1 files changed, 32 insertions, 107 deletions

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6c67b4265..d2c37365e 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -9,7 +9,6 @@
 #include <linux/hugetlb.h>
 #include <linux/mman.h>
 #include <linux/slab.h>
-#include <linux/export.h>
 #include <linux/kernel_stat.h>
 #include <linux/swap.h>
 #include <linux/vmalloc.h>
@@ -44,6 +43,7 @@
 static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
 				 unsigned char);
 static void free_swap_count_continuations(struct swap_info_struct *);
+static sector_t map_swap_entry(swp_entry_t, struct block_device**);
 
 DEFINE_SPINLOCK(swap_lock);
 static unsigned int nr_swapfiles;
@@ -165,8 +165,6 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 	int found_extent = 0;
 
 	while (nr_pages) {
-		struct list_head *lh;
-
 		if (se->start_page <= start_page &&
 		    start_page < se->start_page + se->nr_pages) {
 			pgoff_t offset = start_page - se->start_page;
@@ -188,8 +186,7 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 				break;
 		}
 
-		lh = se->list.next;
-		se = list_entry(lh, struct swap_extent, list);
+		se = list_next_entry(se, list);
 	}
 }
 
@@ -722,60 +719,6 @@ swp_entry_t get_swap_page_of_type(int type)
 	return (swp_entry_t) {0};
 }
 
-static unsigned int find_next_to_unuse(struct swap_info_struct *si,
-					unsigned int prev, bool frontswap);
-
-void get_swap_range_of_type(int type, swp_entry_t *start, swp_entry_t *end,
-		unsigned int limit)
-{
-	struct swap_info_struct *si;
-	pgoff_t start_at;
-	unsigned int i;
-
-	*start = swp_entry(0, 0);
-	*end = swp_entry(0, 0);
-	si = swap_info[type];
-	spin_lock(&si->lock);
-	if (si && (si->flags & SWP_WRITEOK)) {
-		atomic_long_dec(&nr_swap_pages);
-		/* This is called for allocating swap entry, not cache */
-		start_at = scan_swap_map(si, 1);
-		if (start_at) {
-			unsigned long stop_at = find_next_to_unuse(si, start_at, 0);
-			if (stop_at > start_at)
-				stop_at--;
-			else
-				stop_at = si->max - 1;
-			if (stop_at - start_at + 1 > limit)
-				stop_at = min_t(unsigned int,
-						start_at + limit - 1,
-						si->max - 1);
-			/* Mark them used */
-			for (i = start_at; i <= stop_at; i++)
-				si->swap_map[i] = 1;
-			/* first page already done above */
-			si->inuse_pages += stop_at - start_at;
-
-			atomic_long_sub(stop_at - start_at, &nr_swap_pages);
-			if (start_at == si->lowest_bit)
-				si->lowest_bit = stop_at + 1;
-			if (stop_at == si->highest_bit)
-				si->highest_bit = start_at - 1;
-			if (si->inuse_pages == si->pages) {
-				si->lowest_bit = si->max;
-				si->highest_bit = 0;
-			}
-			for (i = start_at + 1; i <= stop_at; i++)
-				inc_cluster_info_page(si, si->cluster_info, i);
-			si->cluster_next = stop_at + 1;
-			*start = swp_entry(type, start_at);
-			*end = swp_entry(type, stop_at);
-		} else
-			atomic_long_inc(&nr_swap_pages);
-	}
-	spin_unlock(&si->lock);
-}
-
 static struct swap_info_struct *swap_info_get(swp_entry_t entry)
 {
 	struct swap_info_struct *p;
@@ -842,14 +785,12 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
 			count--;
 	}
 
-	if (!count)
-		mem_cgroup_uncharge_swap(entry);
-
 	usage = count | has_cache;
 	p->swap_map[offset] = usage;
 
 	/* free if no reference */
 	if (!usage) {
+		mem_cgroup_uncharge_swap(entry);
 		dec_cluster_info_page(p, p->cluster_info, offset);
 		if (offset < p->lowest_bit)
 			p->lowest_bit = offset;
@@ -957,7 +898,7 @@ int swp_swapcount(swp_entry_t entry)
 	VM_BUG_ON(page_private(page) != SWP_CONTINUED);
 
 	do {
-		page = list_entry(page->lru.next, struct page, lru);
+		page = list_next_entry(page, lru);
 		map = kmap_atomic(page);
 		tmp_count = map[offset];
 		kunmap_atomic(map);
@@ -983,6 +924,9 @@ int reuse_swap_page(struct page *page)
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	if (unlikely(PageKsm(page)))
 		return 0;
+	/* The page is part of THP and cannot be reused */
+	if (PageTransCompound(page))
+		return 0;
 	count = page_mapcount(page);
 	if (count <= 1 && PageSwapCache(page)) {
 		count += page_swapcount(page);
@@ -1062,7 +1006,7 @@ int free_swap_and_cache(swp_entry_t entry)
 		 * Also recheck PageSwapCache now page is locked (above).
 		 */
 		if (PageSwapCache(page) && !PageWriteback(page) &&
-				(!page_mapped(page) || vm_swap_full())) {
+		    (!page_mapped(page) || mem_cgroup_swap_full(page))) {
 			delete_from_swap_cache(page);
 			SetPageDirty(page);
 		}
@@ -1165,19 +1109,9 @@ unsigned int count_swap_pages(int type, int free)
 }
 #endif /* CONFIG_HIBERNATION */
 
-static inline int maybe_same_pte(pte_t pte, pte_t swp_pte)
+static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte)
 {
-#ifdef CONFIG_MEM_SOFT_DIRTY
-	/*
-	 * When pte keeps soft dirty bit the pte generated
-	 * from swap entry does not has it, still it's same
-	 * pte from logical point of view.
-	 */
-	pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte);
-	return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty);
-#else
-	return pte_same(pte, swp_pte);
-#endif
+	return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte);
 }
 
 /*
@@ -1199,14 +1133,15 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	if (unlikely(!page))
 		return -ENOMEM;
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) {
+	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL,
+				&memcg, false)) {
 		ret = -ENOMEM;
 		goto out_nolock;
 	}
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) {
-		mem_cgroup_cancel_charge(page, memcg);
+	if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) {
+		mem_cgroup_cancel_charge(page, memcg, false);
 		ret = 0;
 		goto out;
 	}
@@ -1217,11 +1152,11 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	set_pte_at(vma->vm_mm, addr, pte,
 		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
 	if (page == swapcache) {
-		page_add_anon_rmap(page, vma, addr);
-		mem_cgroup_commit_charge(page, memcg, true);
+		page_add_anon_rmap(page, vma, addr, false);
+		mem_cgroup_commit_charge(page, memcg, true, false);
 	} else { /* ksm created a completely new copy */
-		page_add_new_anon_rmap(page, vma, addr);
-		mem_cgroup_commit_charge(page, memcg, false);
+		page_add_new_anon_rmap(page, vma, addr, false);
+		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(page, vma);
 	}
 	swap_free(entry);
@@ -1263,7 +1198,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		 * swapoff spends a _lot_ of time in this loop!
 		 * Test inline before going to call unuse_pte.
 		 */
-		if (unlikely(maybe_same_pte(*pte, swp_pte))) {
+		if (unlikely(pte_same_as_swp(*pte, swp_pte))) {
 			pte_unmap(pte);
 			ret = unuse_pte(vma, pmd, addr, entry, page);
 			if (ret)
@@ -1672,7 +1607,7 @@ static void drain_mmlist(void)
  * Note that the type of this function is sector_t, but it returns page offset
  * into the bdev, not sector offset.
  */
-sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev)
+static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev)
 {
 	struct swap_info_struct *sis;
 	struct swap_extent *start_se;
@@ -1687,14 +1622,11 @@ sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev)
 	se = start_se;
 
 	for ( ; ; ) {
-		struct list_head *lh;
-
 		if (se->start_page <= offset &&
 				offset < (se->start_page + se->nr_pages)) {
 			return se->start_block + (offset - se->start_page);
 		}
-		lh = se->list.next;
-		se = list_entry(lh, struct swap_extent, list);
+		se = list_next_entry(se, list);
 		sis->curr_swap_extent = se;
 		BUG_ON(se == start_se);		/* It *must* be present */
 	}
@@ -1718,7 +1650,7 @@ static void destroy_swap_extents(struct swap_info_struct *sis)
 	while (!list_empty(&sis->first_swap_extent.list)) {
 		struct swap_extent *se;
 
-		se = list_entry(sis->first_swap_extent.list.next,
+		se = list_first_entry(&sis->first_swap_extent.list,
 				struct swap_extent, list);
 		list_del(&se->list);
 		kfree(se);
@@ -2024,9 +1956,9 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 		set_blocksize(bdev, old_block_size);
 		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
 	} else {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		inode->i_flags &= ~S_SWAPFILE;
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 	filp_close(swap_file, NULL);
 
@@ -2251,7 +2183,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 		p->flags |= SWP_BLKDEV;
 	} else if (S_ISREG(inode->i_mode)) {
 		p->bdev = inode->i_sb->s_bdev;
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		if (IS_SWAPFILE(inode))
 			return -EBUSY;
 	} else
@@ -2484,7 +2416,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	mapping = swap_file->f_mapping;
 	inode = mapping->host;
 
-	/* If S_ISREG(inode->i_mode) will do mutex_lock(&inode->i_mutex); */
+	/* If S_ISREG(inode->i_mode) will do inode_lock(inode); */
 	error = claim_swapfile(p, inode);
 	if (unlikely(error))
 		goto bad_swap;
@@ -2629,7 +2561,7 @@ bad_swap:
 	vfree(cluster_info);
 	if (swap_file) {
 		if (inode && S_ISREG(inode->i_mode)) {
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			inode = NULL;
 		}
 		filp_close(swap_file, NULL);
@@ -2642,7 +2574,7 @@ out:
 	if (name)
 		putname(name);
 	if (inode && S_ISREG(inode->i_mode))
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	return error;
 }
 
@@ -2806,14 +2738,8 @@ pgoff_t __page_file_index(struct page *page)
 	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
 	return swp_offset(swap);
 }
-
 EXPORT_SYMBOL_GPL(__page_file_index);
 
-struct swap_info_struct *get_swap_info_struct(unsigned type)
-{
-	return swap_info[type];
-}
-
 /*
  * add_swap_count_continuation - called when a swap count is duplicated
  * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's
@@ -3019,11 +2945,10 @@ static void free_swap_count_continuations(struct swap_info_struct *si)
 		struct page *head;
 		head = vmalloc_to_page(si->swap_map + offset);
 		if (page_private(head)) {
-			struct list_head *this, *next;
-			list_for_each_safe(this, next, &head->lru) {
-				struct page *page;
-				page = list_entry(this, struct page, lru);
-				list_del(this);
+			struct page *page, *next;
+
+			list_for_each_entry_safe(page, next, &head->lru, lru) {
+				list_del(&page->lru);
 				__free_page(page);
 			}
 		}