1 files changed, 272 insertions, 205 deletions

diff --git a/mm/swap_state.c b/mm/swap_state.c
index 8e7ce9a9bc5e..438d0676c5be 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -21,8 +21,9 @@
 #include <linux/vmalloc.h>
 #include <linux/swap_slots.h>
 #include <linux/huge_mm.h>
-
-#include <asm/pgtable.h>
+#include <linux/shmem_fs.h>
+#include "internal.h"
+#include "swap.h"
 
 /*
  * swapper_space is a fiction, retained to simplify the path through
@@ -30,9 +31,9 @@
  */
 static const struct address_space_operations swap_aops = {
 	.writepage	= swap_writepage,
-	.set_page_dirty	= swap_set_page_dirty,
+	.dirty_folio	= noop_dirty_folio,
 #ifdef CONFIG_MIGRATION
-	.migratepage	= migrate_page,
+	.migrate_folio	= migrate_folio,
 #endif
 };
 
@@ -58,72 +59,47 @@ static bool enable_vma_readahead __read_mostly = true;
 #define GET_SWAP_RA_VAL(vma)					\
 	(atomic_long_read(&(vma)->swap_readahead_info) ? : 4)
 
-#define INC_CACHE_INFO(x)	do { swap_cache_info.x++; } while (0)
-#define ADD_CACHE_INFO(x, nr)	do { swap_cache_info.x += (nr); } while (0)
-
-static struct {
-	unsigned long add_total;
-	unsigned long del_total;
-	unsigned long find_success;
-	unsigned long find_total;
-} swap_cache_info;
-
-unsigned long total_swapcache_pages(void)
-{
-	unsigned int i, j, nr;
-	unsigned long ret = 0;
-	struct address_space *spaces;
-	struct swap_info_struct *si;
-
-	for (i = 0; i < MAX_SWAPFILES; i++) {
-		swp_entry_t entry = swp_entry(i, 1);
-
-		/* Avoid get_swap_device() to warn for bad swap entry */
-		if (!swp_swap_info(entry))
-			continue;
-		/* Prevent swapoff to free swapper_spaces */
-		si = get_swap_device(entry);
-		if (!si)
-			continue;
-		nr = nr_swapper_spaces[i];
-		spaces = swapper_spaces[i];
-		for (j = 0; j < nr; j++)
-			ret += spaces[j].nrpages;
-		put_swap_device(si);
-	}
-	return ret;
-}
-
 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("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n",
-		swap_cache_info.add_total, swap_cache_info.del_total,
-		swap_cache_info.find_success, swap_cache_info.find_total);
 	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 add_to_page_cache_locked on swapper_space,
+ * 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 page *page, swp_entry_t entry, gfp_t gfp)
+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, compound_order(page));
-	unsigned long i, nr = compound_nr(page);
+	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_PAGE(!PageLocked(page), page);
-	VM_BUG_ON_PAGE(PageSwapCache(page), page);
-	VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
+	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);
 
-	page_ref_add(page, nr);
-	SetPageSwapCache(page);
+	folio_ref_add(folio, nr);
+	folio_set_swapcache(folio);
 
 	do {
 		xas_lock_irq(&xas);
@@ -131,14 +107,19 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp)
 		if (xas_error(&xas))
 			goto unlock;
 		for (i = 0; i < nr; i++) {
-			VM_BUG_ON_PAGE(xas.xa_index != idx + i, page);
-			set_page_private(page + i, entry.val + i);
-			xas_store(&xas, page);
+			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;
-		__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
-		ADD_CACHE_INFO(add_total, 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));
@@ -146,56 +127,61 @@ unlock:
 	if (!xas_error(&xas))
 		return 0;
 
-	ClearPageSwapCache(page);
-	page_ref_sub(page, nr);
+	folio_clear_swapcache(folio);
+	folio_ref_sub(folio, nr);
 	return xas_error(&xas);
 }
 
 /*
- * This must be called only on pages that have
+ * This must be called only on folios that have
  * been verified to be in the swap cache.
  */
-void __delete_from_swap_cache(struct page *page, swp_entry_t entry)
+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, nr = hpage_nr_pages(page);
+	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_PAGE(!PageLocked(page), page);
-	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
-	VM_BUG_ON_PAGE(PageWriteback(page), page);
+	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, NULL);
-		VM_BUG_ON_PAGE(entry != page, entry);
-		set_page_private(page + i, 0);
+		void *entry = xas_store(&xas, shadow);
+		VM_BUG_ON_PAGE(entry != folio, entry);
+		set_page_private(folio_page(folio, i), 0);
 		xas_next(&xas);
 	}
-	ClearPageSwapCache(page);
+	folio_clear_swapcache(folio);
 	address_space->nrpages -= nr;
-	__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
-	ADD_CACHE_INFO(del_total, 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 page
- * @page: page we want to move to swap
+ * add_to_swap - allocate swap space for a folio
+ * @folio: folio we want to move to swap
  *
- * Allocate swap space for the page and add the page to the
- * swap cache.  Caller needs to hold the page lock. 
+ * 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.
  */
-int add_to_swap(struct page *page)
+bool add_to_swap(struct folio *folio)
 {
 	swp_entry_t entry;
 	int err;
 
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	VM_BUG_ON_PAGE(!PageUptodate(page), page);
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+	VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);
 
-	entry = get_swap_page(page);
+	entry = folio_alloc_swap(folio);
 	if (!entry.val)
-		return 0;
+		return false;
 
 	/*
 	 * XArray node allocations from PF_MEMALLOC contexts could
@@ -208,8 +194,8 @@ int add_to_swap(struct page *page)
 	/*
 	 * Add it to the swap cache.
 	 */
-	err = add_to_swap_cache(page, entry,
-			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
+	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
@@ -217,56 +203,88 @@ int add_to_swap(struct page *page)
 		 */
 		goto fail;
 	/*
-	 * Normally the page will be dirtied in unmap because its pte should be
-	 * dirty. A special case is MADV_FREE page. The page'e pte could have
-	 * dirty bit cleared but the page's SwapBacked bit is still set because
-	 * clearing the dirty bit and SwapBacked bit has no lock protected. For
-	 * such page, unmap will not set dirty bit for it, so page reclaim will
-	 * not write the page out. This can cause data corruption when the page
-	 * is swap in later. Always setting the dirty bit for the page solves
-	 * the problem.
+	 * 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.
 	 */
-	set_page_dirty(page);
+	folio_mark_dirty(folio);
 
-	return 1;
+	return true;
 
 fail:
-	put_swap_page(page, entry);
-	return 0;
+	put_swap_folio(folio, entry);
+	return false;
 }
 
 /*
- * This must be called only on pages that have
+ * This must be called only on folios that have
  * been verified to be in the swap cache and locked.
- * It will never put the page into the free list,
- * the caller has a reference on the page.
+ * It will never put the folio into the free list,
+ * the caller has a reference on the folio.
  */
-void delete_from_swap_cache(struct page *page)
+void delete_from_swap_cache(struct folio *folio)
 {
-	swp_entry_t entry = { .val = page_private(page) };
+	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(page, entry);
+	__delete_from_swap_cache(folio, entry, NULL);
 	xa_unlock_irq(&address_space->i_pages);
 
-	put_swap_page(page, entry);
-	page_ref_sub(page, hpage_nr_pages(page));
+	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 for PageSwapCache without the page lock
+ * Its ok to check the swapcache flag without the folio lock
  * here because we are going to recheck again inside
- * try_to_free_swap() _with_ the lock.
+ * folio_free_swap() _with_ the lock.
  * 					- Marcelo
  */
-static inline void free_swap_cache(struct page *page)
+void free_swap_cache(struct page *page)
 {
-	if (PageSwapCache(page) && !page_mapped(page) && trylock_page(page)) {
-		try_to_free_swap(page);
-		unlock_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);
 	}
 }
 
@@ -302,37 +320,35 @@ static inline bool swap_use_vma_readahead(void)
 }
 
 /*
- * Lookup a swap entry in the swap cache. A found page will be returned
+ * 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 page
+ * lock getting page table operations atomic even if we drop the folio
  * lock before returning.
  */
-struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,
-			       unsigned long addr)
+struct folio *swap_cache_get_folio(swp_entry_t entry,
+		struct vm_area_struct *vma, unsigned long addr)
 {
-	struct page *page;
+	struct folio *folio;
 	struct swap_info_struct *si;
 
 	si = get_swap_device(entry);
 	if (!si)
 		return NULL;
-	page = find_get_page(swap_address_space(entry), swp_offset(entry));
+	folio = filemap_get_folio(swap_address_space(entry), swp_offset(entry));
 	put_swap_device(si);
 
-	INC_CACHE_INFO(find_total);
-	if (page) {
+	if (folio) {
 		bool vma_ra = swap_use_vma_readahead();
 		bool readahead;
 
-		INC_CACHE_INFO(find_success);
 		/*
 		 * 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(PageTransCompound(page)))
-			return page;
+		if (unlikely(folio_test_large(folio)))
+			return folio;
 
-		readahead = TestClearPageReadahead(page);
+		readahead = folio_test_clear_readahead(folio);
 		if (vma && vma_ra) {
 			unsigned long ra_val;
 			int win, hits;
@@ -353,6 +369,43 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,
 		}
 	}
 
+	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;
 }
 
@@ -360,25 +413,27 @@ 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 page *found_page = NULL, *new_page = NULL;
 	struct swap_info_struct *si;
-	int err;
+	struct folio *folio;
+	void *shadow = NULL;
+
 	*new_page_allocated = false;
 
-	do {
+	for (;;) {
+		int err;
 		/*
 		 * First check the swap cache.  Since this is normally
-		 * called after lookup_swap_cache() failed, re-calling
+		 * called after swap_cache_get_folio() failed, re-calling
 		 * that would confuse statistics.
 		 */
 		si = get_swap_device(entry);
 		if (!si)
-			break;
-		found_page = find_get_page(swap_address_space(entry),
-					   swp_offset(entry));
+			return NULL;
+		folio = filemap_get_folio(swap_address_space(entry),
+						swp_offset(entry));
 		put_swap_device(si);
-		if (found_page)
-			break;
+		if (folio)
+			return folio_file_page(folio, swp_offset(entry));
 
 		/*
 		 * Just skip read ahead for unused swap slot.
@@ -389,54 +444,67 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * else swap_off will be aborted if we return NULL.
 		 */
 		if (!__swp_swapcount(entry) && swap_slot_cache_enabled)
-			break;
+			return NULL;
 
 		/*
-		 * Get a new page to read into from swap.
+		 * 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.
 		 */
-		if (!new_page) {
-			new_page = alloc_page_vma(gfp_mask, vma, addr);
-			if (!new_page)
-				break;		/* Out of memory */
-		}
+		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 == -EEXIST) {
-			/*
-			 * We might race against get_swap_page() and stumble
-			 * across a SWAP_HAS_CACHE swap_map entry whose page
-			 * has not been brought into the swapcache yet.
-			 */
-			cond_resched();
-			continue;
-		} else if (err)		/* swp entry is obsolete ? */
+		if (!err)
 			break;
 
-		/* May fail (-ENOMEM) if XArray node allocation failed. */
-		__SetPageLocked(new_page);
-		__SetPageSwapBacked(new_page);
-		err = add_to_swap_cache(new_page, entry, gfp_mask & GFP_KERNEL);
-		if (likely(!err)) {
-			/* Initiate read into locked page */
-			SetPageWorkingset(new_page);
-			lru_cache_add_anon(new_page);
-			*new_page_allocated = true;
-			return new_page;
-		}
-		__ClearPageLocked(new_page);
+		folio_put(folio);
+		if (err != -EEXIST)
+			return NULL;
+
 		/*
-		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
-		 * clear SWAP_HAS_CACHE flag.
+		 * 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.
 		 */
-		put_swap_page(new_page, entry);
-	} while (err != -ENOMEM);
+		schedule_timeout_uninterruptible(1);
+	}
 
-	if (new_page)
-		put_page(new_page);
-	return found_page;
+	/*
+	 * 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;
 }
 
 /*
@@ -446,14 +514,16 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
  * 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 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);
+		swap_readpage(retpage, do_poll, plug);
 
 	return retpage;
 }
@@ -509,10 +579,11 @@ static unsigned long swapin_nr_pages(unsigned long offset)
 		return 1;
 
 	hits = atomic_xchg(&swapin_readahead_hits, 0);
-	pages = __swapin_nr_pages(prev_offset, offset, hits, max_pages,
+	pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits,
+				  max_pages,
 				  atomic_read(&last_readahead_pages));
 	if (!hits)
-		prev_offset = offset;
+		WRITE_ONCE(prev_offset, offset);
 	atomic_set(&last_readahead_pages, pages);
 
 	return pages;
@@ -534,7 +605,7 @@ static unsigned long swapin_nr_pages(unsigned long offset)
  * This has been extended to use the NUMA policies from the mm triggering
  * the readahead.
  *
- * Caller must hold read mmap_sem if vmf->vma is not NULL.
+ * 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)
@@ -546,6 +617,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	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;
@@ -554,13 +626,6 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	if (!mask)
 		goto skip;
 
-	/* Test swap type to make sure the dereference is safe */
-	if (likely(si->flags & (SWP_BLKDEV | SWP_FS))) {
-		struct inode *inode = si->swap_file->f_mapping->host;
-		if (inode_read_congested(inode))
-			goto skip;
-	}
-
 	do_poll = false;
 	/* Read a page_cluster sized and aligned cluster around offset. */
 	start_offset = offset & ~mask;
@@ -579,7 +644,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 		if (!page)
 			continue;
 		if (page_allocated) {
-			swap_readpage(page, false);
+			swap_readpage(page, false, &splug);
 			if (offset != entry_offset) {
 				SetPageReadahead(page);
 				count_vm_event(SWAP_RA);
@@ -588,10 +653,12 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 		put_page(page);
 	}
 	blk_finish_plug(&plug);
+	swap_read_unplug(splug);
 
 	lru_add_drain();	/* Push any new pages onto the LRU now */
 skip:
-	return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll);
+	/* 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)
@@ -619,7 +686,12 @@ int init_swap_address_space(unsigned int type, unsigned long nr_pages)
 
 void exit_swap_address_space(unsigned int type)
 {
-	kvfree(swapper_spaces[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;
 }
@@ -642,7 +714,6 @@ static void swap_ra_info(struct vm_fault *vmf,
 {
 	struct vm_area_struct *vma = vmf->vma;
 	unsigned long ra_val;
-	swp_entry_t entry;
 	unsigned long faddr, pfn, fpfn;
 	unsigned long start, end;
 	pte_t *pte, *orig_pte;
@@ -660,11 +731,6 @@ static void swap_ra_info(struct vm_fault *vmf,
 
 	faddr = vmf->address;
 	orig_pte = pte = pte_offset_map(vmf->pmd, faddr);
-	entry = pte_to_swp_entry(*pte);
-	if ((unlikely(non_swap_entry(entry)))) {
-		pte_unmap(orig_pte);
-		return;
-	}
 
 	fpfn = PFN_DOWN(faddr);
 	ra_val = GET_SWAP_RA_VAL(vma);
@@ -707,29 +773,32 @@ static void swap_ra_info(struct vm_fault *vmf,
 
 /**
  * swap_vma_readahead - swap in pages in hope we need them soon
- * @entry: swap entry of this memory
+ * @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 whoes
+ * 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_sem if vmf->vma is not NULL.
+ * 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 = {0,};
+	struct vma_swap_readahead ra_info = {
+		.win = 1,
+	};
 
 	swap_ra_info(vmf, &ra_info);
 	if (ra_info.win == 1)
@@ -739,9 +808,7 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 	for (i = 0, pte = ra_info.ptes; i < ra_info.nr_pte;
 	     i++, pte++) {
 		pentry = *pte;
-		if (pte_none(pentry))
-			continue;
-		if (pte_present(pentry))
+		if (!is_swap_pte(pentry))
 			continue;
 		entry = pte_to_swp_entry(pentry);
 		if (unlikely(non_swap_entry(entry)))
@@ -751,7 +818,7 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 		if (!page)
 			continue;
 		if (page_allocated) {
-			swap_readpage(page, false);
+			swap_readpage(page, false, &splug);
 			if (i != ra_info.offset) {
 				SetPageReadahead(page);
 				count_vm_event(SWAP_RA);
@@ -760,10 +827,12 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 		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);
+				     ra_info.win == 1, NULL);
 }
 
 /**
@@ -790,31 +859,29 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 static ssize_t vma_ra_enabled_show(struct kobject *kobj,
 				     struct kobj_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%s\n", enable_vma_readahead ? "true" : "false");
+	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)
 {
-	if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1))
-		enable_vma_readahead = true;
-	else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1))
-		enable_vma_readahead = false;
-	else
-		return -EINVAL;
+	ssize_t ret;
+
+	ret = kstrtobool(buf, &enable_vma_readahead);
+	if (ret)
+		return ret;
 
 	return count;
 }
-static struct kobj_attribute vma_ra_enabled_attr =
-	__ATTR(vma_ra_enabled, 0644, vma_ra_enabled_show,
-	       vma_ra_enabled_store);
+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 struct attribute_group swap_attr_group = {
+static const struct attribute_group swap_attr_group = {
 	.attrs = swap_attrs,
 };