/*
   *	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/export.h>

  #include <linux/compiler.h>

  #include <linux/dax.h>

  #include <linux/fs.h>

  #include <linux/sched/signal.h>

  #include <linux/uaccess.h>

  #include <linux/capability.h>

  #include <linux/kernel_stat.h>

  #include <linux/gfp.h>

  #include <linux/mm.h>
  #include <linux/swap.h>
  #include <linux/mman.h>
  #include <linux/pagemap.h>
  #include <linux/file.h>
  #include <linux/uio.h>
  #include <linux/hash.h>
  #include <linux/writeback.h>

  #include <linux/backing-dev.h>

  #include <linux/pagevec.h>
  #include <linux/blkdev.h>
  #include <linux/security.h>

  #include <linux/cpuset.h>

  #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */

  #include <linux/hugetlb.h>

  #include <linux/memcontrol.h>

  #include <linux/cleancache.h>

  #include <linux/rmap.h>

  #include "internal.h"

  #define CREATE_TRACE_POINTS
  #include <trace/events/filemap.h>

  /*

   * FIXME: remove all knowledge of the buffer layer from the core VM
   */

  #include <linux/buffer_head.h> /* for try_to_free_buffers */

  #include <asm/mman.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 <mingo@redhat.com>
   *
   * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de>
   */
  
  /*
   * Lock ordering:
   *

   *  ->i_mmap_rwsem		(truncate_pagecache)

   *    ->private_lock		(__free_pte->__set_page_dirty_buffers)

   *      ->swap_lock		(exclusive_swap_page, others)
   *        ->mapping->tree_lock

   *

   *  ->i_mutex

   *    ->i_mmap_rwsem		(truncate->unmap_mapping_range)

   *
   *  ->mmap_sem

   *    ->i_mmap_rwsem

   *      ->page_table_lock or pte_lock	(various, mainly in memory.c)

   *        ->mapping->tree_lock	(arch-dependent flush_dcache_mmap_lock)
   *
   *  ->mmap_sem
   *    ->lock_page		(access_process_vm)
   *

   *  ->i_mutex			(generic_perform_write)

   *    ->mmap_sem		(fault_in_pages_readable->do_page_fault)

   *

   *  bdi->wb.list_lock

   *    sb_lock			(fs/fs-writeback.c)

   *    ->mapping->tree_lock	(__sync_single_inode)
   *

   *  ->i_mmap_rwsem

   *    ->anon_vma.lock		(vma_adjust)
   *
   *  ->anon_vma.lock

   *    ->page_table_lock or pte_lock	(anon_vma_prepare and various)

   *

   *  ->page_table_lock or pte_lock

   *    ->swap_lock		(try_to_unmap_one)

   *    ->private_lock		(try_to_unmap_one)
   *    ->tree_lock		(try_to_unmap_one)

   *    ->zone_lru_lock(zone)	(follow_page->mark_page_accessed)
   *    ->zone_lru_lock(zone)	(check_pte_range->isolate_lru_page)

   *    ->private_lock		(page_remove_rmap->set_page_dirty)
   *    ->tree_lock		(page_remove_rmap->set_page_dirty)

   *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)

   *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)

   *    ->memcg->move_lock	(page_remove_rmap->lock_page_memcg)

   *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty)

   *    ->inode->i_lock		(zap_pte_range->set_page_dirty)

   *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
   *

   * ->i_mmap_rwsem

   *   ->tasklist_lock            (memory_failure, collect_procs_ao)

   */

  static int page_cache_tree_insert(struct address_space *mapping,
  				  struct page *page, void **shadowp)
  {
  	struct radix_tree_node *node;
  	void **slot;
  	int error;
  
  	error = __radix_tree_create(&mapping->page_tree, page->index, 0,
  				    &node, &slot);
  	if (error)
  		return error;
  	if (*slot) {
  		void *p;
  
  		p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
  		if (!radix_tree_exceptional_entry(p))
  			return -EEXIST;
  
  		mapping->nrexceptional--;

  		if (shadowp)
  			*shadowp = p;

  	}

  	__radix_tree_replace(&mapping->page_tree, node, slot, page,
  			     workingset_update_node, mapping);

  	mapping->nrpages++;

  	return 0;
  }

  static void page_cache_tree_delete(struct address_space *mapping,
  				   struct page *page, void *shadow)
  {

  	int i, nr;
  
  	/* hugetlb pages are represented by one entry in the radix tree */
  	nr = PageHuge(page) ? 1 : hpage_nr_pages(page);

  	VM_BUG_ON_PAGE(!PageLocked(page), page);
  	VM_BUG_ON_PAGE(PageTail(page), page);
  	VM_BUG_ON_PAGE(nr != 1 && shadow, page);

  	for (i = 0; i < nr; i++) {

  		struct radix_tree_node *node;
  		void **slot;
  
  		__radix_tree_lookup(&mapping->page_tree, page->index + i,
  				    &node, &slot);

  		VM_BUG_ON_PAGE(!node && nr != 1, page);

  		radix_tree_clear_tags(&mapping->page_tree, node, slot);
  		__radix_tree_replace(&mapping->page_tree, node, slot, shadow,
  				     workingset_update_node, mapping);

  	}

  
  	if (shadow) {
  		mapping->nrexceptional += nr;
  		/*
  		 * Make sure the nrexceptional update is committed before
  		 * the nrpages update so that final truncate racing
  		 * with reclaim does not see both counters 0 at the
  		 * same time and miss a shadow entry.
  		 */
  		smp_wmb();
  	}
  	mapping->nrpages -= nr;

  }

  /*

   * Delete 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.  The caller must hold the mapping's tree_lock.

   */

  void __delete_from_page_cache(struct page *page, void *shadow)

  {
  	struct address_space *mapping = page->mapping;

  	int nr = hpage_nr_pages(page);

  	trace_mm_filemap_delete_from_page_cache(page);

  	/*
  	 * if we're uptodate, flush out into the cleancache, otherwise
  	 * invalidate any existing cleancache entries.  We can't leave
  	 * stale data around in the cleancache once our page is gone
  	 */
  	if (PageUptodate(page) && PageMappedToDisk(page))
  		cleancache_put_page(page);
  	else

  		cleancache_invalidate_page(mapping, page);

  	VM_BUG_ON_PAGE(PageTail(page), page);

  	VM_BUG_ON_PAGE(page_mapped(page), page);
  	if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) {
  		int mapcount;
  
  		pr_alert("BUG: Bad page cache in process %s  pfn:%05lx
  ",
  			 current->comm, page_to_pfn(page));
  		dump_page(page, "still mapped when deleted");
  		dump_stack();
  		add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
  
  		mapcount = page_mapcount(page);
  		if (mapping_exiting(mapping) &&
  		    page_count(page) >= mapcount + 2) {
  			/*
  			 * All vmas have already been torn down, so it's
  			 * a good bet that actually the page is unmapped,
  			 * and we'd prefer not to leak it: if we're wrong,
  			 * some other bad page check should catch it later.
  			 */
  			page_mapcount_reset(page);

  			page_ref_sub(page, mapcount);

  		}
  	}

  	page_cache_tree_delete(mapping, page, shadow);

  	page->mapping = NULL;

  	/* Leave page->index set: truncation lookup relies upon it */

  	/* hugetlb pages do not participate in page cache accounting. */

  	if (PageHuge(page))
  		return;
  
  	__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);

  	if (PageSwapBacked(page)) {

  		__mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr);

  		if (PageTransHuge(page))

  			__dec_node_page_state(page, NR_SHMEM_THPS);

  	} else {

  		VM_BUG_ON_PAGE(PageTransHuge(page), page);

  	}

  
  	/*

  	 * At this point page must be either written or cleaned by truncate.
  	 * Dirty page here signals a bug and loss of unwritten data.

  	 *

  	 * This fixes dirty accounting after removing the page entirely but
  	 * leaves PageDirty set: it has no effect for truncated page and
  	 * anyway will be cleared before returning page into buddy allocator.

  	 */

  	if (WARN_ON_ONCE(PageDirty(page)))

  		account_page_cleaned(page, mapping, inode_to_wb(mapping->host));

  }

  /**
   * delete_from_page_cache - delete page from page cache
   * @page: the page which the kernel is trying to remove from page cache
   *
   * This must be called only on pages that have been verified to be in the page
   * cache and locked.  It will never put the page into the free list, the caller
   * has a reference on the page.
   */
  void delete_from_page_cache(struct page *page)

  {

  	struct address_space *mapping = page_mapping(page);

  	unsigned long flags;

  	void (*freepage)(struct page *);

  	BUG_ON(!PageLocked(page));

  	freepage = mapping->a_ops->freepage;

  	spin_lock_irqsave(&mapping->tree_lock, flags);

  	__delete_from_page_cache(page, NULL);

  	spin_unlock_irqrestore(&mapping->tree_lock, flags);

  
  	if (freepage)
  		freepage(page);

  
  	if (PageTransHuge(page) && !PageHuge(page)) {
  		page_ref_sub(page, HPAGE_PMD_NR);
  		VM_BUG_ON_PAGE(page_count(page) <= 0, page);
  	} else {
  		put_page(page);
  	}

  }
  EXPORT_SYMBOL(delete_from_page_cache);

  int filemap_check_errors(struct address_space *mapping)

  {
  	int ret = 0;
  	/* Check for outstanding write errors */

  	if (test_bit(AS_ENOSPC, &mapping->flags) &&
  	    test_and_clear_bit(AS_ENOSPC, &mapping->flags))

  		ret = -ENOSPC;

  	if (test_bit(AS_EIO, &mapping->flags) &&
  	    test_and_clear_bit(AS_EIO, &mapping->flags))

  		ret = -EIO;
  	return ret;
  }

  EXPORT_SYMBOL(filemap_check_errors);

  static int filemap_check_and_keep_errors(struct address_space *mapping)
  {
  	/* Check for outstanding write errors */
  	if (test_bit(AS_EIO, &mapping->flags))
  		return -EIO;
  	if (test_bit(AS_ENOSPC, &mapping->flags))
  		return -ENOSPC;
  	return 0;
  }

  /**

   * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range

   * @mapping:	address space structure to write
   * @start:	offset in bytes where the range starts

   * @end:	offset in bytes where the range ends (inclusive)

   * @sync_mode:	enable synchronous operation

   *

   * Start writeback against all of a mapping's dirty pages that lie
   * within the byte offsets <start, end> inclusive.
   *

   * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as

   * opposed to a regular memory cleansing writeback.  The difference between

   * these two operations is that if a dirty page/buffer is encountered, it must
   * be waited upon, and not just skipped over.
   */

  int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
  				loff_t end, int sync_mode)

  {
  	int ret;
  	struct writeback_control wbc = {
  		.sync_mode = sync_mode,

  		.nr_to_write = LONG_MAX,

  		.range_start = start,
  		.range_end = end,

  	};
  
  	if (!mapping_cap_writeback_dirty(mapping))
  		return 0;

  	wbc_attach_fdatawrite_inode(&wbc, mapping->host);

  	ret = do_writepages(mapping, &wbc);

  	wbc_detach_inode(&wbc);

  	return ret;
  }
  
  static inline int __filemap_fdatawrite(struct address_space *mapping,
  	int sync_mode)
  {

  	return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);

  }
  
  int filemap_fdatawrite(struct address_space *mapping)
  {
  	return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
  }
  EXPORT_SYMBOL(filemap_fdatawrite);

  int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,

  				loff_t end)

  {
  	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
  }

  EXPORT_SYMBOL(filemap_fdatawrite_range);

  /**
   * filemap_flush - mostly a non-blocking flush
   * @mapping:	target address_space
   *

   * This is a mostly non-blocking flush.  Not suitable for data-integrity
   * purposes - I/O may not be started against all dirty pages.
   */
  int filemap_flush(struct address_space *mapping)
  {
  	return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
  }
  EXPORT_SYMBOL(filemap_flush);

  /**
   * filemap_range_has_page - check if a page exists in range.
   * @mapping:           address space within which to check
   * @start_byte:        offset in bytes where the range starts
   * @end_byte:          offset in bytes where the range ends (inclusive)
   *
   * Find at least one page in the range supplied, usually used to check if
   * direct writing in this range will trigger a writeback.
   */
  bool filemap_range_has_page(struct address_space *mapping,
  			   loff_t start_byte, loff_t end_byte)
  {
  	pgoff_t index = start_byte >> PAGE_SHIFT;
  	pgoff_t end = end_byte >> PAGE_SHIFT;

  	struct page *page;

  
  	if (end_byte < start_byte)
  		return false;
  
  	if (mapping->nrpages == 0)
  		return false;

  	if (!find_get_pages_range(mapping, &index, end, 1, &page))

  		return false;

  	put_page(page);
  	return true;

  }
  EXPORT_SYMBOL(filemap_range_has_page);

  static void __filemap_fdatawait_range(struct address_space *mapping,

  				     loff_t start_byte, loff_t end_byte)

  {

  	pgoff_t index = start_byte >> PAGE_SHIFT;
  	pgoff_t end = end_byte >> PAGE_SHIFT;

  	struct pagevec pvec;
  	int nr_pages;

  	if (end_byte < start_byte)

  		return;

  
  	pagevec_init(&pvec, 0);

  	while ((index <= end) &&
  			(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
  			PAGECACHE_TAG_WRITEBACK,
  			min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) {
  		unsigned i;
  
  		for (i = 0; i < nr_pages; i++) {
  			struct page *page = pvec.pages[i];
  
  			/* until radix tree lookup accepts end_index */
  			if (page->index > end)
  				continue;
  
  			wait_on_page_writeback(page);

  			ClearPageError(page);

  		}
  		pagevec_release(&pvec);
  		cond_resched();
  	}

  }
  
  /**
   * filemap_fdatawait_range - wait for writeback to complete
   * @mapping:		address space structure to wait for
   * @start_byte:		offset in bytes where the range starts
   * @end_byte:		offset in bytes where the range ends (inclusive)
   *
   * Walk the list of under-writeback pages of the given address space
   * in the given range and wait for all of them.  Check error status of
   * the address space and return it.
   *
   * Since the error status of the address space is cleared by this function,
   * callers are responsible for checking the return value and handling and/or
   * reporting the error.
   */
  int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
  			    loff_t end_byte)
  {

  	__filemap_fdatawait_range(mapping, start_byte, end_byte);
  	return filemap_check_errors(mapping);

  }

  EXPORT_SYMBOL(filemap_fdatawait_range);
  
  /**

   * file_fdatawait_range - wait for writeback to complete
   * @file:		file pointing to address space structure to wait for
   * @start_byte:		offset in bytes where the range starts
   * @end_byte:		offset in bytes where the range ends (inclusive)
   *
   * Walk the list of under-writeback pages of the address space that file
   * refers to, in the given range and wait for all of them.  Check error
   * status of the address space vs. the file->f_wb_err cursor and return it.
   *
   * Since the error status of the file is advanced by this function,
   * callers are responsible for checking the return value and handling and/or
   * reporting the error.
   */
  int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte)
  {
  	struct address_space *mapping = file->f_mapping;
  
  	__filemap_fdatawait_range(mapping, start_byte, end_byte);
  	return file_check_and_advance_wb_err(file);
  }
  EXPORT_SYMBOL(file_fdatawait_range);

  
  /**

   * filemap_fdatawait_keep_errors - wait for writeback without clearing errors
   * @mapping: address space structure to wait for
   *
   * Walk the list of under-writeback pages of the given address space
   * and wait for all of them.  Unlike filemap_fdatawait(), this function
   * does not clear error status of the address space.
   *
   * Use this function if callers don't handle errors themselves.  Expected
   * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
   * fsfreeze(8)
   */

  int filemap_fdatawait_keep_errors(struct address_space *mapping)

  {

  	__filemap_fdatawait_range(mapping, 0, LLONG_MAX);

  	return filemap_check_and_keep_errors(mapping);

  }

  EXPORT_SYMBOL(filemap_fdatawait_keep_errors);

  static bool mapping_needs_writeback(struct address_space *mapping)

  {

  	return (!dax_mapping(mapping) && mapping->nrpages) ||
  	    (dax_mapping(mapping) && mapping->nrexceptional);

  }

  
  int filemap_write_and_wait(struct address_space *mapping)
  {

  	int err = 0;

  	if (mapping_needs_writeback(mapping)) {

  		err = filemap_fdatawrite(mapping);
  		/*
  		 * Even if the above returned error, the pages may be
  		 * written partially (e.g. -ENOSPC), so we wait for it.
  		 * But the -EIO is special case, it may indicate the worst
  		 * thing (e.g. bug) happened, so we avoid waiting for it.
  		 */
  		if (err != -EIO) {
  			int err2 = filemap_fdatawait(mapping);
  			if (!err)
  				err = err2;

  		} else {
  			/* Clear any previously stored errors */
  			filemap_check_errors(mapping);

  		}

  	} else {
  		err = filemap_check_errors(mapping);

  	}

  	return err;

  }

  EXPORT_SYMBOL(filemap_write_and_wait);

  /**
   * filemap_write_and_wait_range - write out & wait on a file range
   * @mapping:	the address_space for the pages
   * @lstart:	offset in bytes where the range starts
   * @lend:	offset in bytes where the range ends (inclusive)
   *

   * Write out and wait upon file offsets lstart->lend, inclusive.
   *

   * Note that @lend is inclusive (describes the last byte to be written) so

   * that this function can be used to write to the very end-of-file (end = -1).
   */

  int filemap_write_and_wait_range(struct address_space *mapping,
  				 loff_t lstart, loff_t lend)
  {

  	int err = 0;

  	if (mapping_needs_writeback(mapping)) {

  		err = __filemap_fdatawrite_range(mapping, lstart, lend,
  						 WB_SYNC_ALL);
  		/* See comment of filemap_write_and_wait() */
  		if (err != -EIO) {

  			int err2 = filemap_fdatawait_range(mapping,
  						lstart, lend);

  			if (!err)
  				err = err2;

  		} else {
  			/* Clear any previously stored errors */
  			filemap_check_errors(mapping);

  		}

  	} else {
  		err = filemap_check_errors(mapping);

  	}

  	return err;

  }

  EXPORT_SYMBOL(filemap_write_and_wait_range);

  void __filemap_set_wb_err(struct address_space *mapping, int err)
  {

  	errseq_t eseq = errseq_set(&mapping->wb_err, err);

  
  	trace_filemap_set_wb_err(mapping, eseq);
  }
  EXPORT_SYMBOL(__filemap_set_wb_err);
  
  /**
   * file_check_and_advance_wb_err - report wb error (if any) that was previously
   * 				   and advance wb_err to current one
   * @file: struct file on which the error is being reported
   *
   * When userland calls fsync (or something like nfsd does the equivalent), we
   * want to report any writeback errors that occurred since the last fsync (or
   * since the file was opened if there haven't been any).
   *
   * Grab the wb_err from the mapping. If it matches what we have in the file,
   * then just quickly return 0. The file is all caught up.
   *
   * If it doesn't match, then take the mapping value, set the "seen" flag in
   * it and try to swap it into place. If it works, or another task beat us
   * to it with the new value, then update the f_wb_err and return the error
   * portion. The error at this point must be reported via proper channels
   * (a'la fsync, or NFS COMMIT operation, etc.).
   *
   * While we handle mapping->wb_err with atomic operations, the f_wb_err
   * value is protected by the f_lock since we must ensure that it reflects
   * the latest value swapped in for this file descriptor.
   */
  int file_check_and_advance_wb_err(struct file *file)
  {
  	int err = 0;
  	errseq_t old = READ_ONCE(file->f_wb_err);
  	struct address_space *mapping = file->f_mapping;
  
  	/* Locklessly handle the common case where nothing has changed */
  	if (errseq_check(&mapping->wb_err, old)) {
  		/* Something changed, must use slow path */
  		spin_lock(&file->f_lock);
  		old = file->f_wb_err;
  		err = errseq_check_and_advance(&mapping->wb_err,
  						&file->f_wb_err);
  		trace_file_check_and_advance_wb_err(file, old);
  		spin_unlock(&file->f_lock);
  	}

  
  	/*
  	 * We're mostly using this function as a drop in replacement for
  	 * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect
  	 * that the legacy code would have had on these flags.
  	 */
  	clear_bit(AS_EIO, &mapping->flags);
  	clear_bit(AS_ENOSPC, &mapping->flags);

  	return err;
  }
  EXPORT_SYMBOL(file_check_and_advance_wb_err);
  
  /**
   * file_write_and_wait_range - write out & wait on a file range
   * @file:	file pointing to address_space with pages
   * @lstart:	offset in bytes where the range starts
   * @lend:	offset in bytes where the range ends (inclusive)
   *
   * Write out and wait upon file offsets lstart->lend, inclusive.
   *
   * Note that @lend is inclusive (describes the last byte to be written) so
   * that this function can be used to write to the very end-of-file (end = -1).
   *
   * After writing out and waiting on the data, we check and advance the
   * f_wb_err cursor to the latest value, and return any errors detected there.
   */
  int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
  {
  	int err = 0, err2;
  	struct address_space *mapping = file->f_mapping;

  	if (mapping_needs_writeback(mapping)) {

  		err = __filemap_fdatawrite_range(mapping, lstart, lend,
  						 WB_SYNC_ALL);
  		/* See comment of filemap_write_and_wait() */
  		if (err != -EIO)
  			__filemap_fdatawait_range(mapping, lstart, lend);
  	}
  	err2 = file_check_and_advance_wb_err(file);
  	if (!err)
  		err = err2;
  	return err;
  }
  EXPORT_SYMBOL(file_write_and_wait_range);

  /**

   * replace_page_cache_page - replace a pagecache page with a new one
   * @old:	page to be replaced
   * @new:	page to replace with
   * @gfp_mask:	allocation mode
   *
   * This function replaces a page in the pagecache with a new one.  On
   * success it acquires the pagecache reference for the new page and
   * drops it for the old page.  Both the old and new pages must be
   * locked.  This function does not add the new page to the LRU, the
   * caller must do that.
   *
   * The remove + add is atomic.  The only way this function can fail is
   * memory allocation failure.
   */
  int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
  {
  	int error;

  	VM_BUG_ON_PAGE(!PageLocked(old), old);
  	VM_BUG_ON_PAGE(!PageLocked(new), new);
  	VM_BUG_ON_PAGE(new->mapping, new);

  	error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);

  	if (!error) {
  		struct address_space *mapping = old->mapping;
  		void (*freepage)(struct page *);

  		unsigned long flags;

  
  		pgoff_t offset = old->index;
  		freepage = mapping->a_ops->freepage;

  		get_page(new);

  		new->mapping = mapping;
  		new->index = offset;

  		spin_lock_irqsave(&mapping->tree_lock, flags);

  		__delete_from_page_cache(old, NULL);

  		error = page_cache_tree_insert(mapping, new, NULL);

  		BUG_ON(error);

  
  		/*
  		 * hugetlb pages do not participate in page cache accounting.
  		 */
  		if (!PageHuge(new))

  			__inc_node_page_state(new, NR_FILE_PAGES);

  		if (PageSwapBacked(new))

  			__inc_node_page_state(new, NR_SHMEM);

  		spin_unlock_irqrestore(&mapping->tree_lock, flags);

  		mem_cgroup_migrate(old, new);

  		radix_tree_preload_end();
  		if (freepage)
  			freepage(old);

  		put_page(old);

  	}
  
  	return error;
  }
  EXPORT_SYMBOL_GPL(replace_page_cache_page);

  static int __add_to_page_cache_locked(struct page *page,
  				      struct address_space *mapping,
  				      pgoff_t offset, gfp_t gfp_mask,
  				      void **shadowp)

  {

  	int huge = PageHuge(page);
  	struct mem_cgroup *memcg;

  	int error;

  	VM_BUG_ON_PAGE(!PageLocked(page), page);
  	VM_BUG_ON_PAGE(PageSwapBacked(page), page);

  	if (!huge) {
  		error = mem_cgroup_try_charge(page, current->mm,

  					      gfp_mask, &memcg, false);

  		if (error)
  			return error;
  	}

  	error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);

  	if (error) {

  		if (!huge)

  			mem_cgroup_cancel_charge(page, memcg, false);

  		return error;
  	}

  	get_page(page);

  	page->mapping = mapping;
  	page->index = offset;
  
  	spin_lock_irq(&mapping->tree_lock);

  	error = page_cache_tree_insert(mapping, page, shadowp);

  	radix_tree_preload_end();
  	if (unlikely(error))
  		goto err_insert;

  
  	/* hugetlb pages do not participate in page cache accounting. */
  	if (!huge)

  		__inc_node_page_state(page, NR_FILE_PAGES);

  	spin_unlock_irq(&mapping->tree_lock);

  	if (!huge)

  		mem_cgroup_commit_charge(page, memcg, false, false);

  	trace_mm_filemap_add_to_page_cache(page);
  	return 0;
  err_insert:
  	page->mapping = NULL;
  	/* Leave page->index set: truncation relies upon it */
  	spin_unlock_irq(&mapping->tree_lock);

  	if (!huge)

  		mem_cgroup_cancel_charge(page, memcg, false);

  	put_page(page);

  	return error;
  }

  
  /**
   * add_to_page_cache_locked - add a locked page to the pagecache
   * @page:	page to add
   * @mapping:	the page's address_space
   * @offset:	page index
   * @gfp_mask:	page allocation mode
   *
   * This function is used to add a page to the pagecache. It must be locked.
   * This function does not add the page to the LRU.  The caller must do that.
   */
  int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
  		pgoff_t offset, gfp_t gfp_mask)
  {
  	return __add_to_page_cache_locked(page, mapping, offset,
  					  gfp_mask, NULL);
  }

  EXPORT_SYMBOL(add_to_page_cache_locked);

  
  int add_to_page_cache_lru(struct page *page, struct address_space *mapping,

  				pgoff_t offset, gfp_t gfp_mask)

  {

  	void *shadow = NULL;

  	int ret;

  	__SetPageLocked(page);

  	ret = __add_to_page_cache_locked(page, mapping, offset,
  					 gfp_mask, &shadow);
  	if (unlikely(ret))

  		__ClearPageLocked(page);

  	else {
  		/*
  		 * The page might have been evicted from cache only
  		 * recently, in which case it should be activated like
  		 * any other repeatedly accessed page.

  		 * The exception is pages getting rewritten; evicting other
  		 * data from the working set, only to cache data that will
  		 * get overwritten with something else, is a waste of memory.

  		 */

  		if (!(gfp_mask & __GFP_WRITE) &&
  		    shadow && workingset_refault(shadow)) {

  			SetPageActive(page);
  			workingset_activation(page);
  		} else
  			ClearPageActive(page);
  		lru_cache_add(page);
  	}

  	return ret;
  }

  EXPORT_SYMBOL_GPL(add_to_page_cache_lru);

  #ifdef CONFIG_NUMA

  struct page *__page_cache_alloc(gfp_t gfp)

  {

  	int n;
  	struct page *page;

  	if (cpuset_do_page_mem_spread()) {

  		unsigned int cpuset_mems_cookie;
  		do {

  			cpuset_mems_cookie = read_mems_allowed_begin();

  			n = cpuset_mem_spread_node();

  			page = __alloc_pages_node(n, gfp, 0);

  		} while (!page && read_mems_allowed_retry(cpuset_mems_cookie));

  		return page;

  	}

  	return alloc_pages(gfp, 0);

  }

  EXPORT_SYMBOL(__page_cache_alloc);

  #endif

  /*
   * In order to wait for pages to become available there must be
   * waitqueues associated with pages. By using a hash table of
   * waitqueues where the bucket discipline is to maintain all
   * waiters on the same queue and wake all when any of the pages
   * become available, and for the woken contexts to check to be
   * sure the appropriate page became available, this saves space
   * at a cost of "thundering herd" phenomena during rare hash
   * collisions.
   */

  #define PAGE_WAIT_TABLE_BITS 8
  #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
  static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
  
  static wait_queue_head_t *page_waitqueue(struct page *page)

  {

  	return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)];

  }

  void __init pagecache_init(void)

  {

  	int i;

  	for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
  		init_waitqueue_head(&page_wait_table[i]);
  
  	page_writeback_init();

  }

  /* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */

  struct wait_page_key {
  	struct page *page;
  	int bit_nr;
  	int page_match;
  };
  
  struct wait_page_queue {
  	struct page *page;
  	int bit_nr;

  	wait_queue_entry_t wait;

  };

  static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)

  {

  	struct wait_page_key *key = arg;
  	struct wait_page_queue *wait_page
  		= container_of(wait, struct wait_page_queue, wait);
  
  	if (wait_page->page != key->page)
  	       return 0;
  	key->page_match = 1;

  	if (wait_page->bit_nr != key->bit_nr)
  		return 0;

  
  	/* Stop walking if it's locked */

  	if (test_bit(key->bit_nr, &key->page->flags))

  		return -1;

  	return autoremove_wake_function(wait, mode, sync, key);

  }

  static void wake_up_page_bit(struct page *page, int bit_nr)

  {

  	wait_queue_head_t *q = page_waitqueue(page);
  	struct wait_page_key key;
  	unsigned long flags;

  	wait_queue_entry_t bookmark;

  	key.page = page;
  	key.bit_nr = bit_nr;
  	key.page_match = 0;

  	bookmark.flags = 0;
  	bookmark.private = NULL;
  	bookmark.func = NULL;
  	INIT_LIST_HEAD(&bookmark.entry);

  	spin_lock_irqsave(&q->lock, flags);

  	__wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark);
  
  	while (bookmark.flags & WQ_FLAG_BOOKMARK) {
  		/*
  		 * Take a breather from holding the lock,
  		 * allow pages that finish wake up asynchronously
  		 * to acquire the lock and remove themselves
  		 * from wait queue
  		 */
  		spin_unlock_irqrestore(&q->lock, flags);
  		cpu_relax();
  		spin_lock_irqsave(&q->lock, flags);
  		__wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark);
  	}

  	/*
  	 * It is possible for other pages to have collided on the waitqueue
  	 * hash, so in that case check for a page match. That prevents a long-
  	 * term waiter
  	 *
  	 * It is still possible to miss a case here, when we woke page waiters
  	 * and removed them from the waitqueue, but there are still other
  	 * page waiters.
  	 */
  	if (!waitqueue_active(q) || !key.page_match) {
  		ClearPageWaiters(page);
  		/*
  		 * It's possible to miss clearing Waiters here, when we woke
  		 * our page waiters, but the hashed waitqueue has waiters for
  		 * other pages on it.
  		 *
  		 * That's okay, it's a rare case. The next waker will clear it.
  		 */
  	}
  	spin_unlock_irqrestore(&q->lock, flags);
  }

  
  static void wake_up_page(struct page *page, int bit)
  {
  	if (!PageWaiters(page))
  		return;
  	wake_up_page_bit(page, bit);
  }

  
  static inline int wait_on_page_bit_common(wait_queue_head_t *q,
  		struct page *page, int bit_nr, int state, bool lock)
  {
  	struct wait_page_queue wait_page;

  	wait_queue_entry_t *wait = &wait_page.wait;

  	int ret = 0;
  
  	init_wait(wait);

  	wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0;

  	wait->func = wake_page_function;
  	wait_page.page = page;
  	wait_page.bit_nr = bit_nr;
  
  	for (;;) {
  		spin_lock_irq(&q->lock);

  		if (likely(list_empty(&wait->entry))) {

  			__add_wait_queue_entry_tail(q, wait);

  			SetPageWaiters(page);
  		}
  
  		set_current_state(state);
  
  		spin_unlock_irq(&q->lock);
  
  		if (likely(test_bit(bit_nr, &page->flags))) {
  			io_schedule();

  		}
  
  		if (lock) {
  			if (!test_and_set_bit_lock(bit_nr, &page->flags))
  				break;
  		} else {
  			if (!test_bit(bit_nr, &page->flags))
  				break;
  		}

  
  		if (unlikely(signal_pending_state(state, current))) {
  			ret = -EINTR;
  			break;
  		}

  	}
  
  	finish_wait(q, wait);
  
  	/*
  	 * A signal could leave PageWaiters set. Clearing it here if
  	 * !waitqueue_active would be possible (by open-coding finish_wait),
  	 * but still fail to catch it in the case of wait hash collision. We
  	 * already can fail to clear wait hash collision cases, so don't
  	 * bother with signals either.
  	 */
  
  	return ret;
  }
  
  void wait_on_page_bit(struct page *page, int bit_nr)
  {
  	wait_queue_head_t *q = page_waitqueue(page);
  	wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, false);
  }
  EXPORT_SYMBOL(wait_on_page_bit);
  
  int wait_on_page_bit_killable(struct page *page, int bit_nr)
  {
  	wait_queue_head_t *q = page_waitqueue(page);
  	return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, false);

  }

  /**

   * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue

   * @page: Page defining the wait queue of interest
   * @waiter: Waiter to add to the queue

   *
   * Add an arbitrary @waiter to the wait queue for the nominated @page.
   */

  void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter)

  {
  	wait_queue_head_t *q = page_waitqueue(page);
  	unsigned long flags;
  
  	spin_lock_irqsave(&q->lock, flags);

  	__add_wait_queue_entry_tail(q, waiter);

  	SetPageWaiters(page);

  	spin_unlock_irqrestore(&q->lock, flags);
  }
  EXPORT_SYMBOL_GPL(add_page_wait_queue);

  #ifndef clear_bit_unlock_is_negative_byte
  
  /*
   * PG_waiters is the high bit in the same byte as PG_lock.
   *
   * On x86 (and on many other architectures), we can clear PG_lock and
   * test the sign bit at the same time. But if the architecture does
   * not support that special operation, we just do this all by hand
   * instead.
   *
   * The read of PG_waiters has to be after (or concurrently with) PG_locked
   * being cleared, but a memory barrier should be unneccssary since it is
   * in the same byte as PG_locked.
   */
  static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
  {
  	clear_bit_unlock(nr, mem);
  	/* smp_mb__after_atomic(); */

  	return test_bit(PG_waiters, mem);

  }
  
  #endif

  /**

   * unlock_page - unlock a locked page

   * @page: the page
   *
   * Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
   * Also wakes sleepers in wait_on_page_writeback() because the wakeup

   * mechanism between PageLocked pages and PageWriteback pages is shared.

   * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
   *

   * Note that this depends on PG_waiters being the sign bit in the byte
   * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
   * clear the PG_locked bit and test PG_waiters at the same time fairly
   * portably (architectures that do LL/SC can test any bit, while x86 can
   * test the sign bit).

   */

  void unlock_page(struct page *page)

  {

  	BUILD_BUG_ON(PG_waiters != 7);

  	page = compound_head(page);

  	VM_BUG_ON_PAGE(!PageLocked(page), page);

  	if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
  		wake_up_page_bit(page, PG_locked);

  }
  EXPORT_SYMBOL(unlock_page);

  /**
   * end_page_writeback - end writeback against a page
   * @page: the page

   */
  void end_page_writeback(struct page *page)
  {

  	/*
  	 * TestClearPageReclaim could be used here but it is an atomic
  	 * operation and overkill in this particular case. Failing to
  	 * shuffle a page marked for immediate reclaim is too mild to
  	 * justify taking an atomic operation penalty at the end of
  	 * ever page writeback.
  	 */
  	if (PageReclaim(page)) {
  		ClearPageReclaim(page);

  		rotate_reclaimable_page(page);

  	}

  
  	if (!test_clear_page_writeback(page))
  		BUG();

  	smp_mb__after_atomic();

  	wake_up_page(page, PG_writeback);
  }
  EXPORT_SYMBOL(end_page_writeback);

  /*
   * After completing I/O on a page, call this routine to update the page
   * flags appropriately
   */

  void page_endio(struct page *page, bool is_write, int err)

  {

  	if (!is_write) {

  		if (!err) {
  			SetPageUptodate(page);
  		} else {
  			ClearPageUptodate(page);
  			SetPageError(page);
  		}
  		unlock_page(page);

  	} else {

  		if (err) {

  			struct address_space *mapping;

  			SetPageError(page);

  			mapping = page_mapping(page);
  			if (mapping)
  				mapping_set_error(mapping, err);

  		}
  		end_page_writeback(page);
  	}
  }
  EXPORT_SYMBOL_GPL(page_endio);

  /**
   * __lock_page - get a lock on the page, assuming we need to sleep to get it

   * @__page: the page to lock

   */

  void __lock_page(struct page *__page)

  {

  	struct page *page = compound_head(__page);
  	wait_queue_head_t *q = page_waitqueue(page);
  	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, true);

  }
  EXPORT_SYMBOL(__lock_page);

  int __lock_page_killable(struct page *__page)

  {

  	struct page *page = compound_head(__page);
  	wait_queue_head_t *q = page_waitqueue(page);
  	return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, true);

  }

  EXPORT_SYMBOL_GPL(__lock_page_killable);

  /*
   * Return values:
   * 1 - page is locked; mmap_sem is still held.
   * 0 - page is not locked.
   *     mmap_sem has been released (up_read()), unless flags had both
   *     FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in
   *     which case mmap_sem is still held.
   *
   * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1
   * with the page locked and the mmap_sem unperturbed.
   */

  int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
  			 unsigned int flags)
  {

  	if (flags & FAULT_FLAG_ALLOW_RETRY) {
  		/*
  		 * CAUTION! In this case, mmap_sem is not released
  		 * even though return 0.
  		 */
  		if (flags & FAULT_FLAG_RETRY_NOWAIT)
  			return 0;
  
  		up_read(&mm->mmap_sem);
  		if (flags & FAULT_FLAG_KILLABLE)
  			wait_on_page_locked_killable(page);
  		else

  			wait_on_page_locked(page);

  		return 0;

  	} else {
  		if (flags & FAULT_FLAG_KILLABLE) {
  			int ret;
  
  			ret = __lock_page_killable(page);
  			if (ret) {
  				up_read(&mm->mmap_sem);
  				return 0;
  			}
  		} else
  			__lock_page(page);
  		return 1;

  	}
  }

  /**

   * page_cache_next_hole - find the next hole (not-present entry)
   * @mapping: mapping
   * @index: index
   * @max_scan: maximum range to search
   *
   * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
   * lowest indexed hole.
   *
   * Returns: the index of the hole if found, otherwise returns an index
   * outside of the set specified (in which case 'return - index >=
   * max_scan' will be true). In rare cases of index wrap-around, 0 will
   * be returned.
   *
   * page_cache_next_hole may be called under rcu_read_lock. However,
   * like radix_tree_gang_lookup, this will not atomically search a
   * snapshot of the tree at a single point in time. For example, if a
   * hole is created at index 5, then subsequently a hole is created at
   * index 10, page_cache_next_hole covering both indexes may return 10
   * if called under rcu_read_lock.
   */
  pgoff_t page_cache_next_hole(struct address_space *mapping,
  			     pgoff_t index, unsigned long max_scan)
  {
  	unsigned long i;
  
  	for (i = 0; i < max_scan; i++) {

  		struct page *page;
  
  		page = radix_tree_lookup(&mapping->page_tree, index);
  		if (!page || radix_tree_exceptional_entry(page))

  			break;
  		index++;
  		if (index == 0)
  			break;
  	}
  
  	return index;
  }
  EXPORT_SYMBOL(page_cache_next_hole);
  
  /**
   * page_cache_prev_hole - find the prev hole (not-present entry)
   * @mapping: mapping
   * @index: index
   * @max_scan: maximum range to search
   *
   * Search backwards in the range [max(index-max_scan+1, 0), index] for
   * the first hole.
   *
   * Returns: the index of the hole if found, otherwise returns an index
   * outside of the set specified (in which case 'index - return >=
   * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
   * will be returned.
   *
   * page_cache_prev_hole may be called under rcu_read_lock. However,
   * like radix_tree_gang_lookup, this will not atomically search a
   * snapshot of the tree at a single point in time. For example, if a
   * hole is created at index 10, then subsequently a hole is created at
   * index 5, page_cache_prev_hole covering both indexes may return 5 if
   * called under rcu_read_lock.
   */
  pgoff_t page_cache_prev_hole(struct address_space *mapping,
  			     pgoff_t index, unsigned long max_scan)
  {
  	unsigned long i;
  
  	for (i = 0; i < max_scan; i++) {

  		struct page *page;
  
  		page = radix_tree_lookup(&mapping->page_tree, index);
  		if (!page || radix_tree_exceptional_entry(page))

  			break;
  		index--;
  		if (index == ULONG_MAX)
  			break;
  	}
  
  	return index;
  }
  EXPORT_SYMBOL(page_cache_prev_hole);
  
  /**

   * find_get_entry - find and get a page cache entry

   * @mapping: the address_space to search

   * @offset: the page cache index
   *
   * Looks up the page cache slot at @mapping & @offset.  If there is a
   * page cache page, it is returned with an increased refcount.

   *

   * If the slot holds a shadow entry of a previously evicted page, or a
   * swap entry from shmem/tmpfs, it is returned.

   *
   * Otherwise, %NULL is returned.

   */

  struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)

  {

  	void **pagep;

  	struct page *head, *page;

  	rcu_read_lock();
  repeat:
  	page = NULL;
  	pagep = radix_tree_lookup_slot(&mapping->page_tree, offset);
  	if (pagep) {
  		page = radix_tree_deref_slot(pagep);

  		if (unlikely(!page))
  			goto out;

  		if (radix_tree_exception(page)) {

  			if (radix_tree_deref_retry(page))
  				goto repeat;
  			/*

  			 * A shadow entry of a recently evicted page,
  			 * or a swap entry from shmem/tmpfs.  Return
  			 * it without attempting to raise page count.

  			 */
  			goto out;

  		}

  
  		head = compound_head(page);
  		if (!page_cache_get_speculative(head))
  			goto repeat;
  
  		/* The page was split under us? */
  		if (compound_head(page) != head) {
  			put_page(head);

  			goto repeat;

  		}

  
  		/*
  		 * Has the page moved?
  		 * This is part of the lockless pagecache protocol. See
  		 * include/linux/pagemap.h for details.
  		 */
  		if (unlikely(page != *pagep)) {

  			put_page(head);

  			goto repeat;
  		}
  	}

  out:

  	rcu_read_unlock();

  	return page;
  }

  EXPORT_SYMBOL(find_get_entry);

  /**

   * find_lock_entry - locate, pin and lock a page cache entry
   * @mapping: the address_space to search
   * @offset: the page cache index
   *
   * Looks up the page cache slot at @mapping & @offset.  If there is a
   * page cache page, it is returned locked and with an increased
   * refcount.
   *

   * If the slot holds a shadow entry of a previously evicted page, or a
   * swap entry from shmem/tmpfs, it is returned.

   *
   * Otherwise, %NULL is returned.
   *
   * find_lock_entry() may sleep.
   */
  struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)

  {
  	struct page *page;

  repeat:

  	page = find_get_entry(mapping, offset);

  	if (page && !radix_tree_exception(page)) {

  		lock_page(page);
  		/* Has the page been truncated? */

  		if (unlikely(page_mapping(page) != mapping)) {

  			unlock_page(page);

  			put_page(page);

  			goto repeat;

  		}

  		VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);

  	}

  	return page;
  }

  EXPORT_SYMBOL(find_lock_entry);
  
  /**

   * pagecache_get_page - find and get a page reference

   * @mapping: the address_space to search
   * @offset: the page index

   * @fgp_flags: PCG flags

   * @gfp_mask: gfp mask to use for the page cache data page allocation

   *

   * Looks up the page cache slot at @mapping & @offset.

   *

   * PCG flags modify how the page is returned.

   *

   * @fgp_flags can be:
   *
   * - FGP_ACCESSED: the page will be marked accessed
   * - FGP_LOCK: Page is return locked
   * - FGP_CREAT: If page is not present then a new page is allocated using
   *   @gfp_mask and added to the page cache and the VM's LRU
   *   list. The page is returned locked and with an increased
   *   refcount. Otherwise, NULL is returned.

   *

   * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
   * if the GFP flags specified for FGP_CREAT are atomic.

   *

   * If there is a page cache page, it is returned with an increased refcount.

   */

  struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,

  	int fgp_flags, gfp_t gfp_mask)

  {

  	struct page *page;

  repeat:

  	page = find_get_entry(mapping, offset);
  	if (radix_tree_exceptional_entry(page))
  		page = NULL;
  	if (!page)
  		goto no_page;
  
  	if (fgp_flags & FGP_LOCK) {
  		if (fgp_flags & FGP_NOWAIT) {
  			if (!trylock_page(page)) {

  				put_page(page);

  				return NULL;
  			}
  		} else {
  			lock_page(page);
  		}
  
  		/* Has the page been truncated? */
  		if (unlikely(page->mapping != mapping)) {
  			unlock_page(page);

  			put_page(page);

  			goto repeat;
  		}
  		VM_BUG_ON_PAGE(page->index != offset, page);
  	}
  
  	if (page && (fgp_flags & FGP_ACCESSED))
  		mark_page_accessed(page);
  
  no_page:
  	if (!page && (fgp_flags & FGP_CREAT)) {
  		int err;
  		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))

  			gfp_mask |= __GFP_WRITE;
  		if (fgp_flags & FGP_NOFS)
  			gfp_mask &= ~__GFP_FS;

  		page = __page_cache_alloc(gfp_mask);

  		if (!page)
  			return NULL;

  
  		if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK)))
  			fgp_flags |= FGP_LOCK;

  		/* Init accessed so avoid atomic mark_page_accessed later */

  		if (fgp_flags & FGP_ACCESSED)

  			__SetPageReferenced(page);

  		err = add_to_page_cache_lru(page, mapping, offset, gfp_mask);

  		if (unlikely(err)) {

  			put_page(page);

  			page = NULL;
  			if (err == -EEXIST)
  				goto repeat;

  		}

  	}

  	return page;
  }

  EXPORT_SYMBOL(pagecache_get_page);

  
  /**

   * find_get_entries - gang pagecache lookup
   * @mapping:	The address_space to search
   * @start:	The starting page cache index
   * @nr_entries:	The maximum number of entries
   * @entries:	Where the resulting entries are placed
   * @indices:	The cache indices corresponding to the entries in @entries
   *
   * find_get_entries() will search for and return a group of up to
   * @nr_entries entries in the mapping.  The entries are placed at
   * @entries.  find_get_entries() takes a reference against any actual
   * pages it returns.
   *
   * The search returns a group of mapping-contiguous page cache entries
   * with ascending indexes.  There may be holes in the indices due to
   * not-present pages.
   *

   * Any shadow entries of evicted pages, or swap entries from
   * shmem/tmpfs, are included in the returned array.

   *
   * find_get_entries() returns the number of pages and shadow entries
   * which were found.
   */
  unsigned find_get_entries(struct address_space *mapping,
  			  pgoff_t start, unsigned int nr_entries,
  			  struct page **entries, pgoff_t *indices)
  {
  	void **slot;
  	unsigned int ret = 0;
  	struct radix_tree_iter iter;
  
  	if (!nr_entries)
  		return 0;
  
  	rcu_read_lock();

  	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {

  		struct page *head, *page;

  repeat:
  		page = radix_tree_deref_slot(slot);
  		if (unlikely(!page))
  			continue;
  		if (radix_tree_exception(page)) {

  			if (radix_tree_deref_retry(page)) {
  				slot = radix_tree_iter_retry(&iter);
  				continue;
  			}

  			/*

  			 * A shadow entry of a recently evicted page, a swap
  			 * entry from shmem/tmpfs or a DAX entry.  Return it
  			 * without attempting to raise page count.

  			 */
  			goto export;
  		}

  
  		head = compound_head(page);
  		if (!page_cache_get_speculative(head))
  			goto repeat;
  
  		/* The page was split under us? */
  		if (compound_head(page) != head) {
  			put_page(head);

  			goto repeat;

  		}

  
  		/* Has the page moved? */
  		if (unlikely(page != *slot)) {

  			put_page(head);

  			goto repeat;
  		}
  export:
  		indices[ret] = iter.index;
  		entries[ret] = page;
  		if (++ret == nr_entries)
  			break;
  	}
  	rcu_read_unlock();
  	return ret;
  }
  
  /**

   * find_get_pages_range - gang pagecache lookup

   * @mapping:	The address_space to search
   * @start:	The starting page index

   * @end:	The final page index (inclusive)

   * @nr_pages:	The maximum number of pages
   * @pages:	Where the resulting pages are placed
   *

   * find_get_pages_range() will search for and return a group of up to @nr_pages
   * pages in the mapping starting at index @start and up to index @end
   * (inclusive).  The pages are placed at @pages.  find_get_pages_range() takes
   * a reference against the returned pages.

   *
   * The search returns a group of mapping-contiguous pages with ascending
   * indexes.  There may be holes in the indices due to not-present pages.

   * We also update @start to index the next page for the traversal.

   *

   * find_get_pages_range() returns the number of pages which were found. If this
   * number is smaller than @nr_pages, the end of specified range has been
   * reached.

   */

  unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
  			      pgoff_t end, unsigned int nr_pages,
  			      struct page **pages)

  {

  	struct radix_tree_iter iter;
  	void **slot;
  	unsigned ret = 0;
  
  	if (unlikely(!nr_pages))
  		return 0;

  
  	rcu_read_lock();

  	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, *start) {

  		struct page *head, *page;

  
  		if (iter.index > end)
  			break;

  repeat:

  		page = radix_tree_deref_slot(slot);

  		if (unlikely(!page))
  			continue;

  		if (radix_tree_exception(page)) {

  			if (radix_tree_deref_retry(page)) {

  				slot = radix_tree_iter_retry(&iter);
  				continue;

  			}

  			/*

  			 * A shadow entry of a recently evicted page,
  			 * or a swap entry from shmem/tmpfs.  Skip
  			 * over it.

  			 */

  			continue;

  		}

  		head = compound_head(page);
  		if (!page_cache_get_speculative(head))
  			goto repeat;
  
  		/* The page was split under us? */
  		if (compound_head(page) != head) {
  			put_page(head);

  			goto repeat;

  		}

  
  		/* Has the page moved? */

  		if (unlikely(page != *slot)) {

  			put_page(head);

  			goto repeat;
  		}

  		pages[ret] = page;

  		if (++ret == nr_pages) {
  			*start = pages[ret - 1]->index + 1;
  			goto out;
  		}

  	}

  	/*
  	 * We come here when there is no page beyond @end. We take care to not
  	 * overflow the index @start as it confuses some of the callers. This
  	 * breaks the iteration when there is page at index -1 but that is
  	 * already broken anyway.
  	 */
  	if (end == (pgoff_t)-1)
  		*start = (pgoff_t)-1;
  	else
  		*start = end + 1;
  out:

  	rcu_read_unlock();

  	return ret;
  }

  /**
   * find_get_pages_contig - gang contiguous pagecache lookup
   * @mapping:	The address_space to search
   * @index:	The starting page index
   * @nr_pages:	The maximum number of pages
   * @pages:	Where the resulting pages are placed
   *
   * find_get_pages_contig() works exactly like find_get_pages(), except
   * that the returned number of pages are guaranteed to be contiguous.
   *
   * find_get_pages_contig() returns the number of pages which were found.
   */
  unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
  			       unsigned int nr_pages, struct page **pages)
  {

  	struct radix_tree_iter iter;
  	void **slot;
  	unsigned int ret = 0;
  
  	if (unlikely(!nr_pages))
  		return 0;

  
  	rcu_read_lock();

  	radix_tree_for_each_contig(slot, &mapping->page_tree, &iter, index) {

  		struct page *head, *page;

  repeat:

  		page = radix_tree_deref_slot(slot);
  		/* The hole, there no reason to continue */

  		if (unlikely(!page))

  			break;

  		if (radix_tree_exception(page)) {

  			if (radix_tree_deref_retry(page)) {

  				slot = radix_tree_iter_retry(&iter);
  				continue;

  			}

  			/*

  			 * A shadow entry of a recently evicted page,
  			 * or a swap entry from shmem/tmpfs.  Stop
  			 * looking for contiguous pages.

  			 */

  			break;

  		}

  		head = compound_head(page);
  		if (!page_cache_get_speculative(head))
  			goto repeat;
  
  		/* The page was split under us? */
  		if (compound_head(page) != head) {
  			put_page(head);

  			goto repeat;

  		}

  
  		/* Has the page moved? */

  		if (unlikely(page != *slot)) {

  			put_page(head);

  			goto repeat;
  		}

  		/*
  		 * must check mapping and index after taking the ref.
  		 * otherwise we can get both false positives and false
  		 * negatives, which is just confusing to the caller.
  		 */

  		if (page->mapping == NULL || page_to_pgoff(page) != iter.index) {

  			put_page(page);

  			break;
  		}

  		pages[ret] = page;

  		if (++ret == nr_pages)
  			break;

  	}

  	rcu_read_unlock();
  	return ret;

  }

  EXPORT_SYMBOL(find_get_pages_contig);

  /**
   * find_get_pages_tag - find and return pages that match @tag
   * @mapping:	the address_space to search
   * @index:	the starting page index
   * @tag:	the tag index
   * @nr_pages:	the maximum number of pages
   * @pages:	where the resulting pages are placed
   *

   * Like find_get_pages, except we only return pages which are tagged with

   * @tag.   We update @index to index the next page for the traversal.

   */
  unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
  			int tag, unsigned int nr_pages, struct page **pages)
  {

  	struct radix_tree_iter iter;
  	void **slot;
  	unsigned ret = 0;
  
  	if (unlikely(!nr_pages))
  		return 0;

  
  	rcu_read_lock();

  	radix_tree_for_each_tagged(slot, &mapping->page_tree,
  				   &iter, *index, tag) {

  		struct page *head, *page;

  repeat:

  		page = radix_tree_deref_slot(slot);

  		if (unlikely(!page))
  			continue;