// SPDX-License-Identifier: GPL-2.0-only

  /*
   *	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/error-injection.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/hugetlb.h>

  #include <linux/memcontrol.h>

  #include <linux/cleancache.h>

  #include <linux/shmem_fs.h>

  #include <linux/rmap.h>

  #include <linux/delayacct.h>

  #include <linux/psi.h>

  #include <linux/ramfs.h>

  #include <linux/page_idle.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)

   *        ->i_pages lock

   *

   *  ->i_mutex

   *    ->i_mmap_rwsem		(truncate->unmap_mapping_range)

   *

   *  ->mmap_lock

   *    ->i_mmap_rwsem

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

   *        ->i_pages lock	(arch-dependent flush_dcache_mmap_lock)

   *

   *  ->mmap_lock

   *    ->lock_page		(access_process_vm)
   *

   *  ->i_mutex			(generic_perform_write)

   *    ->mmap_lock		(fault_in_pages_readable->do_page_fault)

   *

   *  bdi->wb.list_lock

   *    sb_lock			(fs/fs-writeback.c)

   *    ->i_pages 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)

   *    ->i_pages lock		(try_to_unmap_one)

   *    ->pgdat->lru_lock		(follow_page->mark_page_accessed)
   *    ->pgdat->lru_lock		(check_pte_range->isolate_lru_page)

   *    ->private_lock		(page_remove_rmap->set_page_dirty)

   *    ->i_pages 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 void page_cache_delete(struct address_space *mapping,

  				   struct page *page, void *shadow)
  {

  	XA_STATE(xas, &mapping->i_pages, page->index);
  	unsigned int nr = 1;

  	mapping_set_update(&xas, mapping);

  	/* hugetlb pages are represented by a single entry in the xarray */
  	if (!PageHuge(page)) {
  		xas_set_order(&xas, page->index, compound_order(page));

  		nr = compound_nr(page);

  	}

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

  	xas_store(&xas, shadow);
  	xas_init_marks(&xas);

  	page->mapping = NULL;
  	/* Leave page->index set: truncation lookup relies upon it */

  	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;

  }

  static void unaccount_page_cache_page(struct address_space *mapping,
  				      struct page *page)

  {

  	int nr;

  	/*
  	 * 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);

  		}
  	}

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

  	if (PageHuge(page))
  		return;

  	nr = thp_nr_pages(page);

  	__mod_lruvec_page_state(page, NR_FILE_PAGES, -nr);

  	if (PageSwapBacked(page)) {

  		__mod_lruvec_page_state(page, NR_SHMEM, -nr);

  		if (PageTransHuge(page))
  			__dec_node_page_state(page, NR_SHMEM_THPS);

  	} else if (PageTransHuge(page)) {
  		__dec_node_page_state(page, NR_FILE_THPS);

  		filemap_nr_thps_dec(mapping);

  	}

  
  	/*
  	 * 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 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 i_pages lock.

   */
  void __delete_from_page_cache(struct page *page, void *shadow)
  {
  	struct address_space *mapping = page->mapping;
  
  	trace_mm_filemap_delete_from_page_cache(page);
  
  	unaccount_page_cache_page(mapping, page);

  	page_cache_delete(mapping, page, shadow);

  }

  static void page_cache_free_page(struct address_space *mapping,
  				struct page *page)
  {
  	void (*freepage)(struct page *);
  
  	freepage = mapping->a_ops->freepage;
  	if (freepage)
  		freepage(page);
  
  	if (PageTransHuge(page) && !PageHuge(page)) {

  		page_ref_sub(page, thp_nr_pages(page));

  		VM_BUG_ON_PAGE(page_count(page) <= 0, page);
  	} else {
  		put_page(page);
  	}
  }

  /**
   * 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;

  	BUG_ON(!PageLocked(page));

  	xa_lock_irqsave(&mapping->i_pages, flags);

  	__delete_from_page_cache(page, NULL);

  	xa_unlock_irqrestore(&mapping->i_pages, flags);

  	page_cache_free_page(mapping, page);

  }
  EXPORT_SYMBOL(delete_from_page_cache);

  /*

   * page_cache_delete_batch - delete several pages from page cache

   * @mapping: the mapping to which pages belong
   * @pvec: pagevec with pages to delete
   *

   * The function walks over mapping->i_pages and removes pages passed in @pvec

   * from the mapping. The function expects @pvec to be sorted by page index
   * and is optimised for it to be dense.

   * It tolerates holes in @pvec (mapping entries at those indices are not

   * modified). The function expects only THP head pages to be present in the

   * @pvec.

   *

   * The function expects the i_pages lock to be held.

   */

  static void page_cache_delete_batch(struct address_space *mapping,

  			     struct pagevec *pvec)
  {

  	XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index);

  	int total_pages = 0;

  	int i = 0;

  	struct page *page;

  	mapping_set_update(&xas, mapping);
  	xas_for_each(&xas, page, ULONG_MAX) {

  		if (i >= pagevec_count(pvec))

  			break;

  
  		/* A swap/dax/shadow entry got inserted? Skip it. */

  		if (xa_is_value(page))

  			continue;

  		/*
  		 * A page got inserted in our range? Skip it. We have our
  		 * pages locked so they are protected from being removed.
  		 * If we see a page whose index is higher than ours, it
  		 * means our page has been removed, which shouldn't be
  		 * possible because we're holding the PageLock.
  		 */
  		if (page != pvec->pages[i]) {
  			VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index,
  					page);
  			continue;
  		}
  
  		WARN_ON_ONCE(!PageLocked(page));
  
  		if (page->index == xas.xa_index)

  			page->mapping = NULL;

  		/* Leave page->index set: truncation lookup relies on it */
  
  		/*
  		 * Move to the next page in the vector if this is a regular
  		 * page or the index is of the last sub-page of this compound
  		 * page.
  		 */
  		if (page->index + compound_nr(page) - 1 == xas.xa_index)

  			i++;

  		xas_store(&xas, NULL);

  		total_pages++;
  	}
  	mapping->nrpages -= total_pages;
  }
  
  void delete_from_page_cache_batch(struct address_space *mapping,
  				  struct pagevec *pvec)
  {
  	int i;
  	unsigned long flags;
  
  	if (!pagevec_count(pvec))
  		return;

  	xa_lock_irqsave(&mapping->i_pages, flags);

  	for (i = 0; i < pagevec_count(pvec); i++) {
  		trace_mm_filemap_delete_from_page_cache(pvec->pages[i]);
  
  		unaccount_page_cache_page(mapping, pvec->pages[i]);
  	}

  	page_cache_delete_batch(mapping, pvec);

  	xa_unlock_irqrestore(&mapping->i_pages, flags);

  
  	for (i = 0; i < pagevec_count(pvec); i++)
  		page_cache_free_page(mapping, pvec->pages[i]);
  }

  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.

   *
   * Return: %0 on success, negative error code otherwise.

   */

  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_can_writeback(mapping) ||

  	    !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))

  		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.

   *
   * Return: %0 on success, negative error code otherwise.

   */
  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.

   *
   * Return: %true if at least one page exists in the specified range,
   * %false otherwise.

   */
  bool filemap_range_has_page(struct address_space *mapping,
  			   loff_t start_byte, loff_t end_byte)
  {

  	struct page *page;

  	XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
  	pgoff_t max = end_byte >> PAGE_SHIFT;

  
  	if (end_byte < start_byte)
  		return false;

  	rcu_read_lock();
  	for (;;) {
  		page = xas_find(&xas, max);
  		if (xas_retry(&xas, page))
  			continue;
  		/* Shadow entries don't count */
  		if (xa_is_value(page))
  			continue;
  		/*
  		 * We don't need to try to pin this page; we're about to
  		 * release the RCU lock anyway.  It is enough to know that
  		 * there was a page here recently.
  		 */
  		break;
  	}
  	rcu_read_unlock();

  	return page != NULL;

  }
  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);

  	while (index <= end) {

  		unsigned i;

  		nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index,

  				end, PAGECACHE_TAG_WRITEBACK);

  		if (!nr_pages)
  			break;

  		for (i = 0; i < nr_pages; i++) {
  			struct page *page = pvec.pages[i];

  			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.

   *
   * Return: error status of the address space.

   */
  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);
  
  /**

   * filemap_fdatawait_range_keep_errors - 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.  Unlike filemap_fdatawait_range(),
   * 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_range_keep_errors(struct address_space *mapping,
  		loff_t start_byte, loff_t end_byte)
  {
  	__filemap_fdatawait_range(mapping, start_byte, end_byte);
  	return filemap_check_and_keep_errors(mapping);
  }
  EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors);
  
  /**

   * 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.

   *
   * Return: error status of the address space vs. the file->f_wb_err cursor.

   */
  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)

   *
   * Return: error status of the address space.

   */

  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);

  /* Returns true if writeback might be needed or already in progress. */

  static bool mapping_needs_writeback(struct address_space *mapping)

  {

  	if (dax_mapping(mapping))
  		return mapping->nrexceptional;
  
  	return mapping->nrpages;

  }

  /**
   * 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).

   *
   * Return: error status of the address space.

   */

  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);

  		/*
  		 * 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_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.

   *
   * Return: %0 on success, negative error code otherwise.

   */
  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.

   *
   * Return: %0 on success, negative error code otherwise.

   */
  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.  This function cannot fail.

   *
   * Return: %0

   */
  int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
  {

  	struct address_space *mapping = old->mapping;
  	void (*freepage)(struct page *) = mapping->a_ops->freepage;
  	pgoff_t offset = old->index;
  	XA_STATE(xas, &mapping->i_pages, offset);
  	unsigned long flags;

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

  	get_page(new);
  	new->mapping = mapping;
  	new->index = offset;

  	mem_cgroup_migrate(old, new);

  	xas_lock_irqsave(&xas, flags);
  	xas_store(&xas, new);

  	old->mapping = NULL;
  	/* hugetlb pages do not participate in page cache accounting. */
  	if (!PageHuge(old))

  		__dec_lruvec_page_state(old, NR_FILE_PAGES);

  	if (!PageHuge(new))

  		__inc_lruvec_page_state(new, NR_FILE_PAGES);

  	if (PageSwapBacked(old))

  		__dec_lruvec_page_state(old, NR_SHMEM);

  	if (PageSwapBacked(new))

  		__inc_lruvec_page_state(new, NR_SHMEM);

  	xas_unlock_irqrestore(&xas, flags);

  	if (freepage)
  		freepage(old);
  	put_page(old);

  	return 0;

  }
  EXPORT_SYMBOL_GPL(replace_page_cache_page);

  noinline int __add_to_page_cache_locked(struct page *page,

  					struct address_space *mapping,

  					pgoff_t offset, gfp_t gfp,

  					void **shadowp)

  {

  	XA_STATE(xas, &mapping->i_pages, offset);

  	int huge = PageHuge(page);

  	int error;

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

  	mapping_set_update(&xas, mapping);

  	get_page(page);

  	page->mapping = mapping;
  	page->index = offset;

  	if (!huge) {

  		error = mem_cgroup_charge(page, current->mm, gfp);

  		if (error)
  			goto error;
  	}

  	gfp &= GFP_RECLAIM_MASK;

  	do {

  		unsigned int order = xa_get_order(xas.xa, xas.xa_index);
  		void *entry, *old = NULL;
  
  		if (order > thp_order(page))
  			xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index),
  					order, gfp);

  		xas_lock_irq(&xas);

  		xas_for_each_conflict(&xas, entry) {
  			old = entry;
  			if (!xa_is_value(entry)) {
  				xas_set_err(&xas, -EEXIST);
  				goto unlock;
  			}
  		}
  
  		if (old) {
  			if (shadowp)
  				*shadowp = old;
  			/* entry may have been split before we acquired lock */
  			order = xa_get_order(xas.xa, xas.xa_index);
  			if (order > thp_order(page)) {
  				xas_split(&xas, old, order);
  				xas_reset(&xas);
  			}
  		}

  		xas_store(&xas, page);
  		if (xas_error(&xas))
  			goto unlock;

  		if (old)

  			mapping->nrexceptional--;

  		mapping->nrpages++;
  
  		/* hugetlb pages do not participate in page cache accounting */
  		if (!huge)

  			__inc_lruvec_page_state(page, NR_FILE_PAGES);

  unlock:
  		xas_unlock_irq(&xas);

  	} while (xas_nomem(&xas, gfp));

  	if (xas_error(&xas)) {
  		error = xas_error(&xas);

  		goto error;

  	}

  	trace_mm_filemap_add_to_page_cache(page);
  	return 0;

  error:

  	page->mapping = NULL;
  	/* Leave page->index set: truncation relies upon it */

  	put_page(page);

  	return error;

  }

  ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);

  
  /**
   * 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.

   *
   * Return: %0 on success, negative error code otherwise.

   */
  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.

  		 */

  		WARN_ON_ONCE(PageActive(page));
  		if (!(gfp_mask & __GFP_WRITE) && shadow)
  			workingset_refault(page, shadow);

  		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();

  }

  /*
   * The page wait code treats the "wait->flags" somewhat unusually, because

   * we have multiple different kinds of waits, not just the usual "exclusive"

   * one.
   *
   * We have:
   *
   *  (a) no special bits set:
   *
   *	We're just waiting for the bit to be released, and when a waker
   *	calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up,
   *	and remove it from the wait queue.
   *
   *	Simple and straightforward.
   *
   *  (b) WQ_FLAG_EXCLUSIVE:
   *
   *	The waiter is waiting to get the lock, and only one waiter should
   *	be woken up to avoid any thundering herd behavior. We'll set the
   *	WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue.
   *
   *	This is the traditional exclusive wait.
   *

   *  (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM:

   *
   *	The waiter is waiting to get the bit, and additionally wants the
   *	lock to be transferred to it for fair lock behavior. If the lock
   *	cannot be taken, we stop walking the wait queue without waking
   *	the waiter.
   *
   *	This is the "fair lock handoff" case, and in addition to setting
   *	WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see
   *	that it now has the lock.
   */

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

  {

  	unsigned int flags;

  	struct wait_page_key *key = arg;
  	struct wait_page_queue *wait_page
  		= container_of(wait, struct wait_page_queue, wait);

  	if (!wake_page_match(wait_page, key))

  		return 0;

  	/*

  	 * If it's a lock handoff wait, we get the bit for it, and
  	 * stop walking (and do not wake it up) if we can't.

  	 */

  	flags = wait->flags;
  	if (flags & WQ_FLAG_EXCLUSIVE) {
  		if (test_bit(key->bit_nr, &key->page->flags))

  			return -1;

  		if (flags & WQ_FLAG_CUSTOM) {
  			if (test_and_set_bit(key->bit_nr, &key->page->flags))
  				return -1;
  			flags |= WQ_FLAG_DONE;
  		}

  	}

  	/*
  	 * We are holding the wait-queue lock, but the waiter that
  	 * is waiting for this will be checking the flags without
  	 * any locking.
  	 *
  	 * So update the flags atomically, and wake up the waiter
  	 * afterwards to avoid any races. This store-release pairs
  	 * with the load-acquire in wait_on_page_bit_common().
  	 */
  	smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN);

  	wake_up_state(wait->private, mode);
  
  	/*
  	 * Ok, we have successfully done what we're waiting for,
  	 * and we can unconditionally remove the wait entry.
  	 *

  	 * Note that this pairs with the "finish_wait()" in the
  	 * waiter, and has to be the absolute last thing we do.
  	 * After this list_del_init(&wait->entry) the wait entry

  	 * might be de-allocated and the process might even have
  	 * exited.

  	 */

  	list_del_init_careful(&wait->entry);

  	return (flags & WQ_FLAG_EXCLUSIVE) != 0;

  }

  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);
  }

  /*
   * A choice of three behaviors for wait_on_page_bit_common():
   */
  enum behavior {
  	EXCLUSIVE,	/* Hold ref to page and take the bit when woken, like
  			 * __lock_page() waiting on then setting PG_locked.
  			 */
  	SHARED,		/* Hold ref to page and check the bit when woken, like
  			 * wait_on_page_writeback() waiting on PG_writeback.
  			 */
  	DROP,		/* Drop ref to page before wait, no check when woken,
  			 * like put_and_wait_on_page_locked() on PG_locked.
  			 */
  };

  /*

   * Attempt to check (or get) the page bit, and mark us done
   * if successful.

   */
  static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
  					struct wait_queue_entry *wait)
  {
  	if (wait->flags & WQ_FLAG_EXCLUSIVE) {
  		if (test_and_set_bit(bit_nr, &page->flags))
  			return false;
  	} else if (test_bit(bit_nr, &page->flags))
  		return false;

  	wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE;

  	return true;
  }

  /* How many times do we accept lock stealing from under a waiter? */
  int sysctl_page_lock_unfairness = 5;

  static inline __sched int wait_on_page_bit_common(wait_queue_head_t *q,

  	struct page *page, int bit_nr, int state, enum behavior behavior)

  {

  	int unfairness = sysctl_page_lock_unfairness;

  	struct wait_page_queue wait_page;

  	wait_queue_entry_t *wait = &wait_page.wait;

  	bool thrashing = false;

  	bool delayacct = false;

  	unsigned long pflags;

  	if (bit_nr == PG_locked &&

  	    !PageUptodate(page) && PageWorkingset(page)) {

  		if (!PageSwapBacked(page)) {

  			delayacct_thrashing_start();

  			delayacct = true;
  		}

  		psi_memstall_enter(&pflags);

  		thrashing = true;
  	}

  	init_wait(wait);
  	wait->func = wake_page_function;
  	wait_page.page = page;
  	wait_page.bit_nr = bit_nr;

  repeat:
  	wait->flags = 0;
  	if (behavior == EXCLUSIVE) {
  		wait->flags = WQ_FLAG_EXCLUSIVE;
  		if (--unfairness < 0)
  			wait->flags |= WQ_FLAG_CUSTOM;
  	}

  	/*
  	 * Do one last check whether we can get the
  	 * page bit synchronously.
  	 *
  	 * Do the SetPageWaiters() marking before that
  	 * to let any waker we _just_ missed know they
  	 * need to wake us up (otherwise they'll never
  	 * even go to the slow case that looks at the
  	 * page queue), and add ourselves to the wait
  	 * queue if we need to sleep.
  	 *
  	 * This part needs to be done under the queue
  	 * lock to avoid races.
  	 */
  	spin_lock_irq(&q->lock);
  	SetPageWaiters(page);
  	if (!trylock_page_bit_common(page, bit_nr, wait))
  		__add_wait_queue_entry_tail(q, wait);
  	spin_unlock_irq(&q->lock);

  	/*
  	 * From now on, all the logic will be based on

  	 * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to
  	 * see whether the page bit testing has already
  	 * been done by the wake function.

  	 *
  	 * We can drop our reference to the page.
  	 */
  	if (behavior == DROP)
  		put_page(page);

  	/*
  	 * Note that until the "finish_wait()", or until
  	 * we see the WQ_FLAG_WOKEN flag, we need to
  	 * be very careful with the 'wait->flags', because
  	 * we may race with a waker that sets them.
  	 */

  	for (;;) {

  		unsigned int flags;

  		set_current_state(state);

  		/* Loop until we've been woken or interrupted */
  		flags = smp_load_acquire(&wait->flags);
  		if (!(flags & WQ_FLAG_WOKEN)) {
  			if (signal_pending_state(state, current))
  				break;
  
  			io_schedule();
  			continue;
  		}
  
  		/* If we were non-exclusive, we're done */
  		if (behavior != EXCLUSIVE)

  			break;

  		/* If the waker got the lock for us, we're done */
  		if (flags & WQ_FLAG_DONE)

  			break;

  		/*
  		 * Otherwise, if we're getting the lock, we need to
  		 * try to get it ourselves.
  		 *
  		 * And if that fails, we'll have to retry this all.
  		 */
  		if (unlikely(test_and_set_bit(bit_nr, &page->flags)))
  			goto repeat;
  
  		wait->flags |= WQ_FLAG_DONE;
  		break;

  	}

  	/*
  	 * If a signal happened, this 'finish_wait()' may remove the last
  	 * waiter from the wait-queues, but the PageWaiters bit will remain
  	 * set. That's ok. The next wakeup will take care of it, and trying
  	 * to do it here would be difficult and prone to races.
  	 */

  	finish_wait(q, wait);

  	if (thrashing) {

  		if (delayacct)

  			delayacct_thrashing_end();
  		psi_memstall_leave(&pflags);
  	}

  	/*

  	 * NOTE! The wait->flags weren't stable until we've done the
  	 * 'finish_wait()', and we could have exited the loop above due
  	 * to a signal, and had a wakeup event happen after the signal
  	 * test but before the 'finish_wait()'.
  	 *
  	 * So only after the finish_wait() can we reliably determine
  	 * if we got woken up or not, so we can now figure out the final
  	 * return value based on that state without races.
  	 *
  	 * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive
  	 * waiter, but an exclusive one requires WQ_FLAG_DONE.

  	 */

  	if (behavior == EXCLUSIVE)
  		return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR;

  	return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;

  }

  __sched 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, SHARED);

  }
  EXPORT_SYMBOL(wait_on_page_bit);

  __sched 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, SHARED);

  }

  EXPORT_SYMBOL(wait_on_page_bit_killable);

  static int __wait_on_page_locked_async(struct page *page,
  				       struct wait_page_queue *wait, bool set)
  {
  	struct wait_queue_head *q = page_waitqueue(page);
  	int ret = 0;
  
  	wait->page = page;
  	wait->bit_nr = PG_locked;
  
  	spin_lock_irq(&q->lock);
  	__add_wait_queue_entry_tail(q, &wait->wait);
  	SetPageWaiters(page);
  	if (set)
  		ret = !trylock_page(page);
  	else
  		ret = PageLocked(page);
  	/*
  	 * If we were succesful now, we know we're still on the
  	 * waitqueue as we're still under the lock. This means it's
  	 * safe to remove and return success, we know the callback
  	 * isn't going to trigger.
  	 */
  	if (!ret)
  		__remove_wait_queue(q, &wait->wait);
  	else
  		ret = -EIOCBQUEUED;
  	spin_unlock_irq(&q->lock);
  	return ret;
  }

  static int wait_on_page_locked_async(struct page *page,
  				     struct wait_page_queue *wait)
  {
  	if (!PageLocked(page))
  		return 0;
  	return __wait_on_page_locked_async(compound_head(page), wait, false);
  }

  /**

   * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked
   * @page: The page to wait for.
   *
   * The caller should hold a reference on @page.  They expect the page to
   * become unlocked relatively soon, but do not wish to hold up migration
   * (for example) by holding the reference while waiting for the page to
   * come unlocked.  After this function returns, the caller should not
   * dereference @page.
   */
  void put_and_wait_on_page_locked(struct page *page)
  {
  	wait_queue_head_t *q;
  
  	page = compound_head(page);
  	q = page_waitqueue(page);
  	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP);
  }
  
  /**

   * 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 unnecessary 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);

  	}

  	/*
  	 * Writeback does not hold a page reference of its own, relying
  	 * on truncation to wait for the clearing of PG_writeback.
  	 * But here we must make sure that the page is not freed and
  	 * reused before the wake_up_page().
  	 */
  	get_page(page);

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

  	smp_mb__after_atomic();

  	wake_up_page(page, PG_writeback);

  	put_page(page);

  }
  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

   */

  __sched 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,
  				EXCLUSIVE);

  }
  EXPORT_SYMBOL(__lock_page);

  __sched 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,
  					EXCLUSIVE);

  }

  EXPORT_SYMBOL_GPL(__lock_page_killable);

  __sched int __lock_page_async(struct page *page, struct wait_page_queue *wait)

  {
  	return __wait_on_page_locked_async(page, wait, true);
  }

  /*
   * Return values:

   * 1 - page is locked; mmap_lock is still held.

   * 0 - page is not locked.

   *     mmap_lock has been released (mmap_read_unlock(), unless flags had both

   *     FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in

   *     which case mmap_lock is still held.

   *
   * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1

   * with the page locked and the mmap_lock unperturbed.

   */

  __sched int __lock_page_or_retry(struct page *page, struct mm_struct *mm,

  			 unsigned int flags)
  {

  	if (fault_flag_allow_retry_first(flags)) {

  		/*

  		 * CAUTION! In this case, mmap_lock is not released

  		 * even though return 0.
  		 */
  		if (flags & FAULT_FLAG_RETRY_NOWAIT)
  			return 0;

  		mmap_read_unlock(mm);

  		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) {

  				mmap_read_unlock(mm);

  				return 0;
  			}
  		} else
  			__lock_page(page);
  		return 1;

  	}
  }

  /**

   * page_cache_next_miss() - Find the next gap in the page cache.
   * @mapping: Mapping.
   * @index: Index.
   * @max_scan: Maximum range to search.

   *

   * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the
   * gap with the lowest index.

   *

   * This function may be called under the rcu_read_lock.  However, this will
   * not atomically search a snapshot of the cache at a single point in time.
   * For example, if a gap is created at index 5, then subsequently a gap is
   * created at index 10, page_cache_next_miss covering both indices may
   * return 10 if called under the rcu_read_lock.

   *

   * Return: The index of the gap if found, otherwise an index outside the
   * range specified (in which case 'return - index >= max_scan' will be true).
   * In the rare case of index wrap-around, 0 will be returned.

   */

  pgoff_t page_cache_next_miss(struct address_space *mapping,

  			     pgoff_t index, unsigned long max_scan)
  {

  	XA_STATE(xas, &mapping->i_pages, index);

  	while (max_scan--) {
  		void *entry = xas_next(&xas);
  		if (!entry || xa_is_value(entry))

  			break;

  		if (xas.xa_index == 0)

  			break;
  	}

  	return xas.xa_index;

  }

  EXPORT_SYMBOL(page_cache_next_miss);

  
  /**

   * page_cache_prev_miss() - Find the previous gap in the page cache.

   * @mapping: Mapping.
   * @index: Index.
   * @max_scan: Maximum range to search.

   *

   * Search the range [max(index - max_scan + 1, 0), index] for the
   * gap with the highest index.

   *

   * This function may be called under the rcu_read_lock.  However, this will
   * not atomically search a snapshot of the cache at a single point in time.
   * For example, if a gap is created at index 10, then subsequently a gap is
   * created at index 5, page_cache_prev_miss() covering both indices may
   * return 5 if called under the rcu_read_lock.

   *

   * Return: The index of the gap if found, otherwise an index outside the
   * range specified (in which case 'index - return >= max_scan' will be true).
   * In the rare case of wrap-around, ULONG_MAX will be returned.

   */

  pgoff_t page_cache_prev_miss(struct address_space *mapping,

  			     pgoff_t index, unsigned long max_scan)
  {

  	XA_STATE(xas, &mapping->i_pages, index);

  	while (max_scan--) {
  		void *entry = xas_prev(&xas);
  		if (!entry || xa_is_value(entry))

  			break;

  		if (xas.xa_index == ULONG_MAX)

  			break;
  	}

  	return xas.xa_index;