Merge branch 'android-4.4-p' of https://android.googlesource.com/kernel/common into lineage-18.1-caf-msm8998

This brings LA.UM.9.2.r1-02700-SDMxx0.0 up to date with
https://android.googlesource.com/kernel/common/ android-4.4-p at commit:
58bc8e0469d08 Merge 4.4.261 into android-4.4-p

Conflicts:
	drivers/block/zram/zram_drv.c
	drivers/block/zram/zram_drv.h
	mm/zsmalloc.c

Change-Id: I451bffa685eaaea04938bc6d0b8e3f4bb0f869e9

5 files changed, 76 insertions, 31 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index dc877712ef1f..e933cae307bf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -66,6 +66,21 @@ DEFINE_SPINLOCK(hugetlb_lock);
 static int num_fault_mutexes;
 struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
 
+static inline bool PageHugeFreed(struct page *head)
+{
+	return page_private(head + 4) == -1UL;
+}
+
+static inline void SetPageHugeFreed(struct page *head)
+{
+	set_page_private(head + 4, -1UL);
+}
+
+static inline void ClearPageHugeFreed(struct page *head)
+{
+	set_page_private(head + 4, 0);
+}
+
 /* Forward declaration */
 static int hugetlb_acct_memory(struct hstate *h, long delta);
 
@@ -841,6 +856,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 	list_move(&page->lru, &h->hugepage_freelists[nid]);
 	h->free_huge_pages++;
 	h->free_huge_pages_node[nid]++;
+	SetPageHugeFreed(page);
 }
 
 static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
@@ -858,6 +874,7 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
 		return NULL;
 	list_move(&page->lru, &h->hugepage_activelist);
 	set_page_refcounted(page);
+	ClearPageHugeFreed(page);
 	h->free_huge_pages--;
 	h->free_huge_pages_node[nid]--;
 	return page;
@@ -1142,14 +1159,16 @@ static inline int alloc_fresh_gigantic_page(struct hstate *h,
 static void update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
+	struct page *subpage = page;
 
 	if (hstate_is_gigantic(h) && !gigantic_page_supported())
 		return;
 
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[page_to_nid(page)]--;
-	for (i = 0; i < pages_per_huge_page(h); i++) {
-		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
+	for (i = 0; i < pages_per_huge_page(h);
+	     i++, subpage = mem_map_next(subpage, page, i)) {
+		subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
 				1 << PG_referenced | 1 << PG_dirty |
 				1 << PG_active | 1 << PG_private |
 				1 << PG_writeback);
@@ -1266,6 +1285,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	set_hugetlb_cgroup(page, NULL);
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
+	ClearPageHugeFreed(page);
 	spin_unlock(&hugetlb_lock);
 	put_page(page); /* free it into the hugepage allocator */
 }
@@ -1424,11 +1444,32 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
  */
 static void dissolve_free_huge_page(struct page *page)
 {
+retry:
 	spin_lock(&hugetlb_lock);
 	if (PageHuge(page) && !page_count(page)) {
 		struct page *head = compound_head(page);
 		struct hstate *h = page_hstate(head);
 		int nid = page_to_nid(head);
+
+		/*
+		 * We should make sure that the page is already on the free list
+		 * when it is dissolved.
+		 */
+		if (unlikely(!PageHugeFreed(head))) {
+			spin_unlock(&hugetlb_lock);
+			cond_resched();
+
+			/*
+			 * Theoretically, we should return -EBUSY when we
+			 * encounter this race. In fact, we have a chance
+			 * to successfully dissolve the page if we do a
+			 * retry. Because the race window is quite small.
+			 * If we seize this opportunity, it is an optimization
+			 * for increasing the success rate of dissolving page.
+			 */
+			goto retry;
+		}
+
 		list_del(&head->lru);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
@@ -2485,8 +2526,10 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
 		return -ENOMEM;
 
 	retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group);
-	if (retval)
+	if (retval) {
 		kobject_put(hstate_kobjs[hi]);
+		hstate_kobjs[hi] = NULL;
+	}
 
 	return retval;
 }
@@ -4279,21 +4322,23 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end)
 {
-	unsigned long a_start, a_end;
+	unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE),
+		v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
 
-	if (!(vma->vm_flags & VM_MAYSHARE))
+	/*
+	 * vma need span at least one aligned PUD size and the start,end range
+	 * must at least partialy within it.
+	 */
+	if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) ||
+		(*end <= v_start) || (*start >= v_end))
 		return;
 
 	/* Extend the range to be PUD aligned for a worst case scenario */
-	a_start = ALIGN_DOWN(*start, PUD_SIZE);
-	a_end = ALIGN(*end, PUD_SIZE);
+	if (*start > v_start)
+		*start = ALIGN_DOWN(*start, PUD_SIZE);
 
-	/*
-	 * Intersect the range with the vma range, since pmd sharing won't be
-	 * across vma after all
-	 */
-	*start = max(vma->vm_start, a_start);
-	*end = min(vma->vm_end, a_end);
+	if (*end < v_end)
+		*end = ALIGN(*end, PUD_SIZE);
 }
 
 /*
diff --git a/mm/memory.c b/mm/memory.c
index 5dfc9fac8b74..8e41c675f7af 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1686,11 +1686,11 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 			unsigned long addr, unsigned long end,
 			unsigned long pfn, pgprot_t prot)
 {
-	pte_t *pte;
+	pte_t *pte, *mapped_pte;
 	spinlock_t *ptl;
 	int err = 0;
 
-	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
+	mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
 		return -ENOMEM;
 	arch_enter_lazy_mmu_mode();
@@ -1704,7 +1704,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
-	pte_unmap_unlock(pte - 1, ptl);
+	pte_unmap_unlock(mapped_pte, ptl);
 	return err;
 }
 
diff --git a/mm/page_io.c b/mm/page_io.c
index b995a5ba5e8f..ab92cd559404 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -32,7 +32,6 @@ static struct bio *get_swap_bio(gfp_t gfp_flags,
 	bio = bio_alloc(gfp_flags, 1);
 	if (bio) {
 		bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev);
-		bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
 		bio->bi_end_io = end_io;
 
 		bio_add_page(bio, page, PAGE_SIZE, 0);
@@ -244,11 +243,6 @@ out:
 	return ret;
 }
 
-static sector_t swap_page_sector(struct page *page)
-{
-	return (sector_t)__page_file_index(page) << (PAGE_CACHE_SHIFT - 9);
-}
-
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		bio_end_io_t end_write_func)
 {
@@ -297,7 +291,8 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		return ret;
 	}
 
-	ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc);
+	ret = bdev_write_page(sis->bdev, map_swap_page(page, &sis->bdev),
+			      page, wbc);
 	if (!ret) {
 		count_vm_event(PSWPOUT);
 		return 0;
@@ -345,7 +340,7 @@ int swap_readpage(struct page *page)
 		return ret;
 	}
 
-	ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
+	ret = bdev_read_page(sis->bdev, map_swap_page(page, &sis->bdev), page);
 	if (!ret) {
 		count_vm_event(PSWPIN);
 		return 0;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index feb9abb8e8cc..204224d8e0d1 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1710,7 +1710,7 @@ sector_t map_swap_page(struct page *page, struct block_device **bdev)
 {
 	swp_entry_t entry;
 	entry.val = page_private(page);
-	return map_swap_entry(entry, bdev);
+	return map_swap_entry(entry, bdev) << (PAGE_SHIFT - 9);
 }
 
 /*
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 3f1b584bd5d0..174c08cf5270 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -2284,11 +2284,13 @@ static unsigned long zs_can_compact(struct size_class *class)
 	return obj_wasted * class->pages_per_zspage;
 }
 
-static void __zs_compact(struct zs_pool *pool, struct size_class *class)
+static unsigned long __zs_compact(struct zs_pool *pool,
+				   struct size_class *class)
 {
 	struct zs_compact_control cc;
 	struct zspage *src_zspage;
 	struct zspage *dst_zspage = NULL;
+	unsigned long pages_freed = 0;
 
 	spin_lock(&class->lock);
 	while ((src_zspage = isolate_zspage(class, true))) {
@@ -2318,7 +2320,7 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class)
 		putback_zspage(class, dst_zspage);
 		if (putback_zspage(class, src_zspage) == ZS_EMPTY) {
 			free_zspage(pool, class, src_zspage);
-			pool->stats.pages_compacted += class->pages_per_zspage;
+			pages_freed += class->pages_per_zspage;
 		}
 		spin_unlock(&class->lock);
 		cond_resched();
@@ -2329,12 +2331,15 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class)
 		putback_zspage(class, src_zspage);
 
 	spin_unlock(&class->lock);
+
+	return pages_freed;
 }
 
 unsigned long zs_compact(struct zs_pool *pool)
 {
 	int i;
 	struct size_class *class;
+	unsigned long pages_freed = 0;
 
 	for (i = zs_size_classes - 1; i >= 0; i--) {
 		class = pool->size_class[i];
@@ -2342,10 +2347,11 @@ unsigned long zs_compact(struct zs_pool *pool)
 			continue;
 		if (class->index != i)
 			continue;
-		__zs_compact(pool, class);
+		pages_freed += __zs_compact(pool, class);
 	}
+	atomic_long_add(pages_freed, &pool->stats.pages_compacted);
 
-	return pool->stats.pages_compacted;
+	return pages_freed;
 }
 EXPORT_SYMBOL_GPL(zs_compact);
 
@@ -2362,13 +2368,12 @@ static unsigned long zs_shrinker_scan(struct shrinker *shrinker,
 	struct zs_pool *pool = container_of(shrinker, struct zs_pool,
 			shrinker);
 
-	pages_freed = pool->stats.pages_compacted;
 	/*
 	 * Compact classes and calculate compaction delta.
 	 * Can run concurrently with a manually triggered
 	 * (by user) compaction.
 	 */
-	pages_freed = zs_compact(pool) - pages_freed;
+	pages_freed = zs_compact(pool);
 
 	return pages_freed ? pages_freed : SHRINK_STOP;
 }