of the list.