// SPDX-License-Identifier: GPL-2.0
/*
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Swap reorganised 29.12.95, Stephen Tweedie.
 *  kswapd added: 7.1.96  sct
 *  Removed kswapd_ctl limits, and swap out as many pages as needed
 *  to bring the system back to freepages.high: 2.4.97, Rik van Riel.
 *  Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com).
 *  Multiqueue VM started 5.8.00, Rik van Riel.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

/*
 * Official Linux v6.0: mm/vmscan.c
 * https://github.com/torvalds/linux/blob/v6.0/mm/vmscan.c#L1289
 * Exact definition/declaration; not a reconstruction of a book listing.
 * See GPL-2.0.txt. Not a standalone translation unit.
 */

static int __remove_mapping(struct address_space *mapping, struct folio *folio,
			    bool reclaimed, struct mem_cgroup *target_memcg)
{
	int refcount;
	void *shadow = NULL;

	BUG_ON(!folio_test_locked(folio));
	BUG_ON(mapping != folio_mapping(folio));

	if (!folio_test_swapcache(folio))
		spin_lock(&mapping->host->i_lock);
	xa_lock_irq(&mapping->i_pages);
	/*
	 * The non racy check for a busy page.
	 *
	 * Must be careful with the order of the tests. When someone has
	 * a ref to the page, it may be possible that they dirty it then
	 * drop the reference. So if PageDirty is tested before page_count
	 * here, then the following race may occur:
	 *
	 * get_user_pages(&page);
	 * [user mapping goes away]
	 * write_to(page);
	 *				!PageDirty(page)    [good]
	 * SetPageDirty(page);
	 * put_page(page);
	 *				!page_count(page)   [good, discard it]
	 *
	 * [oops, our write_to data is lost]
	 *
	 * Reversing the order of the tests ensures such a situation cannot
	 * escape unnoticed. The smp_rmb is needed to ensure the page->flags
	 * load is not satisfied before that of page->_refcount.
	 *
	 * Note that if SetPageDirty is always performed via set_page_dirty,
	 * and thus under the i_pages lock, then this ordering is not required.
	 */
	refcount = 1 + folio_nr_pages(folio);
	if (!folio_ref_freeze(folio, refcount))
		goto cannot_free;
	/* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */
	if (unlikely(folio_test_dirty(folio))) {
		folio_ref_unfreeze(folio, refcount);
		goto cannot_free;
	}

	if (folio_test_swapcache(folio)) {
		swp_entry_t swap = folio_swap_entry(folio);
		mem_cgroup_swapout(folio, swap);
		if (reclaimed && !mapping_exiting(mapping))
			shadow = workingset_eviction(folio, target_memcg);
		__delete_from_swap_cache(folio, swap, shadow);
		xa_unlock_irq(&mapping->i_pages);
		put_swap_page(&folio->page, swap);
	} else {
		void (*free_folio)(struct folio *);

		free_folio = mapping->a_ops->free_folio;
		/*
		 * Remember a shadow entry for reclaimed file cache in
		 * order to detect refaults, thus thrashing, later on.
		 *
		 * But don't store shadows in an address space that is
		 * already exiting.  This is not just an optimization,
		 * inode reclaim needs to empty out the radix tree or
		 * the nodes are lost.  Don't plant shadows behind its
		 * back.
		 *
		 * We also don't store shadows for DAX mappings because the
		 * only page cache pages found in these are zero pages
		 * covering holes, and because we don't want to mix DAX
		 * exceptional entries and shadow exceptional entries in the
		 * same address_space.
		 */
		if (reclaimed && folio_is_file_lru(folio) &&
		    !mapping_exiting(mapping) && !dax_mapping(mapping))
			shadow = workingset_eviction(folio, target_memcg);
		__filemap_remove_folio(folio, shadow);
		xa_unlock_irq(&mapping->i_pages);
		if (mapping_shrinkable(mapping))
			inode_add_lru(mapping->host);
		spin_unlock(&mapping->host->i_lock);

		if (free_folio)
			free_folio(folio);
	}

	return 1;

cannot_free:
	xa_unlock_irq(&mapping->i_pages);
	if (!folio_test_swapcache(folio))
		spin_unlock(&mapping->host->i_lock);
	return 0;
}