/*
 * mm/rmap.c - physical to virtual reverse mappings
 *
 * Copyright 2001, Rik van Riel <riel@conectiva.com.br>
 * Released under the General Public License (GPL).
 *
 * Simple, low overhead reverse mapping scheme.
 * Please try to keep this thing as modular as possible.
 *
 * Provides methods for unmapping each kind of mapped page:
 * the anon methods track anonymous pages, and
 * the file methods track pages belonging to an inode.
 *
 * Original design by Rik van Riel <riel@conectiva.com.br> 2001
 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004
 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004
 * Contributions by Hugh Dickins 2003, 2004
 */

/*
 * Lock ordering in mm:
 *
 * inode->i_rwsem	(while writing or truncating, not reading or faulting)
 *   mm->mmap_lock
 *     mapping->invalidate_lock (in filemap_fault)
 *       page->flags PG_locked (lock_page)   * (see hugetlbfs below)
 *         hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
 *           mapping->i_mmap_rwsem
 *             hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
 *             anon_vma->rwsem
 *               mm->page_table_lock or pte_lock
 *                 swap_lock (in swap_duplicate, swap_info_get)
 *                   mmlist_lock (in mmput, drain_mmlist and others)
 *                   mapping->private_lock (in block_dirty_folio)
 *                     folio_lock_memcg move_lock (in block_dirty_folio)
 *                       i_pages lock (widely used)
 *                         lruvec->lru_lock (in folio_lruvec_lock_irq)
 *                   inode->i_lock (in set_page_dirty's __mark_inode_dirty)
 *                   bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
 *                     sb_lock (within inode_lock in fs/fs-writeback.c)
 *                     i_pages lock (widely used, in set_page_dirty,
 *                               in arch-dependent flush_dcache_mmap_lock,
 *                               within bdi.wb->list_lock in __sync_single_inode)
 *
 * anon_vma->rwsem,mapping->i_mmap_rwsem   (memory_failure, collect_procs_anon)
 *   ->tasklist_lock
 *     pte map lock
 *
 * * hugetlbfs PageHuge() pages take locks in this order:
 *         mapping->i_mmap_rwsem
 *           hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
 *             page->flags PG_locked (lock_page)
 */

/* Upstream Linux v6.0: mm/rmap.c:1200-1247
 * Exact source lines, not a restored book listing or standalone program.
 */
void page_add_anon_rmap(struct page *page,
	struct vm_area_struct *vma, unsigned long address, rmap_t flags)
{
	bool compound = flags & RMAP_COMPOUND;
	bool first;

	if (unlikely(PageKsm(page)))
		lock_page_memcg(page);
	else
		VM_BUG_ON_PAGE(!PageLocked(page), page);

	if (compound) {
		atomic_t *mapcount;
		VM_BUG_ON_PAGE(!PageLocked(page), page);
		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
		mapcount = compound_mapcount_ptr(page);
		first = atomic_inc_and_test(mapcount);
	} else {
		first = atomic_inc_and_test(&page->_mapcount);
	}
	VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page);
	VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page);

	if (first) {
		int nr = compound ? thp_nr_pages(page) : 1;
		/*
		 * We use the irq-unsafe __{inc|mod}_zone_page_stat because
		 * these counters are not modified in interrupt context, and
		 * pte lock(a spinlock) is held, which implies preemption
		 * disabled.
		 */
		if (compound)
			__mod_lruvec_page_state(page, NR_ANON_THPS, nr);
		__mod_lruvec_page_state(page, NR_ANON_MAPPED, nr);
	}

	if (unlikely(PageKsm(page)))
		unlock_page_memcg(page);

	/* address might be in next vma when migration races vma_adjust */
	else if (first)
		__page_set_anon_rmap(page, vma, address,
				     !!(flags & RMAP_EXCLUSIVE));
	else
		__page_check_anon_rmap(page, vma, address);

	mlock_vma_page(page, vma, compound);
}