1 files changed, 291 insertions, 161 deletions

diff --git a/mm/swap_state.c b/mm/swap_state.c
index dfd9a46755b..2972eee184a 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -6,41 +6,43 @@
  *
  *  Rewritten to use page cache, (C) 1998 Stephen Tweedie
  */
-#include <linux/module.h>
 #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/buffer_head.h>
 #include <linux/backing-dev.h>
+#include <linux/blkdev.h>
+#include <linux/pagevec.h>
+#include <linux/migrate.h>
+#include <linux/page_cgroup.h>
 
 #include <asm/pgtable.h>
 
 /*
  * swapper_space is a fiction, retained to simplify the path through
- * vmscan's shrink_list, to make sync_page look nicer, and to allow
- * future use of radix_tree tags in the swap cache.
+ * vmscan's shrink_page_list.
  */
-static struct address_space_operations swap_aops = {
+static const struct address_space_operations swap_aops = {
 	.writepage	= swap_writepage,
-	.sync_page	= block_sync_page,
-	.set_page_dirty	= __set_page_dirty_nobuffers,
+	.set_page_dirty	= swap_set_page_dirty,
+	.migratepage	= migrate_page,
 };
 
 static struct backing_dev_info swap_backing_dev_info = {
-	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
-	.unplug_io_fn	= swap_unplug_io_fn,
+	.name		= "swap",
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
 };
 
-struct address_space swapper_space = {
-	.page_tree	= RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
-	.tree_lock	= RW_LOCK_UNLOCKED,
-	.a_ops		= &swap_aops,
-	.i_mmap_nonlinear = LIST_HEAD_INIT(swapper_space.i_mmap_nonlinear),
-	.backing_dev_info = &swap_backing_dev_info,
+struct address_space swapper_spaces[MAX_SWAPFILES] = {
+	[0 ... MAX_SWAPFILES - 1] = {
+		.page_tree	= RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
+		.a_ops		= &swap_aops,
+		.backing_dev_info = &swap_backing_dev_info,
+	}
 };
-EXPORT_SYMBOL(swapper_space);
 
 #define INC_CACHE_INFO(x)	do { swap_cache_info.x++; } while (0)
 
@@ -49,70 +51,85 @@ static struct {
 	unsigned long del_total;
 	unsigned long find_success;
 	unsigned long find_total;
-	unsigned long noent_race;
-	unsigned long exist_race;
 } swap_cache_info;
 
+unsigned long total_swapcache_pages(void)
+{
+	int i;
+	unsigned long ret = 0;
+
+	for (i = 0; i < MAX_SWAPFILES; i++)
+		ret += swapper_spaces[i].nrpages;
+	return ret;
+}
+
+static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
+
 void show_swap_cache_info(void)
 {
-	printk("Swap cache: add %lu, delete %lu, find %lu/%lu, race %lu+%lu\n",
+	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,
-		swap_cache_info.noent_race, swap_cache_info.exist_race);
-	printk("Free swap  = %lukB\n", nr_swap_pages << (PAGE_SHIFT - 10));
+		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));
 }
 
 /*
- * __add_to_swap_cache resembles add_to_page_cache on swapper_space,
+ * __add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
  * but sets SwapCache flag and private instead of mapping and index.
  */
-static int __add_to_swap_cache(struct page *page, swp_entry_t entry,
-			       gfp_t gfp_mask)
+int __add_to_swap_cache(struct page *page, swp_entry_t entry)
 {
 	int error;
+	struct address_space *address_space;
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(PageSwapCache(page), page);
+	VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
+
+	page_cache_get(page);
+	SetPageSwapCache(page);
+	set_page_private(page, entry.val);
+
+	address_space = swap_address_space(entry);
+	spin_lock_irq(&address_space->tree_lock);
+	error = radix_tree_insert(&address_space->page_tree,
+					entry.val, page);
+	if (likely(!error)) {
+		address_space->nrpages++;
+		__inc_zone_page_state(page, NR_FILE_PAGES);
+		INC_CACHE_INFO(add_total);
+	}
+	spin_unlock_irq(&address_space->tree_lock);
 
-	BUG_ON(PageSwapCache(page));
-	BUG_ON(PagePrivate(page));
-	error = radix_tree_preload(gfp_mask);
-	if (!error) {
-		write_lock_irq(&swapper_space.tree_lock);
-		error = radix_tree_insert(&swapper_space.page_tree,
-						entry.val, page);
-		if (!error) {
-			page_cache_get(page);
-			SetPageLocked(page);
-			SetPageSwapCache(page);
-			set_page_private(page, entry.val);
-			total_swapcache_pages++;
-			pagecache_acct(1);
-		}
-		write_unlock_irq(&swapper_space.tree_lock);
-		radix_tree_preload_end();
+	if (unlikely(error)) {
+		/*
+		 * Only the context which have set SWAP_HAS_CACHE flag
+		 * would call add_to_swap_cache().
+		 * So add_to_swap_cache() doesn't returns -EEXIST.
+		 */
+		VM_BUG_ON(error == -EEXIST);
+		set_page_private(page, 0UL);
+		ClearPageSwapCache(page);
+		page_cache_release(page);
 	}
+
 	return error;
 }
 
-static int add_to_swap_cache(struct page *page, swp_entry_t entry)
+
+int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
 {
 	int error;
 
-	if (!swap_duplicate(entry)) {
-		INC_CACHE_INFO(noent_race);
-		return -ENOENT;
-	}
-	error = __add_to_swap_cache(page, entry, GFP_KERNEL);
-	/*
-	 * Anon pages are already on the LRU, we don't run lru_cache_add here.
-	 */
-	if (error) {
-		swap_free(entry);
-		if (error == -EEXIST)
-			INC_CACHE_INFO(exist_race);
-		return error;
+	error = radix_tree_maybe_preload(gfp_mask);
+	if (!error) {
+		error = __add_to_swap_cache(page, entry);
+		radix_tree_preload_end();
 	}
-	INC_CACHE_INFO(add_total);
-	return 0;
+	return error;
 }
 
 /*
@@ -121,16 +138,20 @@ static int add_to_swap_cache(struct page *page, swp_entry_t entry)
  */
 void __delete_from_swap_cache(struct page *page)
 {
-	BUG_ON(!PageLocked(page));
-	BUG_ON(!PageSwapCache(page));
-	BUG_ON(PageWriteback(page));
-	BUG_ON(PagePrivate(page));
+	swp_entry_t entry;
+	struct address_space *address_space;
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
+	VM_BUG_ON_PAGE(PageWriteback(page), page);
 
-	radix_tree_delete(&swapper_space.page_tree, page_private(page));
+	entry.val = page_private(page);
+	address_space = swap_address_space(entry);
+	radix_tree_delete(&address_space->page_tree, page_private(page));
 	set_page_private(page, 0);
 	ClearPageSwapCache(page);
-	total_swapcache_pages--;
-	pagecache_acct(-1);
+	address_space->nrpages--;
+	__dec_zone_page_state(page, NR_FILE_PAGES);
 	INC_CACHE_INFO(del_total);
 }
 
@@ -141,49 +162,48 @@ void __delete_from_swap_cache(struct page *page)
  * Allocate swap space for the page and add the page to the
  * swap cache.  Caller needs to hold the page lock. 
  */
-int add_to_swap(struct page * page)
+int add_to_swap(struct page *page, struct list_head *list)
 {
 	swp_entry_t entry;
 	int err;
 
-	if (!PageLocked(page))
-		BUG();
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(!PageUptodate(page), page);
+
+	entry = get_swap_page();
+	if (!entry.val)
+		return 0;
 
-	for (;;) {
-		entry = get_swap_page();
-		if (!entry.val)
+	if (unlikely(PageTransHuge(page)))
+		if (unlikely(split_huge_page_to_list(page, list))) {
+			swapcache_free(entry, NULL);
 			return 0;
+		}
 
+	/*
+	 * Radix-tree 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 and mark it dirty
+	 */
+	err = add_to_swap_cache(page, entry,
+			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
+
+	if (!err) {	/* Success */
+		SetPageDirty(page);
+		return 1;
+	} else {	/* -ENOMEM radix-tree allocation failure */
 		/*
-		 * Radix-tree 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 and mark it dirty
+		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
+		 * clear SWAP_HAS_CACHE flag.
 		 */
-		err = __add_to_swap_cache(page, entry,
-				GFP_ATOMIC|__GFP_NOMEMALLOC|__GFP_NOWARN);
-
-		switch (err) {
-		case 0:				/* Success */
-			SetPageUptodate(page);
-			SetPageDirty(page);
-			INC_CACHE_INFO(add_total);
-			return 1;
-		case -EEXIST:
-			/* Raced with "speculative" read_swap_cache_async */
-			INC_CACHE_INFO(exist_race);
-			swap_free(entry);
-			continue;
-		default:
-			/* -ENOMEM radix-tree allocation failure */
-			swap_free(entry);
-			return 0;
-		}
+		swapcache_free(entry, NULL);
+		return 0;
 	}
 }
 
@@ -196,63 +216,31 @@ int add_to_swap(struct page * page)
 void delete_from_swap_cache(struct page *page)
 {
 	swp_entry_t entry;
+	struct address_space *address_space;
 
 	entry.val = page_private(page);
 
-	write_lock_irq(&swapper_space.tree_lock);
+	address_space = swap_address_space(entry);
+	spin_lock_irq(&address_space->tree_lock);
 	__delete_from_swap_cache(page);
-	write_unlock_irq(&swapper_space.tree_lock);
+	spin_unlock_irq(&address_space->tree_lock);
 
-	swap_free(entry);
+	swapcache_free(entry, page);
 	page_cache_release(page);
 }
 
-/*
- * Strange swizzling function only for use by shmem_writepage
- */
-int move_to_swap_cache(struct page *page, swp_entry_t entry)
-{
-	int err = __add_to_swap_cache(page, entry, GFP_ATOMIC);
-	if (!err) {
-		remove_from_page_cache(page);
-		page_cache_release(page);	/* pagecache ref */
-		if (!swap_duplicate(entry))
-			BUG();
-		SetPageDirty(page);
-		INC_CACHE_INFO(add_total);
-	} else if (err == -EEXIST)
-		INC_CACHE_INFO(exist_race);
-	return err;
-}
-
-/*
- * Strange swizzling function for shmem_getpage (and shmem_unuse)
- */
-int move_from_swap_cache(struct page *page, unsigned long index,
-		struct address_space *mapping)
-{
-	int err = add_to_page_cache(page, mapping, index, GFP_ATOMIC);
-	if (!err) {
-		delete_from_swap_cache(page);
-		/* shift page from clean_pages to dirty_pages list */
-		ClearPageDirty(page);
-		set_page_dirty(page);
-	}
-	return err;
-}
-
 /* 
  * If we are the only user, then try to free up the swap cache. 
  * 
  * Its ok to check for PageSwapCache without the page lock
- * here because we are going to recheck again inside 
- * exclusive_swap_page() _with_ the lock. 
+ * here because we are going to recheck again inside
+ * try_to_free_swap() _with_ the lock.
  * 					- Marcelo
  */
 static inline void free_swap_cache(struct page *page)
 {
-	if (PageSwapCache(page) && !TestSetPageLocked(page)) {
-		remove_exclusive_swap_page(page);
+	if (PageSwapCache(page) && !page_mapped(page) && trylock_page(page)) {
+		try_to_free_swap(page);
 		unlock_page(page);
 	}
 }
@@ -273,17 +261,16 @@ void free_page_and_swap_cache(struct page *page)
  */
 void free_pages_and_swap_cache(struct page **pages, int nr)
 {
-	int chunk = 16;
 	struct page **pagep = pages;
 
 	lru_add_drain();
 	while (nr) {
-		int todo = min(chunk, nr);
+		int todo = min(nr, PAGEVEC_SIZE);
 		int i;
 
 		for (i = 0; i < todo; i++)
 			free_swap_cache(pagep[i]);
-		release_pages(pagep, todo, 0);
+		release_pages(pagep, todo, false);
 		pagep += todo;
 		nr -= todo;
 	}
@@ -299,10 +286,13 @@ struct page * lookup_swap_cache(swp_entry_t entry)
 {
 	struct page *page;
 
-	page = find_get_page(&swapper_space, entry.val);
+	page = find_get_page(swap_address_space(entry), entry.val);
 
-	if (page)
+	if (page) {
 		INC_CACHE_INFO(find_success);
+		if (TestClearPageReadahead(page))
+			atomic_inc(&swapin_readahead_hits);
+	}
 
 	INC_CACHE_INFO(find_total);
 	return page;
@@ -314,7 +304,7 @@ struct page * lookup_swap_cache(swp_entry_t entry)
  * 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,
+struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			struct vm_area_struct *vma, unsigned long addr)
 {
 	struct page *found_page, *new_page = NULL;
@@ -326,7 +316,8 @@ struct page *read_swap_cache_async(swp_entry_t entry,
 		 * called after lookup_swap_cache() failed, re-calling
 		 * that would confuse statistics.
 		 */
-		found_page = find_get_page(&swapper_space, entry.val);
+		found_page = find_get_page(swap_address_space(entry),
+					entry.val);
 		if (found_page)
 			break;
 
@@ -334,33 +325,172 @@ struct page *read_swap_cache_async(swp_entry_t entry,
 		 * Get a new page to read into from swap.
 		 */
 		if (!new_page) {
-			new_page = alloc_page_vma(GFP_HIGHUSER, vma, addr);
+			new_page = alloc_page_vma(gfp_mask, vma, addr);
 			if (!new_page)
 				break;		/* Out of memory */
 		}
 
 		/*
-		 * Associate the page with swap entry in the swap cache.
-		 * May fail (-ENOENT) if swap entry has been freed since
-		 * our caller observed it.  May fail (-EEXIST) if there
-		 * is already a page associated with this entry in the
-		 * swap cache: added by a racing read_swap_cache_async,
-		 * or by try_to_swap_out (or shmem_writepage) re-using
-		 * the just freed swap entry for an existing page.
-		 * May fail (-ENOMEM) if radix-tree node allocation failed.
+		 * call radix_tree_preload() while we can wait.
+		 */
+		err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL);
+		if (err)
+			break;
+
+		/*
+		 * Swap entry may have been freed since our caller observed it.
 		 */
-		err = add_to_swap_cache(new_page, entry);
-		if (!err) {
+		err = swapcache_prepare(entry);
+		if (err == -EEXIST) {
+			radix_tree_preload_end();
+			/*
+			 * 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, while
+			 * the other end is scheduled away waiting on discard
+			 * I/O completion at scan_swap_map().
+			 *
+			 * In order to avoid turning this transitory state
+			 * into a permanent loop around this -EEXIST case
+			 * if !CONFIG_PREEMPT and the I/O completion happens
+			 * to be waiting on the CPU waitqueue where we are now
+			 * busy looping, we just conditionally invoke the
+			 * scheduler here, if there are some more important
+			 * tasks to run.
+			 */
+			cond_resched();
+			continue;
+		}
+		if (err) {		/* swp entry is obsolete ? */
+			radix_tree_preload_end();
+			break;
+		}
+
+		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
+		__set_page_locked(new_page);
+		SetPageSwapBacked(new_page);
+		err = __add_to_swap_cache(new_page, entry);
+		if (likely(!err)) {
+			radix_tree_preload_end();
 			/*
 			 * Initiate read into locked page and return.
 			 */
-			lru_cache_add_active(new_page);
-			swap_readpage(NULL, new_page);
+			lru_cache_add_anon(new_page);
+			swap_readpage(new_page);
 			return new_page;
 		}
-	} while (err != -ENOENT && err != -ENOMEM);
+		radix_tree_preload_end();
+		ClearPageSwapBacked(new_page);
+		__clear_page_locked(new_page);
+		/*
+		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
+		 * clear SWAP_HAS_CACHE flag.
+		 */
+		swapcache_free(entry, NULL);
+	} while (err != -ENOMEM);
 
 	if (new_page)
 		page_cache_release(new_page);
 	return found_page;
 }
+
+static unsigned long swapin_nr_pages(unsigned long offset)
+{
+	static unsigned long prev_offset;
+	unsigned int pages, max_pages, last_ra;
+	static atomic_t last_readahead_pages;
+
+	max_pages = 1 << ACCESS_ONCE(page_cluster);
+	if (max_pages <= 1)
+		return 1;
+
+	/*
+	 * 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 = atomic_xchg(&swapin_readahead_hits, 0) + 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;
+		prev_offset = offset;
+	} 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 = atomic_read(&last_readahead_pages) / 2;
+	if (pages < last_ra)
+		pages = last_ra;
+	atomic_set(&last_readahead_pages, pages);
+
+	return pages;
+}
+
+/**
+ * swapin_readahead - swap in pages in hope we need them soon
+ * @entry: swap entry of this memory
+ * @gfp_mask: memory allocation flags
+ * @vma: user vma this address belongs to
+ * @addr: target address for mempolicy
+ *
+ * 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 down_read on the vma->vm_mm if vma is not NULL.
+ */
+struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
+			struct vm_area_struct *vma, unsigned long addr)
+{
+	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 blk_plug plug;
+
+	mask = swapin_nr_pages(offset) - 1;
+	if (!mask)
+		goto skip;
+
+	/* 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++;
+
+	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);
+		if (!page)
+			continue;
+		if (offset != entry_offset)
+			SetPageReadahead(page);
+		page_cache_release(page);
+	}
+	blk_finish_plug(&plug);
+
+	lru_add_drain();	/* Push any new pages onto the LRU now */
+skip:
+	return read_swap_cache_async(entry, gfp_mask, vma, addr);
+}