25 files changed, 269 insertions, 241 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index a550635ea5c3..de64ea658716 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -637,6 +637,7 @@ config DEFERRED_STRUCT_PAGE_INIT
 	depends on NO_BOOTMEM
 	depends on SPARSEMEM
 	depends on !NEED_PER_CPU_KM
+	depends on 64BIT
 	help
 	  Ordinarily all struct pages are initialised during early boot in a
 	  single thread. On very large machines this can take a considerable
diff --git a/mm/Makefile b/mm/Makefile
index 7c48e0d3d8ab..6485d5745dd7 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -32,7 +32,7 @@ ifdef CONFIG_CROSS_MEMORY_ATTACH
 mmu-$(CONFIG_MMU)	+= process_vm_access.o
 endif
 
-obj-y			:= filemap.o mempool.o oom_kill.o \
+obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
@@ -49,7 +49,6 @@ else
 	obj-y		+= bootmem.o
 endif
 
-obj-$(CONFIG_ADVISE_SYSCALLS)	+= fadvise.o
 ifdef CONFIG_MMU
 	obj-$(CONFIG_ADVISE_SYSCALLS)	+= madvise.o
 endif
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f5981e9d6ae2..8a8bb8796c6c 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -491,6 +491,7 @@ static void cgwb_release_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
 						release_work);
+	struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css);
 
 	mutex_lock(&wb->bdi->cgwb_release_mutex);
 	wb_shutdown(wb);
@@ -499,6 +500,9 @@ static void cgwb_release_workfn(struct work_struct *work)
 	css_put(wb->blkcg_css);
 	mutex_unlock(&wb->bdi->cgwb_release_mutex);
 
+	/* triggers blkg destruction if cgwb_refcnt becomes zero */
+	blkcg_cgwb_put(blkcg);
+
 	fprop_local_destroy_percpu(&wb->memcg_completions);
 	percpu_ref_exit(&wb->refcnt);
 	wb_exit(wb);
@@ -597,6 +601,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 			list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list);
 			list_add(&wb->memcg_node, memcg_cgwb_list);
 			list_add(&wb->blkcg_node, blkcg_cgwb_list);
+			blkcg_cgwb_get(blkcg);
 			css_get(memcg_css);
 			css_get(blkcg_css);
 		}
diff --git a/mm/debug.c b/mm/debug.c
index 38c926520c97..bd10aad8539a 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -114,7 +114,7 @@ EXPORT_SYMBOL(dump_vma);
 
 void dump_mm(const struct mm_struct *mm)
 {
-	pr_emerg("mm %px mmap %px seqnum %d task_size %lu\n"
+	pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n"
 #ifdef CONFIG_MMU
 		"get_unmapped_area %px\n"
 #endif
@@ -142,7 +142,7 @@ void dump_mm(const struct mm_struct *mm)
 		"tlb_flush_pending %d\n"
 		"def_flags: %#lx(%pGv)\n",
 
-		mm, mm->mmap, mm->vmacache_seqnum, mm->task_size,
+		mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size,
 #ifdef CONFIG_MMU
 		mm->get_unmapped_area,
 #endif
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 2d8376e3c640..467bcd032037 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -27,9 +27,9 @@
  * deactivate the pages and clear PG_Referenced.
  */
 
-int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
+static int generic_fadvise(struct file *file, loff_t offset, loff_t len,
+			   int advice)
 {
-	struct fd f = fdget(fd);
 	struct inode *inode;
 	struct address_space *mapping;
 	struct backing_dev_info *bdi;
@@ -37,22 +37,14 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 	pgoff_t start_index;
 	pgoff_t end_index;
 	unsigned long nrpages;
-	int ret = 0;
-
-	if (!f.file)
-		return -EBADF;
 
-	inode = file_inode(f.file);
-	if (S_ISFIFO(inode->i_mode)) {
-		ret = -ESPIPE;
-		goto out;
-	}
+	inode = file_inode(file);
+	if (S_ISFIFO(inode->i_mode))
+		return -ESPIPE;
 
-	mapping = f.file->f_mapping;
-	if (!mapping || len < 0) {
-		ret = -EINVAL;
-		goto out;
-	}
+	mapping = file->f_mapping;
+	if (!mapping || len < 0)
+		return -EINVAL;
 
 	bdi = inode_to_bdi(mapping->host);
 
@@ -67,9 +59,9 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 			/* no bad return value, but ignore advice */
 			break;
 		default:
-			ret = -EINVAL;
+			return -EINVAL;
 		}
-		goto out;
+		return 0;
 	}
 
 	/*
@@ -85,21 +77,21 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 
 	switch (advice) {
 	case POSIX_FADV_NORMAL:
-		f.file->f_ra.ra_pages = bdi->ra_pages;
-		spin_lock(&f.file->f_lock);
-		f.file->f_mode &= ~FMODE_RANDOM;
-		spin_unlock(&f.file->f_lock);
+		file->f_ra.ra_pages = bdi->ra_pages;
+		spin_lock(&file->f_lock);
+		file->f_mode &= ~FMODE_RANDOM;
+		spin_unlock(&file->f_lock);
 		break;
 	case POSIX_FADV_RANDOM:
-		spin_lock(&f.file->f_lock);
-		f.file->f_mode |= FMODE_RANDOM;
-		spin_unlock(&f.file->f_lock);
+		spin_lock(&file->f_lock);
+		file->f_mode |= FMODE_RANDOM;
+		spin_unlock(&file->f_lock);
 		break;
 	case POSIX_FADV_SEQUENTIAL:
-		f.file->f_ra.ra_pages = bdi->ra_pages * 2;
-		spin_lock(&f.file->f_lock);
-		f.file->f_mode &= ~FMODE_RANDOM;
-		spin_unlock(&f.file->f_lock);
+		file->f_ra.ra_pages = bdi->ra_pages * 2;
+		spin_lock(&file->f_lock);
+		file->f_mode &= ~FMODE_RANDOM;
+		spin_unlock(&file->f_lock);
 		break;
 	case POSIX_FADV_WILLNEED:
 		/* First and last PARTIAL page! */
@@ -115,8 +107,7 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 		 * Ignore return value because fadvise() shall return
 		 * success even if filesystem can't retrieve a hint,
 		 */
-		force_page_cache_readahead(mapping, f.file, start_index,
-					   nrpages);
+		force_page_cache_readahead(mapping, file, start_index, nrpages);
 		break;
 	case POSIX_FADV_NOREUSE:
 		break;
@@ -183,9 +174,32 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 		}
 		break;
 	default:
-		ret = -EINVAL;
+		return -EINVAL;
 	}
-out:
+	return 0;
+}
+
+int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
+{
+	if (file->f_op->fadvise)
+		return file->f_op->fadvise(file, offset, len, advice);
+
+	return generic_fadvise(file, offset, len, advice);
+}
+EXPORT_SYMBOL(vfs_fadvise);
+
+#ifdef CONFIG_ADVISE_SYSCALLS
+
+int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
+{
+	struct fd f = fdget(fd);
+	int ret;
+
+	if (!f.file)
+		return -EBADF;
+
+	ret = vfs_fadvise(f.file, offset, len, advice);
+
 	fdput(f);
 	return ret;
 }
@@ -203,3 +217,4 @@ SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice)
 }
 
 #endif
+#endif
diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index 6a473709e9b6..7405c9d89d65 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -19,7 +19,8 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 		struct gup_benchmark *gup)
 {
 	ktime_t start_time, end_time;
-	unsigned long i, nr, nr_pages, addr, next;
+	unsigned long i, nr_pages, addr, next;
+	int nr;
 	struct page **pages;
 
 	nr_pages = gup->size / PAGE_SIZE;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c3bc7e9c9a2a..deed97fba979 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -821,11 +821,11 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
 	 * but we need to be consistent with PTEs and architectures that
 	 * can't support a 'special' bit.
 	 */
-	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
+			!pfn_t_devmap(pfn));
 	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
 						(VM_PFNMAP|VM_MIXEDMAP));
 	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
-	BUG_ON(!pfn_t_devmap(pfn));
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return VM_FAULT_SIGBUS;
@@ -1780,7 +1780,7 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd)
 
 bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		  unsigned long new_addr, unsigned long old_end,
-		  pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush)
+		  pmd_t *old_pmd, pmd_t *new_pmd)
 {
 	spinlock_t *old_ptl, *new_ptl;
 	pmd_t pmd;
@@ -1811,7 +1811,7 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		if (new_ptl != old_ptl)
 			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
 		pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
-		if (pmd_present(pmd) && pmd_dirty(pmd))
+		if (pmd_present(pmd))
 			force_flush = true;
 		VM_BUG_ON(!pmd_none(*new_pmd));
 
@@ -1822,12 +1822,10 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		}
 		pmd = move_soft_dirty_pmd(pmd);
 		set_pmd_at(mm, new_addr, new_pmd, pmd);
-		if (new_ptl != old_ptl)
-			spin_unlock(new_ptl);
 		if (force_flush)
 			flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
-		else
-			*need_flush = true;
+		if (new_ptl != old_ptl)
+			spin_unlock(new_ptl);
 		spin_unlock(old_ptl);
 		return true;
 	}
@@ -2885,9 +2883,6 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	if (!(pvmw->pmd && !pvmw->pte))
 		return;
 
-	mmu_notifier_invalidate_range_start(mm, address,
-			address + HPAGE_PMD_SIZE);
-
 	flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
 	pmdval = *pvmw->pmd;
 	pmdp_invalidate(vma, address, pvmw->pmd);
@@ -2900,9 +2895,6 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	set_pmd_at(mm, address, pvmw->pmd, pmdswp);
 	page_remove_rmap(page, true);
 	put_page(page);
-
-	mmu_notifier_invalidate_range_end(mm, address,
-			address + HPAGE_PMD_SIZE);
 }
 
 void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
@@ -2931,7 +2923,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 	else
 		page_add_file_rmap(new, true);
 	set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
-	if (vma->vm_flags & VM_LOCKED)
+	if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new))
 		mlock_vma_page(new);
 	update_mmu_cache_pmd(vma, address, pvmw->pmd);
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3c21775f196b..5c390f5a5207 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3326,8 +3326,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	struct page *page;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
-	const unsigned long mmun_start = start;	/* For mmu_notifiers */
-	const unsigned long mmun_end   = end;	/* For mmu_notifiers */
+	unsigned long mmun_start = start;	/* For mmu_notifiers */
+	unsigned long mmun_end   = end;		/* For mmu_notifiers */
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
 	BUG_ON(start & ~huge_page_mask(h));
@@ -3339,6 +3339,11 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	 */
 	tlb_remove_check_page_size_change(tlb, sz);
 	tlb_start_vma(tlb, vma);
+
+	/*
+	 * If sharing possible, alert mmu notifiers of worst case.
+	 */
+	adjust_range_if_pmd_sharing_possible(vma, &mmun_start, &mmun_end);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	address = start;
 	for (; address < end; address += sz) {
@@ -3349,6 +3354,10 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, &address, ptep)) {
 			spin_unlock(ptl);
+			/*
+			 * We just unmapped a page of PMDs by clearing a PUD.
+			 * The caller's TLB flush range should cover this area.
+			 */
 			continue;
 		}
 
@@ -3431,12 +3440,23 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 {
 	struct mm_struct *mm;
 	struct mmu_gather tlb;
+	unsigned long tlb_start = start;
+	unsigned long tlb_end = end;
+
+	/*
+	 * If shared PMDs were possibly used within this vma range, adjust
+	 * start/end for worst case tlb flushing.
+	 * Note that we can not be sure if PMDs are shared until we try to
+	 * unmap pages.  However, we want to make sure TLB flushing covers
+	 * the largest possible range.
+	 */
+	adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end);
 
 	mm = vma->vm_mm;
 
-	tlb_gather_mmu(&tlb, mm, start, end);
+	tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end);
 	__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
-	tlb_finish_mmu(&tlb, start, end);
+	tlb_finish_mmu(&tlb, tlb_start, tlb_end);
 }
 
 /*
@@ -4298,11 +4318,21 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	pte_t pte;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long pages = 0;
+	unsigned long f_start = start;
+	unsigned long f_end = end;
+	bool shared_pmd = false;
+
+	/*
+	 * In the case of shared PMDs, the area to flush could be beyond
+	 * start/end.  Set f_start/f_end to cover the maximum possible
+	 * range if PMD sharing is possible.
+	 */
+	adjust_range_if_pmd_sharing_possible(vma, &f_start, &f_end);
 
 	BUG_ON(address >= end);
-	flush_cache_range(vma, address, end);
+	flush_cache_range(vma, f_start, f_end);
 
-	mmu_notifier_invalidate_range_start(mm, start, end);
+	mmu_notifier_invalidate_range_start(mm, f_start, f_end);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
 	for (; address < end; address += huge_page_size(h)) {
 		spinlock_t *ptl;
@@ -4313,6 +4343,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		if (huge_pmd_unshare(mm, &address, ptep)) {
 			pages++;
 			spin_unlock(ptl);
+			shared_pmd = true;
 			continue;
 		}
 		pte = huge_ptep_get(ptep);
@@ -4348,9 +4379,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare
 	 * may have cleared our pud entry and done put_page on the page table:
 	 * once we release i_mmap_rwsem, another task can do the final put_page
-	 * and that page table be reused and filled with junk.
+	 * and that page table be reused and filled with junk.  If we actually
+	 * did unshare a page of pmds, flush the range corresponding to the pud.
 	 */
-	flush_hugetlb_tlb_range(vma, start, end);
+	if (shared_pmd)
+		flush_hugetlb_tlb_range(vma, f_start, f_end);
+	else
+		flush_hugetlb_tlb_range(vma, start, end);
 	/*
 	 * No need to call mmu_notifier_invalidate_range() we are downgrading
 	 * page table protection not changing it to point to a new page.
@@ -4358,7 +4393,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 * See Documentation/vm/mmu_notifier.rst
 	 */
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
-	mmu_notifier_invalidate_range_end(mm, start, end);
+	mmu_notifier_invalidate_range_end(mm, f_start, f_end);
 
 	return pages << h->order;
 }
@@ -4545,13 +4580,41 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 	/*
 	 * check on proper vm_flags and page table alignment
 	 */
-	if (vma->vm_flags & VM_MAYSHARE &&
-	    vma->vm_start <= base && end <= vma->vm_end)
+	if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end))
 		return true;
 	return false;
 }
 
 /*
+ * Determine if start,end range within vma could be mapped by shared pmd.
+ * If yes, adjust start and end to cover range associated with possible
+ * shared pmd mappings.
+ */
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+	unsigned long check_addr = *start;
+
+	if (!(vma->vm_flags & VM_MAYSHARE))
+		return;
+
+	for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) {
+		unsigned long a_start = check_addr & PUD_MASK;
+		unsigned long a_end = a_start + PUD_SIZE;
+
+		/*
+		 * If sharing is possible, adjust start/end if necessary.
+		 */
+		if (range_in_vma(vma, a_start, a_end)) {
+			if (a_start < *start)
+				*start = a_start;
+			if (a_end > *end)
+				*end = a_end;
+		}
+	}
+}
+
+/*
  * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
  * and returns the corresponding pte. While this is not necessary for the
  * !shared pmd case because we can allocate the pmd later as well, it makes the
@@ -4648,6 +4711,11 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
+
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+}
 #define want_pmd_share()	(0)
 #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 9a085d525bbc..17dd883198ae 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -2097,6 +2097,11 @@ static int __init kmemleak_late_init(void)
 
 	kmemleak_initialized = 1;
 
+	dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL,
+				     &kmemleak_fops);
+	if (!dentry)
+		pr_warn("Failed to create the debugfs kmemleak file\n");
+
 	if (kmemleak_error) {
 		/*
 		 * Some error occurred and kmemleak was disabled. There is a
@@ -2108,10 +2113,6 @@ static int __init kmemleak_late_init(void)
 		return -ENOMEM;
 	}
 
-	dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL,
-				     &kmemleak_fops);
-	if (!dentry)
-		pr_warn("Failed to create the debugfs kmemleak file\n");
 	mutex_lock(&scan_mutex);
 	start_scan_thread();
 	mutex_unlock(&scan_mutex);
diff --git a/mm/madvise.c b/mm/madvise.c
index 972a9eaa898b..71d21df2a3f3 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -96,7 +96,7 @@ static long madvise_behavior(struct vm_area_struct *vma,
 		new_flags |= VM_DONTDUMP;
 		break;
 	case MADV_DODUMP:
-		if (new_flags & VM_SPECIAL) {
+		if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) {
 			error = -EINVAL;
 			goto out;
 		}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4ead5a4817de..e79cb59552d9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1701,8 +1701,6 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int
 	if (mem_cgroup_out_of_memory(memcg, mask, order))
 		return OOM_SUCCESS;
 
-	WARN(1,"Memory cgroup charge failed because of no reclaimable memory! "
-		"This looks like a misconfiguration or a kernel bug.");
 	return OOM_FAILED;
 }
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9eea6e809a4e..38d94b703e9d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1333,7 +1333,8 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 			if (__PageMovable(page))
 				return pfn;
 			if (PageHuge(page)) {
-				if (page_huge_active(page))
+				if (hugepage_migration_supported(page_hstate(page)) &&
+				    page_huge_active(page))
 					return pfn;
 				else
 					pfn = round_up(pfn + 1,
diff --git a/mm/migrate.c b/mm/migrate.c
index d6a2e89b086a..84381b55b2bd 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -275,6 +275,9 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new))
 			mlock_vma_page(new);
 
+		if (PageTransHuge(page) && PageMlocked(page))
+			clear_page_mlock(page);
+
 		/* No need to invalidate - it was non-present before */
 		update_mmu_cache(vma, pvmw.address, pvmw.pte);
 	}
@@ -1411,7 +1414,7 @@ retry:
 				 * we encounter them after the rest of the list
 				 * is processed.
 				 */
-				if (PageTransHuge(page)) {
+				if (PageTransHuge(page) && !PageHuge(page)) {
 					lock_page(page);
 					rc = split_huge_page_to_list(page, from);
 					unlock_page(page);
@@ -1855,46 +1858,6 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 	return newpage;
 }
 
-/*
- * page migration rate limiting control.
- * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs
- * window of time. Default here says do not migrate more than 1280M per second.
- */
-static unsigned int migrate_interval_millisecs __read_mostly = 100;
-static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT);
-
-/* Returns true if the node is migrate rate-limited after the update */
-static bool numamigrate_update_ratelimit(pg_data_t *pgdat,
-					unsigned long nr_pages)
-{
-	/*
-	 * Rate-limit the amount of data that is being migrated to a node.
-	 * Optimal placement is no good if the memory bus is saturated and
-	 * all the time is being spent migrating!
-	 */
-	if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) {
-		spin_lock(&pgdat->numabalancing_migrate_lock);
-		pgdat->numabalancing_migrate_nr_pages = 0;
-		pgdat->numabalancing_migrate_next_window = jiffies +
-			msecs_to_jiffies(migrate_interval_millisecs);
-		spin_unlock(&pgdat->numabalancing_migrate_lock);
-	}
-	if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) {
-		trace_mm_numa_migrate_ratelimit(current, pgdat->node_id,
-								nr_pages);
-		return true;
-	}
-
-	/*
-	 * This is an unlocked non-atomic update so errors are possible.
-	 * The consequences are failing to migrate when we potentiall should
-	 * have which is not severe enough to warrant locking. If it is ever
-	 * a problem, it can be converted to a per-cpu counter.
-	 */
-	pgdat->numabalancing_migrate_nr_pages += nr_pages;
-	return false;
-}
-
 static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 {
 	int page_lru;
@@ -1967,14 +1930,6 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 	if (page_is_file_cache(page) && PageDirty(page))
 		goto out;
 
-	/*
-	 * Rate-limit the amount of data that is being migrated to a node.
-	 * Optimal placement is no good if the memory bus is saturated and
-	 * all the time is being spent migrating!
-	 */
-	if (numamigrate_update_ratelimit(pgdat, 1))
-		goto out;
-
 	isolated = numamigrate_isolate_page(pgdat, page);
 	if (!isolated)
 		goto out;
@@ -2021,14 +1976,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	unsigned long mmun_start = address & HPAGE_PMD_MASK;
 	unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
 
-	/*
-	 * Rate-limit the amount of data that is being migrated to a node.
-	 * Optimal placement is no good if the memory bus is saturated and
-	 * all the time is being spent migrating!
-	 */
-	if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR))
-		goto out_dropref;
-
 	new_page = alloc_pages_node(node,
 		(GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
 		HPAGE_PMD_ORDER);
@@ -2125,7 +2072,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 
 out_fail:
 	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-out_dropref:
 	ptl = pmd_lock(mm, pmd);
 	if (pmd_same(*pmd, entry)) {
 		entry = pmd_modify(entry, vma->vm_page_prot);
diff --git a/mm/mmap.c b/mm/mmap.c
index 5f2b2b184c60..f7cd9cb966c0 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1410,7 +1410,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 	if (flags & MAP_FIXED_NOREPLACE) {
 		struct vm_area_struct *vma = find_vma(mm, addr);
 
-		if (vma && vma->vm_start <= addr)
+		if (vma && vma->vm_start < addr + len)
 			return -EEXIST;
 	}
 
diff --git a/mm/mremap.c b/mm/mremap.c
index 5c2e18505f75..a9617e72e6b7 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -115,7 +115,7 @@ static pte_t move_soft_dirty_pte(pte_t pte)
 static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		unsigned long old_addr, unsigned long old_end,
 		struct vm_area_struct *new_vma, pmd_t *new_pmd,
-		unsigned long new_addr, bool need_rmap_locks, bool *need_flush)
+		unsigned long new_addr, bool need_rmap_locks)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *old_pte, *new_pte, pte;
@@ -163,15 +163,17 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 
 		pte = ptep_get_and_clear(mm, old_addr, old_pte);
 		/*
-		 * If we are remapping a dirty PTE, make sure
+		 * If we are remapping a valid PTE, make sure
 		 * to flush TLB before we drop the PTL for the
-		 * old PTE or we may race with page_mkclean().
+		 * PTE.
 		 *
-		 * This check has to be done after we removed the
-		 * old PTE from page tables or another thread may
-		 * dirty it after the check and before the removal.
+		 * NOTE! Both old and new PTL matter: the old one
+		 * for racing with page_mkclean(), the new one to
+		 * make sure the physical page stays valid until
+		 * the TLB entry for the old mapping has been
+		 * flushed.
 		 */
-		if (pte_present(pte) && pte_dirty(pte))
+		if (pte_present(pte))
 			force_flush = true;
 		pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
 		pte = move_soft_dirty_pte(pte);
@@ -179,13 +181,11 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	}
 
 	arch_leave_lazy_mmu_mode();
+	if (force_flush)
+		flush_tlb_range(vma, old_end - len, old_end);
 	if (new_ptl != old_ptl)
 		spin_unlock(new_ptl);
 	pte_unmap(new_pte - 1);
-	if (force_flush)
-		flush_tlb_range(vma, old_end - len, old_end);
-	else
-		*need_flush = true;
 	pte_unmap_unlock(old_pte - 1, old_ptl);
 	if (need_rmap_locks)
 		drop_rmap_locks(vma);
@@ -198,7 +198,6 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 {
 	unsigned long extent, next, old_end;
 	pmd_t *old_pmd, *new_pmd;
-	bool need_flush = false;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
@@ -229,8 +228,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 				if (need_rmap_locks)
 					take_rmap_locks(vma);
 				moved = move_huge_pmd(vma, old_addr, new_addr,
-						    old_end, old_pmd, new_pmd,
-						    &need_flush);
+						    old_end, old_pmd, new_pmd);
 				if (need_rmap_locks)
 					drop_rmap_locks(vma);
 				if (moved)
@@ -246,10 +244,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 		if (extent > next - new_addr)
 			extent = next - new_addr;
 		move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma,
-			  new_pmd, new_addr, need_rmap_locks, &need_flush);
+			  new_pmd, new_addr, need_rmap_locks);
 	}
-	if (need_flush)
-		flush_tlb_range(vma, old_end-len, old_addr);
 
 	mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index b5b25e4dcbbb..f10aa5360616 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -522,6 +522,7 @@ bool __oom_reap_task_mm(struct mm_struct *mm)
 
 			tlb_gather_mmu(&tlb, mm, start, end);
 			if (mmu_notifier_invalidate_range_start_nonblock(mm, start, end)) {
+				tlb_finish_mmu(&tlb, start, end);
 				ret = false;
 				continue;
 			}
@@ -1103,10 +1104,17 @@ bool out_of_memory(struct oom_control *oc)
 	}
 
 	select_bad_process(oc);
-	/* Found nothing?!?! Either we hang forever, or we panic. */
-	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
+	/* Found nothing?!?! */
+	if (!oc->chosen) {
 		dump_header(oc, NULL);
-		panic("Out of memory and no killable processes...\n");
+		pr_warn("Out of memory and no killable processes...\n");
+		/*
+		 * If we got here due to an actual allocation at the
+		 * system level, we cannot survive this and will enter
+		 * an endless loop in the allocator. Bail out now.
+		 */
+		if (!is_sysrq_oom(oc) && !is_memcg_oom(oc))
+			panic("System is deadlocked on memory\n");
 	}
 	if (oc->chosen && oc->chosen != (void *)-1UL)
 		oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" :
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 05e983f42316..e2ef1c17942f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6193,17 +6193,6 @@ static unsigned long __init calc_memmap_size(unsigned long spanned_pages,
 	return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT;
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static void pgdat_init_numabalancing(struct pglist_data *pgdat)
-{
-	spin_lock_init(&pgdat->numabalancing_migrate_lock);
-	pgdat->numabalancing_migrate_nr_pages = 0;
-	pgdat->numabalancing_migrate_next_window = jiffies;
-}
-#else
-static void pgdat_init_numabalancing(struct pglist_data *pgdat) {}
-#endif
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static void pgdat_init_split_queue(struct pglist_data *pgdat)
 {
@@ -6228,7 +6217,6 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
 {
 	pgdat_resize_init(pgdat);
 
-	pgdat_init_numabalancing(pgdat);
 	pgdat_init_split_queue(pgdat);
 	pgdat_init_kcompactd(pgdat);
 
@@ -7708,6 +7696,10 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		 * handle each tail page individually in migration.
 		 */
 		if (PageHuge(page)) {
+
+			if (!hugepage_migration_supported(page_hstate(page)))
+				goto unmovable;
+
 			iter = round_up(iter + 1, 1<<compound_order(page)) - 1;
 			continue;
 		}
diff --git a/mm/percpu.c b/mm/percpu.c
index a749d4d96e3e..4b90682623e9 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1212,6 +1212,7 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk)
 {
 	if (!chunk)
 		return;
+	pcpu_mem_free(chunk->md_blocks);
 	pcpu_mem_free(chunk->bound_map);
 	pcpu_mem_free(chunk->alloc_map);
 	pcpu_mem_free(chunk);
diff --git a/mm/readahead.c b/mm/readahead.c
index a59ea70527b9..4e630143a0ba 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -20,6 +20,7 @@
 #include <linux/file.h>
 #include <linux/mm_inline.h>
 #include <linux/blk-cgroup.h>
+#include <linux/fadvise.h>
 
 #include "internal.h"
 
@@ -575,24 +576,6 @@ page_cache_async_readahead(struct address_space *mapping,
 }
 EXPORT_SYMBOL_GPL(page_cache_async_readahead);
 
-static ssize_t
-do_readahead(struct address_space *mapping, struct file *filp,
-	     pgoff_t index, unsigned long nr)
-{
-	if (!mapping || !mapping->a_ops)
-		return -EINVAL;
-
-	/*
-	 * Readahead doesn't make sense for DAX inodes, but we don't want it
-	 * to report a failure either.  Instead, we just return success and
-	 * don't do any work.
-	 */
-	if (dax_mapping(mapping))
-		return 0;
-
-	return force_page_cache_readahead(mapping, filp, index, nr);
-}
-
 ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
 {
 	ssize_t ret;
@@ -600,16 +583,22 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
 
 	ret = -EBADF;
 	f = fdget(fd);
-	if (f.file) {
-		if (f.file->f_mode & FMODE_READ) {
-			struct address_space *mapping = f.file->f_mapping;
-			pgoff_t start = offset >> PAGE_SHIFT;
-			pgoff_t end = (offset + count - 1) >> PAGE_SHIFT;
-			unsigned long len = end - start + 1;
-			ret = do_readahead(mapping, f.file, start, len);
-		}
-		fdput(f);
-	}
+	if (!f.file || !(f.file->f_mode & FMODE_READ))
+		goto out;
+
+	/*
+	 * The readahead() syscall is intended to run only on files
+	 * that can execute readahead. If readahead is not possible
+	 * on this file, then we must return -EINVAL.
+	 */
+	ret = -EINVAL;
+	if (!f.file->f_mapping || !f.file->f_mapping->a_ops ||
+	    !S_ISREG(file_inode(f.file)->i_mode))
+		goto out;
+
+	ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED);
+out:
+	fdput(f);
 	return ret;
 }
 
diff --git a/mm/rmap.c b/mm/rmap.c
index eb477809a5c0..1e79fac3186b 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1362,11 +1362,21 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	}
 
 	/*
-	 * We have to assume the worse case ie pmd for invalidation. Note that
-	 * the page can not be free in this function as call of try_to_unmap()
-	 * must hold a reference on the page.
+	 * For THP, we have to assume the worse case ie pmd for invalidation.
+	 * For hugetlb, it could be much worse if we need to do pud
+	 * invalidation in the case of pmd sharing.
+	 *
+	 * Note that the page can not be free in this function as call of
+	 * try_to_unmap() must hold a reference on the page.
 	 */
 	end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page)));
+	if (PageHuge(page)) {
+		/*
+		 * If sharing is possible, start and end will be adjusted
+		 * accordingly.
+		 */
+		adjust_range_if_pmd_sharing_possible(vma, &start, &end);
+	}
 	mmu_notifier_invalidate_range_start(vma->vm_mm, start, end);
 
 	while (page_vma_mapped_walk(&pvmw)) {
@@ -1409,6 +1419,32 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
 		address = pvmw.address;
 
+		if (PageHuge(page)) {
+			if (huge_pmd_unshare(mm, &address, pvmw.pte)) {
+				/*
+				 * huge_pmd_unshare unmapped an entire PMD
+				 * page.  There is no way of knowing exactly
+				 * which PMDs may be cached for this mm, so
+				 * we must flush them all.  start/end were
+				 * already adjusted above to cover this range.
+				 */
+				flush_cache_range(vma, start, end);
+				flush_tlb_range(vma, start, end);
+				mmu_notifier_invalidate_range(mm, start, end);
+
+				/*
+				 * The ref count of the PMD page was dropped
+				 * which is part of the way map counting
+				 * is done for shared PMDs.  Return 'true'
+				 * here.  When there is no other sharing,
+				 * huge_pmd_unshare returns false and we will
+				 * unmap the actual page and drop map count
+				 * to zero.
+				 */
+				page_vma_mapped_walk_done(&pvmw);
+				break;
+			}
+		}
 
 		if (IS_ENABLED(CONFIG_MIGRATION) &&
 		    (flags & TTU_MIGRATION) &&
diff --git a/mm/shmem.c b/mm/shmem.c
index 0376c124b043..446942677cd4 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2227,6 +2227,8 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 			mpol_shared_policy_init(&info->policy, NULL);
 			break;
 		}
+
+		lockdep_annotate_inode_mutex_key(inode);
 	} else
 		shmem_free_inode(sb);
 	return inode;
diff --git a/mm/util.c b/mm/util.c
index d2890a407332..9e3ebd2ef65f 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -435,11 +435,14 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 EXPORT_SYMBOL(kvmalloc_node);
 
 /**
- * kvfree - free memory allocated with kvmalloc
- * @addr: pointer returned by kvmalloc
+ * kvfree() - Free memory.
+ * @addr: Pointer to allocated memory.
  *
- * If the memory is allocated from vmalloc area it is freed with vfree().
- * Otherwise kfree() is used.
+ * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc().
+ * It is slightly more efficient to use kfree() or vfree() if you are certain
+ * that you know which one to use.
+ *
+ * Context: Any context except NMI.
  */
 void kvfree(const void *addr)
 {
diff --git a/mm/vmacache.c b/mm/vmacache.c
index ea517bef7dc5..cdc32a3b02fa 100644
--- a/mm/vmacache.c
+++ b/mm/vmacache.c
@@ -20,44 +20,6 @@
 #define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK)
 
 /*
- * Flush vma caches for threads that share a given mm.
- *
- * The operation is safe because the caller holds the mmap_sem
- * exclusively and other threads accessing the vma cache will
- * have mmap_sem held at least for read, so no extra locking
- * is required to maintain the vma cache.
- */
-void vmacache_flush_all(struct mm_struct *mm)
-{
-	struct task_struct *g, *p;
-
-	count_vm_vmacache_event(VMACACHE_FULL_FLUSHES);
-
-	/*
-	 * Single threaded tasks need not iterate the entire
-	 * list of process. We can avoid the flushing as well
-	 * since the mm's seqnum was increased and don't have
-	 * to worry about other threads' seqnum. Current's
-	 * flush will occur upon the next lookup.
-	 */
-	if (atomic_read(&mm->mm_users) == 1)
-		return;
-
-	rcu_read_lock();
-	for_each_process_thread(g, p) {
-		/*
-		 * Only flush the vmacache pointers as the
-		 * mm seqnum is already set and curr's will
-		 * be set upon invalidation when the next
-		 * lookup is done.
-		 */
-		if (mm == p->mm)
-			vmacache_flush(p);
-	}
-	rcu_read_unlock();
-}
-
-/*
  * This task may be accessing a foreign mm via (for example)
  * get_user_pages()->find_vma().  The vmacache is task-local and this
  * task's vmacache pertains to a different mm (ie, its own).  There is
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7e7d25504651..c5ef7240cbcb 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -476,6 +476,17 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	delta = freeable >> priority;
 	delta *= 4;
 	do_div(delta, shrinker->seeks);
+
+	/*
+	 * Make sure we apply some minimal pressure on default priority
+	 * even on small cgroups. Stale objects are not only consuming memory
+	 * by themselves, but can also hold a reference to a dying cgroup,
+	 * preventing it from being reclaimed. A dying cgroup with all
+	 * corresponding structures like per-cpu stats and kmem caches
+	 * can be really big, so it may lead to a significant waste of memory.
+	 */
+	delta = max_t(unsigned long long, delta, min(freeable, batch_size));
+
 	total_scan += delta;
 	if (total_scan < 0) {
 		pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",
@@ -569,8 +580,8 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
 			struct mem_cgroup *memcg, int priority)
 {
 	struct memcg_shrinker_map *map;
-	unsigned long freed = 0;
-	int ret, i;
+	unsigned long ret, freed = 0;
+	int i;
 
 	if (!memcg_kmem_enabled() || !mem_cgroup_online(memcg))
 		return 0;
@@ -666,9 +677,8 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 				 struct mem_cgroup *memcg,
 				 int priority)
 {
+	unsigned long ret, freed = 0;
 	struct shrinker *shrinker;
-	unsigned long freed = 0;
-	int ret;
 
 	if (!mem_cgroup_is_root(memcg))
 		return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 8ba0870ecddd..7878da76abf2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1275,6 +1275,9 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
 	"nr_tlb_remote_flush_received",
+#else
+	"", /* nr_tlb_remote_flush */
+	"", /* nr_tlb_remote_flush_received */
 #endif /* CONFIG_SMP */
 	"nr_tlb_local_flush_all",
 	"nr_tlb_local_flush_one",
@@ -1283,7 +1286,6 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_DEBUG_VM_VMACACHE
 	"vmacache_find_calls",
 	"vmacache_find_hits",
-	"vmacache_full_flushes",
 #endif
 #ifdef CONFIG_SWAP
 	"swap_ra",