Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - v9fs updates

 - MM

 - procfs updates

 - lib/ updates

 - autofs updates

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  autofs: small cleanup in autofs_getpath()
  autofs: clean up includes
  autofs: comment on selinux changes needed for module autoload
  autofs: update MAINTAINERS entry for autofs
  autofs: use autofs instead of autofs4 in documentation
  autofs: rename autofs documentation files
  autofs: create autofs Kconfig and Makefile
  autofs: delete fs/autofs4 source files
  autofs: update fs/autofs4/Makefile
  autofs: update fs/autofs4/Kconfig
  autofs: copy autofs4 to autofs
  autofs4: use autofs instead of autofs4 everywhere
  autofs4: merge auto_fs.h and auto_fs4.h
  fs/binfmt_misc.c: do not allow offset overflow
  checkpatch: improve patch recognition
  lib/ucs2_string.c: add MODULE_LICENSE()
  lib/mpi: headers cleanup
  lib/percpu_ida.c: use _irqsave() instead of local_irq_save() + spin_lock
  lib/idr.c: remove simple_ida_lock
  lib/bitmap.c: micro-optimization for __bitmap_complement()
  ...

32 files changed, 1008 insertions, 737 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 3e0b6e87f65d..00bffa7a5112 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -754,3 +754,6 @@ config GUP_BENCHMARK
 	  performance of get_user_pages_fast().
 
 	  See tools/testing/selftests/vm/gup_benchmark.c
+
+config ARCH_HAS_PTE_SPECIAL
+	bool
diff --git a/mm/Makefile b/mm/Makefile
index b4e54a9ae9c5..8716bdabe1e6 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -105,3 +105,4 @@ obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o
 obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
 obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o
 obj-$(CONFIG_HMM) += hmm.o
+obj-$(CONFIG_MEMFD_CREATE) += memfd.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 8fe3ebd6ac00..347cc834c04a 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -557,7 +557,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 	memcg = mem_cgroup_from_css(memcg_css);
 	blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys);
 	blkcg = css_to_blkcg(blkcg_css);
-	memcg_cgwb_list = mem_cgroup_cgwb_list(memcg);
+	memcg_cgwb_list = &memcg->cgwb_list;
 	blkcg_cgwb_list = &blkcg->cgwb_list;
 
 	/* look up again under lock and discard on blkcg mismatch */
@@ -736,7 +736,7 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi)
  */
 void wb_memcg_offline(struct mem_cgroup *memcg)
 {
-	struct list_head *memcg_cgwb_list = mem_cgroup_cgwb_list(memcg);
+	struct list_head *memcg_cgwb_list = &memcg->cgwb_list;
 	struct bdi_writeback *wb, *next;
 
 	spin_lock_irq(&cgwb_lock);
diff --git a/mm/filemap.c b/mm/filemap.c
index 0604cb02e6f3..52517f28e6f4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2489,7 +2489,7 @@ static void do_async_mmap_readahead(struct vm_area_struct *vma,
  *
  * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set.
  */
-int filemap_fault(struct vm_fault *vmf)
+vm_fault_t filemap_fault(struct vm_fault *vmf)
 {
 	int error;
 	struct file *file = vmf->vma->vm_file;
@@ -2499,7 +2499,7 @@ int filemap_fault(struct vm_fault *vmf)
 	pgoff_t offset = vmf->pgoff;
 	pgoff_t max_off;
 	struct page *page;
-	int ret = 0;
+	vm_fault_t ret = 0;
 
 	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 	if (unlikely(offset >= max_off))
@@ -2693,11 +2693,11 @@ next:
 }
 EXPORT_SYMBOL(filemap_map_pages);
 
-int filemap_page_mkwrite(struct vm_fault *vmf)
+vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
-	int ret = VM_FAULT_LOCKED;
+	vm_fault_t ret = VM_FAULT_LOCKED;
 
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vmf->vma->vm_file);
diff --git a/mm/gup.c b/mm/gup.c
index 541904a7c60f..1020c7f8f5ee 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -212,53 +212,69 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 				    unsigned long address, pud_t *pudp,
 				    unsigned int flags, unsigned int *page_mask)
 {
-	pmd_t *pmd;
+	pmd_t *pmd, pmdval;
 	spinlock_t *ptl;
 	struct page *page;
 	struct mm_struct *mm = vma->vm_mm;
 
 	pmd = pmd_offset(pudp, address);
-	if (pmd_none(*pmd))
+	/*
+	 * The READ_ONCE() will stabilize the pmdval in a register or
+	 * on the stack so that it will stop changing under the code.
+	 */
+	pmdval = READ_ONCE(*pmd);
+	if (pmd_none(pmdval))
 		return no_page_table(vma, flags);
-	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
+	if (pmd_huge(pmdval) && vma->vm_flags & VM_HUGETLB) {
 		page = follow_huge_pmd(mm, address, pmd, flags);
 		if (page)
 			return page;
 		return no_page_table(vma, flags);
 	}
-	if (is_hugepd(__hugepd(pmd_val(*pmd)))) {
+	if (is_hugepd(__hugepd(pmd_val(pmdval)))) {
 		page = follow_huge_pd(vma, address,
-				      __hugepd(pmd_val(*pmd)), flags,
+				      __hugepd(pmd_val(pmdval)), flags,
 				      PMD_SHIFT);
 		if (page)
 			return page;
 		return no_page_table(vma, flags);
 	}
 retry:
-	if (!pmd_present(*pmd)) {
+	if (!pmd_present(pmdval)) {
 		if (likely(!(flags & FOLL_MIGRATION)))
 			return no_page_table(vma, flags);
 		VM_BUG_ON(thp_migration_supported() &&
-				  !is_pmd_migration_entry(*pmd));
-		if (is_pmd_migration_entry(*pmd))
+				  !is_pmd_migration_entry(pmdval));
+		if (is_pmd_migration_entry(pmdval))
 			pmd_migration_entry_wait(mm, pmd);
+		pmdval = READ_ONCE(*pmd);
+		/*
+		 * MADV_DONTNEED may convert the pmd to null because
+		 * mmap_sem is held in read mode
+		 */
+		if (pmd_none(pmdval))
+			return no_page_table(vma, flags);
 		goto retry;
 	}
-	if (pmd_devmap(*pmd)) {
+	if (pmd_devmap(pmdval)) {
 		ptl = pmd_lock(mm, pmd);
 		page = follow_devmap_pmd(vma, address, pmd, flags);
 		spin_unlock(ptl);
 		if (page)
 			return page;
 	}
-	if (likely(!pmd_trans_huge(*pmd)))
+	if (likely(!pmd_trans_huge(pmdval)))
 		return follow_page_pte(vma, address, pmd, flags);
 
-	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
+	if ((flags & FOLL_NUMA) && pmd_protnone(pmdval))
 		return no_page_table(vma, flags);
 
 retry_locked:
 	ptl = pmd_lock(mm, pmd);
+	if (unlikely(pmd_none(*pmd))) {
+		spin_unlock(ptl);
+		return no_page_table(vma, flags);
+	}
 	if (unlikely(!pmd_present(*pmd))) {
 		spin_unlock(ptl);
 		if (likely(!(flags & FOLL_MIGRATION)))
@@ -1354,7 +1370,7 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
 	}
 }
 
-#ifdef __HAVE_ARCH_PTE_SPECIAL
+#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			 int write, struct page **pages, int *nr)
 {
@@ -1430,7 +1446,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 {
 	return 0;
 }
-#endif /* __HAVE_ARCH_PTE_SPECIAL */
+#endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
 
 #if defined(__HAVE_ARCH_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
 static int __gup_device_huge(unsigned long pfn, unsigned long addr,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ac5591d8622c..ba8fdc0b6e7f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -483,11 +483,8 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 
 static inline struct list_head *page_deferred_list(struct page *page)
 {
-	/*
-	 * ->lru in the tail pages is occupied by compound_head.
-	 * Let's use ->mapping + ->index in the second tail page as list_head.
-	 */
-	return (struct list_head *)&page[2].mapping;
+	/* ->lru in the tail pages is occupied by compound_head. */
+	return &page[2].deferred_list;
 }
 
 void prep_transhuge_page(struct page *page)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 129088710510..696befffe6f7 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3159,7 +3159,7 @@ static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma)
  * hugegpage VMA.  do_page_fault() is supposed to trap this, so BUG is we get
  * this far.
  */
-static int hugetlb_vm_op_fault(struct vm_fault *vmf)
+static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf)
 {
 	BUG();
 	return 0;
@@ -3686,6 +3686,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	pte_t new_pte;
 	spinlock_t *ptl;
+	unsigned long haddr = address & huge_page_mask(h);
 
 	/*
 	 * Currently, we are forced to kill the process in the event the
@@ -3716,7 +3717,7 @@ retry:
 			u32 hash;
 			struct vm_fault vmf = {
 				.vma = vma,
-				.address = address,
+				.address = haddr,
 				.flags = flags,
 				/*
 				 * Hard to debug if it ends up being
@@ -3733,14 +3734,14 @@ retry:
 			 * fault to make calling code simpler.
 			 */
 			hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping,
-							idx, address);
+							idx, haddr);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			ret = handle_userfault(&vmf, VM_UFFD_MISSING);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 			goto out;
 		}
 
-		page = alloc_huge_page(vma, address, 0);
+		page = alloc_huge_page(vma, haddr, 0);
 		if (IS_ERR(page)) {
 			ret = PTR_ERR(page);
 			if (ret == -ENOMEM)
@@ -3789,12 +3790,12 @@ retry:
 	 * the spinlock.
 	 */
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
-		if (vma_needs_reservation(h, vma, address) < 0) {
+		if (vma_needs_reservation(h, vma, haddr) < 0) {
 			ret = VM_FAULT_OOM;
 			goto backout_unlocked;
 		}
 		/* Just decrements count, does not deallocate */
-		vma_end_reservation(h, vma, address);
+		vma_end_reservation(h, vma, haddr);
 	}
 
 	ptl = huge_pte_lock(h, mm, ptep);
@@ -3808,17 +3809,17 @@ retry:
 
 	if (anon_rmap) {
 		ClearPagePrivate(page);
-		hugepage_add_new_anon_rmap(page, vma, address);
+		hugepage_add_new_anon_rmap(page, vma, haddr);
 	} else
 		page_dup_rmap(page, true);
 	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
 				&& (vma->vm_flags & VM_SHARED)));
-	set_huge_pte_at(mm, address, ptep, new_pte);
+	set_huge_pte_at(mm, haddr, ptep, new_pte);
 
 	hugetlb_count_add(pages_per_huge_page(h), mm);
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
-		ret = hugetlb_cow(mm, vma, address, ptep, page, ptl);
+		ret = hugetlb_cow(mm, vma, haddr, ptep, page, ptl);
 	}
 
 	spin_unlock(ptl);
@@ -3830,7 +3831,7 @@ backout:
 	spin_unlock(ptl);
 backout_unlocked:
 	unlock_page(page);
-	restore_reserve_on_error(h, vma, address, page);
+	restore_reserve_on_error(h, vma, haddr, page);
 	put_page(page);
 	goto out;
 }
@@ -3883,10 +3884,9 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct hstate *h = hstate_vma(vma);
 	struct address_space *mapping;
 	int need_wait_lock = 0;
+	unsigned long haddr = address & huge_page_mask(h);
 
-	address &= huge_page_mask(h);
-
-	ptep = huge_pte_offset(mm, address, huge_page_size(h));
+	ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
 	if (ptep) {
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
@@ -3896,20 +3896,20 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			return VM_FAULT_HWPOISON_LARGE |
 				VM_FAULT_SET_HINDEX(hstate_index(h));
 	} else {
-		ptep = huge_pte_alloc(mm, address, huge_page_size(h));
+		ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
 		if (!ptep)
 			return VM_FAULT_OOM;
 	}
 
 	mapping = vma->vm_file->f_mapping;
-	idx = vma_hugecache_offset(h, vma, address);
+	idx = vma_hugecache_offset(h, vma, haddr);
 
 	/*
 	 * Serialize hugepage allocation and instantiation, so that we don't
 	 * get spurious allocation failures if two CPUs race to instantiate
 	 * the same page in the page cache.
 	 */
-	hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, address);
+	hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, haddr);
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 	entry = huge_ptep_get(ptep);
@@ -3939,16 +3939,16 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * consumed.
 	 */
 	if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) {
-		if (vma_needs_reservation(h, vma, address) < 0) {
+		if (vma_needs_reservation(h, vma, haddr) < 0) {
 			ret = VM_FAULT_OOM;
 			goto out_mutex;
 		}
 		/* Just decrements count, does not deallocate */
-		vma_end_reservation(h, vma, address);
+		vma_end_reservation(h, vma, haddr);
 
 		if (!(vma->vm_flags & VM_MAYSHARE))
 			pagecache_page = hugetlbfs_pagecache_page(h,
-								vma, address);
+								vma, haddr);
 	}
 
 	ptl = huge_pte_lock(h, mm, ptep);
@@ -3973,16 +3973,16 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (flags & FAULT_FLAG_WRITE) {
 		if (!huge_pte_write(entry)) {
-			ret = hugetlb_cow(mm, vma, address, ptep,
+			ret = hugetlb_cow(mm, vma, haddr, ptep,
 					  pagecache_page, ptl);
 			goto out_put_page;
 		}
 		entry = huge_pte_mkdirty(entry);
 	}
 	entry = pte_mkyoung(entry);
-	if (huge_ptep_set_access_flags(vma, address, ptep, entry,
+	if (huge_ptep_set_access_flags(vma, haddr, ptep, entry,
 						flags & FAULT_FLAG_WRITE))
-		update_mmu_cache(vma, address, ptep);
+		update_mmu_cache(vma, haddr, ptep);
 out_put_page:
 	if (page != pagecache_page)
 		unlock_page(page);
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index eec1150125b9..68c2f2f3c05b 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -84,7 +84,7 @@ static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup,
 
 		limit = round_down(PAGE_COUNTER_MAX,
 				   1 << huge_page_order(&hstates[idx]));
-		ret = page_counter_limit(counter, limit);
+		ret = page_counter_set_max(counter, limit);
 		VM_BUG_ON(ret);
 	}
 }
@@ -273,7 +273,7 @@ static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
 	case RES_USAGE:
 		return (u64)page_counter_read(counter) * PAGE_SIZE;
 	case RES_LIMIT:
-		return (u64)counter->limit * PAGE_SIZE;
+		return (u64)counter->max * PAGE_SIZE;
 	case RES_MAX_USAGE:
 		return (u64)counter->watermark * PAGE_SIZE;
 	case RES_FAILCNT:
@@ -306,7 +306,7 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_LIMIT:
 		mutex_lock(&hugetlb_limit_mutex);
-		ret = page_counter_limit(&h_cg->hugepage[idx], nr_pages);
+		ret = page_counter_set_max(&h_cg->hugepage[idx], nr_pages);
 		mutex_unlock(&hugetlb_limit_mutex);
 		break;
 	default:
diff --git a/mm/init-mm.c b/mm/init-mm.c
index f94d5d15ebc0..f0179c9c04c2 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -22,6 +22,7 @@ struct mm_struct init_mm = {
 	.mm_count	= ATOMIC_INIT(1),
 	.mmap_sem	= __RWSEM_INITIALIZER(init_mm.mmap_sem),
 	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
+	.arg_lock	=  __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
 	.mmlist		= LIST_HEAD_INIT(init_mm.mmlist),
 	.user_ns	= &init_user_ns,
 	INIT_MM_CONTEXT(init_mm)
diff --git a/mm/ksm.c b/mm/ksm.c
index 7d6558f3bac9..e2d2886fb1df 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -840,6 +840,17 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma,
 	return err;
 }
 
+static inline struct stable_node *page_stable_node(struct page *page)
+{
+	return PageKsm(page) ? page_rmapping(page) : NULL;
+}
+
+static inline void set_page_stable_node(struct page *page,
+					struct stable_node *stable_node)
+{
+	page->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM);
+}
+
 #ifdef CONFIG_SYSFS
 /*
  * Only called through the sysfs control interface:
diff --git a/mm/memblock.c b/mm/memblock.c
index 5108356ad8aa..93ad42bc8a73 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -68,7 +68,7 @@ ulong __init_memblock choose_memblock_flags(void)
 /* adjust *@size so that (@base + *@size) doesn't overflow, return new size */
 static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size)
 {
-	return *size = min(*size, (phys_addr_t)ULLONG_MAX - base);
+	return *size = min(*size, PHYS_ADDR_MAX - base);
 }
 
 /*
@@ -697,6 +697,11 @@ static int __init_memblock memblock_remove_range(struct memblock_type *type,
 
 int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
 {
+	phys_addr_t end = base + size - 1;
+
+	memblock_dbg("memblock_remove: [%pa-%pa] %pS\n",
+		     &base, &end, (void *)_RET_IP_);
+
 	return memblock_remove_range(&memblock.memory, base, size);
 }
 
@@ -925,7 +930,7 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
 			r = &type_b->regions[idx_b];
 			r_start = idx_b ? r[-1].base + r[-1].size : 0;
 			r_end = idx_b < type_b->cnt ?
-				r->base : (phys_addr_t)ULLONG_MAX;
+				r->base : PHYS_ADDR_MAX;
 
 			/*
 			 * if idx_b advanced past idx_a,
@@ -1041,7 +1046,7 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags,
 			r = &type_b->regions[idx_b];
 			r_start = idx_b ? r[-1].base + r[-1].size : 0;
 			r_end = idx_b < type_b->cnt ?
-				r->base : (phys_addr_t)ULLONG_MAX;
+				r->base : PHYS_ADDR_MAX;
 			/*
 			 * if idx_b advanced past idx_a,
 			 * break out to advance idx_a
@@ -1516,13 +1521,13 @@ phys_addr_t __init_memblock memblock_end_of_DRAM(void)
 
 static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit)
 {
-	phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX;
+	phys_addr_t max_addr = PHYS_ADDR_MAX;
 	struct memblock_region *r;
 
 	/*
 	 * translate the memory @limit size into the max address within one of
 	 * the memory memblock regions, if the @limit exceeds the total size
-	 * of those regions, max_addr will keep original value ULLONG_MAX
+	 * of those regions, max_addr will keep original value PHYS_ADDR_MAX
 	 */
 	for_each_memblock(memory, r) {
 		if (limit <= r->size) {
@@ -1537,7 +1542,7 @@ static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit)
 
 void __init memblock_enforce_memory_limit(phys_addr_t limit)
 {
-	phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX;
+	phys_addr_t max_addr = PHYS_ADDR_MAX;
 
 	if (!limit)
 		return;
@@ -1545,14 +1550,14 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit)
 	max_addr = __find_max_addr(limit);
 
 	/* @limit exceeds the total size of the memory, do nothing */
-	if (max_addr == (phys_addr_t)ULLONG_MAX)
+	if (max_addr == PHYS_ADDR_MAX)
 		return;
 
 	/* truncate both memory and reserved regions */
 	memblock_remove_range(&memblock.memory, max_addr,
-			      (phys_addr_t)ULLONG_MAX);
+			      PHYS_ADDR_MAX);
 	memblock_remove_range(&memblock.reserved, max_addr,
-			      (phys_addr_t)ULLONG_MAX);
+			      PHYS_ADDR_MAX);
 }
 
 void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size)
@@ -1580,7 +1585,7 @@ void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size)
 	/* truncate the reserved regions */
 	memblock_remove_range(&memblock.reserved, 0, base);
 	memblock_remove_range(&memblock.reserved,
-			base + size, (phys_addr_t)ULLONG_MAX);
+			base + size, PHYS_ADDR_MAX);
 }
 
 void __init memblock_mem_limit_remove_map(phys_addr_t limit)
@@ -1593,7 +1598,7 @@ void __init memblock_mem_limit_remove_map(phys_addr_t limit)
 	max_addr = __find_max_addr(limit);
 
 	/* @limit exceeds the total size of the memory, do nothing */
-	if (max_addr == (phys_addr_t)ULLONG_MAX)
+	if (max_addr == PHYS_ADDR_MAX)
 		return;
 
 	memblock_cap_memory_range(0, max_addr);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1695f38630f1..c1e64d60ed02 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1034,13 +1034,13 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
 	unsigned long limit;
 
 	count = page_counter_read(&memcg->memory);
-	limit = READ_ONCE(memcg->memory.limit);
+	limit = READ_ONCE(memcg->memory.max);
 	if (count < limit)
 		margin = limit - count;
 
 	if (do_memsw_account()) {
 		count = page_counter_read(&memcg->memsw);
-		limit = READ_ONCE(memcg->memsw.limit);
+		limit = READ_ONCE(memcg->memsw.max);
 		if (count <= limit)
 			margin = min(margin, limit - count);
 		else
@@ -1148,13 +1148,13 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 
 	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
 		K((u64)page_counter_read(&memcg->memory)),
-		K((u64)memcg->memory.limit), memcg->memory.failcnt);
+		K((u64)memcg->memory.max), memcg->memory.failcnt);
 	pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n",
 		K((u64)page_counter_read(&memcg->memsw)),
-		K((u64)memcg->memsw.limit), memcg->memsw.failcnt);
+		K((u64)memcg->memsw.max), memcg->memsw.failcnt);
 	pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n",
 		K((u64)page_counter_read(&memcg->kmem)),
-		K((u64)memcg->kmem.limit), memcg->kmem.failcnt);
+		K((u64)memcg->kmem.max), memcg->kmem.failcnt);
 
 	for_each_mem_cgroup_tree(iter, memcg) {
 		pr_info("Memory cgroup stats for ");
@@ -1179,21 +1179,21 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 /*
  * Return the memory (and swap, if configured) limit for a memcg.
  */
-unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg)
+unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
 {
-	unsigned long limit;
+	unsigned long max;
 
-	limit = memcg->memory.limit;
+	max = memcg->memory.max;
 	if (mem_cgroup_swappiness(memcg)) {
-		unsigned long memsw_limit;
-		unsigned long swap_limit;
+		unsigned long memsw_max;
+		unsigned long swap_max;
 
-		memsw_limit = memcg->memsw.limit;
-		swap_limit = memcg->swap.limit;
-		swap_limit = min(swap_limit, (unsigned long)total_swap_pages);
-		limit = min(limit + swap_limit, memsw_limit);
+		memsw_max = memcg->memsw.max;
+		swap_max = memcg->swap.max;
+		swap_max = min(swap_max, (unsigned long)total_swap_pages);
+		max = min(max + swap_max, memsw_max);
 	}
-	return limit;
+	return max;
 }
 
 static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
@@ -2444,12 +2444,13 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
 }
 #endif
 
-static DEFINE_MUTEX(memcg_limit_mutex);
+static DEFINE_MUTEX(memcg_max_mutex);
 
-static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
-				   unsigned long limit, bool memsw)
+static int mem_cgroup_resize_max(struct mem_cgroup *memcg,
+				 unsigned long max, bool memsw)
 {
 	bool enlarge = false;
+	bool drained = false;
 	int ret;
 	bool limits_invariant;
 	struct page_counter *counter = memsw ? &memcg->memsw : &memcg->memory;
@@ -2460,26 +2461,32 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 			break;
 		}
 
-		mutex_lock(&memcg_limit_mutex);
+		mutex_lock(&memcg_max_mutex);
 		/*
 		 * Make sure that the new limit (memsw or memory limit) doesn't
-		 * break our basic invariant rule memory.limit <= memsw.limit.
+		 * break our basic invariant rule memory.max <= memsw.max.
 		 */
-		limits_invariant = memsw ? limit >= memcg->memory.limit :
-					   limit <= memcg->memsw.limit;
+		limits_invariant = memsw ? max >= memcg->memory.max :
+					   max <= memcg->memsw.max;
 		if (!limits_invariant) {
-			mutex_unlock(&memcg_limit_mutex);
+			mutex_unlock(&memcg_max_mutex);
 			ret = -EINVAL;
 			break;
 		}
-		if (limit > counter->limit)
+		if (max > counter->max)
 			enlarge = true;
-		ret = page_counter_limit(counter, limit);
-		mutex_unlock(&memcg_limit_mutex);
+		ret = page_counter_set_max(counter, max);
+		mutex_unlock(&memcg_max_mutex);
 
 		if (!ret)
 			break;
 
+		if (!drained) {
+			drain_all_stock(memcg);
+			drained = true;
+			continue;
+		}
+
 		if (!try_to_free_mem_cgroup_pages(memcg, 1,
 					GFP_KERNEL, !memsw)) {
 			ret = -EBUSY;
@@ -2603,6 +2610,9 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 
 	/* we call try-to-free pages for make this cgroup empty */
 	lru_add_drain_all();
+
+	drain_all_stock(memcg);
+
 	/* try to free all pages in this cgroup */
 	while (nr_retries && page_counter_read(&memcg->memory)) {
 		int progress;
@@ -2757,7 +2767,7 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 			return (u64)mem_cgroup_usage(memcg, true) * PAGE_SIZE;
 		return (u64)page_counter_read(counter) * PAGE_SIZE;
 	case RES_LIMIT:
-		return (u64)counter->limit * PAGE_SIZE;
+		return (u64)counter->max * PAGE_SIZE;
 	case RES_MAX_USAGE:
 		return (u64)counter->watermark * PAGE_SIZE;
 	case RES_FAILCNT:
@@ -2871,24 +2881,24 @@ static void memcg_free_kmem(struct mem_cgroup *memcg)
 }
 #endif /* !CONFIG_SLOB */
 
-static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
-				   unsigned long limit)
+static int memcg_update_kmem_max(struct mem_cgroup *memcg,
+				 unsigned long max)
 {
 	int ret;
 
-	mutex_lock(&memcg_limit_mutex);
-	ret = page_counter_limit(&memcg->kmem, limit);
-	mutex_unlock(&memcg_limit_mutex);
+	mutex_lock(&memcg_max_mutex);
+	ret = page_counter_set_max(&memcg->kmem, max);
+	mutex_unlock(&memcg_max_mutex);
 	return ret;
 }
 
-static int memcg_update_tcp_limit(struct mem_cgroup *memcg, unsigned long limit)
+static int memcg_update_tcp_max(struct mem_cgroup *memcg, unsigned long max)
 {
 	int ret;
 
-	mutex_lock(&memcg_limit_mutex);
+	mutex_lock(&memcg_max_mutex);
 
-	ret = page_counter_limit(&memcg->tcpmem, limit);
+	ret = page_counter_set_max(&memcg->tcpmem, max);
 	if (ret)
 		goto out;
 
@@ -2913,7 +2923,7 @@ static int memcg_update_tcp_limit(struct mem_cgroup *memcg, unsigned long limit)
 		memcg->tcpmem_active = true;
 	}
 out:
-	mutex_unlock(&memcg_limit_mutex);
+	mutex_unlock(&memcg_max_mutex);
 	return ret;
 }
 
@@ -2941,16 +2951,16 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
 		}
 		switch (MEMFILE_TYPE(of_cft(of)->private)) {
 		case _MEM:
-			ret = mem_cgroup_resize_limit(memcg, nr_pages, false);
+			ret = mem_cgroup_resize_max(memcg, nr_pages, false);
 			break;
 		case _MEMSWAP:
-			ret = mem_cgroup_resize_limit(memcg, nr_pages, true);
+			ret = mem_cgroup_resize_max(memcg, nr_pages, true);
 			break;
 		case _KMEM:
-			ret = memcg_update_kmem_limit(memcg, nr_pages);
+			ret = memcg_update_kmem_max(memcg, nr_pages);
 			break;
 		case _TCP:
-			ret = memcg_update_tcp_limit(memcg, nr_pages);