void __flush_dcache_page(struct page *page)
{
	struct address_space *mapping = page_mapping(page);
	unsigned long addr;

	if (PageHighMem(page))
		return;
	if (mapping && !mapping_mapped(mapping)) {
		SetPageDcacheDirty(page);
		return;
	}

	/*
	 * We could delay the flush for the !page_mapping case too.  But that
	 * case is for exec env/arg pages and those are %99 certainly going to
	 * get faulted into the tlb (and thus flushed) anyways.
	 */
	addr = (unsigned long) page_address(page);
	flush_data_cache_page(addr);
}

int test_clear_page_writeback(struct page *page)
{
	struct address_space *mapping = page_mapping(page);
	int ret;

	if (mapping) {
		unsigned long flags;

		write_lock_irqsave(&mapping->tree_lock, flags);
		ret = TestClearPageWriteback(page);
		if (ret)
			radix_tree_tag_clear(&mapping->page_tree,
						page_index(page),
						PAGECACHE_TAG_WRITEBACK);
		write_unlock_irqrestore(&mapping->tree_lock, flags);
	} else {
		ret = TestClearPageWriteback(page);
	}
	return ret;
}

/*
 * Ensure cache coherency between kernel mapping and userspace mapping
 * of this page.
 */
void flush_dcache_page(struct page *page)
{
	struct address_space *mapping;

	/*
	 * The zero page is never written to, so never has any dirty
	 * cache lines, and therefore never needs to be flushed.
	 */
	if (page == ZERO_PAGE(0))
		return;

	mapping = page_mapping(page);

	if (mapping && !mapping_mapped(mapping))
		clear_bit(PG_dcache_clean, &page->flags);
	else {
		__flush_dcache_page(mapping, page);
		if (mapping)
			__flush_icache_all();
		set_bit(PG_dcache_clean, &page->flags);
	}
}

void flush_dcache_page(struct page *page)
{
	struct address_space *mapping;

	mapping = page_mapping(page);
	if (mapping && !mapping_mapped(mapping))
		set_bit(PG_dcache_dirty, &page->flags);
	else {
		int i, pc;
		unsigned long vto, kaddr, flags;
		kaddr = (unsigned long)page_address(page);
		cpu_dcache_wbinval_page(kaddr);
		pc = CACHE_SET(DCACHE) * CACHE_LINE_SIZE(DCACHE) / PAGE_SIZE;
		local_irq_save(flags);
		for (i = 0; i < pc; i++) {
			vto =
			    kremap0(kaddr + i * PAGE_SIZE, page_to_phys(page));
			cpu_dcache_wbinval_page(vto);
			kunmap01(vto);
		}
		local_irq_restore(flags);
	}
}

void __flush_dcache_page(struct page *page)
{
	void *addr;

	if (page_mapping(page) && !page_mapped(page)) {
		SetPageDcacheDirty(page);
		return;
	}

	/*
	 * We could delay the flush for the !page_mapping case too.  But that
	 * case is for exec env/arg pages and those are %99 certainly going to
	 * get faulted into the tlb (and thus flushed) anyways.
	 */
	if (PageHighMem(page)) {
		addr = kmap_atomic(page);
		flush_data_cache_page((unsigned long)addr);
		kunmap_atomic(addr);
	} else {
		addr = (void *) page_address(page);
		flush_data_cache_page((unsigned long)addr);
	}
	ClearPageDcacheDirty(page);
}

//.........这里部分代码省略.........
		if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
			break;
		if (pages_written >= write_chunk)
			break;		/* We've done our duty */

		congestion_wait(WRITE, HZ/10);
	}

	if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
			bdi->dirty_exceeded)
		bdi->dirty_exceeded = 0;

	if (writeback_in_progress(bdi))
		return;		/* pdflush is already working this queue */

	/*
	 * In laptop mode, we wait until hitting the higher threshold before
	 * starting background writeout, and then write out all the way down
	 * to the lower threshold.  So slow writers cause minimal disk activity.
	 *
	 * In normal mode, we start background writeout at the lower
	 * background_thresh, to keep the amount of dirty memory low.
	 */
	if ((laptop_mode && pages_written) ||
			(!laptop_mode && (global_page_state(NR_FILE_DIRTY)
					  + global_page_state(NR_UNSTABLE_NFS)
					  > background_thresh)))
		pdflush_operation(background_writeout, 0);
}

void set_page_dirty_balance(struct page *page, int page_mkwrite)
{
	if (set_page_dirty(page) || page_mkwrite) {
		struct address_space *mapping = page_mapping(page);

		if (mapping)
			balance_dirty_pages_ratelimited(mapping);
	}
}

/**
 * balance_dirty_pages_ratelimited_nr - balance dirty memory state
 * @mapping: address_space which was dirtied
 * @nr_pages_dirtied: number of pages which the caller has just dirtied
 *
 * Processes which are dirtying memory should call in here once for each page
 * which was newly dirtied.  The function will periodically check the system's
 * dirty state and will initiate writeback if needed.
 *
 * On really big machines, get_writeback_state is expensive, so try to avoid
 * calling it too often (ratelimiting).  But once we're over the dirty memory
 * limit we decrease the ratelimiting by a lot, to prevent individual processes
 * from overshooting the limit by (ratelimit_pages) each.
 */
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
					unsigned long nr_pages_dirtied)
{
	static DEFINE_PER_CPU(unsigned long, ratelimits) = 0;
	unsigned long ratelimit;
	unsigned long *p;

	ratelimit = ratelimit_pages;
	if (mapping->backing_dev_info->dirty_exceeded)
		ratelimit = 8;

	/*

/**
 * write_one_page - write out a single page and optionally wait on I/O
 * @page: the page to write
 * @wait: if true, wait on writeout
 *
 * The page must be locked by the caller and will be unlocked upon return.
 *
 * write_one_page() returns a negative error code if I/O failed.
 */
int write_one_page(struct page *page, int wait)
{
	struct address_space *mapping = page->mapping;
	int ret = 0;
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = 1,
	};

	BUG_ON(!PageLocked(page));

	if (wait)
		wait_on_page_writeback(page);

	if (clear_page_dirty_for_io(page)) {
		page_cache_get(page);
		ret = mapping->a_ops->writepage(page, &wbc);
		if (ret == 0 && wait) {
			wait_on_page_writeback(page);
			if (PageError(page))
				ret = -EIO;
		}
		page_cache_release(page);
	} else {
		unlock_page(page);
	}
	return ret;
}
EXPORT_SYMBOL(write_one_page);

/*
 * For address_spaces which do not use buffers nor write back.
 */
int __set_page_dirty_no_writeback(struct page *page)
{
	if (!PageDirty(page))
		SetPageDirty(page);
	return 0;
}

/*
 * For address_spaces which do not use buffers.  Just tag the page as dirty in
 * its radix tree.
 *
 * This is also used when a single buffer is being dirtied: we want to set the
 * page dirty in that case, but not all the buffers.  This is a "bottom-up"
 * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
 *
 * Most callers have locked the page, which pins the address_space in memory.
 * But zap_pte_range() does not lock the page, however in that case the
 * mapping is pinned by the vma's ->vm_file reference.
 *
 * We take care to handle the case where the page was truncated from the
 * mapping by re-checking page_mapping() inside tree_lock.
 */
int __set_page_dirty_nobuffers(struct page *page)
{
	if (!TestSetPageDirty(page)) {
		struct address_space *mapping = page_mapping(page);
		struct address_space *mapping2;

		if (!mapping)
			return 1;

		spin_lock_irq(&mapping->tree_lock);
		mapping2 = page_mapping(page);
		if (mapping2) { /* Race with truncate? */
			BUG_ON(mapping2 != mapping);
			WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
			if (mapping_cap_account_dirty(mapping)) {
				__inc_zone_page_state(page, NR_FILE_DIRTY);
				__inc_bdi_stat(mapping->backing_dev_info,
						BDI_RECLAIMABLE);
				task_io_account_write(PAGE_CACHE_SIZE);
			}
			radix_tree_tag_set(&mapping->page_tree,
				page_index(page), PAGECACHE_TAG_DIRTY);
		}
		spin_unlock_irq(&mapping->tree_lock);
		if (mapping->host) {
			/* !PageAnon && !swapper_space */
			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
		}
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);

/*
 * When a writepage implementation decides that it doesn't want to write this
//.........这里部分代码省略.........

//.........这里部分代码省略.........
		 * Unstable writes are a feature of certain networked
		 * filesystems (i.e. NFS) in which data may have been
		 * written to the server's write cache, but has not yet
		 * been flushed to permanent storage.
		 * Only move pages to writeback if this bdi is over its
		 * threshold otherwise wait until the disk writes catch
		 * up.
		 */
		trace_wbc_balance_dirty_start(&wbc, bdi);
		if (bdi_nr_reclaimable > bdi_thresh) {
			writeback_inodes_wb(&bdi->wb, &wbc);
			pages_written += write_chunk - wbc.nr_to_write;
			trace_wbc_balance_dirty_written(&wbc, bdi);
			if (pages_written >= write_chunk)
				break;		/* We've done our duty */
		}
		trace_wbc_balance_dirty_wait(&wbc, bdi);
		__set_current_state(TASK_UNINTERRUPTIBLE);
		io_schedule_timeout(pause);

		/*
		 * Increase the delay for each loop, up to our previous
		 * default of taking a 100ms nap.
		 */
		pause <<= 1;
		if (pause > HZ / 10)
			break;
	}

	if (!dirty_exceeded && bdi->dirty_exceeded)
		bdi->dirty_exceeded = 0;

	if (writeback_in_progress(bdi))
		return;

	/*
	 * In laptop mode, we wait until hitting the higher threshold before
	 * starting background writeout, and then write out all the way down
	 * to the lower threshold.  So slow writers cause minimal disk activity.
	 *
	 * In normal mode, we start background writeout at the lower
	 * background_thresh, to keep the amount of dirty memory low.
	 */
	if ((laptop_mode && pages_written) ||
	    (!laptop_mode && (nr_reclaimable > background_thresh)))
		bdi_start_background_writeback(bdi);
}

void set_page_dirty_balance(struct page *page, int page_mkwrite)
{
	if (set_page_dirty(page) || page_mkwrite) {
		struct address_space *mapping = page_mapping(page);

		if (mapping)
			balance_dirty_pages_ratelimited(mapping);
	}
}

static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;

/**
 * balance_dirty_pages_ratelimited_nr - balance dirty memory state
 * @mapping: address_space which was dirtied
 * @nr_pages_dirtied: number of pages which the caller has just dirtied
 *
 * Processes which are dirtying memory should call in here once for each page
 * which was newly dirtied.  The function will periodically check the system's
 * dirty state and will initiate writeback if needed.
 *
 * On really big machines, get_writeback_state is expensive, so try to avoid
 * calling it too often (ratelimiting).  But once we're over the dirty memory
 * limit we decrease the ratelimiting by a lot, to prevent individual processes
 * from overshooting the limit by (ratelimit_pages) each.
 */
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
					unsigned long nr_pages_dirtied)
{
	unsigned long ratelimit;
	unsigned long *p;

	ratelimit = ratelimit_pages;
	if (mapping->backing_dev_info->dirty_exceeded)
		ratelimit = 8;

	/*
	 * Check the rate limiting. Also, we do not want to throttle real-time
	 * tasks in balance_dirty_pages(). Period.
	 */
	preempt_disable();
	p =  &__get_cpu_var(bdp_ratelimits);
	*p += nr_pages_dirtied;
	if (unlikely(*p >= ratelimit)) {
		ratelimit = sync_writeback_pages(*p);
		*p = 0;
		preempt_enable();
		balance_dirty_pages(mapping, ratelimit);
		return;
	}
	preempt_enable();
}

//.........这里部分代码省略.........
		 * default of taking a 100ms nap.
		 */
		pause <<= 1;
		if (pause > HZ / 10)
			pause = HZ / 10;

		if (fatal_signal_pending(current))
			break;
	}

	if(pages_written) trace_mm_balancedirty_writeout(pages_written);
	if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
			bdi->dirty_exceeded)
		bdi->dirty_exceeded = 0;

	if (ub_dirty + ub_writeback < ub_thresh &&
	    test_bit(UB_DIRTY_EXCEEDED, &ub->ub_flags))
		clear_bit(UB_DIRTY_EXCEEDED, &ub->ub_flags);

	virtinfo_notifier_call(VITYPE_IO, VIRTINFO_IO_BALANCE_DIRTY,
			       (void*)write_chunk);

	/*
	 * Even if this is filtered writeback for other ub it will write
	 * inodes for this ub, because ub->dirty_exceeded is set.
	 */
	if (writeback_in_progress(bdi))
		return;

	/*
	 * In laptop mode, we wait until hitting the higher threshold before
	 * starting background writeout, and then write out all the way down
	 * to the lower threshold.  So slow writers cause minimal disk activity.
	 *
	 * In normal mode, we start background writeout at the lower
	 * background_thresh, to keep the amount of dirty memory low.
	 */
	if ((laptop_mode && pages_written) ||
	    (!laptop_mode && ((global_page_state(NR_FILE_DIRTY)
			       + global_page_state(NR_UNSTABLE_NFS))
					  > background_thresh)))
		bdi_start_background_writeback(bdi, NULL);
	else if ((laptop_mode && pages_written) ||
		 (!laptop_mode && ub_dirty > ub_background_thresh))
		bdi_start_background_writeback(bdi, ub);
}

void set_page_dirty_balance(struct page *page, int page_mkwrite)
{
	if (set_page_dirty(page) || page_mkwrite) {
		struct address_space *mapping = page_mapping(page);

		if (mapping)
			balance_dirty_pages_ratelimited(mapping);
	}
}

static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;

/**
 * balance_dirty_pages_ratelimited_nr - balance dirty memory state
 * @mapping: address_space which was dirtied
 * @nr_pages_dirtied: number of pages which the caller has just dirtied
 *
 * Processes which are dirtying memory should call in here once for each page
 * which was newly dirtied.  The function will periodically check the system's
 * dirty state and will initiate writeback if needed.
 *
 * On really big machines, get_writeback_state is expensive, so try to avoid
 * calling it too often (ratelimiting).  But once we're over the dirty memory
 * limit we decrease the ratelimiting by a lot, to prevent individual processes
 * from overshooting the limit by (ratelimit_pages) each.
 */
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
					unsigned long nr_pages_dirtied)
{
	unsigned long ratelimit;
	unsigned long *p;

	ratelimit = ratelimit_pages;
	if (mapping->backing_dev_info->dirty_exceeded ||
	    test_bit(UB_DIRTY_EXCEEDED, &get_io_ub()->ub_flags))
		ratelimit = 8;

	/*
	 * Check the rate limiting. Also, we do not want to throttle real-time
	 * tasks in balance_dirty_pages(). Period.
	 */
	preempt_disable();
	p =  &__get_cpu_var(bdp_ratelimits);
	*p += nr_pages_dirtied;
	if (unlikely(*p >= ratelimit)) {
		ratelimit = sync_writeback_pages(*p);
		*p = 0;
		preempt_enable();
		balance_dirty_pages(mapping, ratelimit);
		return;
	}
	preempt_enable();
}

void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
		   pte_t *ptep, pte_t orig, int fullmm)
{
	struct tlb_batch *tb = &get_cpu_var(tlb_batch);
	unsigned long nr;

	vaddr &= PAGE_MASK;
	if (pte_exec(orig))
		vaddr |= 0x1UL;

	if (tlb_type != hypervisor &&
	    pte_dirty(orig)) {
		unsigned long paddr, pfn = pte_pfn(orig);
		struct address_space *mapping;
		struct page *page;

		if (!pfn_valid(pfn))
			goto no_cache_flush;

		page = pfn_to_page(pfn);
		if (PageReserved(page))
			goto no_cache_flush;

		/* A real file page? */
		mapping = page_mapping(page);
		if (!mapping)
			goto no_cache_flush;

		paddr = (unsigned long) page_address(page);
		if ((paddr ^ vaddr) & (1 << 13))
			flush_dcache_page_all(mm, page);
	}

no_cache_flush:

	if (fullmm) {
		put_cpu_var(tlb_batch);
		return;
	}

	nr = tb->tlb_nr;

	if (unlikely(nr != 0 && mm != tb->mm)) {
		flush_tlb_pending();
		nr = 0;
	}

	if (!tb->active) {
		global_flush_tlb_page(mm, vaddr);
		flush_tsb_user_page(mm, vaddr);
		goto out;
	}

	if (nr == 0)
		tb->mm = mm;

	tb->vaddrs[nr] = vaddr;
	tb->tlb_nr = ++nr;
	if (nr >= TLB_BATCH_NR)
		flush_tlb_pending();

out:
	put_cpu_var(tlb_batch);
}

void alloc_user_stack(struct pcb* p)
{
  p->u_stack = (uint64_t*)0x0000000000800000;
  page_mapping((uint64_t)p->u_stack);
}

int write_one_page(struct page *page, int wait)
{
	struct address_space *mapping = page->mapping;
	int ret = 0;
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = 1,
	};

	BUG_ON(!PageLocked(page));

	if (wait)
		wait_on_page_writeback(page);

	if (clear_page_dirty_for_io(page)) {
		page_cache_get(page);
		ret = mapping->a_ops->writepage(page, &wbc);
		if (ret == 0 && wait) {
			wait_on_page_writeback(page);
			if (PageError(page))
				ret = -EIO;
		}
		page_cache_release(page);
	} else {
		unlock_page(page);
	}
	return ret;
}
EXPORT_SYMBOL(write_one_page);

int __set_page_dirty_no_writeback(struct page *page)
{
	if (!PageDirty(page))
		SetPageDirty(page);
	return 0;
}

void account_page_dirtied(struct page *page, struct address_space *mapping)
{
	if (mapping_cap_account_dirty(mapping)) {
		__inc_zone_page_state(page, NR_FILE_DIRTY);
		__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
		task_dirty_inc(current);
		task_io_account_write(PAGE_CACHE_SIZE);
	}
}

int __set_page_dirty_nobuffers(struct page *page)
{
	if (!TestSetPageDirty(page)) {
		struct address_space *mapping = page_mapping(page);
		struct address_space *mapping2;

		if (!mapping)
			return 1;

		spin_lock_irq(&mapping->tree_lock);
		mapping2 = page_mapping(page);
		if (mapping2) { /* Race with truncate? */
			BUG_ON(mapping2 != mapping);
			WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
			account_page_dirtied(page, mapping);
			radix_tree_tag_set(&mapping->page_tree,
				page_index(page), PAGECACHE_TAG_DIRTY);
		}
		spin_unlock_irq(&mapping->tree_lock);
		if (mapping->host) {
			/* !PageAnon && !swapper_space */
			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
		}
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);

int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
	wbc->pages_skipped++;
	return __set_page_dirty_nobuffers(page);
}

//.........这里部分代码省略.........
			pages_written += write_chunk - wbc.nr_to_write;
			get_dirty_limits(&background_thresh, &dirty_thresh,
				       &bdi_thresh, bdi);
		}

		/*
		 * In order to avoid the stacked BDI deadlock we need
		 * to ensure we accurately count the 'dirty' pages when
		 * the threshold is low.
		 *
		 * Otherwise it would be possible to get thresh+n pages
		 * reported dirty, even though there are thresh-m pages
		 * actually dirty; with m+n sitting in the percpu
		 * deltas.
		 */
		if (bdi_thresh < 2*bdi_stat_error(bdi)) {
			bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
			bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK);
		} else if (bdi_nr_reclaimable) {
			bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
			bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
		}

		if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
			break;
		if (pages_written >= write_chunk)
			break;		/* We've done our duty */

		__set_current_state(TASK_INTERRUPTIBLE);
		io_schedule_timeout(pause);

		/*
		 * Increase the delay for each loop, up to our previous
		 * default of taking a 100ms nap.
		 */
		pause <<= 1;
		if (pause > HZ / 10)
			pause = HZ / 10;
	}

	if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
			bdi->dirty_exceeded)
		bdi->dirty_exceeded = 0;

	if (writeback_in_progress(bdi))
		return;

	/*
	 * In laptop mode, we wait until hitting the higher threshold before
	 * starting background writeout, and then write out all the way down
	 * to the lower threshold.  So slow writers cause minimal disk activity.
	 *
	 * In normal mode, we start background writeout at the lower
	 * background_thresh, to keep the amount of dirty memory low.
	 */
	if ((laptop_mode && pages_written) ||
	    (!laptop_mode && ((global_page_state(NR_FILE_DIRTY)
			       + global_page_state(NR_UNSTABLE_NFS))
					  > background_thresh)))
		bdi_start_background_writeback(bdi);
}

void set_page_dirty_balance(struct page *page, int page_mkwrite)
{
	if (set_page_dirty(page) || page_mkwrite) {
		struct address_space *mapping = page_mapping(page);

		if (mapping)
			balance_dirty_pages_ratelimited(mapping);
	}
}

static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;

void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
					unsigned long nr_pages_dirtied)
{
	unsigned long ratelimit;
	unsigned long *p;

	ratelimit = ratelimit_pages;
	if (mapping->backing_dev_info->dirty_exceeded)
		ratelimit = 8;

	/*
	 * Check the rate limiting. Also, we do not want to throttle real-time
	 * tasks in balance_dirty_pages(). Period.
	 */
	preempt_disable();
	p =  &__get_cpu_var(bdp_ratelimits);
	*p += nr_pages_dirtied;
	if (unlikely(*p >= ratelimit)) {
		ratelimit = sync_writeback_pages(*p);
		*p = 0;
		preempt_enable();
		balance_dirty_pages(mapping, ratelimit);
		return;
	}
	preempt_enable();
}