Merge 3.11-rc6 into char-misc-next

We want these fixes in this tree.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

14 files changed, 111 insertions, 70 deletions

diff --git a/mm/fremap.c b/mm/fremap.c
index 87da3590c61e..5bff08147768 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -57,17 +57,22 @@ static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long addr, unsigned long pgoff, pgprot_t prot)
 {
 	int err = -ENOMEM;
-	pte_t *pte;
+	pte_t *pte, ptfile;
 	spinlock_t *ptl;
 
 	pte = get_locked_pte(mm, addr, &ptl);
 	if (!pte)
 		goto out;
 
-	if (!pte_none(*pte))
+	ptfile = pgoff_to_pte(pgoff);
+
+	if (!pte_none(*pte)) {
+		if (pte_present(*pte) && pte_soft_dirty(*pte))
+			pte_file_mksoft_dirty(ptfile);
 		zap_pte(mm, vma, addr, pte);
+	}
 
-	set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff));
+	set_pte_at(mm, addr, pte, ptfile);
 	/*
 	 * We don't need to run update_mmu_cache() here because the "file pte"
 	 * being installed by install_file_pte() is not a real pte - it's a
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 243e710c6039..a92012a71702 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1620,7 +1620,9 @@ static void __split_huge_page_refcount(struct page *page,
 				     ((1L << PG_referenced) |
 				      (1L << PG_swapbacked) |
 				      (1L << PG_mlocked) |
-				      (1L << PG_uptodate)));
+				      (1L << PG_uptodate) |
+				      (1L << PG_active) |
+				      (1L << PG_unevictable)));
 		page_tail->flags |= (1L << PG_dirty);
 
 		/* clear PageTail before overwriting first_page */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 83aff0a4d093..b60f33080a28 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2490,7 +2490,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 
 	mm = vma->vm_mm;
 
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, start, end);
 	__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
 	tlb_finish_mmu(&tlb, start, end);
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 00a7a664b9c1..c5792a5d87ce 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3195,11 +3195,11 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
 	if (!s->memcg_params)
 		return -ENOMEM;
 
-	INIT_WORK(&s->memcg_params->destroy,
-			kmem_cache_destroy_work_func);
 	if (memcg) {
 		s->memcg_params->memcg = memcg;
 		s->memcg_params->root_cache = root_cache;
+		INIT_WORK(&s->memcg_params->destroy,
+				kmem_cache_destroy_work_func);
 	} else
 		s->memcg_params->is_root_cache = true;
 
@@ -6335,6 +6335,7 @@ static void mem_cgroup_css_offline(struct cgroup *cont)
 	mem_cgroup_invalidate_reclaim_iterators(memcg);
 	mem_cgroup_reparent_charges(memcg);
 	mem_cgroup_destroy_all_caches(memcg);
+	vmpressure_cleanup(&memcg->vmpressure);
 }
 
 static void mem_cgroup_css_free(struct cgroup *cont)
diff --git a/mm/memory.c b/mm/memory.c
index 8d9255b69ff0..b3c6bf9a398e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -209,14 +209,15 @@ static int tlb_next_batch(struct mmu_gather *tlb)
  *	tear-down from @mm. The @fullmm argument is used when @mm is without
  *	users and we're going to destroy the full address space (exit/execve).
  */
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 
-	tlb->fullmm     = fullmm;
+	/* Is it from 0 to ~0? */
+	tlb->fullmm     = !(start | (end+1));
 	tlb->need_flush_all = 0;
-	tlb->start	= -1UL;
-	tlb->end	= 0;
+	tlb->start	= start;
+	tlb->end	= end;
 	tlb->need_flush = 0;
 	tlb->local.next = NULL;
 	tlb->local.nr   = 0;
@@ -256,8 +257,6 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
 {
 	struct mmu_gather_batch *batch, *next;
 
-	tlb->start = start;
-	tlb->end   = end;
 	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */
@@ -1099,7 +1098,6 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	spinlock_t *ptl;
 	pte_t *start_pte;
 	pte_t *pte;
-	unsigned long range_start = addr;
 
 again:
 	init_rss_vec(rss);
@@ -1141,9 +1139,12 @@ again:
 				continue;
 			if (unlikely(details) && details->nonlinear_vma
 			    && linear_page_index(details->nonlinear_vma,
-						addr) != page->index)
-				set_pte_at(mm, addr, pte,
-					   pgoff_to_pte(page->index));
+						addr) != page->index) {
+				pte_t ptfile = pgoff_to_pte(page->index);
+				if (pte_soft_dirty(ptent))
+					pte_file_mksoft_dirty(ptfile);
+				set_pte_at(mm, addr, pte, ptfile);
+			}
 			if (PageAnon(page))
 				rss[MM_ANONPAGES]--;
 			else {
@@ -1202,17 +1203,25 @@ again:
 	 * and page-free while holding it.
 	 */
 	if (force_flush) {
+		unsigned long old_end;
+
 		force_flush = 0;
 
-#ifdef HAVE_GENERIC_MMU_GATHER
-		tlb->start = range_start;
+		/*
+		 * Flush the TLB just for the previous segment,
+		 * then update the range to be the remaining
+		 * TLB range.
+		 */
+		old_end = tlb->end;
 		tlb->end = addr;
-#endif
+
 		tlb_flush_mmu(tlb);
-		if (addr != end) {
-			range_start = addr;
+
+		tlb->start = addr;
+		tlb->end = old_end;
+
+		if (addr != end)
 			goto again;
-		}
 	}
 
 	return addr;
@@ -1397,7 +1406,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
 	unsigned long end = start + size;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, start, end);
 	update_hiwater_rss(mm);
 	mmu_notifier_invalidate_range_start(mm, start, end);
 	for ( ; vma && vma->vm_start < end; vma = vma->vm_next)
@@ -1423,7 +1432,7 @@ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long addr
 	unsigned long end = address + size;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, address, end);
 	update_hiwater_rss(mm);
 	mmu_notifier_invalidate_range_start(mm, address, end);
 	unmap_single_vma(&tlb, vma, address, end, details);
@@ -3115,6 +3124,8 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		exclusive = 1;
 	}
 	flush_icache_page(vma, page);
+	if (pte_swp_soft_dirty(orig_pte))
+		pte = pte_mksoft_dirty(pte);
 	set_pte_at(mm, address, page_table, pte);
 	if (page == swapcache)
 		do_page_add_anon_rmap(page, vma, address, exclusive);
@@ -3408,6 +3419,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		entry = mk_pte(page, vma->vm_page_prot);
 		if (flags & FAULT_FLAG_WRITE)
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		else if (pte_file(orig_pte) && pte_file_soft_dirty(orig_pte))
+			pte_mksoft_dirty(entry);
 		if (anon) {
 			inc_mm_counter_fast(mm, MM_ANONPAGES);
 			page_add_new_anon_rmap(page, vma, address);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 74310017296e..4baf12e534d1 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -732,7 +732,10 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 		if (prev) {
 			vma = prev;
 			next = vma->vm_next;
-			continue;
+			if (mpol_equal(vma_policy(vma), new_pol))
+				continue;
+			/* vma_merge() joined vma && vma->next, case 8 */
+			goto replace;
 		}
 		if (vma->vm_start != vmstart) {
 			err = split_vma(vma->vm_mm, vma, vmstart, 1);
@@ -744,6 +747,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 			if (err)
 				goto out;
 		}
+ replace:
 		err = vma_replace_policy(vma, new_pol);
 		if (err)
 			goto out;
diff --git a/mm/mmap.c b/mm/mmap.c
index fbad7b091090..f9c97d10b873 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -865,7 +865,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 		if (next->anon_vma)
 			anon_vma_merge(vma, next);
 		mm->map_count--;
-		vma_set_policy(vma, vma_policy(next));
+		mpol_put(vma_policy(next));
 		kmem_cache_free(vm_area_cachep, next);
 		/*
 		 * In mprotect's case 6 (see comments on vma_merge),
@@ -2336,7 +2336,7 @@ static void unmap_region(struct mm_struct *mm,
 	struct mmu_gather tlb;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, start, end);
 	update_hiwater_rss(mm);
 	unmap_vmas(&tlb, vma, start, end);
 	free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
@@ -2709,7 +2709,7 @@ void exit_mmap(struct mm_struct *mm)
 
 	lru_add_drain();
 	flush_cache_mm(mm);
-	tlb_gather_mmu(&tlb, mm, 1);
+	tlb_gather_mmu(&tlb, mm, 0, -1);
 	/* update_hiwater_rss(mm) here? but nobody should be looking */
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	unmap_vmas(&tlb, vma, 0, -1);
diff --git a/mm/rmap.c b/mm/rmap.c
index cd356df4f71a..b2e29acd7e3d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1236,6 +1236,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			   swp_entry_to_pte(make_hwpoison_entry(page)));
 	} else if (PageAnon(page)) {
 		swp_entry_t entry = { .val = page_private(page) };
+		pte_t swp_pte;
 
 		if (PageSwapCache(page)) {
 			/*
@@ -1264,7 +1265,10 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION);
 			entry = make_migration_entry(page, pte_write(pteval));
 		}
-		set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
+		swp_pte = swp_entry_to_pte(entry);
+		if (pte_soft_dirty(pteval))
+			swp_pte = pte_swp_mksoft_dirty(swp_pte);
+		set_pte_at(mm, address, pte, swp_pte);
 		BUG_ON(pte_file(*pte));
 	} else if (IS_ENABLED(CONFIG_MIGRATION) &&
 		   (TTU_ACTION(flags) == TTU_MIGRATION)) {
@@ -1401,8 +1405,12 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 		pteval = ptep_clear_flush(vma, address, pte);
 
 		/* If nonlinear, store the file page offset in the pte. */
-		if (page->index != linear_page_index(vma, address))
-			set_pte_at(mm, address, pte, pgoff_to_pte(page->index));
+		if (page->index != linear_page_index(vma, address)) {
+			pte_t ptfile = pgoff_to_pte(page->index);
+			if (pte_soft_dirty(pteval))
+				pte_file_mksoft_dirty(ptfile);
+			set_pte_at(mm, address, pte, ptfile);
+		}
 
 		/* Move the dirty bit to the physical page now the pte is gone. */
 		if (pte_dirty(pteval))
diff --git a/mm/shmem.c b/mm/shmem.c
index a87990cf9f94..8335dbd3fc35 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1798,7 +1798,8 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 		}
 	}
 
-	offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE);
+	if (offset >= 0)
+		offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE);
 	mutex_unlock(&inode->i_mutex);
 	return offset;
 }
diff --git a/mm/slub.c b/mm/slub.c
index 2b02d666bf63..e3ba1f2cf60c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1968,9 +1968,6 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 	int pages;
 	int pobjects;
 
-	if (!s->cpu_partial)
-		return;
-
 	do {
 		pages = 0;
 		pobjects = 0;
diff --git a/mm/swap.c b/mm/swap.c
index 4a1d0d2c52fa..62b78a6e224f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -512,12 +512,7 @@ EXPORT_SYMBOL(__lru_cache_add);
  */
 void lru_cache_add(struct page *page)
 {
-	if (PageActive(page)) {
-		VM_BUG_ON(PageUnevictable(page));
-	} else if (PageUnevictable(page)) {
-		VM_BUG_ON(PageActive(page));
-	}
-
+	VM_BUG_ON(PageActive(page) && PageUnevictable(page));
 	VM_BUG_ON(PageLRU(page));
 	__lru_cache_add(page);
 }
@@ -539,6 +534,7 @@ void add_page_to_unevictable_list(struct page *page)
 
 	spin_lock_irq(&zone->lru_lock);
 	lruvec = mem_cgroup_page_lruvec(page, zone);
+	ClearPageActive(page);
 	SetPageUnevictable(page);
 	SetPageLRU(page);
 	add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE);
@@ -774,8 +770,6 @@ EXPORT_SYMBOL(__pagevec_release);
 void lru_add_page_tail(struct page *page, struct page *page_tail,
 		       struct lruvec *lruvec, struct list_head *list)
 {
-	int uninitialized_var(active);
-	enum lru_list lru;
 	const int file = 0;
 
 	VM_BUG_ON(!PageHead(page));
@@ -787,20 +781,6 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
 	if (!list)
 		SetPageLRU(page_tail);
 
-	if (page_evictable(page_tail)) {
-		if (PageActive(page)) {
-			SetPageActive(page_tail);
-			active = 1;
-			lru = LRU_ACTIVE_ANON;
-		} else {
-			active = 0;
-			lru = LRU_INACTIVE_ANON;
-		}
-	} else {
-		SetPageUnevictable(page_tail);
-		lru = LRU_UNEVICTABLE;
-	}
-
 	if (likely(PageLRU(page)))
 		list_add_tail(&page_tail->lru, &page->lru);
 	else if (list) {
@@ -816,13 +796,13 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
 		 * Use the standard add function to put page_tail on the list,
 		 * but then correct its position so they all end up in order.
 		 */
-		add_page_to_lru_list(page_tail, lruvec, lru);
+		add_page_to_lru_list(page_tail, lruvec, page_lru(page_tail));
 		list_head = page_tail->lru.prev;
 		list_move_tail(&page_tail->lru, list_head);
 	}
 
 	if (!PageUnevictable(page))
-		update_page_reclaim_stat(lruvec, file, active);
+		update_page_reclaim_stat(lruvec, file, PageActive(page_tail));
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
@@ -833,7 +813,6 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
 	int active = PageActive(page);
 	enum lru_list lru = page_lru(page);
 
-	VM_BUG_ON(PageUnevictable(page));
 	VM_BUG_ON(PageLRU(page));
 
 	SetPageLRU(page);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 36af6eeaa67e..6cf2e60983b7 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -866,6 +866,21 @@ 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)
+{
+#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
+}
+
 /*
  * No need to decide whether this PTE shares the swap entry with others,
  * just let do_wp_page work it out if a write is requested later - to
@@ -892,7 +907,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	}
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
+	if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) {
 		mem_cgroup_cancel_charge_swapin(memcg);
 		ret = 0;
 		goto out;
@@ -947,7 +962,7 @@ 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(pte_same(*pte, swp_pte))) {
+		if (unlikely(maybe_same_pte(*pte, swp_pte))) {
 			pte_unmap(pte);
 			ret = unuse_pte(vma, pmd, addr, entry, page);
 			if (ret)
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 736a6011c2c8..0c1e37d829fa 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -180,12 +180,12 @@ static void vmpressure_work_fn(struct work_struct *work)
 	if (!vmpr->scanned)
 		return;
 
-	mutex_lock(&vmpr->sr_lock);
+	spin_lock(&vmpr->sr_lock);
 	scanned = vmpr->scanned;
 	reclaimed = vmpr->reclaimed;
 	vmpr->scanned = 0;
 	vmpr->reclaimed = 0;
-	mutex_unlock(&vmpr->sr_lock);
+	spin_unlock(&vmpr->sr_lock);
 
 	do {
 		if (vmpressure_event(vmpr, scanned, reclaimed))
@@ -240,13 +240,13 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg,
 	if (!scanned)
 		return;
 
-	mutex_lock(&vmpr->sr_lock);
+	spin_lock(&vmpr->sr_lock);
 	vmpr->scanned += scanned;
 	vmpr->reclaimed += reclaimed;
 	scanned = vmpr->scanned;
-	mutex_unlock(&vmpr->sr_lock);
+	spin_unlock(&vmpr->sr_lock);
 
-	if (scanned < vmpressure_win || work_pending(&vmpr->work))
+	if (scanned < vmpressure_win)
 		return;
 	schedule_work(&vmpr->work);
 }
@@ -367,8 +367,24 @@ void vmpressure_unregister_event(struct cgroup *cg, struct cftype *cft,
  */
 void vmpressure_init(struct vmpressure *vmpr)
 {
-	mutex_init(&vmpr->sr_lock);
+	spin_lock_init(&vmpr->sr_lock);
 	mutex_init(&vmpr->events_lock);
 	INIT_LIST_HEAD(&vmpr->events);
 	INIT_WORK(&vmpr->work, vmpressure_work_fn);
 }
+
+/**
+ * vmpressure_cleanup() - shuts down vmpressure control structure
+ * @vmpr:	Structure to be cleaned up
+ *
+ * This function should be called before the structure in which it is
+ * embedded is cleaned up.
+ */
+void vmpressure_cleanup(struct vmpressure *vmpr)
+{
+	/*
+	 * Make sure there is no pending work before eventfd infrastructure
+	 * goes away.
+	 */
+	flush_work(&vmpr->work);
+}
diff --git a/mm/zbud.c b/mm/zbud.c
index 9bb4710e3589..ad1e781284fd 100644
--- a/mm/zbud.c
+++ b/mm/zbud.c
@@ -257,7 +257,7 @@ int zbud_alloc(struct zbud_pool *pool, int size, gfp_t gfp,
 
 	if (size <= 0 || gfp & __GFP_HIGHMEM)
 		return -EINVAL;
-	if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED)
+	if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE)
 		return -ENOSPC;
 	chunks = size_to_chunks(size);
 	spin_lock(&pool->lock);