Contributors: 44
Author Tokens Token Proportion Commits Commit Proportion
Huang Ying 1501 42.21% 14 10.14%
Matthew Wilcox 479 13.47% 23 16.67%
JoonSoo Kim 237 6.66% 2 1.45%
Shaohua Li 218 6.13% 5 3.62%
MinChan Kim 187 5.26% 4 2.90%
Andrew Morton 178 5.01% 10 7.25%
Linus Torvalds (pre-git) 131 3.68% 15 10.87%
Hugh Dickins 125 3.52% 10 7.25%
Dmitry Safonov 73 2.05% 1 0.72%
Johannes Weiner 65 1.83% 3 2.17%
Neil Brown 48 1.35% 3 2.17%
Linus Torvalds 44 1.24% 4 2.90%
Rik Van Riel 43 1.21% 2 1.45%
Shakeel Butt 35 0.98% 2 1.45%
Nicholas Piggin 28 0.79% 4 2.90%
Andrea Arcangeli 22 0.62% 1 0.72%
Christian Ehrhardt 19 0.53% 1 0.72%
Miaohe Lin 19 0.53% 4 2.90%
Tim Chen 11 0.31% 2 1.45%
Jagdish Gediya 11 0.31% 1 0.72%
Kamezawa Hiroyuki 10 0.28% 2 1.45%
Christoph Lameter 10 0.28% 3 2.17%
Sasha Levin 8 0.22% 1 0.72%
Gerald Schaefer 7 0.20% 1 0.72%
Qian Cai 7 0.20% 1 0.72%
Michal Hocko 5 0.14% 1 0.72%
Vladimir Davydov 4 0.11% 1 0.72%
Guo Ziliang 4 0.11% 1 0.72%
Kees Cook 3 0.08% 1 0.72%
Daisuke Nishimura 3 0.08% 1 0.72%
Changbin Du 3 0.08% 1 0.72%
Tejun Heo 3 0.08% 1 0.72%
Colin Ian King 2 0.06% 1 0.72%
Kirill A. Shutemov 2 0.06% 1 0.72%
Eric Sesterhenn / Snakebyte 2 0.06% 1 0.72%
Christoph Hellwig 1 0.03% 1 0.72%
Aaron Lu 1 0.03% 1 0.72%
Rafael Aquini 1 0.03% 1 0.72%
Jens Axboe 1 0.03% 1 0.72%
Shijie Luo 1 0.03% 1 0.72%
Greg Kroah-Hartman 1 0.03% 1 0.72%
Joe Perches 1 0.03% 1 0.72%
Michel Lespinasse 1 0.03% 1 0.72%
Rikard Falkeborn 1 0.03% 1 0.72%
Total 3556 138 
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/mm/swap_state.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *  Swap reorganised 29.12.95, Stephen Tweedie
 *
 *  Rewritten to use page cache, (C) 1998 Stephen Tweedie
 */
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/blkdev.h>
#include <linux/pagevec.h>
#include <linux/migrate.h>
#include <linux/vmalloc.h>
#include <linux/swap_slots.h>
#include <linux/huge_mm.h>
#include <linux/shmem_fs.h>
#include "internal.h"
#include "swap.h"

/*
 * swapper_space is a fiction, retained to simplify the path through
 * vmscan's shrink_page_list.
 */
static const struct address_space_operations swap_aops = {
	.writepage	= swap_writepage,
	.dirty_folio	= noop_dirty_folio,
#ifdef CONFIG_MIGRATION
	.migrate_folio	= migrate_folio,
#endif
};

struct address_space *swapper_spaces[MAX_SWAPFILES] __read_mostly;
static unsigned int nr_swapper_spaces[MAX_SWAPFILES] __read_mostly;
static bool enable_vma_readahead __read_mostly = true;

#define SWAP_RA_WIN_SHIFT	(PAGE_SHIFT / 2)
#define SWAP_RA_HITS_MASK	((1UL << SWAP_RA_WIN_SHIFT) - 1)
#define SWAP_RA_HITS_MAX	SWAP_RA_HITS_MASK
#define SWAP_RA_WIN_MASK	(~PAGE_MASK & ~SWAP_RA_HITS_MASK)

#define SWAP_RA_HITS(v)		((v) & SWAP_RA_HITS_MASK)
#define SWAP_RA_WIN(v)		(((v) & SWAP_RA_WIN_MASK) >> SWAP_RA_WIN_SHIFT)
#define SWAP_RA_ADDR(v)		((v) & PAGE_MASK)

#define SWAP_RA_VAL(addr, win, hits)				\
	(((addr) & PAGE_MASK) |					\
	 (((win) << SWAP_RA_WIN_SHIFT) & SWAP_RA_WIN_MASK) |	\
	 ((hits) & SWAP_RA_HITS_MASK))

/* Initial readahead hits is 4 to start up with a small window */
#define GET_SWAP_RA_VAL(vma)					\
	(atomic_long_read(&(vma)->swap_readahead_info) ? : 4)

static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);

void show_swap_cache_info(void)
{
	printk("%lu pages in swap cache\n", total_swapcache_pages());
	printk("Free swap  = %ldkB\n",
		get_nr_swap_pages() << (PAGE_SHIFT - 10));
	printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10));
}

void *get_shadow_from_swap_cache(swp_entry_t entry)
{
	struct address_space *address_space = swap_address_space(entry);
	pgoff_t idx = swp_offset(entry);
	struct page *page;

	page = xa_load(&address_space->i_pages, idx);
	if (xa_is_value(page))
		return page;
	return NULL;
}

/*
 * add_to_swap_cache resembles filemap_add_folio on swapper_space,
 * but sets SwapCache flag and private instead of mapping and index.
 */
int add_to_swap_cache(struct folio *folio, swp_entry_t entry,
			gfp_t gfp, void **shadowp)
{
	struct address_space *address_space = swap_address_space(entry);
	pgoff_t idx = swp_offset(entry);
	XA_STATE_ORDER(xas, &address_space->i_pages, idx, folio_order(folio));
	unsigned long i, nr = folio_nr_pages(folio);
	void *old;

	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
	VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
	VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio);

	folio_ref_add(folio, nr);
	folio_set_swapcache(folio);

	do {
		xas_lock_irq(&xas);
		xas_create_range(&xas);
		if (xas_error(&xas))
			goto unlock;
		for (i = 0; i < nr; i++) {
			VM_BUG_ON_FOLIO(xas.xa_index != idx + i, folio);
			old = xas_load(&xas);
			if (xa_is_value(old)) {
				if (shadowp)
					*shadowp = old;
			}
			set_page_private(folio_page(folio, i), entry.val + i);
			xas_store(&xas, folio);
			xas_next(&xas);
		}
		address_space->nrpages += nr;
		__node_stat_mod_folio(folio, NR_FILE_PAGES, nr);
		__lruvec_stat_mod_folio(folio, NR_SWAPCACHE, nr);
unlock:
		xas_unlock_irq(&xas);
	} while (xas_nomem(&xas, gfp));

	if (!xas_error(&xas))
		return 0;

	folio_clear_swapcache(folio);
	folio_ref_sub(folio, nr);
	return xas_error(&xas);
}

/*
 * This must be called only on folios that have
 * been verified to be in the swap cache.
 */
void __delete_from_swap_cache(struct folio *folio,
			swp_entry_t entry, void *shadow)
{
	struct address_space *address_space = swap_address_space(entry);
	int i;
	long nr = folio_nr_pages(folio);
	pgoff_t idx = swp_offset(entry);
	XA_STATE(xas, &address_space->i_pages, idx);

	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
	VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
	VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio);

	for (i = 0; i < nr; i++) {
		void *entry = xas_store(&xas, shadow);
		VM_BUG_ON_PAGE(entry != folio, entry);
		set_page_private(folio_page(folio, i), 0);
		xas_next(&xas);
	}
	folio_clear_swapcache(folio);
	address_space->nrpages -= nr;
	__node_stat_mod_folio(folio, NR_FILE_PAGES, -nr);
	__lruvec_stat_mod_folio(folio, NR_SWAPCACHE, -nr);
}

/**
 * add_to_swap - allocate swap space for a folio
 * @folio: folio we want to move to swap
 *
 * Allocate swap space for the folio and add the folio to the
 * swap cache.
 *
 * Context: Caller needs to hold the folio lock.
 * Return: Whether the folio was added to the swap cache.
 */
bool add_to_swap(struct folio *folio)
{
	swp_entry_t entry;
	int err;

	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
	VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);

	entry = folio_alloc_swap(folio);
	if (!entry.val)
		return false;

	/*
	 * XArray node allocations from PF_MEMALLOC contexts could
	 * completely exhaust the page allocator. __GFP_NOMEMALLOC
	 * stops emergency reserves from being allocated.
	 *
	 * TODO: this could cause a theoretical memory reclaim
	 * deadlock in the swap out path.
	 */
	/*
	 * Add it to the swap cache.
	 */
	err = add_to_swap_cache(folio, entry,
			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN, NULL);
	if (err)
		/*
		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
		 * clear SWAP_HAS_CACHE flag.
		 */
		goto fail;
	/*
	 * Normally the folio will be dirtied in unmap because its
	 * pte should be dirty. A special case is MADV_FREE page. The
	 * page's pte could have dirty bit cleared but the folio's
	 * SwapBacked flag is still set because clearing the dirty bit
	 * and SwapBacked flag has no lock protected. For such folio,
	 * unmap will not set dirty bit for it, so folio reclaim will
	 * not write the folio out. This can cause data corruption when
	 * the folio is swapped in later. Always setting the dirty flag
	 * for the folio solves the problem.
	 */
	folio_mark_dirty(folio);

	return true;

fail:
	put_swap_folio(folio, entry);
	return false;
}

/*
 * This must be called only on folios that have
 * been verified to be in the swap cache and locked.
 * It will never put the folio into the free list,
 * the caller has a reference on the folio.
 */
void delete_from_swap_cache(struct folio *folio)
{
	swp_entry_t entry = folio_swap_entry(folio);
	struct address_space *address_space = swap_address_space(entry);

	xa_lock_irq(&address_space->i_pages);
	__delete_from_swap_cache(folio, entry, NULL);
	xa_unlock_irq(&address_space->i_pages);

	put_swap_folio(folio, entry);
	folio_ref_sub(folio, folio_nr_pages(folio));
}

void clear_shadow_from_swap_cache(int type, unsigned long begin,
				unsigned long end)
{
	unsigned long curr = begin;
	void *old;

	for (;;) {
		swp_entry_t entry = swp_entry(type, curr);
		struct address_space *address_space = swap_address_space(entry);
		XA_STATE(xas, &address_space->i_pages, curr);

		xa_lock_irq(&address_space->i_pages);
		xas_for_each(&xas, old, end) {
			if (!xa_is_value(old))
				continue;
			xas_store(&xas, NULL);
		}
		xa_unlock_irq(&address_space->i_pages);

		/* search the next swapcache until we meet end */
		curr >>= SWAP_ADDRESS_SPACE_SHIFT;
		curr++;
		curr <<= SWAP_ADDRESS_SPACE_SHIFT;
		if (curr > end)
			break;
	}
}

/* 
 * If we are the only user, then try to free up the swap cache. 
 * 
 * Its ok to check the swapcache flag without the folio lock
 * here because we are going to recheck again inside
 * folio_free_swap() _with_ the lock.
 * 					- Marcelo
 */
void free_swap_cache(struct page *page)
{
	struct folio *folio = page_folio(page);

	if (folio_test_swapcache(folio) && !folio_mapped(folio) &&
	    folio_trylock(folio)) {
		folio_free_swap(folio);
		folio_unlock(folio);
	}
}

/* 
 * Perform a free_page(), also freeing any swap cache associated with
 * this page if it is the last user of the page.
 */
void free_page_and_swap_cache(struct page *page)
{
	free_swap_cache(page);
	if (!is_huge_zero_page(page))
		put_page(page);
}

/*
 * Passed an array of pages, drop them all from swapcache and then release
 * them.  They are removed from the LRU and freed if this is their last use.
 */
void free_pages_and_swap_cache(struct page **pages, int nr)
{
	struct page **pagep = pages;
	int i;

	lru_add_drain();
	for (i = 0; i < nr; i++)
		free_swap_cache(pagep[i]);
	release_pages(pagep, nr);
}

static inline bool swap_use_vma_readahead(void)
{
	return READ_ONCE(enable_vma_readahead) && !atomic_read(&nr_rotate_swap);
}

/*
 * Lookup a swap entry in the swap cache. A found folio will be returned
 * unlocked and with its refcount incremented - we rely on the kernel
 * lock getting page table operations atomic even if we drop the folio
 * lock before returning.
 */
struct folio *swap_cache_get_folio(swp_entry_t entry,
		struct vm_area_struct *vma, unsigned long addr)
{
	struct folio *folio;
	struct swap_info_struct *si;

	si = get_swap_device(entry);
	if (!si)
		return NULL;
	folio = filemap_get_folio(swap_address_space(entry), swp_offset(entry));
	put_swap_device(si);

	if (folio) {
		bool vma_ra = swap_use_vma_readahead();
		bool readahead;

		/*
		 * At the moment, we don't support PG_readahead for anon THP
		 * so let's bail out rather than confusing the readahead stat.
		 */
		if (unlikely(folio_test_large(folio)))
			return folio;

		readahead = folio_test_clear_readahead(folio);
		if (vma && vma_ra) {
			unsigned long ra_val;
			int win, hits;

			ra_val = GET_SWAP_RA_VAL(vma);
			win = SWAP_RA_WIN(ra_val);
			hits = SWAP_RA_HITS(ra_val);
			if (readahead)
				hits = min_t(int, hits + 1, SWAP_RA_HITS_MAX);
			atomic_long_set(&vma->swap_readahead_info,
					SWAP_RA_VAL(addr, win, hits));
		}

		if (readahead) {
			count_vm_event(SWAP_RA_HIT);
			if (!vma || !vma_ra)
				atomic_inc(&swapin_readahead_hits);
		}
	}

	return folio;
}

/**
 * find_get_incore_page - Find and get a page from the page or swap caches.
 * @mapping: The address_space to search.
 * @index: The page cache index.
 *
 * This differs from find_get_page() in that it will also look for the
 * page in the swap cache.
 *
 * Return: The found page or %NULL.
 */
struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index)
{
	swp_entry_t swp;
	struct swap_info_struct *si;
	struct page *page = pagecache_get_page(mapping, index,
						FGP_ENTRY | FGP_HEAD, 0);

	if (!page)
		return page;
	if (!xa_is_value(page))
		return find_subpage(page, index);
	if (!shmem_mapping(mapping))
		return NULL;

	swp = radix_to_swp_entry(page);
	/* There might be swapin error entries in shmem mapping. */
	if (non_swap_entry(swp))
		return NULL;
	/* Prevent swapoff from happening to us */
	si = get_swap_device(swp);
	if (!si)
		return NULL;
	page = find_get_page(swap_address_space(swp), swp_offset(swp));
	put_swap_device(si);
	return page;
}

struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
			struct vm_area_struct *vma, unsigned long addr,
			bool *new_page_allocated)
{
	struct swap_info_struct *si;
	struct folio *folio;
	void *shadow = NULL;

	*new_page_allocated = false;

	for (;;) {
		int err;
		/*
		 * First check the swap cache.  Since this is normally
		 * called after swap_cache_get_folio() failed, re-calling
		 * that would confuse statistics.
		 */
		si = get_swap_device(entry);
		if (!si)
			return NULL;
		folio = filemap_get_folio(swap_address_space(entry),
						swp_offset(entry));
		put_swap_device(si);
		if (folio)
			return folio_file_page(folio, swp_offset(entry));

		/*
		 * Just skip read ahead for unused swap slot.
		 * During swap_off when swap_slot_cache is disabled,
		 * we have to handle the race between putting
		 * swap entry in swap cache and marking swap slot
		 * as SWAP_HAS_CACHE.  That's done in later part of code or
		 * else swap_off will be aborted if we return NULL.
		 */
		if (!__swp_swapcount(entry) && swap_slot_cache_enabled)
			return NULL;

		/*
		 * Get a new page to read into from swap.  Allocate it now,
		 * before marking swap_map SWAP_HAS_CACHE, when -EEXIST will
		 * cause any racers to loop around until we add it to cache.
		 */
		folio = vma_alloc_folio(gfp_mask, 0, vma, addr, false);
		if (!folio)
			return NULL;

		/*
		 * Swap entry may have been freed since our caller observed it.
		 */
		err = swapcache_prepare(entry);
		if (!err)
			break;

		folio_put(folio);
		if (err != -EEXIST)
			return NULL;

		/*
		 * We might race against __delete_from_swap_cache(), and
		 * stumble across a swap_map entry whose SWAP_HAS_CACHE
		 * has not yet been cleared.  Or race against another
		 * __read_swap_cache_async(), which has set SWAP_HAS_CACHE
		 * in swap_map, but not yet added its page to swap cache.
		 */
		schedule_timeout_uninterruptible(1);
	}

	/*
	 * The swap entry is ours to swap in. Prepare the new page.
	 */

	__folio_set_locked(folio);
	__folio_set_swapbacked(folio);

	if (mem_cgroup_swapin_charge_folio(folio, NULL, gfp_mask, entry))
		goto fail_unlock;

	/* May fail (-ENOMEM) if XArray node allocation failed. */
	if (add_to_swap_cache(folio, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow))
		goto fail_unlock;

	mem_cgroup_swapin_uncharge_swap(entry);

	if (shadow)
		workingset_refault(folio, shadow);

	/* Caller will initiate read into locked folio */
	folio_add_lru(folio);
	*new_page_allocated = true;
	return &folio->page;

fail_unlock:
	put_swap_folio(folio, entry);
	folio_unlock(folio);
	folio_put(folio);
	return NULL;
}

/*
 * Locate a page of swap in physical memory, reserving swap cache space
 * and reading the disk if it is not already cached.
 * A failure return means that either the page allocation failed or that
 * the swap entry is no longer in use.
 */
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
				   struct vm_area_struct *vma,
				   unsigned long addr, bool do_poll,
				   struct swap_iocb **plug)
{
	bool page_was_allocated;
	struct page *retpage = __read_swap_cache_async(entry, gfp_mask,
			vma, addr, &page_was_allocated);

	if (page_was_allocated)
		swap_readpage(retpage, do_poll, plug);

	return retpage;
}

static unsigned int __swapin_nr_pages(unsigned long prev_offset,
				      unsigned long offset,
				      int hits,
				      int max_pages,
				      int prev_win)
{
	unsigned int pages, last_ra;

	/*
	 * This heuristic has been found to work well on both sequential and
	 * random loads, swapping to hard disk or to SSD: please don't ask
	 * what the "+ 2" means, it just happens to work well, that's all.
	 */
	pages = hits + 2;
	if (pages == 2) {
		/*
		 * We can have no readahead hits to judge by: but must not get
		 * stuck here forever, so check for an adjacent offset instead
		 * (and don't even bother to check whether swap type is same).
		 */
		if (offset != prev_offset + 1 && offset != prev_offset - 1)
			pages = 1;
	} else {
		unsigned int roundup = 4;
		while (roundup < pages)
			roundup <<= 1;
		pages = roundup;
	}

	if (pages > max_pages)
		pages = max_pages;

	/* Don't shrink readahead too fast */
	last_ra = prev_win / 2;
	if (pages < last_ra)
		pages = last_ra;

	return pages;
}

static unsigned long swapin_nr_pages(unsigned long offset)
{
	static unsigned long prev_offset;
	unsigned int hits, pages, max_pages;
	static atomic_t last_readahead_pages;

	max_pages = 1 << READ_ONCE(page_cluster);
	if (max_pages <= 1)
		return 1;

	hits = atomic_xchg(&swapin_readahead_hits, 0);
	pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits,
				  max_pages,
				  atomic_read(&last_readahead_pages));
	if (!hits)
		WRITE_ONCE(prev_offset, offset);
	atomic_set(&last_readahead_pages, pages);

	return pages;
}

/**
 * swap_cluster_readahead - swap in pages in hope we need them soon
 * @entry: swap entry of this memory
 * @gfp_mask: memory allocation flags
 * @vmf: fault information
 *
 * Returns the struct page for entry and addr, after queueing swapin.
 *
 * Primitive swap readahead code. We simply read an aligned block of
 * (1 << page_cluster) entries in the swap area. This method is chosen
 * because it doesn't cost us any seek time.  We also make sure to queue
 * the 'original' request together with the readahead ones...
 *
 * This has been extended to use the NUMA policies from the mm triggering
 * the readahead.
 *
 * Caller must hold read mmap_lock if vmf->vma is not NULL.
 */
struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
				struct vm_fault *vmf)
{
	struct page *page;
	unsigned long entry_offset = swp_offset(entry);
	unsigned long offset = entry_offset;
	unsigned long start_offset, end_offset;
	unsigned long mask;
	struct swap_info_struct *si = swp_swap_info(entry);
	struct blk_plug plug;
	struct swap_iocb *splug = NULL;
	bool do_poll = true, page_allocated;
	struct vm_area_struct *vma = vmf->vma;
	unsigned long addr = vmf->address;

	mask = swapin_nr_pages(offset) - 1;
	if (!mask)
		goto skip;

	do_poll = false;
	/* Read a page_cluster sized and aligned cluster around offset. */
	start_offset = offset & ~mask;
	end_offset = offset | mask;
	if (!start_offset)	/* First page is swap header. */
		start_offset++;
	if (end_offset >= si->max)
		end_offset = si->max - 1;

	blk_start_plug(&plug);
	for (offset = start_offset; offset <= end_offset ; offset++) {
		/* Ok, do the async read-ahead now */
		page = __read_swap_cache_async(
			swp_entry(swp_type(entry), offset),
			gfp_mask, vma, addr, &page_allocated);
		if (!page)
			continue;
		if (page_allocated) {
			swap_readpage(page, false, &splug);
			if (offset != entry_offset) {
				SetPageReadahead(page);
				count_vm_event(SWAP_RA);
			}
		}
		put_page(page);
	}
	blk_finish_plug(&plug);
	swap_read_unplug(splug);

	lru_add_drain();	/* Push any new pages onto the LRU now */
skip:
	/* The page was likely read above, so no need for plugging here */
	return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll, NULL);
}

int init_swap_address_space(unsigned int type, unsigned long nr_pages)
{
	struct address_space *spaces, *space;
	unsigned int i, nr;

	nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES);
	spaces = kvcalloc(nr, sizeof(struct address_space), GFP_KERNEL);
	if (!spaces)
		return -ENOMEM;
	for (i = 0; i < nr; i++) {
		space = spaces + i;
		xa_init_flags(&space->i_pages, XA_FLAGS_LOCK_IRQ);
		atomic_set(&space->i_mmap_writable, 0);
		space->a_ops = &swap_aops;
		/* swap cache doesn't use writeback related tags */
		mapping_set_no_writeback_tags(space);
	}
	nr_swapper_spaces[type] = nr;
	swapper_spaces[type] = spaces;

	return 0;
}

void exit_swap_address_space(unsigned int type)
{
	int i;
	struct address_space *spaces = swapper_spaces[type];

	for (i = 0; i < nr_swapper_spaces[type]; i++)
		VM_WARN_ON_ONCE(!mapping_empty(&spaces[i]));
	kvfree(spaces);
	nr_swapper_spaces[type] = 0;
	swapper_spaces[type] = NULL;
}

static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma,
				     unsigned long faddr,
				     unsigned long lpfn,
				     unsigned long rpfn,
				     unsigned long *start,
				     unsigned long *end)
{
	*start = max3(lpfn, PFN_DOWN(vma->vm_start),
		      PFN_DOWN(faddr & PMD_MASK));
	*end = min3(rpfn, PFN_DOWN(vma->vm_end),
		    PFN_DOWN((faddr & PMD_MASK) + PMD_SIZE));
}

static void swap_ra_info(struct vm_fault *vmf,
			struct vma_swap_readahead *ra_info)
{
	struct vm_area_struct *vma = vmf->vma;
	unsigned long ra_val;
	unsigned long faddr, pfn, fpfn;
	unsigned long start, end;
	pte_t *pte, *orig_pte;
	unsigned int max_win, hits, prev_win, win, left;
#ifndef CONFIG_64BIT
	pte_t *tpte;
#endif

	max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster),
			     SWAP_RA_ORDER_CEILING);
	if (max_win == 1) {
		ra_info->win = 1;
		return;
	}

	faddr = vmf->address;
	orig_pte = pte = pte_offset_map(vmf->pmd, faddr);

	fpfn = PFN_DOWN(faddr);
	ra_val = GET_SWAP_RA_VAL(vma);
	pfn = PFN_DOWN(SWAP_RA_ADDR(ra_val));
	prev_win = SWAP_RA_WIN(ra_val);
	hits = SWAP_RA_HITS(ra_val);
	ra_info->win = win = __swapin_nr_pages(pfn, fpfn, hits,
					       max_win, prev_win);
	atomic_long_set(&vma->swap_readahead_info,
			SWAP_RA_VAL(faddr, win, 0));

	if (win == 1) {
		pte_unmap(orig_pte);
		return;
	}

	/* Copy the PTEs because the page table may be unmapped */
	if (fpfn == pfn + 1)
		swap_ra_clamp_pfn(vma, faddr, fpfn, fpfn + win, &start, &end);
	else if (pfn == fpfn + 1)
		swap_ra_clamp_pfn(vma, faddr, fpfn - win + 1, fpfn + 1,
				  &start, &end);
	else {
		left = (win - 1) / 2;
		swap_ra_clamp_pfn(vma, faddr, fpfn - left, fpfn + win - left,
				  &start, &end);
	}
	ra_info->nr_pte = end - start;
	ra_info->offset = fpfn - start;
	pte -= ra_info->offset;
#ifdef CONFIG_64BIT
	ra_info->ptes = pte;
#else
	tpte = ra_info->ptes;
	for (pfn = start; pfn != end; pfn++)
		*tpte++ = *pte++;
#endif
	pte_unmap(orig_pte);
}

/**
 * swap_vma_readahead - swap in pages in hope we need them soon
 * @fentry: swap entry of this memory
 * @gfp_mask: memory allocation flags
 * @vmf: fault information
 *
 * Returns the struct page for entry and addr, after queueing swapin.
 *
 * Primitive swap readahead code. We simply read in a few pages whose
 * virtual addresses are around the fault address in the same vma.
 *
 * Caller must hold read mmap_lock if vmf->vma is not NULL.
 *
 */
static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
				       struct vm_fault *vmf)
{
	struct blk_plug plug;
	struct swap_iocb *splug = NULL;
	struct vm_area_struct *vma = vmf->vma;
	struct page *page;
	pte_t *pte, pentry;
	swp_entry_t entry;
	unsigned int i;
	bool page_allocated;
	struct vma_swap_readahead ra_info = {
		.win = 1,
	};

	swap_ra_info(vmf, &ra_info);
	if (ra_info.win == 1)
		goto skip;

	blk_start_plug(&plug);
	for (i = 0, pte = ra_info.ptes; i < ra_info.nr_pte;
	     i++, pte++) {
		pentry = *pte;
		if (!is_swap_pte(pentry))
			continue;
		entry = pte_to_swp_entry(pentry);
		if (unlikely(non_swap_entry(entry)))
			continue;
		page = __read_swap_cache_async(entry, gfp_mask, vma,
					       vmf->address, &page_allocated);
		if (!page)
			continue;
		if (page_allocated) {
			swap_readpage(page, false, &splug);
			if (i != ra_info.offset) {
				SetPageReadahead(page);
				count_vm_event(SWAP_RA);
			}
		}
		put_page(page);
	}
	blk_finish_plug(&plug);
	swap_read_unplug(splug);
	lru_add_drain();
skip:
	/* The page was likely read above, so no need for plugging here */
	return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address,
				     ra_info.win == 1, NULL);
}

/**
 * swapin_readahead - swap in pages in hope we need them soon
 * @entry: swap entry of this memory
 * @gfp_mask: memory allocation flags
 * @vmf: fault information
 *
 * Returns the struct page for entry and addr, after queueing swapin.
 *
 * It's a main entry function for swap readahead. By the configuration,
 * it will read ahead blocks by cluster-based(ie, physical disk based)
 * or vma-based(ie, virtual address based on faulty address) readahead.
 */
struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
				struct vm_fault *vmf)
{
	return swap_use_vma_readahead() ?
			swap_vma_readahead(entry, gfp_mask, vmf) :
			swap_cluster_readahead(entry, gfp_mask, vmf);
}

#ifdef CONFIG_SYSFS
static ssize_t vma_ra_enabled_show(struct kobject *kobj,
				     struct kobj_attribute *attr, char *buf)
{
	return sysfs_emit(buf, "%s\n",
			  enable_vma_readahead ? "true" : "false");
}
static ssize_t vma_ra_enabled_store(struct kobject *kobj,
				      struct kobj_attribute *attr,
				      const char *buf, size_t count)
{
	ssize_t ret;

	ret = kstrtobool(buf, &enable_vma_readahead);
	if (ret)
		return ret;

	return count;
}
static struct kobj_attribute vma_ra_enabled_attr = __ATTR_RW(vma_ra_enabled);

static struct attribute *swap_attrs[] = {
	&vma_ra_enabled_attr.attr,
	NULL,
};

static const struct attribute_group swap_attr_group = {
	.attrs = swap_attrs,
};

static int __init swap_init_sysfs(void)
{
	int err;
	struct kobject *swap_kobj;

	swap_kobj = kobject_create_and_add("swap", mm_kobj);
	if (!swap_kobj) {
		pr_err("failed to create swap kobject\n");
		return -ENOMEM;
	}
	err = sysfs_create_group(swap_kobj, &swap_attr_group);
	if (err) {
		pr_err("failed to register swap group\n");
		goto delete_obj;
	}
	return 0;

delete_obj:
	kobject_put(swap_kobj);
	return err;
}
subsys_initcall(swap_init_sysfs);
#endif