Merge branch 'akpm-current/current'

59 files changed, 4576 insertions, 1912 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 9b8fccb969dc..4aff67e042f1 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -690,6 +690,7 @@ config ZONE_DEVICE
 	depends on MEMORY_HOTREMOVE
 	depends on SPARSEMEM_VMEMMAP
 	depends on X86_64 #arch_add_memory() comprehends device memory
+	select RADIX_TREE_MULTIORDER
 
 	help
 	  Device memory hotplug support allows for establishing pmem,
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index afcc550877ff..3e5eada506df 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -90,3 +90,10 @@ config DEBUG_PAGE_REF
 	  careful when enabling this feature because it adds about 30 KB to the
 	  kernel code.  However the runtime performance overhead is virtually
 	  nil until the tracepoints are actually enabled.
+
+config DEBUG_RODATA_TEST
+    bool "Testcase for the marking rodata read-only"
+    depends on DEBUG_RODATA
+    ---help---
+      This option enables a testcase for the setting rodata read-only.
+
diff --git a/mm/Makefile b/mm/Makefile
index 295bd7a9f76b..026f6a828a50 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -23,8 +23,10 @@ KCOV_INSTRUMENT_vmstat.o := n
 
 mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= gup.o highmem.o memory.o mincore.o \
-			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
-			   vmalloc.o pagewalk.o pgtable-generic.o
+			   mlock.o mmap.o mprotect.o mremap.o msync.o \
+			   page_vma_mapped.o pagewalk.o pgtable-generic.o \
+			   rmap.o vmalloc.o
+
 
 ifdef CONFIG_CROSS_MEMORY_ATTACH
 mmu-$(CONFIG_MMU)	+= process_vm_access.o
@@ -35,7 +37,7 @@ obj-y			:= filemap.o mempool.o oom_kill.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
-			   compaction.o vmacache.o \
+			   compaction.o vmacache.o swap_slots.o \
 			   interval_tree.o list_lru.o workingset.o \
 			   debug.o $(mmu-y)
 
@@ -83,6 +85,7 @@ obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
 obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
 obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
+obj-$(CONFIG_DEBUG_RODATA_TEST) += rodata_test.o
 obj-$(CONFIG_PAGE_OWNER) += page_owner.o
 obj-$(CONFIG_CLEANCACHE) += cleancache.o
 obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 39ce616a9d71..6d861d090e9f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -411,8 +411,8 @@ retry:
 
 	while (*node != NULL) {
 		parent = *node;
-		congested = container_of(parent, struct bdi_writeback_congested,
-					 rb_node);
+		congested = rb_entry(parent, struct bdi_writeback_congested,
+				     rb_node);
 		if (congested->blkcg_id < blkcg_id)
 			node = &parent->rb_left;
 		else if (congested->blkcg_id > blkcg_id)
diff --git a/mm/bootmem.c b/mm/bootmem.c
index e8a55a3c9feb..9fedb27c6451 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -53,7 +53,7 @@ early_param("bootmem_debug", bootmem_debug_setup);
 
 static unsigned long __init bootmap_bytes(unsigned long pages)
 {
-	unsigned long bytes = DIV_ROUND_UP(pages, 8);
+	unsigned long bytes = DIV_ROUND_UP(pages, BITS_PER_BYTE);
 
 	return ALIGN(bytes, sizeof(long));
 }
diff --git a/mm/cma.c b/mm/cma.c
index 94b3460cd608..a6033e344430 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -348,6 +348,32 @@ err:
 	return ret;
 }
 
+#ifdef CONFIG_CMA_DEBUG
+static void cma_debug_show_areas(struct cma *cma)
+{
+	unsigned long next_zero_bit, next_set_bit;
+	unsigned long start = 0;
+	unsigned int nr_zero, nr_total = 0;
+
+	mutex_lock(&cma->lock);
+	pr_info("number of available pages: ");
+	for (;;) {
+		next_zero_bit = find_next_zero_bit(cma->bitmap, cma->count, start);
+		if (next_zero_bit >= cma->count)
+			break;
+		next_set_bit = find_next_bit(cma->bitmap, cma->count, next_zero_bit);
+		nr_zero = next_set_bit - next_zero_bit;
+		pr_cont("%s%u@%lu", nr_total ? "+" : "", nr_zero, next_zero_bit);
+		nr_total += nr_zero;
+		start = next_zero_bit + nr_zero;
+	}
+	pr_cont("=> %u free of %lu total pages\n", nr_total, cma->count);
+	mutex_unlock(&cma->lock);
+}
+#else
+static inline void cma_debug_show_areas(struct cma *cma) { }
+#endif
+
 /**
  * cma_alloc() - allocate pages from contiguous area
  * @cma:   Contiguous memory region for which the allocation is performed.
@@ -357,14 +383,15 @@ err:
  * This function allocates part of contiguous memory on specific
  * contiguous memory area.
  */
-struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align)
+struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align,
+		       gfp_t gfp_mask)
 {
 	unsigned long mask, offset;
 	unsigned long pfn = -1;
 	unsigned long start = 0;
 	unsigned long bitmap_maxno, bitmap_no, bitmap_count;
 	struct page *page = NULL;
-	int ret;
+	int ret = -ENOMEM;
 
 	if (!cma || !cma->count)
 		return NULL;
@@ -402,7 +429,8 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align)
 
 		pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit);
 		mutex_lock(&cma_mutex);
-		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
+		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA,
+					 gfp_mask);
 		mutex_unlock(&cma_mutex);
 		if (ret == 0) {
 			page = pfn_to_page(pfn);
@@ -421,6 +449,12 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align)
 
 	trace_cma_alloc(pfn, page, count, align);
 
+	if (ret) {
+		pr_info("%s: alloc failed, req-size: %zu pages, ret: %d\n",
+			__func__, count, ret);
+		cma_debug_show_areas(cma);
+	}
+
 	pr_debug("%s(): returned %p\n", __func__, page);
 	return page;
 }
diff --git a/mm/cma_debug.c b/mm/cma_debug.c
index f8e4b60db167..ffc0c3d0ae64 100644
--- a/mm/cma_debug.c
+++ b/mm/cma_debug.c
@@ -138,7 +138,7 @@ static int cma_alloc_mem(struct cma *cma, int count)
 	if (!mem)
 		return -ENOMEM;
 
-	p = cma_alloc(cma, count, 0);
+	p = cma_alloc(cma, count, 0, GFP_KERNEL);
 	if (!p) {
 		kfree(mem);
 		return -ENOMEM;
diff --git a/mm/compaction.c b/mm/compaction.c
index 949198d01260..0fdfde016ee2 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -548,7 +548,7 @@ isolate_fail:
 	if (blockpfn == end_pfn)
 		update_pageblock_skip(cc, valid_page, total_isolated, false);
 
-	count_compact_events(COMPACTFREE_SCANNED, nr_scanned);
+	cc->total_free_scanned += nr_scanned;
 	if (total_isolated)
 		count_compact_events(COMPACTISOLATED, total_isolated);
 	return total_isolated;
@@ -802,7 +802,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 					locked = false;
 				}
 
-				if (isolate_movable_page(page, isolate_mode))
+				if (!isolate_movable_page(page, isolate_mode))
 					goto isolate_success;
 			}
 
@@ -931,7 +931,7 @@ isolate_fail:
 	trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
 						nr_scanned, nr_isolated);
 
-	count_compact_events(COMPACTMIGRATE_SCANNED, nr_scanned);
+	cc->total_migrate_scanned += nr_scanned;
 	if (nr_isolated)
 		count_compact_events(COMPACTISOLATED, nr_isolated);
 
@@ -1631,6 +1631,9 @@ out:
 			zone->compact_cached_free_pfn = free_pfn;
 	}
 
+	count_compact_events(COMPACTMIGRATE_SCANNED, cc->total_migrate_scanned);
+	count_compact_events(COMPACTFREE_SCANNED, cc->total_free_scanned);
+
 	trace_mm_compaction_end(start_pfn, cc->migrate_pfn,
 				cc->free_pfn, end_pfn, sync, ret);
 
@@ -1645,6 +1648,8 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
 	struct compact_control cc = {
 		.nr_freepages = 0,
 		.nr_migratepages = 0,
+		.total_migrate_scanned = 0,
+		.total_free_scanned = 0,
 		.order = order,
 		.gfp_mask = gfp_mask,
 		.zone = zone,
@@ -1757,6 +1762,8 @@ static void compact_node(int nid)
 	struct zone *zone;
 	struct compact_control cc = {
 		.order = -1,
+		.total_migrate_scanned = 0,
+		.total_free_scanned = 0,
 		.mode = MIGRATE_SYNC,
 		.ignore_skip_hint = true,
 		.whole_zone = true,
@@ -1883,6 +1890,8 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 	struct zone *zone;
 	struct compact_control cc = {
 		.order = pgdat->kcompactd_max_order,
+		.total_migrate_scanned = 0,
+		.total_free_scanned = 0,
 		.classzone_idx = pgdat->kcompactd_classzone_idx,
 		.mode = MIGRATE_SYNC_LIGHT,
 		.ignore_skip_hint = true,
@@ -1891,7 +1900,7 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 	};
 	trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order,
 							cc.classzone_idx);
-	count_vm_event(KCOMPACTD_WAKE);
+	count_compact_event(KCOMPACTD_WAKE);
 
 	for (zoneid = 0; zoneid <= cc.classzone_idx; zoneid++) {
 		int status;
@@ -1909,6 +1918,8 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 
 		cc.nr_freepages = 0;
 		cc.nr_migratepages = 0;
+		cc.total_migrate_scanned = 0;
+		cc.total_free_scanned = 0;
 		cc.zone = zone;
 		INIT_LIST_HEAD(&cc.freepages);
 		INIT_LIST_HEAD(&cc.migratepages);
@@ -1927,6 +1938,11 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 			defer_compaction(zone, cc.order);
 		}
 
+		count_compact_events(KCOMPACTD_MIGRATE_SCANNED,
+				     cc.total_migrate_scanned);
+		count_compact_events(KCOMPACTD_FREE_SCANNED,
+				     cc.total_free_scanned);
+
 		VM_BUG_ON(!list_empty(&cc.freepages));
 		VM_BUG_ON(!list_empty(&cc.migratepages));
 	}
@@ -1950,6 +1966,13 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx)
 	if (pgdat->kcompactd_max_order < order)
 		pgdat->kcompactd_max_order = order;
 
+	/*
+	 * Pairs with implicit barrier in wait_event_freezable()
+	 * such that wakeups are not missed in the lockless
+	 * waitqueue_active() call.
+	 */
+	smp_acquire__after_ctrl_dep();
+
 	if (pgdat->kcompactd_classzone_idx > classzone_idx)
 		pgdat->kcompactd_classzone_idx = classzone_idx;
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 3f9afded581b..2ba46f410c7c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -788,7 +788,7 @@ static int wake_page_function(wait_queue_t *wait, unsigned mode, int sync, void
 	return autoremove_wake_function(wait, mode, sync, key);
 }
 
-void wake_up_page_bit(struct page *page, int bit_nr)
+static void wake_up_page_bit(struct page *page, int bit_nr)
 {
 	wait_queue_head_t *q = page_waitqueue(page);
 	struct wait_page_key key;
@@ -821,7 +821,13 @@ void wake_up_page_bit(struct page *page, int bit_nr)
 	}
 	spin_unlock_irqrestore(&q->lock, flags);
 }
-EXPORT_SYMBOL(wake_up_page_bit);
+
+static void wake_up_page(struct page *page, int bit)
+{
+	if (!PageWaiters(page))
+		return;
+	wake_up_page_bit(page, bit);
+}
 
 static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 		struct page *page, int bit_nr, int state, bool lock)
@@ -1013,7 +1019,7 @@ EXPORT_SYMBOL_GPL(page_endio);
 
 /**
  * __lock_page - get a lock on the page, assuming we need to sleep to get it
- * @page: the page to lock
+ * @__page: the page to lock
  */
 void __lock_page(struct page *__page)
 {
@@ -2163,7 +2169,6 @@ static void do_async_mmap_readahead(struct vm_area_struct *vma,
 
 /**
  * filemap_fault - read in file data for page fault handling
- * @vma:	vma in which the fault was taken
  * @vmf:	struct vm_fault containing details of the fault
  *
  * filemap_fault() is invoked via the vma operations vector for a
@@ -2185,10 +2190,10 @@ 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_area_struct *vma, struct vm_fault *vmf)
+int filemap_fault(struct vm_fault *vmf)
 {
 	int error;
-	struct file *file = vma->vm_file;
+	struct file *file = vmf->vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	struct file_ra_state *ra = &file->f_ra;
 	struct inode *inode = mapping->host;
@@ -2210,12 +2215,12 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		 * We found the page, so try async readahead before
 		 * waiting for the lock.
 		 */
-		do_async_mmap_readahead(vma, ra, file, page, offset);
+		do_async_mmap_readahead(vmf->vma, ra, file, page, offset);
 	} else if (!page) {
 		/* No page in the page cache at all */
-		do_sync_mmap_readahead(vma, ra, file, offset);
+		do_sync_mmap_readahead(vmf->vma, ra, file, offset);
 		count_vm_event(PGMAJFAULT);
-		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+		mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT);
 		ret = VM_FAULT_MAJOR;
 retry_find:
 		page = find_get_page(mapping, offset);
@@ -2223,7 +2228,7 @@ retry_find:
 			goto no_cached_page;
 	}
 
-	if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
+	if (!lock_page_or_retry(page, vmf->vma->vm_mm, vmf->flags)) {
 		put_page(page);
 		return ret | VM_FAULT_RETRY;
 	}
@@ -2390,14 +2395,14 @@ next:
 }
 EXPORT_SYMBOL(filemap_map_pages);
 
-int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+int filemap_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	int ret = VM_FAULT_LOCKED;
 
 	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
+	file_update_time(vmf->vma->vm_file);
 	lock_page(page);
 	if (page->mapping != inode->i_mapping) {
 		unlock_page(page);
diff --git a/mm/gup.c b/mm/gup.c
index 55315555489d..1e67461b2733 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -253,6 +253,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 			return page;
 		return no_page_table(vma, flags);
 	}
+	if (pud_devmap(*pud)) {
+		ptl = pud_lock(mm, pud);
+		page = follow_devmap_pud(vma, address, pud, flags);
+		spin_unlock(ptl);
+		if (page)
+			return page;
+	}
 	if (unlikely(pud_bad(*pud)))
 		return no_page_table(vma, flags);
 
@@ -572,7 +579,7 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			if (is_vm_hugetlb_page(vma)) {
 				i = follow_hugetlb_page(mm, vma, pages, vmas,
 						&start, &nr_pages, i,
-						gup_flags);
+						gup_flags, nonblocking);
 				continue;
 			}
 		}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5f3ad65c85de..efddd02141a8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -142,42 +142,6 @@ static struct shrinker huge_zero_page_shrinker = {
 };
 
 #ifdef CONFIG_SYSFS
-
-static ssize_t triple_flag_store(struct kobject *kobj,
-				 struct kobj_attribute *attr,
-				 const char *buf, size_t count,
-				 enum transparent_hugepage_flag enabled,
-				 enum transparent_hugepage_flag deferred,
-				 enum transparent_hugepage_flag req_madv)
-{
-	if (!memcmp("defer", buf,
-		    min(sizeof("defer")-1, count))) {
-		if (enabled == deferred)
-			return -EINVAL;
-		clear_bit(enabled, &transparent_hugepage_flags);
-		clear_bit(req_madv, &transparent_hugepage_flags);
-		set_bit(deferred, &transparent_hugepage_flags);
-	} else if (!memcmp("always", buf,
-		    min(sizeof("always")-1, count))) {
-		clear_bit(deferred, &transparent_hugepage_flags);
-		clear_bit(req_madv, &transparent_hugepage_flags);
-		set_bit(enabled, &transparent_hugepage_flags);
-	} else if (!memcmp("madvise", buf,
-			   min(sizeof("madvise")-1, count))) {
-		clear_bit(enabled, &transparent_hugepage_flags);
-		clear_bit(deferred, &transparent_hugepage_flags);
-		set_bit(req_madv, &transparent_hugepage_flags);
-	} else if (!memcmp("never", buf,
-			   min(sizeof("never")-1, count))) {
-		clear_bit(enabled, &transparent_hugepage_flags);
-		clear_bit(req_madv, &transparent_hugepage_flags);
-		clear_bit(deferred, &transparent_hugepage_flags);
-	} else
-		return -EINVAL;
-
-	return count;
-}
-
 static ssize_t enabled_show(struct kobject *kobj,
 			    struct kobj_attribute *attr, char *buf)
 {
@@ -193,19 +157,28 @@ static ssize_t enabled_store(struct kobject *kobj,
 			     struct kobj_attribute *attr,
 			     const char *buf, size_t count)
 {
-	ssize_t ret;
+	ssize_t ret = count;
 
-	ret = triple_flag_store(kobj, attr, buf, count,
-				TRANSPARENT_HUGEPAGE_FLAG,
-				TRANSPARENT_HUGEPAGE_FLAG,
-				TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
+	if (!memcmp("always", buf,
+		    min(sizeof("always")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("madvise", buf,
+			   min(sizeof("madvise")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("never", buf,
+			   min(sizeof("never")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+	} else
+		ret = -EINVAL;
 
 	if (ret > 0) {
 		int err = start_stop_khugepaged();
 		if (err)
 			ret = err;
 	}
-
 	return ret;
 }
 static struct kobj_attribute enabled_attr =
@@ -241,32 +214,58 @@ ssize_t single_hugepage_flag_store(struct kobject *kobj,
 	return count;
 }
 
-/*
- * Currently defrag only disables __GFP_NOWAIT for allocation. A blind
- * __GFP_REPEAT is too aggressive, it's never worth swapping tons of
- * memory just to allocate one more hugepage.
- */
 static ssize_t defrag_show(struct kobject *kobj,
 			   struct kobj_attribute *attr, char *buf)
 {
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
-		return sprintf(buf, "[always] defer madvise never\n");
+		return sprintf(buf, "[always] defer defer+madvise madvise never\n");
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
-		return sprintf(buf, "always [defer] madvise never\n");
-	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
-		return sprintf(buf, "always defer [madvise] never\n");
-	else
-		return sprintf(buf, "always defer madvise [never]\n");
-
+		return sprintf(buf, "always [defer] defer+madvise madvise never\n");
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
+		return sprintf(buf, "always defer [defer+madvise] madvise never\n");
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
+		return sprintf(buf, "always defer defer+madvise [madvise] never\n");
+	return sprintf(buf, "always defer defer+madvise madvise [never]\n");
 }
+
 static ssize_t defrag_store(struct kobject *kobj,
 			    struct kobj_attribute *attr,
 			    const char *buf, size_t count)
 {
-	return triple_flag_store(kobj, attr, buf, count,
-				 TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
-				 TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
-				 TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
+	if (!memcmp("always", buf,
+		    min(sizeof("always")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("defer", buf,
+		    min(sizeof("defer")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("defer+madvise", buf,
+		    min(sizeof("defer+madvise")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("madvise", buf,
+			   min(sizeof("madvise")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("never", buf,
+			   min(sizeof("never")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+	} else
+		return -EINVAL;
+
+	return count;
 }
 static struct kobj_attribute defrag_attr =
 	__ATTR(defrag, 0644, defrag_show, defrag_store);
@@ -612,25 +611,28 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 }
 
 /*
- * If THP defrag is set to always then directly reclaim/compact as necessary
- * If set to defer then do only background reclaim/compact and defer to khugepaged
- * If set to madvise and the VMA is flagged then directly reclaim/compact
- * When direct reclaim/compact is allowed, don't retry except for flagged VMA's
+ * always: directly stall for all thp allocations
+ * defer: wake kswapd and fail if not immediately available
+ * defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise
+ *		  fail if not immediately available
+ * madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately
+ *	    available
+ * never: never stall for any thp allocation
  */
 static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
 {
-	bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+	const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
 
-	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
-				&transparent_hugepage_flags) && vma_madvised)
-		return GFP_TRANSHUGE;
-	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
-						&transparent_hugepage_flags))
-		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
-	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
-						&transparent_hugepage_flags))
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
-
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
+		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
+		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
+							     __GFP_KSWAPD_RECLAIM);
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
+		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
+							     0);
 	return GFP_TRANSHUGE_LIGHT;
 }
 
@@ -755,6 +757,60 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
 
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_flags & VM_WRITE))
+		pud = pud_mkwrite(pud);
+	return pud;
+}
+
+static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+		pud_t *pud, pfn_t pfn, pgprot_t prot, bool write)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pud_t entry;
+	spinlock_t *ptl;
+
+	ptl = pud_lock(mm, pud);
+	entry = pud_mkhuge(pfn_t_pud(pfn, prot));
+	if (pfn_t_devmap(pfn))
+		entry = pud_mkdevmap(entry);
+	if (write) {
+		entry = pud_mkyoung(pud_mkdirty(entry));
+		entry = maybe_pud_mkwrite(entry, vma);
+	}
+	set_pud_at(mm, addr, pud, entry);
+	update_mmu_cache_pud(vma, addr, pud);
+	spin_unlock(ptl);
+}
+
+int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+			pud_t *pud, pfn_t pfn, bool write)
+{
+	pgprot_t pgprot = vma->vm_page_prot;
+	/*
+	 * If we had pud_special, we could avoid all these restrictions,
+	 * 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)) ==
+						(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;
+
+	track_pfn_insert(vma, &pgprot, pfn);
+
+	insert_pfn_pud(vma, addr, pud, pfn, pgprot, write);
+	return VM_FAULT_NOPAGE;
+}
+EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
 static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 		pmd_t *pmd)
 {
@@ -885,6 +941,123 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static void touch_pud(struct vm_area_struct *vma, unsigned long addr,
+		pud_t *pud)
+{
+	pud_t _pud;
+
+	/*
+	 * We should set the dirty bit only for FOLL_WRITE but for now
+	 * the dirty bit in the pud is meaningless.  And if the dirty
+	 * bit will become meaningful and we'll only set it with
+	 * FOLL_WRITE, an atomic set_bit will be required on the pud to
+	 * set the young bit, instead of the current set_pud_at.
+	 */
+	_pud = pud_mkyoung(pud_mkdirty(*pud));
+	if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK,
+				pud, _pud,  1))
+		update_mmu_cache_pud(vma, addr, pud);
+}
+
+struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
+		pud_t *pud, int flags)
+{
+	unsigned long pfn = pud_pfn(*pud);
+	struct mm_struct *mm = vma->vm_mm;
+	struct dev_pagemap *pgmap;
+	struct page *page;
+
+	assert_spin_locked(pud_lockptr(mm, pud));
+
+	if (flags & FOLL_WRITE && !pud_write(*pud))
+		return NULL;
+
+	if (pud_present(*pud) && pud_devmap(*pud))
+		/* pass */;
+	else
+		return NULL;
+
+	if (flags & FOLL_TOUCH)
+		touch_pud(vma, addr, pud);
+
+	/*
+	 * device mapped pages can only be returned if the
+	 * caller will manage the page reference count.
+	 */
+	if (!(flags & FOLL_GET))
+		return ERR_PTR(-EEXIST);
+
+	pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
+	pgmap = get_dev_pagemap(pfn, NULL);
+	if (!pgmap)
+		return ERR_PTR(-EFAULT);
+	page = pfn_to_page(pfn);
+	get_page(page);
+	put_dev_pagemap(pgmap);
+
+	return page;
+}
+
+int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		  pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
+		  struct vm_area_struct *vma)
+{
+	spinlock_t *dst_ptl, *src_ptl;
+	pud_t pud;
+	int ret;
+
+	dst_ptl = pud_lock(dst_mm, dst_pud);
+	src_ptl = pud_lockptr(src_mm, src_pud);
+	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+
+	ret = -EAGAIN;
+	pud = *src_pud;
+	if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud)))
+		goto out_unlock;
+
+	/*
+	 * When page table lock is held, the huge zero pud should not be
+	 * under splitting since we don't split the page itself, only pud to
+	 * a page table.
+	 */
+	if (is_huge_zero_pud(pud)) {
+		/* No huge zero pud yet */
+	}
+
+	pudp_set_wrprotect(src_mm, addr, src_pud);
+	pud = pud_mkold(pud_wrprotect(pud));
+	set_pud_at(dst_mm, addr, dst_pud, pud);
+
+	ret = 0;
+out_unlock:
+	spin_unlock(src_ptl);
+	spin_unlock(dst_ptl);
+	return ret;
+}
+
+void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
+{
+	pud_t entry;
+	unsigned long haddr;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
+
+	vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud);
+	if (unlikely(!pud_same(*vmf->pud, orig_pud)))
+		goto unlock;
+
+	entry = pud_mkyoung(orig_pud);
+	if (write)
+		entry = pud_mkdirty(entry);
+	haddr = vmf->address & HPAGE_PUD_MASK;
+	if (pudp_set_access_flags(vmf->vma, haddr, vmf->pud, entry, write))
+		update_mmu_cache_pud(vmf->vma, vmf->address, vmf->pud);
+
+unlock:
+	spin_unlock(vmf->ptl);
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
 void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd)
 {
 	pmd_t entry;
@@ -1599,6 +1772,84 @@ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
 	return NULL;
 }
 
+/*
+ * Returns true if a given pud maps a thp, false otherwise.
+ *
+ * Note that if it returns true, this routine returns without unlocking page
+ * table lock. So callers must unlock it.
+ */
+spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma)
+{
+	spinlock_t *ptl;
+
+	ptl = pud_lock(vma->vm_mm, pud);
+	if (likely(pud_trans_huge(*pud) || pud_devmap(*pud)))
+		return ptl;
+	spin_unlock(ptl);
+	return NULL;
+}
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		 pud_t *pud, unsigned long addr)
+{
+	pud_t orig_pud;
+	spinlock_t *ptl;
+
+	ptl = __pud_trans_huge_lock(pud, vma);
+	if (!ptl)
+		return 0;
+	/*
+	 * For architectures like ppc64 we look at deposited pgtable
+	 * when calling pudp_huge_get_and_clear. So do the
+	 * pgtable_trans_huge_withdraw after finishing pudp related
+	 * operations.
+	 */
+	orig_pud = pudp_huge_get_and_clear_full(tlb->mm, addr, pud,
+			tlb->fullmm);
+	tlb_remove_pud_tlb_entry(tlb, pud, addr);
+	if (vma_is_dax(vma)) {
+		spin_unlock(ptl);
+		/* No zero page support yet */
+	} else {
+		/* No support for anonymous PUD pages yet */
+		BUG();
+	}
+	return 1;
+}
+
+static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
+		unsigned long haddr)
+{
+	VM_BUG_ON(haddr & ~HPAGE_PUD_MASK);
+	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
+	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
+	VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
+
+	count_vm_event(THP_SPLIT_PMD);
+
+	pudp_huge_clear_flush_notify(vma, haddr, pud);
+}
+
+void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
+		unsigned long address)
+{
+	spinlock_t *ptl;
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long haddr = address & HPAGE_PUD_MASK;
+
+	mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PUD_SIZE);
+	ptl = pud_lock(mm, pud);
+	if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud)))
+		goto out;
+	__split_huge_pud_locked(vma, pud, haddr);
+
+out:
+	spin_unlock(ptl);
+	mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PUD_SIZE);
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
 static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 		unsigned long haddr, pmd_t *pmd)
 {
@@ -1855,32 +2106,27 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 static void freeze_page(struct page *page)
 {
 	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
-		TTU_RMAP_LOCKED;
-	int i, ret;
+		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
+	int ret;
 
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
 	if (PageAnon(page))
 		ttu_flags |= TTU_MIGRATION;
 
-	/* We only need TTU_SPLIT_HUGE_PMD once */
-	ret = try_to_unmap(page, ttu_flags | TTU_SPLIT_HUGE_PMD);
-	for (i = 1; !ret && i < HPAGE_PMD_NR; i++) {
-		/* Cut short if the page is unmapped */
-		if (page_count(page) == 1)
-			return;
-
-		ret = try_to_unmap(page + i, ttu_flags);
-	}
-	VM_BUG_ON_PAGE(ret, page + i - 1);
+	ret = try_to_unmap(page, ttu_flags);
+	VM_BUG_ON_PAGE(ret, page);
 }
 
 static void unfreeze_page(struct page *page)
 {
 	int i;
-
-	for (i = 0; i < HPAGE_PMD_NR; i++)
-		remove_migration_ptes(page + i, page + i, true);
+	if (PageTransHuge(page)) {
+		remove_migration_ptes(page, page, true);
+	} else {
+		for (i = 0; i < HPAGE_PMD_NR; i++)
+			remove_migration_ptes(page + i, page + i, true);
+	}
 }
 
 static void __split_huge_page_tail(struct page *head, int tail,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c7025c132670..d0d1d083c432 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -32,6 +32,7 @@
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
 #include <linux/node.h>
+#include <linux/userfaultfd_k.h>
 #include "internal.h"
 
 int hugepages_treat_as_movable;
@@ -1051,7 +1052,8 @@ static int __alloc_gigantic_page(unsigned long start_pfn,
 				unsigned long nr_pages)
 {
 	unsigned long end_pfn = start_pfn + nr_pages;
-	return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
+	return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE,
+				  GFP_KERNEL);
 }
 
 static bool pfn_range_valid_gigantic(struct zone *z,
@@ -3141,7 +3143,7 @@ static void hugetlb_vm_op_close(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_area_struct *vma, struct vm_fault *vmf)
+static int hugetlb_vm_op_fault(struct vm_fault *vmf)
 {
 	BUG();
 	return 0;
@@ -3680,6 +3682,38 @@ retry:
 		size = i_size_read(mapping->host) >> huge_page_shift(h);
 		if (idx >= size)
 			goto out;
+
+		/*
+		 * Check for page in userfault range
+		 */
+		if (userfaultfd_missing(vma)) {
+			u32 hash;
+			struct vm_fault vmf = {
+				.vma = vma,
+				.address = address,
+				.flags = flags,
+				/*
+				 * Hard to debug if it ends up being
+				 * used by a callee that assumes
+				 * something about the other
+				 * uninitialized fields... same as in
+				 * memory.c
+				 */
+			};
+
+			/*
+			 * hugetlb_fault_mutex must be dropped before
+			 * handling userfault.  Reacquire after handling
+			 * fault to make calling code simpler.
+			 */
+			hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping,
+							idx, address);
+			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);
 		if (IS_ERR(page)) {
 			ret = PTR_ERR(page);
@@ -3948,10 +3982,91 @@ out_mutex:
 	return ret;
 }
 
+/*
+ * Used by userfaultfd UFFDIO_COPY.  Based on mcopy_atomic_pte with
+ * modifications for huge pages.
+ */
+int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
+			    pte_t *dst_pte,
+			    struct vm_area_struct *dst_vma,
+			    unsigned long dst_addr,
+			    unsigned long src_addr,
+			    struct page **pagep)
+{
+	struct hstate *h = hstate_vma(dst_vma);
+	pte_t _dst_pte;
+	spinlock_t *ptl;
+	int ret;
+	struct page *page;
+
+	if (!*pagep) {
+		ret = -ENOMEM;
+		page = alloc_huge_page(dst_vma, dst_addr, 0);
+		if (IS_ERR(page))
+			goto out;
+
+		ret = copy_huge_page_from_user(page,
+						(const void __user *) src_addr,
+						pages_per_huge_page(h), false);
+
+		/* fallback to copy_from_user outside mmap_sem */
+		if (unlikely(ret)) {
+			ret = -EFAULT;
+			*pagep = page;
+			/* don't free the page */
+			goto out;
+		}
+	} else {
+		page = *pagep;
+		*pagep = NULL;
+	}
+
+	/*
+	 * The memory barrier inside __SetPageUptodate makes sure that
+	 * preceding stores to the page contents become visible before
+	 * the set_pte_at() write.
+	 */
+	__SetPageUptodate(page);
+	set_page_huge_active(page);
+
+	ptl = huge_pte_lockptr(h, dst_mm, dst_pte);
+	spin_lock(ptl);
+
+	ret = -EEXIST;
+	if (!huge_pte_none(huge_ptep_get(dst_pte)))
+		goto out_release_unlock;
+
+	ClearPagePrivate(page);
+	hugepage_add_new_anon_rmap(page, dst_vma, dst_addr);
+
+	_dst_pte = make_huge_pte(dst_vma, page, dst_vma->vm_flags & VM_WRITE);
+	if (dst_vma->vm_flags & VM_WRITE)
+		_dst_pte = huge_pte_mkdirty(_dst_pte);
+	_dst_pte = pte_mkyoung(_dst_pte);
+
+	set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+
+	(void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte,
+					dst_vma->vm_flags & VM_WRITE);
+	hugetlb_count_add(pages_per_huge_page(h), dst_mm);
+
+	/* No need to invalidate - it was non-present before */
+	update_mmu_cache(dst_vma, dst_addr, dst_pte);
+
+	spin_unlock(ptl);
+	ret = 0;
+out:
+	return ret;
+out_release_unlock:
+	spin_unlock(ptl);
+	put_page(page);
+	goto out;
+}
+
 long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			 struct page **pages, struct vm_area_struct **vmas,
 			 unsigned long *position, unsigned long *nr_pages,
-			 long i, unsigned int flags)
+			 long i, unsigned int flags, int *nonblocking)
 {
 	unsigned long pfn_offset;
 	unsigned long vaddr = *position;
@@ -4014,16 +4129,43 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		    ((flags & FOLL_WRITE) &&
 		      !huge_pte_write(huge_ptep_get(pte)))) {
 			int ret;
+			unsigned int fault_flags = 0;
 
 			if (pte)
 				spin_unlock(ptl);
-			ret = hugetlb_fault(mm, vma, vaddr,
-				(flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0);
-			if (!(ret & VM_FAULT_ERROR))
-				continue;
-
-			remainder = 0;
-			break;
+			if (flags & FOLL_WRITE)
+				fault_flags |= FAULT_FLAG_WRITE;
+			if (nonblocking)
+				fault_flags |= FAULT_FLAG_ALLOW_RETRY;
+			if (flags & FOLL_NOWAIT)
+				fault_flags |= FAULT_FLAG_ALLOW_RETRY |
+					FAULT_FLAG_RETRY_NOWAIT;
+			if (flags & FOLL_TRIED) {
+				VM_WARN_ON_ONCE(fault_flags &
+						FAULT_FLAG_ALLOW_RETRY);
+				fault_flags |= FAULT_FLAG_TRIED;
+			}
+			ret = hugetlb_fault(mm, vma, vaddr, fault_flags);
+			if (ret & VM_FAULT_ERROR) {
+				remainder = 0;
+				break;
+			}
+			if (ret & VM_FAULT_RETRY) {
+				if (nonblocking)
+					*nonblocking = 0;
+				*nr_pages = 0;
+				/*
+				 * VM_FAULT_RETRY must not return an
+				 * error, it will return zero
+				 * instead.
+				 *
+				 * No need to update "position" as the
+				 * caller will not check it after
+				 * *nr_pages is set to 0.
+				 */
+				return i;
+			}
+			continue;
 		}
 
 		pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
@@ -4052,6 +4194,11 @@ same_page:
 		spin_unlock(ptl);
 	}
 	*nr_pages = remainder;
+	/*
+	 * setting position is actually required only if remainder is
+	 * not zero but it's faster not to add a "if (remainder)"
+	 * branch.
+	 */
 	*position = vaddr;
 
 	return i ? i : -EFAULT;
diff --git a/mm/internal.h b/mm/internal.h
index 7aa2ea0a8623..ccfc2a2969f4 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -43,6 +43,11 @@ int do_swap_page(struct vm_fault *vmf);
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long floor, unsigned long ceiling);
 
+static inline bool can_madv_dontneed_vma(struct vm_area_struct *vma)
+{
+	return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP));
+}
+
 void unmap_page_range(struct mmu_gather *tlb,
 			     struct vm_area_struct *vma,
 			     unsigned long addr, unsigned long end,
@@ -133,9 +138,9 @@ struct alloc_context {
  * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
  */
 static inline unsigned long
-__find_buddy_index(unsigned long page_idx, unsigned int order)
+__find_buddy_pfn(unsigned long page_pfn, unsigned int order)
 {
-	return page_idx ^ (1 << order);
+	return page_pfn ^ (1 << order);
 }
 
 extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
@@ -175,6 +180,8 @@ struct compact_control {
 	struct list_head migratepages;	/* List of pages being migrated */
 	unsigned long nr_freepages;	/* Number of isolated free pages */
 	unsigned long nr_migratepages;	/* Number of pages to migrate */
+	unsigned long total_migrate_scanned;
+	unsigned long total_free_scanned;
 	unsigned long free_pfn;		/* isolate_freepages search base */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	unsigned long last_migrated_pfn;/* Not yet flushed page being freed */
@@ -328,12 +335,15 @@ __vma_address(struct page *page, struct vm_area_struct *vma)
 static inline unsigned long
 vma_address(struct page *page, struct vm_area_struct *vma)
 {
-	unsigned long address = __vma_address(page, vma);
+	unsigned long start, end;
+
+	start = __vma_address(page, vma);
+	end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1);
 
 	/* page should be within @vma mapping range */
-	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
+	VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma);
 
-	return address;
+	return max(start, vma->vm_start);
 }
 
 #else /* !CONFIG_MMU */
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 82e27d52d67a..a25dc7e82593 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -437,7 +437,7 @@ void kasan_cache_shrink(struct kmem_cache *cache)
 	quarantine_remove_cache(cache);
 }
 
-void kasan_cache_destroy(struct kmem_cache *cache)
+void kasan_cache_shutdown(struct kmem_cache *cache)
 {
 	quarantine_remove_cache(cache);
 }
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index dae929c02bbb..6f1ed1630873 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -274,6 +274,7 @@ static void per_cpu_remove_cache(void *arg)
 	qlist_free_all(&to_free, cache);
 }
 
+/* Free all quarantined objects belonging to cache. */
 void quarantine_remove_cache(struct kmem_cache *cache)
 {
 	unsigned long flags, i;
diff --git a/mm/ksm.c b/mm/ksm.c
index 9ae6011a41f8..8960f6ecbc12 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -223,6 +223,12 @@ static unsigned int ksm_thread_pages_to_scan = 100;
 /* Milliseconds ksmd should sleep between batches */
 static unsigned int ksm_thread_sleep_millisecs = 20;
 
+/* Checksum of an empty (zeroed) page */
+static unsigned int zero_checksum __read_mostly;
+
+/* Whether to merge empty (zeroed) pages with actual zero pages */
+static bool ksm_use_zero_pages __read_mostly;
+
 #ifdef CONFIG_NUMA
 /* Zeroed when merging across nodes is not allowed */
 static unsigned int ksm_merge_across_nodes = 1;
@@ -850,33 +856,35 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 			      pte_t *orig_pte)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long addr;
-	pte_t *ptep;
-	spinlock_t *ptl;
+	struct page_vma_mapped_walk pvmw = {
+		.page = page,
+		.vma = vma,
+	};
 	int swapped;
 	int err = -EFAULT;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
-	addr = page_address_in_vma(page, vma);
-	if (addr == -EFAULT)
+	pvmw.address = page_address_in_vma(page, vma);
+	if (pvmw.address == -EFAULT)
 		goto out;
 
 	BUG_ON(PageTransCompound(page));
 
-	mmun_start = addr;
-	mmun_end   = addr + PAGE_SIZE;
+	mmun_start = pvmw.address;
+	mmun_end   = pvmw.address + PAGE_SIZE;
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 
-	ptep = page_check_address(page, mm, addr, &ptl, 0);
-	if (!ptep)
+	if (!page_vma_mapped_walk(&pvmw))
 		goto out_mn;
+	if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?"))
+		goto out_unlock;
 
-	if (pte_write(*ptep) || pte_dirty(*ptep)) {
+	if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte)) {
 		pte_t entry;
 
 		swapped = PageSwapCache(page);
-		flush_cache_page(vma, addr, page_to_pfn(page));
+		flush_cache_page(vma, pvmw.address, page_to_pfn(page));
 		/*
 		 * Ok this is tricky, when get_user_pages_fast() run it doesn't
 		 * take any lock, therefore the check that we are going to make
@@ -886,25 +894,25 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 		 * this assure us that no O_DIRECT can happen after the check
 		 * or in the middle of the check.
 		 */
-		entry = ptep_clear_flush_notify(vma, addr, ptep);
+		entry = ptep_clear_flush_notify(vma, pvmw.address, pvmw.pte);
 		/*
 		 * Check that no O_DIRECT or similar I/O is in progress on the
 		 * page
 		 */
 		if (page_mapcount(page) + 1 + swapped != page_count(page)) {
-			set_pte_at(mm, addr, ptep, entry);
+			set_pte_at(mm, pvmw.address, pvmw.pte, entry);
 			goto out_unlock;
 		}
 		if (pte_dirty(entry))
 			set_page_dirty(page);
 		entry = pte_mkclean(pte_wrprotect(entry));
-		set_pte_at_notify(mm, addr, ptep, entry);
+		set_pte_at_notify(mm, pvmw.address, pvmw.pte, entry);
 	}
-	*orig_pte = *ptep;
+	*orig_pte = *pvmw.pte;
 	err = 0;
 
 out_unlock:
-	pte_unmap_unlock(ptep, ptl);
+	page_vma_mapped_walk_done(&pvmw);
 out_mn:
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 out:
@@ -926,6 +934,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	struct mm_struct *mm = vma->vm_mm;
 	pmd_t *pmd;
 	pte_t *ptep;
+	pte_t newpte;
 	spinlock_t *ptl;
 	unsigned long addr;
 	int err = -EFAULT;
@@ -950,12 +959,22 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 		goto out_mn;
 	}
 
-	get_page(kpage);
-	page_add_anon_rmap(kpage, vma, addr, false);
+	/*
+	 * No need to check ksm_use_zero_pages here: we can only have a
+	 * zero_page here if ksm_use_zero_pages was enabled alreaady.
+	 */
+	if (!is_zero_pfn(page_to_pfn(kpage))) {
+		get_page(kpage);
+		page_add_anon_rmap(kpage, vma, addr, false);
+		newpte = mk_pte(kpage, vma->vm_page_prot);
+	} else {
+		newpte = pte_mkspecial(pfn_pte(page_to_pfn(kpage),
+					       vma->vm_page_prot));
+	}
 
 	flush_cache_page(vma, addr, pte_pfn(*ptep));
 	ptep_clear_flush_notify(vma, addr, ptep);
-	set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));
+	set_pte_at_notify(mm, addr, ptep, newpte);
 
 	page_remove_rmap(page, false);
 	if (!page_mapped(page))
@@ -1467,6 +1486,23 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 		return;
 	}
 
+	/*
+	 * Same checksum as an empty page. We attempt to merge it with the
+	 * appropriate zero page if the user enabled this via sysfs.
+	 */
+	if (ksm_use_zero_pages && (checksum == zero_checksum)) {
+		struct vm_area_struct *vma;
+
+		vma = find_mergeable_vma(rmap_item->mm, rmap_item->address);
+		err = try_to_merge_one_page(vma, page,
+					    ZERO_PAGE(rmap_item->address));
+		/*
+		 * In case of failure, the page was not really empty, so we
+		 * need to continue. Otherwise we're done.
+		 */
+		if (!err)
+			return;
+	}
 	tree_rmap_item =
 		unstable_tree_search_insert(rmap_item, page, &tree_page);
 	if (tree_rmap_item) {
@@ -2233,6 +2269,28 @@ static ssize_t merge_across_nodes_store(struct kobject *kobj,
 KSM_ATTR(merge_across_nodes);
 #endif
 
+static ssize_t use_zero_pages_show(struct kobject *kobj,
+				struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", ksm_use_zero_pages);
+}
+static ssize_t use_zero_pages_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t count)
+{
+	int err;
+	bool value;
+
+	err = kstrtobool(buf, &value);
+	if (err)
+		return -EINVAL;
+
+	ksm_use_zero_pages = value;
+
+	return count;
+}
+KSM_ATTR(use_zero_pages);
+
 static ssize_t pages_shared_show(struct kobject *kobj,
 				 struct kobj_attribute *attr, char *buf)
 {
@@ -2290,6 +2348,7 @@ static struct attribute *ksm_attrs[] = {
 #ifdef CONFIG_NUMA
 	&merge_across_nodes_attr.attr,
 #endif
+	&use_zero_pages_attr.attr,
 	NULL,
 };
 
@@ -2304,6 +2363,11 @@ static int __init ksm_init(void)
 	struct task_struct *ksm_thread;
 	int err;
 
+	/* The correct value depends on page size and endianness */
+	zero_checksum = calc_checksum(ZERO_PAGE(0));
+	/* Default to false for backwards compatibility */
+	ksm_use_zero_pages = false;
+
 	err = ksm_slab_init();
 	if (err)
 		goto out;
diff --git a/mm/madvise.c b/mm/madvise.c
index 0e3828eae9f8..11fc65f81ecd 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -10,6 +10,7 @@
 #include <linux/syscalls.h>
 #include <linux/mempolicy.h>
 #include <linux/page-isolation.h>
+#include <linux/userfaultfd_k.h>
 #include <linux/hugetlb.h>
 #include <linux/falloc.h>
 #include <linux/sched.h>
@@ -24,6 +25,8 @@
 
 #include <asm/tlb.h>
 
+#include "internal.h"
+
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
  * take mmap_sem for writing. Others, which simply traverse vmas, need
@@ -89,14 +92,28 @@ static long madvise_behavior(struct vm_area_struct *vma,
 	case MADV_MERGEABLE:
 	case MADV_UNMERGEABLE:
 		error = ksm_madvise(vma, start, end, behavior, &new_flags);
-		if (error)
+		if (error) {
+			/*
+			 * madvise() returns EAGAIN if kernel resources, such as
+			 * slab, are temporarily unavailable.
+			 */
+			if (error == -ENOMEM)
+				error = -EAGAIN;
 			goto out;
+		}
 		break;
 	case MADV_HUGEPAGE:
 	case MADV_NOHUGEPAGE:
 		error = hugepage_madvise(vma, &new_flags, behavior);
-		if (error)
+		if (error) {
+			/*
+			 * madvise() returns EAGAIN if kernel resources, such as
+			 * slab, are temporarily unavailable.
+			 */
+			if (error == -ENOMEM)
+				error = -EAGAIN;
 			goto out;
+		}
 		break;
 	}
 
@@ -117,15 +134,37 @@ static long madvise_behavior(struct vm_area_struct *vma,
 	*prev = vma;
 
 	if (start != vma->vm_start) {
-		error = split_vma(mm, vma, start, 1);
-		if (error)
+		if (unlikely(mm->map_count >= sysctl_max_map_count)) {
+			error = -ENOMEM;
 			goto out;
+		}
+		error = __split_vma(mm, vma, start, 1);
+		if (error) {
+			/*
+			 * madvise() returns EAGAIN if kernel resources, such as
+			 * slab, are temporarily unavailable.
+			 */
+			if (error == -ENOMEM)
+				error = -EAGAIN;
+			goto out;
+		}
 	}
 
 	if (end != vma->vm_end) {
-		error = split_vma(mm, vma, end, 0);
-		if (error)
+		if (unlikely(mm->map_count >= sysctl_max_map_count)) {
+			error = -ENOMEM;
 			goto out;
+		}
+		error = __split_vma(mm, vma, end, 0);
+		if (error) {
+			/*
+			 * madvise() returns EAGAIN if kernel resources, such as
+			 * slab, are temporarily unavailable.
+			 */
+			if (error == -ENOMEM)
+				error = -EAGAIN;
+			goto out;
+		}
 	}
 
 success:
@@ -133,10 +172,7 @@ success:
 	 * vm_flags is protected by the mmap_sem held in write mode.
 	 */
 	vma->vm_flags = new_flags;
-
 out:
-	if (error == -ENOMEM)
-		error = -EAGAIN;
 	return error;
 }
 
@@ -473,10 +509,11 @@ static long madvise_dontneed(struct vm_area_struct *vma,
 			     unsigned long start, unsigned long end)
 {
 	*prev = vma;
-	if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
+	if (!can_madv_dontneed_vma(vma))
 		return -EINVAL;
 
-	zap_page_range(vma, start, end - start, NULL);
+	userfaultfd_remove(vma, prev, start, end);
+	zap_page_range(vma, start, end - start);
 	return 0;
 }
 
@@ -516,6 +553,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 	 * mmap_sem.
 	 */
 	get_file(f);
+	userfaultfd_remove(vma, prev, start, end);
 	up_read(&current->mm->mmap_sem);
 	error = vfs_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
diff --git a/mm/memblock.c b/mm/memblock.c
index 7608bc305936..b64b47803e52 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -35,15 +35,18 @@ struct memblock memblock __initdata_memblock = {
 	.memory.regions		= memblock_memory_init_regions,
 	.memory.cnt		= 1,	/* empty dummy entry */
 	.memory.max		= INIT_MEMBLOCK_REGIONS,
+	.memory.name		= "memory",
 
 	.reserved.regions	= memblock_reserved_init_regions,
 	.reserved.cnt		= 1,	/* empty dummy entry */
 	.reserved.max		= INIT_MEMBLOCK_REGIONS,
+	.reserved.name		= "reserved",
 
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
 	.physmem.regions	= memblock_physmem_init_regions,
 	.physmem.cnt		= 1,	/* empty dummy entry */
 	.physmem.max		= INIT_PHYSMEM_REGIONS,
+	.physmem.name		= "physmem",
 #endif
 
 	.bottom_up		= false,
@@ -64,18 +67,6 @@ ulong __init_memblock choose_memblock_flags(void)
 	return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE;
 }
 
-/* inline so we don't get a warning when pr_debug is compiled out */
-static __init_memblock const char *
-memblock_type_name(struct memblock_type *type)
-{
-	if (type == &memblock.memory)
-		return "memory";
-	else if (type == &memblock.reserved)
-		return "reserved";
-	else
-		return "unknown";
-}
-
 /* 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)
 {
@@ -402,12 +393,12 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 	}
 	if (!addr) {
 		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
-		       memblock_type_name(type), type->max, type->max * 2);
+		       type->name, type->max, type->max * 2);
 		return -1;
 	}
 
 	memblock_dbg("memblock: %s is doubled to %ld at [%#010llx-%#010llx]",
-			memblock_type_name(type), type->max * 2, (u64)addr,
+			type->name, type->max * 2, (u64)addr,
 			(u64)addr + new_size - 1);
 
 	/*
@@ -611,10 +602,10 @@ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
 
 int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 {
-	memblock_dbg("memblock_add: [%#016llx-%#016llx] flags %#02lx %pF\n",
-		     (unsigned long long)base,
-		     (unsigned long long)base + size - 1,
-		     0UL, (void *)_RET_IP_);
+	phys_addr_t end = base + size - 1;
+
+	memblock_dbg("memblock_add: [%pa-%pa] %pF\n",
+		     &base, &end, (void *)_RET_IP_);
 
 	return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0);
 }
@@ -718,10 +709,10 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
 
 int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
 {
-	memblock_dbg("   memblock_free: [%#016llx-%#016llx] %pF\n",
-		     (unsigned long long)base,
-		     (unsigned long long)base + size - 1,
-		     (void *)_RET_IP_);
+	phys_addr_t end = base + size - 1;
+
+	memblock_dbg("   memblock_free: [%pa-%pa] %pF\n",
+		     &base, &end, (void *)_RET_IP_);
 
 	kmemleak_free_part_phys(base, size);
 	return memblock_remove_range(&memblock.reserved, base, size);
@@ -729,10 +720,10 @@ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
 
 int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
 {
-	memblock_dbg("memblock_reserve: [%#016llx-%#016llx] flags %#02lx %pF\n",
-		     (unsigned long long)base,
-		     (unsigned long long)base + size - 1,
-		     0UL, (void *)_RET_IP_);
+	phys_addr_t end = base + size - 1;
+
+	memblock_dbg("memblock_reserve: [%pa-%pa] %pF\n",
+		     &base, &end, (void *)_RET_IP_);
 
 	return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0);
 }
@@ -1105,6 +1096,31 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid,
 		*out_nid = r->nid;
 }
 
+unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn,
+						      unsigned long max_pfn)
+{
+	struct memblock_type *type = &memblock.memory;
+	unsigned int right = type->cnt;
+	unsigned int mid, left = 0;
+	phys_addr_t addr = PFN_PHYS(pfn + 1);
+
+	do {
+		mid = (right + left) / 2;
+
+		if (addr < type->regions[mid].base)
+			right = mid;
+		else if (addr >= (type->regions[mid].base +
+				  type->regions[mid].size))
+			left = mid + 1;
+		else {
+			/* addr is within the region, so pfn + 1 is valid */
+			return min(pfn + 1, max_pfn);
+		}
+	} while (left < right);
+
+	return min(PHYS_PFN(type->regions[right].base), max_pfn);
+}
+
 /**
  * memblock_set_node - set node ID on memblock regions
  * @base: base of area to set node ID for
@@ -1202,8 +1218,8 @@ phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys
 	alloc = __memblock_alloc_base(size, align, max_addr);
 
 	if (alloc == 0)
-		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
-		      (unsigned long long) size, (unsigned long long) max_addr);
+		panic("ERROR: Failed to allocate %pa bytes below %pa.\n",
+		      &size, &max_addr);
 
 	return alloc;
 }
@@ -1274,18 +1290,17 @@ static void * __init memblock_virt_alloc_internal(
 
 	if (max_addr > memblock.current_limit)
 		max_addr = memblock.current_limit;
-
 again:
 	alloc = memblock_find_in_range_node(size, align, min_addr, max_addr,
 					    nid, flags);
-	if (alloc)
+	if (alloc && !memblock_reserve(alloc, size))
 		goto done;
 
 	if (nid != NUMA_NO_NODE) {
 		alloc = memblock_find_in_range_node(size, align, min_addr,
 						    max_addr, NUMA_NO_NODE,
 						    flags);
-		if (alloc)
+		if (alloc && !memblock_reserve(alloc, size))
 			goto done;
 	}
 
@@ -1303,7 +1318,6 @@ again:
 
 	return NULL;
 done:
-	memblock_reserve(alloc, size);
 	ptr = phys_to_virt(alloc);
 	memset(ptr, 0, size);
 
@@ -1615,8 +1629,7 @@ int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size
 
 	if (idx == -1)
 		return 0;
-	return memblock.memory.regions[idx].base <= base &&
-		(memblock.memory.regions[idx].base +
+	return (memblock.memory.regions[idx].base +
 		 memblock.memory.regions[idx].size) >= end;
 }
 
@@ -1671,40 +1684,44 @@ phys_addr_t __init_memblock memblock_get_current_limit(void)
 	return memblock.current_limit;
 }
 
-static void __init_memblock memblock_dump(struct memblock_type *type, char *name)
+static void __init_memblock memblock_dump(struct memblock_type *type)
 {
-	unsigned long long base, size;
+	phys_addr_t base, end, size;
 	unsigned long flags;
 	int idx;
 	struct memblock_region *rgn;
 
-	pr_info(" %s.cnt  = 0x%lx\n", name, type->cnt);
+	pr_info(" %s.cnt  = 0x%lx\n", type->name, type->cnt);
 
 	for_each_memblock_type(type, rgn) {
 		char nid_buf[32] = "";
 
 		base = rgn->base;
 		size = rgn->size;
+		end = base + size - 1;
 		flags = rgn->flags;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 		if (memblock_get_region_node(rgn) != MAX_NUMNODES)
 			snprintf(nid_buf, sizeof(nid_buf), " on node %d",
 				 memblock_get_region_node(rgn));
 #endif
-		pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s flags: %#lx\n",
-			name, idx, base, base + size - 1, size, nid_buf, flags);
+		pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#lx\n",
+			type->name, idx, &base, &end, &size, nid_buf, flags);
 	}
 }
 
 void __init_memblock __memblock_dump_all(void)
 {
 	pr_info("MEMBLOCK configuration:\n");
-	pr_info(" memory size = %#llx reserved size = %#llx\n",
-		(unsigned long long)memblock.memory.total_size,
-		(unsigned long long)memblock.reserved.total_size);
+	pr_info(" memory size = %pa reserved size = %pa\n",
+		&memblock.memory.total_size,
+		&memblock.reserved.total_size);
 
-	memblock_dump(&memblock.memory, "memory");
-	memblock_dump(&memblock.reserved, "reserved");
+	memblock_dump(&memblock.memory);
+	memblock_dump(&memblock.reserved);
+#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
+	memblock_dump(&memblock.physmem);
+#endif
 }
 
 void __init memblock_allow_resize(void)
@@ -1727,19 +1744,14 @@ static int memblock_debug_show(struct seq_file *m, void *private)
 	struct memblock_type *type = m->private;
 	struct memblock_region *reg;
 	int i;
+	phys_addr_t end;
 
 	for (i = 0; i < type->cnt; i++) {
 		reg = &type->regions[i];
-		seq_printf(m, "%4d: ", i);
-		if (sizeof(phys_addr_t) == 4)
-			seq_printf(m, "0x%08lx..0x%08lx\n",
-				   (unsigned long)reg->base,
-				   (unsigned long)(reg->base + reg->size - 1));
-		else
-			seq_printf(m, "0x%016llx..0x%016llx\n",
-				   (unsigned long long)reg->base,
-				   (unsigned long long)(reg->base + reg->size - 1));
+		end = reg->base + reg->size - 1;
 
+		seq_printf(m, "%4d: ", i);
+		seq_printf(m, "%pa..%pa\n", &reg->base, &end);
 	}
 	return 0;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b822e158b319..1fd6affcdde7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -317,6 +317,8 @@ void memcg_put_cache_ids(void)
 DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key);
 EXPORT_SYMBOL(memcg_kmem_enabled_key);
 
+struct workqueue_struct *memcg_kmem_cache_wq;
+
 #endif /* !CONFIG_SLOB */
 
 /**
@@ -2143,8 +2145,6 @@ struct memcg_kmem_cache_create_work {
 	struct work_struct work;
 };
 
-static struct workqueue_struct *memcg_kmem_cache_create_wq;
-
 static void memcg_kmem_cache_create_func(struct work_struct *w)
 {
 	struct memcg_kmem_cache_create_work *cw =
@@ -2176,7 +2176,7 @@ static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
 	cw->cachep = cachep;
 	INIT_WORK(&cw->work, memcg_kmem_cache_create_func);
 
-	queue_work(memcg_kmem_cache_create_wq, &cw->work);
+	queue_work(memcg_kmem_cache_wq, &cw->work);
 }
 
 static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
@@ -2837,6 +2837,7 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
 	 */
 	memcg->kmemcg_id = memcg_id;
 	memcg->kmem_state = KMEM_ONLINE;
+	INIT_LIST_HEAD(&memcg->kmem_caches);
 
 	return 0;
 }
@@ -4002,9 +4003,9 @@ static struct cftype mem_cgroup_legacy_files[] = {
 #ifdef CONFIG_SLABINFO
 	{
 		.name = "kmem.slabinfo",
-		.seq_start = slab_start,
-		.seq_next = slab_next,
-		.seq_stop = slab_stop,
+		.seq_start = memcg_slab_start,
+		.seq_next = memcg_slab_next,
+		.seq_stop = memcg_slab_stop,
 		.seq_show = memcg_slab_show,
 	},
 #endif
@@ -5777,12 +5778,12 @@ static int __init mem_cgroup_init(void)
 #ifndef CONFIG_SLOB
 	/*
 	 * Kmem cache creation is mostly done with the slab_mutex held,
-	 * so use a special workqueue to avoid stalling all worker
-	 * threads in case lots of cgroups are created simultaneously.
+	 * so use a workqueue with limited concurrency to avoid stalling
+	 * all worker threads in case lots of cgroups are created and
+	 * destroyed simultaneously.
 	 */
-	memcg_kmem_cache_create_wq =
-		alloc_ordered_workqueue("memcg_kmem_cache_create", 0);
-	BUG_ON(!memcg_kmem_cache_create_wq);
+	memcg_kmem_cache_wq = alloc_workqueue("memcg_kmem_cache", 0, 1);
+	BUG_ON(!memcg_kmem_cache_wq);
 #endif
 
 	cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index f283c7e0a2a3..3d0f2fd4bf73 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1527,7 +1527,8 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 {
 	int ret = __get_any_page(page, pfn, flags);
 
-	if (ret == 1 && !PageHuge(page) && !PageLRU(page)) {
+	if (ret == 1 && !PageHuge(page) &&
+	    !PageLRU(page) && !__PageMovable(page)) {
 		/*
 		 * Try to free it.
 		 */
@@ -1649,7 +1650,10 @@ static int __soft_offline_page(struct page *page, int flags)
 	 * Try to migrate to a new page instead. migrate.c
 	 * handles a large number of cases for us.
 	 */
-	ret = isolate_lru_page(page);
+	if (PageLRU(page))
+		ret = isolate_lru_page(page);
+	else
+		ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE);
 	/*
 	 * Drop page reference which is came from get_any_page()
 	 * successful isolate_lru_page() already took another one.
@@ -1657,18 +1661,20 @@ static int __soft_offline_page(struct page *page, int flags)
 	put_hwpoison_page(page);
 	if (!ret) {
 		LIST_HEAD(pagelist);
-		inc_node_page_state(page, NR_ISOLATED_ANON +
-					page_is_file_cache(page));
+		/*
+		 * After isolated lru page, the PageLRU will be cleared,
+		 * so use !__PageMovable instead for LRU page's mapping
+		 * cannot have PAGE_MAPPING_MOVABLE.
+		 */
+		if (!__PageMovable(page))
+			inc_node_page_state(page, NR_ISOLATED_ANON +
+						page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
 		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 					MIGRATE_SYNC, MR_MEMORY_FAILURE);
 		if (ret) {
-			if (!list_empty(&pagelist)) {
-				list_del(&page->lru);
-				dec_node_page_state(page, NR_ISOLATED_ANON +
-						page_is_file_cache(page));
-				putback_lru_page(page);
-			}
+			if (!list_empty(&pagelist))
+				putback_movable_pages(&pagelist);
 
 			pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
 				pfn, ret, page->flags);
diff --git a/mm/memory.c b/mm/memory.c
index 6bf2b471e30c..0c759ba122e1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -30,7 +30,7 @@
 
 /*
  * 05.04.94  -  Multi-page memory management added for v1.1.
- * 		Idea by Alex Bligh (alex@cconcepts.co.uk)
+ *              Idea by Alex Bligh (alex@cconcepts.co.uk)
  *
  * 16.07.99  -  Support of BIGMEM added by Gerhard Wichert, Siemens AG
  *		(Gerhard.Wichert@pdb.siemens.de)
@@ -82,9 +82,9 @@
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 /* use the per-pgdat data instead for discontigmem - mbligh */
 unsigned long max_mapnr;
-struct page *mem_map;
-
 EXPORT_SYMBOL(max_mapnr);
+
+struct page *mem_map;
 EXPORT_SYMBOL(mem_map);
 #endif
 
@@ -95,8 +95,7 @@ EXPORT_SYMBOL(mem_map);
  * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
  * and ZONE_HIGHMEM.
  */
-void * high_memory;
-
+void *high_memory;
 EXPORT_SYMBOL(high_memory);
 
 /*
@@ -120,10 +119,10 @@ static int __init disable_randmaps(char *s)
 __setup("norandmaps", disable_randmaps);
 
 unsigned long zero_pfn __read_mostly;
-unsigned long highest_memmap_pfn __read_mostly;
-
 EXPORT_SYMBOL(zero_pfn);
 
+unsigned long highest_memmap_pfn __read_mostly;
+
 /*
  * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
  */
@@ -556,7 +555,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 		if (is_vm_hugetlb_page(vma)) {
 			hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
-				floor, next? next->vm_start: ceiling);
+				floor, next ? next->vm_start : ceiling);
 		} else {
 			/*
 			 * Optimization: gather nearby vmas into one call down
@@ -569,7 +568,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
 				unlink_file_vma(vma);
 			}
 			free_pgd_range(tlb, addr, vma->vm_end,
-				floor, next? next->vm_start: ceiling);
+				floor, next ? next->vm_start : ceiling);
 		}
 		vma = next;
 	}
@@ -1001,7 +1000,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 		next = pmd_addr_end(addr, end);
 		if (pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) {
 			int err;
-			VM_BUG_ON(next-addr != HPAGE_PMD_SIZE);
+			VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, vma);
 			err = copy_huge_pmd(dst_mm, src_mm,
 					    dst_pmd, src_pmd, addr, vma);
 			if (err == -ENOMEM)
@@ -1032,6 +1031,18 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
 	src_pud = pud_offset(src_pgd, addr);
 	do {
 		next = pud_addr_end(addr, end);
+		if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
+			int err;
+
+			VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, vma);
+			err = copy_huge_pud(dst_mm, src_mm,
+					    dst_pud, src_pud, addr, vma);
+			if (err == -ENOMEM)
+				return -ENOMEM;
+			if (!err)
+				continue;
+			/* fall through */
+		}
 		if (pud_none_or_clear_bad(src_pud))
 			continue;
 		if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
@@ -1129,9 +1140,8 @@ again:
 	arch_enter_lazy_mmu_mode();
 	do {
 		pte_t ptent = *pte;
-		if (pte_none(ptent)) {
+		if (pte_none(ptent))
 			continue;
-		}
 
 		if (pte_present(ptent)) {
 			struct page *page;
@@ -1155,12 +1165,6 @@ again:
 
 			if (!PageAnon(page)) {
 				if (pte_dirty(ptent)) {
-					/*
-					 * oom_reaper cannot tear down dirty
-					 * pages
-					 */
-					if (unlikely(details && details->ignore_dirty))
-						continue;
 					force_flush = 1;
 					set_page_dirty(page);
 				}
@@ -1179,8 +1183,8 @@ again:
 			}
 			continue;
 		}
-		/* only check swap_entries if explicitly asked for in details */
-		if (unlikely(details && !details->check_swap_entries))
+		/* If details->check_mapping, we leave swap entries. */
+		if (unlikely(details))
 			continue;
 
 		entry = pte_to_swp_entry(ptent);
@@ -1269,9 +1273,19 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 	pud = pud_offset(pgd, addr);
 	do {
 		next = pud_addr_end(addr, end);
+		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
+			if (next - addr != HPAGE_PUD_SIZE) {
+				VM_BUG_ON_VMA(!rwsem_is_locked(&tlb->mm->mmap_sem), vma);
+				split_huge_pud(vma, pud, addr);
+			} else if (zap_huge_pud(tlb, vma, pud, addr))
+				goto next;
+			/* fall through */
+		}
 		if (pud_none_or_clear_bad(pud))
 			continue;
 		next = zap_pmd_range(tlb, vma, pud, addr, next, details);
+next:
+		cond_resched();
 	} while (pud++, addr = next, addr != end);
 
 	return addr;
@@ -1376,12 +1390,11 @@ void unmap_vmas(struct mmu_gather *tlb,
  * @vma: vm_area_struct holding the applicable pages
  * @start: starting address of pages to zap
  * @size: number of bytes to zap
- * @details: details of shared cache invalidation
  *
  * Caller must protect the VMA list
  */
 void zap_page_range(struct vm_area_struct *vma, unsigned long start,
-		unsigned long size, struct zap_details *details)
+		unsigned long size)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct mmu_gather tlb;
@@ -1392,7 +1405,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
 	update_hiwater_rss(mm);
 	mmu_notifier_invalidate_range_start(mm, start, end);
 	for ( ; vma && vma->vm_start < end; vma = vma->vm_next)
-		unmap_single_vma(&tlb, vma, start, end, details);
+		unmap_single_vma(&tlb, vma, start, end, NULL);
 	mmu_notifier_invalidate_range_end(mm, start, end);
 	tlb_finish_mmu(&tlb, start, end);
 }
@@ -1448,10 +1461,10 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes);
 pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
 			spinlock_t **ptl)
 {
-	pgd_t * pgd = pgd_offset(mm, addr);
-	pud_t * pud = pud_alloc(mm, pgd, addr);
+	pgd_t *pgd = pgd_offset(mm, addr);
+	pud_t *pud = pud_alloc(mm, pgd, addr);
 	if (pud) {
-		pmd_t * pmd = pmd_alloc(mm, pud, addr);
+		pmd_t *pmd = pmd_alloc(mm, pud, addr);
 		if (pmd) {
 			VM_BUG_ON(pmd_trans_huge(*pmd));
 			return pte_alloc_map_lock(mm, pmd, addr, ptl);
@@ -2042,7 +2055,7 @@ static int do_page_mkwrite(struct vm_fault *vmf)
 
 	vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
 
-	ret = vmf->vma->vm_ops->page_mkwrite(vmf->vma, vmf);
+	ret = vmf->vma->vm_ops->page_mkwrite(vmf);
 	/* Restore original flags so that caller is not surprised */
 	vmf->flags = old_flags;
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
@@ -2314,7 +2327,7 @@ static int wp_pfn_shared(struct vm_fault *vmf)
 
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		vmf->flags |= FAULT_FLAG_MKWRITE;
-		ret = vma->vm_ops->pfn_mkwrite(vma, vmf);
+		ret = vma->vm_ops->pfn_mkwrite(vmf);
 		if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))
 			return ret;
 		return finish_mkwrite_fault(vmf);
@@ -2510,7 +2523,7 @@ void unmap_mapping_range(struct address_space *mapping,
 			hlen = ULONG_MAX - hba + 1;
 	}
 
-	details.check_mapping = even_cows? NULL: mapping;
+	details.check_mapping = even_cows ? NULL : mapping;
 	details.first_index = hba;
 	details.last_index = hba + hlen - 1;
 	if (details.last_index < details.first_index)
@@ -2868,7 +2881,7 @@ static int __do_fault(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	int ret;
 
-	ret = vma->vm_ops->fault(vma, vmf);
+	ret = vma->vm_ops->fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY |
 			    VM_FAULT_DONE_COW)))
 		return ret;
@@ -2905,7 +2918,7 @@ static int pte_alloc_one_map(struct vm_fault *vmf)
 		atomic_long_inc(&vma->vm_mm->nr_ptes);
 		pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
 		spin_unlock(vmf->ptl);
-		vmf->prealloc_pte = 0;
+		vmf->prealloc_pte = NULL;
 	} else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd, vmf->address))) {
 		return VM_FAULT_OOM;
 	}
@@ -2953,7 +2966,7 @@ static void deposit_prealloc_pte(struct vm_fault *vmf)
 	 * count that as nr_ptes.
 	 */
 	atomic_long_inc(&vma->vm_mm->nr_ptes);
-	vmf->prealloc_pte = 0;
+	vmf->prealloc_pte = NULL;
 }
 
 static int do_set_pmd(struct vm_fault *vmf, struct page *page)
@@ -3359,7 +3372,7 @@ static int do_fault(struct vm_fault *vmf)
 	/* preallocated pagetable is unused: free it */
 	if (vmf->prealloc_pte) {
 		pte_free(vma->vm_mm, vmf->prealloc_pte);
-		vmf->prealloc_pte = 0;
+		vmf->prealloc_pte = NULL;
 	}
 	return ret;
 }
@@ -3387,32 +3400,32 @@ static int do_numa_page(struct vm_fault *vmf)
 	int last_cpupid;
 	int target_nid;
 	bool migrated = false;
-	pte_t pte = vmf->orig_pte;
-	bool was_writable = pte_write(pte);
+	pte_t pte;
+	bool was_writable = pte_write(vmf->orig_pte);
 	int flags = 0;
 
 	/*
-	* The "pte" at this point cannot be used safely without
-	* validation through pte_unmap_same(). It's of NUMA type but
-	* the pfn may be screwed if the read is non atomic.
-	*
-	* We can safely just do a "set_pte_at()", because the old
-	* page table entry is not accessible, so there would be no
-	* concurrent hardware modifications to the PTE.
-	*/
+	 * The "pte" at this point cannot be used safely without
+	 * validation through pte_unmap_same(). It's of NUMA type but
+	 * the pfn may be screwed if the read is non atomic.
+	 */
 	vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd);
 	spin_lock(vmf->ptl);
-	if (unlikely(!pte_same(*vmf->pte, pte))) {
+	if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) {
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		goto out;
 	}
 
-	/* Make it present again */
+	/*
+	 * Make it present again, Depending on how arch implementes non
+	 * accessible ptes, some can allow access by kernel mode.
+	 */
+	pte = ptep_modify_prot_start(vma->vm_mm, vmf->address, vmf->pte);
 	pte = pte_modify(pte, vma->vm_page_prot);
 	pte = pte_mkyoung(pte);
 	if (was_writable)
 		pte = pte_mkwrite(pte);
-	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
+	ptep_modify_prot_commit(vma->vm_mm, vmf->address, vmf->pte, pte);
 	update_mmu_cache(vma, vmf->address, vmf->pte);
 
 	page = vm_normal_page(vma, vmf->address, pte);
@@ -3471,12 +3484,10 @@ out:
 
 static int create_huge_pmd(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = vmf->vma;
-	if (vma_is_anonymous(vma))
+	if (vma_is_anonymous(vmf->vma))
 		return do_huge_pmd_anonymous_page(vmf);
-	if (vma->vm_ops->pmd_fault)
-		return vma->vm_ops->pmd_fault(vma, vmf->address, vmf->pmd,
-				vmf->flags);
+	if (vmf->vma->vm_ops->huge_fault)
+		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
 	return VM_FAULT_FALLBACK;
 }
 
@@ -3484,9 +3495,8 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 {
 	if (vma_is_anonymous(vmf->vma))
 		return do_huge_pmd_wp_page(vmf, orig_pmd);
-	if (vmf->vma->vm_ops->pmd_fault)
-		return vmf->vma->vm_ops->pmd_fault(vmf->vma, vmf->address,
-						   vmf->pmd, vmf->flags);
+	if (vmf->vma->vm_ops->huge_fault)
+		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
 
 	/* COW handled on pte level: split pmd */
 	VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
@@ -3500,6 +3510,30 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma)
 	return vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE);
 }
 
+static int create_huge_pud(struct vm_fault *vmf)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	/* No support for anonymous transparent PUD pages yet */
+	if (vma_is_anonymous(vmf->vma))
+		return VM_FAULT_FALLBACK;
+	if (vmf->vma->vm_ops->huge_fault)
+		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+	return VM_FAULT_FALLBACK;
+}
+
+static int wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	/* No support for anonymous transparent PUD pages yet */
+	if (vma_is_anonymous(vmf->vma))
+		return VM_FAULT_FALLBACK;
+	if (vmf->vma->vm_ops->huge_fault)
+		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+	return VM_FAULT_FALLBACK;
+}
+
 /*
  * These routines also need to handle stuff like marking pages dirty
  * and/or accessed for architectures that don't do it in hardware (most
@@ -3615,22 +3649,46 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	};
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
-	pud_t *pud;
+	int ret;
 
 	pgd = pgd_offset(mm, address);
-	pud = pud_alloc(mm, pgd, address);
-	if (!pud)
+
+	vmf.pud = pud_alloc(mm, pgd, address);
+	if (!vmf.pud)
 		return VM_FAULT_OOM;
-	vmf.pmd = pmd_alloc(mm, pud, address);
+	if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
+		ret = create_huge_pud(&vmf);
+		if (!(ret & VM_FAULT_FALLBACK))
+			return ret;
+	} else {
+		pud_t orig_pud = *vmf.pud;
+
+		barrier();
+		if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
+			unsigned int dirty = flags & FAULT_FLAG_WRITE;
+
+			/* NUMA case for anonymous PUDs would go here */
+
+			if (dirty && !pud_write(orig_pud)) {
+				ret = wp_huge_pud(&vmf, orig_pud);
+				if (!(ret & VM_FAULT_FALLBACK))
+					return ret;
+			} else {
+				huge_pud_set_accessed(&vmf, orig_pud);
+				return 0;
+			}
+		}
+	}
+
+	vmf.pmd = pmd_alloc(mm, vmf.pud, address);
 	if (!vmf.pmd)
 		return VM_FAULT_OOM;
 	if (pmd_none(*vmf.pmd) && transparent_hugepage_enabled(vma)) {
-		int ret = create_huge_pmd(&vmf);
+		ret = create_huge_pmd(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
 	} else {
 		pmd_t orig_pmd = *vmf.pmd;
-		int ret;
 
 		barrier();
 		if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
@@ -3690,14 +3748,14 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 
 	if (flags & FAULT_FLAG_USER) {
 		mem_cgroup_oom_disable();
-                /*
-                 * The task may have entered a memcg OOM situation but
-                 * if the allocation error was handled gracefully (no
-                 * VM_FAULT_OOM), there is no need to kill anything.
-                 * Just clean up the OOM state peacefully.
-                 */
-                if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
-                        mem_cgroup_oom_synchronize(false);
+		/*
+		 * The task may have entered a memcg OOM situation but
+		 * if the allocation error was handled gracefully (no
+		 * VM_FAULT_OOM), there is no need to kill anything.
+		 * Just clean up the OOM state peacefully.
+		 */
+		if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
+			mem_cgroup_oom_synchronize(false);
 	}
 
 	/*
@@ -3747,13 +3805,14 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
  */
 int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 {
+	spinlock_t *ptl;
 	pmd_t *new = pmd_alloc_one(mm, address);
 	if (!new)
 		return -ENOMEM;
 
 	smp_wmb(); /* See comment in __pte_alloc */
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pud_lock(mm, pud);
 #ifndef __ARCH_HAS_4LEVEL_HACK
 	if (!pud_present(*pud)) {
 		mm_inc_nr_pmds(mm);
@@ -3767,7 +3826,7 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 	} else /* Another has populated it */
 		pmd_free(mm, new);
 #endif /* __ARCH_HAS_4LEVEL_HACK */
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	return 0;
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
@@ -4155,6 +4214,38 @@ void copy_user_huge_page(struct page *dst, struct page *src,
 		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
 	}
 }
+
+long copy_huge_page_from_user(struct page *dst_page,
+				const void __user *usr_src,
+				unsigned int pages_per_huge_page,
+				bool allow_pagefault)
+{
+	void *src = (void *)usr_src;
+	void *page_kaddr;
+	unsigned long i, rc = 0;
+	unsigned long ret_val = pages_per_huge_page * PAGE_SIZE;
+
+	for (i = 0; i < pages_per_huge_page; i++) {
+		if (allow_pagefault)
+			page_kaddr = kmap(dst_page + i);
+		else
+			page_kaddr = kmap_atomic(dst_page + i);
+		rc = copy_from_user(page_kaddr,
+				(const void __user *)(src + i * PAGE_SIZE),
+				PAGE_SIZE);
+		if (allow_pagefault)
+			kunmap(dst_page + i);
+		else
+			kunmap_atomic(page_kaddr);
+
+		ret_val -= (PAGE_SIZE - rc);
+		if (rc)
+			break;
+
+		cond_resched();
+	}
+	return ret_val;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
 
 #if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b8c11e063ff0..11581f4cfbb4 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -179,7 +179,7 @@ static void release_memory_resource(struct resource *res)
 void get_page_bootmem(unsigned long info,  struct page *page,
 		      unsigned long type)
 {
-	page->lru.next = (struct list_head *) type;
+	page->freelist = (void *)type;
 	SetPagePrivate(page);
 	set_page_private(page, info);
 	page_ref_inc(page);
@@ -189,11 +189,12 @@ void put_page_bootmem(struct page *page)
 {
 	unsigned long type;
 
-	type = (unsigned long) page->lru.next;
+	type = (unsigned long) page->freelist;
 	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
 	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
 
 	if (page_ref_dec_return(page) == 1) {
+		page->freelist = NULL;
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
 		INIT_LIST_HEAD(&page->lru);
@@ -227,7 +228,7 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 	for (i = 0; i < mapsize; i++, page++)
 		get_page_bootmem(section_nr, page, SECTION_INFO);
 
-	usemap = __nr_to_section(section_nr)->pageblock_flags;
+	usemap = section_to_usemap(__nr_to_section(section_nr));
 	page = virt_to_page(usemap);
 
 	mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
@@ -253,7 +254,7 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 
 	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
 
-	usemap = __nr_to_section(section_nr)->pageblock_flags;
+	usemap = section_to_usemap(__nr_to_section(section_nr));
 	page = virt_to_page(usemap);
 
 	mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
@@ -466,10 +467,10 @@ static void __meminit grow_pgdat_span(struct pglist_data *pgdat, unsigned long s
 					pgdat->node_start_pfn;
 }
 
-static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
+static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn,
+		unsigned long nr_pages)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
-	int nr_pages = PAGES_PER_SECTION;
 	int nid = pgdat->node_id;
 	int zone_type;
 	unsigned long flags, pfn;
@@ -499,24 +500,21 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 }
 
 static int __meminit __add_section(int nid, struct zone *zone,
-					unsigned long phys_start_pfn)
+		unsigned long pfn, unsigned long nr_pages)
 {
 	int ret;
 
-	if (pfn_valid(phys_start_pfn))
-		return -EEXIST;
-
-	ret = sparse_add_one_section(zone, phys_start_pfn);
+	ret = sparse_add_section(zone, pfn, nr_pages);
 
 	if (ret < 0)
 		return ret;
 
-	ret = __add_zone(zone, phys_start_pfn);
+	ret = __add_zone(zone, pfn, nr_pages);
 
 	if (ret < 0)
 		return ret;
 
-	return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
+	return register_new_memory(zone, nid, __pfn_to_section(pfn));
 }
 
 /*
@@ -525,26 +523,20 @@ static int __meminit __add_section(int nid, struct zone *zone,
  * call this function after deciding the zone to which to
  * add the new pages.
  */
-int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
+int __ref __add_pages(int nid, struct zone *zone, unsigned long pfn,
 			unsigned long nr_pages)
 {
-	unsigned long i;
-	int err = 0;
-	int start_sec, end_sec;
+	int err = 0, i, start_sec, end_sec;
 	struct vmem_altmap *altmap;
 
 	clear_zone_contiguous(zone);
 
-	/* during initialize mem_map, align hot-added range to section */
-	start_sec = pfn_to_section_nr(phys_start_pfn);
-	end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
-
-	altmap = to_vmem_altmap((unsigned long) pfn_to_page(phys_start_pfn));
+	altmap = to_vmem_altmap((unsigned long) pfn_to_page(pfn));
 	if (altmap) {
 		/*
 		 * Validate altmap is within bounds of the total request
 		 */
-		if (altmap->base_pfn != phys_start_pfn
+		if (altmap->base_pfn != pfn
 				|| vmem_altmap_offset(altmap) > nr_pages) {
 			pr_warn_once("memory add fail, invalid altmap\n");
 			err = -EINVAL;
@@ -553,8 +545,16 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
 		altmap->alloc = 0;
 	}
 
+	start_sec = pfn_to_section_nr(pfn);
+	end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
 	for (i = start_sec; i <= end_sec; i++) {
-		err = __add_section(nid, zone, section_nr_to_pfn(i));
+		unsigned long pfns;
+
+		pfns = min(nr_pages, PAGES_PER_SECTION
+				- (pfn & ~PAGE_SECTION_MASK));
+		err = __add_section(nid, zone, pfn, pfns);
+		pfn += pfns;
+		nr_pages -= pfns;
 
 		/*
 		 * EEXIST is finally dealt with by ioresource collision
@@ -760,10 +760,10 @@ static void shrink_pgdat_span(struct pglist_data *pgdat,
 	pgdat->node_spanned_pages = 0;
 }
 
-static void __remove_zone(struct zone *zone, unsigned long start_pfn)
+static void __remove_zone(struct zone *zone, unsigned long start_pfn,
+		unsigned long nr_pages)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
-	int nr_pages = PAGES_PER_SECTION;
 	int zone_type;
 	unsigned long flags;
 
@@ -775,25 +775,22 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn)
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 }
 
-static int __remove_section(struct zone *zone, struct mem_section *ms,
-		unsigned long map_offset)
+static int __remove_section(struct zone *zone, unsigned long pfn,
+		unsigned long nr_pages, unsigned long map_offset)
 {
-	unsigned long start_pfn;
-	int scn_nr;
+	struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn));
 	int ret = -EINVAL;
 
 	if (!valid_section(ms))
 		return ret;
 
-	ret = unregister_memory_section(ms);
+	ret = unregister_memory_section(zone, ms);
 	if (ret)
 		return ret;
 
-	scn_nr = __section_nr(ms);
-	start_pfn = section_nr_to_pfn(scn_nr);
-	__remove_zone(zone, start_pfn);
+	__remove_zone(zone, pfn, nr_pages);
 
-	sparse_remove_one_section(zone, ms, map_offset);
+	sparse_remove_section(zone, ms, pfn, nr_pages, map_offset);
 	return 0;
 }
 
@@ -808,16 +805,15 @@ static int __remove_section(struct zone *zone, struct mem_section *ms,
  * sure that pages are marked reserved and zones are adjust properly by
  * calling offline_pages().
  */
-int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
+int __remove_pages(struct zone *zone, unsigned long pfn,
 		 unsigned long nr_pages)
 {
-	unsigned long i;
 	unsigned long map_offset = 0;
-	int sections_to_remove, ret = 0;
+	int i, start_sec, end_sec, ret = 0;
 
 	/* In the ZONE_DEVICE case device driver owns the memory region */
 	if (is_dev_zone(zone)) {
-		struct page *page = pfn_to_page(phys_start_pfn);
+		struct page *page = pfn_to_page(pfn);
 		struct vmem_altmap *altmap;
 
 		altmap = to_vmem_altmap((unsigned long) page);
@@ -826,7 +822,7 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 	} else {
 		resource_size_t start, size;
 
-		start = phys_start_pfn << PAGE_SHIFT;
+		start = pfn << PAGE_SHIFT;
 		size = nr_pages * PAGE_SIZE;
 
 		ret = release_mem_region_adjustable(&iomem_resource, start,
@@ -842,16 +838,26 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 	clear_zone_contiguous(zone);
 
 	/*
-	 * We can only remove entire sections
+	 * Only ZONE_DEVICE memory is enabled to remove
+	 * section-unaligned ranges. See register_new_memory() which
+	 * assumes section alignment and is skipped for ZONE_DEVICE
+	 * ranges.
 	 */
-	BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
-	BUG_ON(nr_pages % PAGES_PER_SECTION);
+	if (!is_dev_zone(zone) && ((pfn | nr_pages) & ~PAGE_SECTION_MASK)) {
+		WARN(1, "section unaligned removal not supported\n");
+		return -EINVAL;
+	}
 
-	sections_to_remove = nr_pages / PAGES_PER_SECTION;
-	for (i = 0; i < sections_to_remove; i++) {
-		unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
+	start_sec = pfn_to_section_nr(pfn);
+	end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
+	for (i = start_sec; i <= end_sec; i++) {
+		unsigned long pfns;
 
-		ret = __remove_section(zone, __pfn_to_section(pfn), map_offset);
+		pfns = min(nr_pages, PAGES_PER_SECTION
+				- (pfn & ~PAGE_SECTION_MASK));
+		ret = __remove_section(zone, pfn, pfns, map_offset);
+		pfn += pfns;
+		nr_pages -= pfns;
 		map_offset = 0;
 		if (ret)
 			break;
@@ -861,7 +867,6 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__remove_pages);
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 int set_online_page_callback(online_page_callback_t callback)
@@ -1507,7 +1512,7 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
 			while ((i < MAX_ORDER_NR_PAGES) &&
 				!pfn_valid_within(pfn + i))
 				i++;
-			if (i == MAX_ORDER_NR_PAGES)
+			if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn)
 				continue;
 			page = pfn_to_page(pfn + i);
 			if (zone && page_zone(page) != zone)
@@ -1521,7 +1526,7 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
 
 	if (zone) {
 		*valid_start = start;
-		*valid_end = end;
+		*valid_end = min(end, end_pfn);
 		return 1;
 	} else {
 		return 0;
@@ -1529,10 +1534,10 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
 }
 
 /*
- * Scan pfn range [start,end) to find movable/migratable pages (LRU pages
- * and hugepages). We scan pfn because it's much easier than scanning over
- * linked list. This function returns the pfn of the first found movable
- * page if it's found, otherwise 0.
+ * Scan pfn range [start,end) to find movable/migratable pages (LRU pages,
+ * non-lru movable pages and hugepages). We scan pfn because it's much
+ * easier than scanning over linked list. This function returns the pfn
+ * of the first found movable page if it's found, otherwise 0.
  */
 static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 {
@@ -1543,6 +1548,8 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 			page = pfn_to_page(pfn);
 			if (PageLRU(page))
 				return pfn;
+			if (__PageMovable(page))
+				return pfn;
 			if (PageHuge(page)) {
 				if (page_huge_active(page))
 					return pfn;
@@ -1619,21 +1626,25 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		if (!get_page_unless_zero(page))
 			continue;
 		/*
-		 * We can skip free pages. And we can only deal with pages on
-		 * LRU.
+		 * We can skip free pages. And we can deal with pages on
+		 * LRU and non-lru movable pages.
 		 */
-		ret = isolate_lru_page(page);
+		if (PageLRU(page))
+			ret = isolate_lru_page(page);
+		else
+			ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE);
 		if (!ret) { /* Success */
 			put_page(page);
 			list_add_tail(&page->lru, &source);
 			move_pages--;
-			inc_node_page_state(page, NR_ISOLATED_ANON +
-					    page_is_file_cache(page));
+			if (!__PageMovable(page))
+				inc_node_page_state(page, NR_ISOLATED_ANON +
+						    page_is_file_cache(page));
 
 		} else {
 #ifdef CONFIG_DEBUG_VM
-			pr_alert("removing pfn %lx from LRU failed\n", pfn);
-			dump_page(page, "failed to remove from LRU");
+			pr_alert("failed to isolate pfn %lx\n", pfn);
+			dump_page(page, "isolation failed");
 #endif
 			put_page(page);
 			/* Because we don't have big zone->lock. we should
diff --git a/mm/migrate.c b/mm/migrate.c
index 87f4d0f81819..2c63ac06791b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -74,7 +74,7 @@ int migrate_prep_local(void)
 	return 0;
 }
 
-bool isolate_movable_page(struct page *page, isolate_mode_t mode)
+int isolate_movable_page(struct page *page, isolate_mode_t mode)
 {
 	struct address_space *mapping;
 
@@ -125,14 +125,14 @@ bool isolate_movable_page(struct page *page, isolate_mode_t mode)
 	__SetPageIsolated(page);
 	unlock_page(page);
 
-	return true;
+	return 0;
 
 out_no_isolated:
 	unlock_page(page);
 out_putpage:
 	put_page(page);
 out:
-	return false;
+	return -EBUSY;
 }
 
 /* It should be called on page which is PG_movable */
@@ -193,82 +193,62 @@ void putback_movable_pages(struct list_head *l)
 /*
  * Restore a potential migration pte to a working pte entry
  */
-static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
+static int remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 				 unsigned long addr, void *old)
 {
-	struct mm_struct *mm = vma->vm_mm;
+	struct page_vma_mapped_walk pvmw = {
+		.page = old,
+		.vma = vma,
+		.address = addr,
+		.flags = PVMW_SYNC | PVMW_MIGRATION,
+	};
+	struct page *new;
+	pte_t pte;
 	swp_entry_t entry;
- 	pmd_t *pmd;
-	pte_t *ptep, pte;
- 	spinlock_t *ptl;
 
-	if (unlikely(PageHuge(new))) {
-		ptep = huge_pte_offset(mm, addr);
-		if (!ptep)
-			goto out;
-		ptl = huge_pte_lockptr(hstate_vma(vma), mm, ptep);
-	} else {
-		pmd = mm_find_pmd(mm, addr);
-		if (!pmd)
-			goto out;
+	VM_BUG_ON_PAGE(PageTail(page), page);
+	while (page_vma_mapped_walk(&pvmw)) {
+		new = page - pvmw.page->index +
+			linear_page_index(vma, pvmw.address);
 
-		ptep = pte_offset_map(pmd, addr);
+		get_page(new);
+		pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot)));
+		if (pte_swp_soft_dirty(*pvmw.pte))
+			pte = pte_mksoft_dirty(pte);
 
 		/*
-		 * Peek to check is_swap_pte() before taking ptlock?  No, we
-		 * can race mremap's move_ptes(), which skips anon_vma lock.
+		 * Recheck VMA as permissions can change since migration started
 		 */
-
-		ptl = pte_lockptr(mm, pmd);
-	}
-
- 	spin_lock(ptl);
-	pte = *ptep;
-	if (!is_swap_pte(pte))
-		goto unlock;
-
-	entry = pte_to_swp_entry(pte);
-
-	if (!is_migration_entry(entry) ||
-	    migration_entry_to_page(entry) != old)
-		goto unlock;
-
-	get_page(new);
-	pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot)));
-	if (pte_swp_soft_dirty(*ptep))
-		pte = pte_mksoft_dirty(pte);
-
-	/* Recheck VMA as permissions can change since migration started  */
-	if (is_write_migration_entry(entry))
-		pte = maybe_mkwrite(pte, vma);
+		entry = pte_to_swp_entry(*pvmw.pte);
+		if (is_write_migration_entry(entry))
+			pte = maybe_mkwrite(pte, vma);
 
 #ifdef CONFIG_HUGETLB_PAGE
-	if (PageHuge(new)) {
-		pte = pte_mkhuge(pte);
-		pte = arch_make_huge_pte(pte, vma, new, 0);
-	}
+		if (PageHuge(new)) {
+			pte = pte_mkhuge(pte);
+			pte = arch_make_huge_pte(pte, vma, new, 0);
+		}
 #endif
-	flush_dcache_page(new);
-	set_pte_at(mm, addr, ptep, pte);
+		flush_dcache_page(new);
+		set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
 
-	if (PageHuge(new)) {
-		if (PageAnon(new))
-			hugepage_add_anon_rmap(new, vma, addr);
+		if (PageHuge(new)) {
+			if (PageAnon(new))
+				hugepage_add_anon_rmap(new, vma, pvmw.address);
+			else
+				page_dup_rmap(new, true);
+		} else if (PageAnon(new))
+			page_add_anon_rmap(new, vma, pvmw.address, false);
 		else
-			page_dup_rmap(new, true);
-	} else if (PageAnon(new))
-		page_add_anon_rmap(new, vma, addr, false);
-	else
-		page_add_file_rmap(new, false);
+			page_add_file_rmap(new, false);
 
-	if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new))
-		mlock_vma_page(new);
+		if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new))
+			mlock_vma_page(new);
+
+		/* No need to invalidate - it was non-present before */
+		update_mmu_cache(vma, pvmw.address, pvmw.pte);
+	}
 
-	/* No need to invalidate - it was non-present before */
-	update_mmu_cache(vma, addr, ptep);
-unlock:
-	pte_unmap_unlock(ptep, ptl);
-out:
 	return SWAP_AGAIN;
 }
 
diff --git a/mm/mmap.c b/mm/mmap.c
index dc4291dcc99b..499b988b1639 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -176,7 +176,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	return next;
 }
 
-static int do_brk(unsigned long addr, unsigned long len);
+static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf);
 
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
@@ -185,6 +185,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	struct mm_struct *mm = current->mm;
 	unsigned long min_brk;
 	bool populate;
+	LIST_HEAD(uf);
 
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
@@ -222,7 +223,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 
 	/* Always allow shrinking brk. */
 	if (brk <= mm->brk) {
-		if (!do_munmap(mm, newbrk, oldbrk-newbrk))
+		if (!do_munmap(mm, newbrk, oldbrk-newbrk, &uf))
 			goto set_brk;
 		goto out;
 	}
@@ -232,13 +233,14 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 		goto out;
 
 	/* Ok, looks good - let it rip. */
-	if (do_brk(oldbrk, newbrk-oldbrk) < 0)
+	if (do_brk(oldbrk, newbrk-oldbrk, &uf) < 0)
 		goto out;
 
 set_brk:
 	mm->brk = brk;
 	populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0;
 	up_write(&mm->mmap_sem);
+	userfaultfd_unmap_complete(mm, &uf);
 	if (populate)
 		mm_populate(oldbrk, newbrk - oldbrk);
 	return brk;
@@ -1304,7 +1306,8 @@ static inline int mlock_future_check(struct mm_struct *mm,
 unsigned long do_mmap(struct file *file, unsigned long addr,
 			unsigned long len, unsigned long prot,
 			unsigned long flags, vm_flags_t vm_flags,
-			unsigned long pgoff, unsigned long *populate)
+			unsigned long pgoff, unsigned long *populate,
+			struct list_head *uf)
 {
 	struct mm_struct *mm = current->mm;
 	int pkey = 0;
@@ -1447,7 +1450,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 			vm_flags |= VM_NORESERVE;
 	}
 
-	addr = mmap_region(file, addr, len, vm_flags, pgoff);
+	addr = mmap_region(file, addr, len, vm_flags, pgoff, uf);
 	if (!IS_ERR_VALUE(addr) &&
 	    ((vm_flags & VM_LOCKED) ||
 	     (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
@@ -1583,7 +1586,8 @@ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags)
 }
 
 unsigned long mmap_region(struct file *file, unsigned long addr,
-		unsigned long len, vm_flags_t vm_flags, unsigned long pgoff)
+		unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
+		struct list_head *uf)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
@@ -1609,7 +1613,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	/* Clear old maps */
 	while (find_vma_links(mm, addr, addr + len, &prev, &rb_link,
 			      &rb_parent)) {
-		if (do_munmap(mm, addr, len))
+		if (do_munmap(mm, addr, len, uf))
 			return -ENOMEM;
 	}
 
@@ -2495,11 +2499,11 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /*
- * __split_vma() bypasses sysctl_max_map_count checking.  We use this on the
- * munmap path where it doesn't make sense to fail.
+ * __split_vma() bypasses sysctl_max_map_count checking.  We use this where it
+ * has already been checked or doesn't make sense to fail.
  */
-static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
-	      unsigned long addr, int new_below)
+int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long addr, int new_below)
 {
 	struct vm_area_struct *new;
 	int err;
@@ -2579,7 +2583,8 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
  * work.  This now handles partial unmappings.
  * Jeremy Fitzhardinge <jeremy@goop.org>
  */
-int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
+int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
+	      struct list_head *uf)
 {
 	unsigned long end;
 	struct vm_area_struct *vma, *prev, *last;
@@ -2603,6 +2608,13 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	if (vma->vm_start >= end)
 		return 0;
 
+	if (uf) {
+		int error = userfaultfd_unmap_prep(vma, start, end, uf);
+
+		if (error)
+			return error;
+	}
+
 	/*
 	 * If we need to split any vma, do it now to save pain later.
 	 *
@@ -2668,27 +2680,22 @@ int vm_munmap(unsigned long start, size_t len)
 {
 	int ret;
 	struct mm_struct *mm = current->mm;
+	LIST_HEAD(uf);
 
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
-	ret = do_munmap(mm, start, len);
+	ret = do_munmap(mm, start, len, &uf);
 	up_write(&mm->mmap_sem);
+	userfaultfd_unmap_complete(mm, &uf);
 	return ret;
 }
 EXPORT_SYMBOL(vm_munmap);
 
 SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 {
-	int ret;
-	struct mm_struct *mm = current->mm;
-
 	profile_munmap(addr);
-	if (down_write_killable(&mm->mmap_sem))
-		return -EINTR;
-	ret = do_munmap(mm, addr, len);
-	up_write(&mm->mmap_sem);
-	return ret;
+	return vm_munmap(addr, len);
 }
 
 
@@ -2780,7 +2787,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 
 	file = get_file(vma->vm_file);
 	ret = do_mmap_pgoff(vma->vm_file, start, size,
-			prot, flags, pgoff, &populate);
+			prot, flags, pgoff, &populate, NULL);
 	fput(file);
 out:
 	up_write(&mm->mmap_sem);
@@ -2806,11 +2813,11 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-static int do_brk(unsigned long addr, unsigned long request)
+static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
-	unsigned long flags, len;
+	unsigned long len;
 	struct rb_node **rb_link, *rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
@@ -2821,7 +2828,10 @@ static int do_brk(unsigned long addr, unsigned long request)
 	if (!len)
 		return 0;
 
-	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
+	/* Until we need other flags, refuse anything except VM_EXEC. */
+	if ((flags & (~VM_EXEC)) != 0)
+		return -EINVAL;
+	flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
 	error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
 	if (offset_in_page(error))
@@ -2842,7 +2852,7 @@ static int do_brk(unsigned long addr, unsigned long request)
 	 */
 	while (find_vma_links(mm, addr, addr + len, &prev, &rb_link,
 			      &rb_parent)) {
-		if (do_munmap(mm, addr, len))
+		if (do_munmap(mm, addr, len, uf))
 			return -ENOMEM;
 	}
 
@@ -2889,22 +2899,35 @@ out:
 	return 0;
 }
 
-int vm_brk(unsigned long addr, unsigned long len)
+static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf)
+{
+	return do_brk_flags(addr, len, 0, uf);
+}
+
+int vm_brk_flags(unsigned long addr, unsigned long len, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
 	int ret;
 	bool populate;
+	LIST_HEAD(uf);
 
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
-	ret = do_brk(addr, len);
+	ret = do_brk_flags(addr, len, flags, &uf);
 	populate = ((mm->def_flags & VM_LOCKED) != 0);
 	up_write(&mm->mmap_sem);
+	userfaultfd_unmap_complete(mm, &uf);
 	if (populate && !ret)
 		mm_populate(addr, len);
 	return ret;
 }
+EXPORT_SYMBOL(vm_brk_flags);
+
+int vm_brk(unsigned long addr, unsigned long len)
+{
+	return vm_brk_flags(addr, len, 0);
+}
 EXPORT_SYMBOL(vm_brk);
 
 /* Release all mmaps. */
@@ -3111,8 +3134,7 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages)
 		mm->data_vm += npages;
 }
 
-static int special_mapping_fault(struct vm_area_struct *vma,
-				 struct vm_fault *vmf);
+static int special_mapping_fault(struct vm_fault *vmf);
 
 /*
  * Having a close hook prevents vma merging regardless of flags.
@@ -3147,9 +3169,9 @@ static const struct vm_operations_struct legacy_special_mapping_vmops = {
 	.fault = special_mapping_fault,
 };
 
-static int special_mapping_fault(struct vm_area_struct *vma,
-				struct vm_fault *vmf)
+static int special_mapping_fault(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	pgoff_t pgoff;
 	struct page **pages;
 
@@ -3159,7 +3181,7 @@ static int special_mapping_fault(struct vm_area_struct *vma,
 		struct vm_special_mapping *sm = vma->vm_private_data;
 
 		if (sm->fault)
-			return sm->fault(sm, vma, vmf);
+			return sm->fault(sm, vmf->vma, vmf);
 
 		pages = sm->pages;
 	}
@@ -3433,7 +3455,7 @@ void mm_drop_all_locks(struct mm_struct *mm)
 }
 
 /*
- * initialise the VMA slab
+ * initialise the percpu counter for VM
  */
 void __init mmap_init(void)
 {
diff --git a/mm/mmzone.c b/mm/mmzone.c
index 5652be858e5e..a51c0a67ea3d 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -60,7 +60,7 @@ struct zoneref *__next_zones_zonelist(struct zoneref *z,
 	 * Find the next suitable zone to use for the allocation.
 	 * Only filter based on nodemask if it's set
 	 */
-	if (likely(nodes == NULL))
+	if (unlikely(nodes == NULL))
 		while (zonelist_zone_idx(z) > highest_zoneidx)
 			z++;
 	else
diff --git a/mm/mprotect.c b/mm/mprotect.c
index f9c07f54dd62..77115bb7c953 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -33,34 +33,6 @@
 
 #include "internal.h"
 
-/*
- * For a prot_numa update we only hold mmap_sem for read so there is a
- * potential race with faulting where a pmd was temporarily none. This
- * function checks for a transhuge pmd under the appropriate lock. It
- * returns a pte if it was successfully locked or NULL if it raced with
- * a transhuge insertion.
- */
-static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd,
-			unsigned long addr, int prot_numa, spinlock_t **ptl)
-{
-	pte_t *pte;
-	spinlock_t *pmdl;
-
-	/* !prot_numa is protected by mmap_sem held for write */
-	if (!prot_numa)
-		return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
-
-	pmdl = pmd_lock(vma->vm_mm, pmd);
-	if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) {
-		spin_unlock(pmdl);
-		return NULL;
-	}
-
-	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
-	spin_unlock(pmdl);
-	return pte;
-}
-
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable, int prot_numa)
@@ -71,7 +43,21 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	unsigned long pages = 0;
 	int target_node = NUMA_NO_NODE;
 
-	pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl);
+	/*
+	 * Can be called with only the mmap_sem for reading by
+	 * prot_numa so we must check the pmd isn't constantly
+	 * changing from under us from pmd_none to pmd_trans_huge
+	 * and/or the other way around.
+	 */
+	if (pmd_trans_unstable(pmd))
+		return 0;
+
+	/*
+	 * The pmd points to a regular pte so the pmd can't change
+	 * from under us even if the mmap_sem is only hold for
+	 * reading.
+	 */
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (!pte)
 		return 0;
 
diff --git a/mm/mremap.c b/mm/mremap.c
index 30d7d2482eea..8233b0105c82 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -22,6 +22,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/uaccess.h>
 #include <linux/mm-arch-hooks.h>
+#include <linux/userfaultfd_k.h>
 
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
@@ -250,7 +251,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 
 static unsigned long move_vma(struct vm_area_struct *vma,
 		unsigned long old_addr, unsigned long old_len,
-		unsigned long new_len, unsigned long new_addr, bool *locked)
+		unsigned long new_len, unsigned long new_addr,
+		bool *locked, struct vm_userfaultfd_ctx *uf,
+		struct list_head *uf_unmap)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *new_vma;
@@ -309,6 +312,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 		old_addr = new_addr;
 		new_addr = err;
 	} else {
+		mremap_userfaultfd_prep(new_vma, uf);
 		arch_remap(mm, old_addr, old_addr + old_len,
 			   new_addr, new_addr + new_len);
 	}
@@ -338,7 +342,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	if (unlikely(vma->vm_flags & VM_PFNMAP))
 		untrack_pfn_moved(vma);
 
-	if (do_munmap(mm, old_addr, old_len) < 0) {
+	if (do_munmap(mm, old_addr, old_len, uf_unmap) < 0) {
 		/* OOM: unable to split vma, just get accounts right */
 		vm_unacct_memory(excess >> PAGE_SHIFT);
 		excess = 0;
@@ -413,7 +417,9 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
 }
 
 static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
-		unsigned long new_addr, unsigned long new_len, bool *locked)
+		unsigned long new_addr, unsigned long new_len, bool *locked,
+		struct vm_userfaultfd_ctx *uf,
+		struct list_head *uf_unmap)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
@@ -431,12 +437,12 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 	if (addr + old_len > new_addr && new_addr + new_len > addr)
 		goto out;
 
-	ret = do_munmap(mm, new_addr, new_len);
+	ret = do_munmap(mm, new_addr, new_len, NULL);
 	if (ret)
 		goto out;
 
 	if (old_len >= new_len) {
-		ret = do_munmap(mm, addr+new_len, old_len - new_len);
+		ret = do_munmap(mm, addr+new_len, old_len - new_len, uf_unmap);
 		if (ret && old_len != new_len)
 			goto out;
 		old_len = new_len;
@@ -458,7 +464,8 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 	if (offset_in_page(ret))
 		goto out1;
 
-	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked);
+	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, uf,
+		       uf_unmap);
 	if (!(offset_in_page(ret)))
 		goto out;
 out1:
@@ -497,6 +504,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	unsigned long ret = -EINVAL;
 	unsigned long charged = 0;
 	bool locked = false;
+	struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX;
+	LIST_HEAD(uf_unmap);
 
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
 		return ret;
@@ -523,7 +532,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 
 	if (flags & MREMAP_FIXED) {
 		ret = mremap_to(addr, old_len, new_addr, new_len,
-				&locked);
+				&locked, &uf, &uf_unmap);
 		goto out;
 	}
 
@@ -533,7 +542,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	 * do_munmap does all the needed commit accounting
 	 */
 	if (old_len >= new_len) {
-		ret = do_munmap(mm, addr+new_len, old_len - new_len);
+		ret = do_munmap(mm, addr+new_len, old_len - new_len, &uf_unmap);
 		if (ret && old_len != new_len)
 			goto out;
 		ret = addr;
@@ -592,7 +601,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 			goto out;
 		}
 
-		ret = move_vma(vma, addr, old_len, new_len, new_addr, &locked);
+		ret = move_vma(vma, addr, old_len, new_len, new_addr,
+			       &locked, &uf, &uf_unmap);
 	}
 out:
 	if (offset_in_page(ret)) {
@@ -602,5 +612,7 @@ out:
 	up_write(&current->mm->mmap_sem);
 	if (locked && new_len > old_len)
 		mm_populate(new_addr + old_len, new_len - old_len);
+	mremap_userfaultfd_complete(&uf, addr, new_addr, old_len);
+	userfaultfd_unmap_complete(mm, &uf_unmap);
 	return ret;
 }
diff --git a/mm/nommu.c b/mm/nommu.c
index 24f9f5f39145..fe9f4fa4a7a7 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -517,7 +517,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 }
 
 /*
- * initialise the VMA and region record slabs
+ * initialise the percpu counter for VM and region record slabs
  */
 void __init mmap_init(void)
 {
@@ -1191,7 +1191,7 @@ error_free:
 enomem:
 	pr_err("Allocation of length %lu from process %d (%s) failed\n",
 	       len, current->pid, current->comm);
-	show_free_areas(0);
+	show_free_areas(0, NULL);
 	return -ENOMEM;
 }
 
@@ -1205,7 +1205,8 @@ unsigned long do_mmap(struct file *file,
 			unsigned long flags,
 			vm_flags_t vm_flags,
 			unsigned long pgoff,
-			unsigned long *populate)
+			unsigned long *populate,
+			struct list_head *uf)
 {
 	struct vm_area_struct *vma;
 	struct vm_region *region;
@@ -1412,13 +1413,13 @@ error_getting_vma:
 	kmem_cache_free(vm_region_jar, region);
 	pr_warn("Allocation of vma for %lu byte allocation from process %d failed\n",
 			len, current->pid);
-	show_free_areas(0);
+	show_free_areas(0, NULL);
 	return -ENOMEM;
 
 error_getting_region:
 	pr_warn("Allocation of vm region for %lu byte allocation from process %d failed\n",
 			len, current->pid);
-	show_free_areas(0);
+	show_free_areas(0, NULL);
 	return -ENOMEM;
 }
 
@@ -1577,7 +1578,7 @@ static int shrink_vma(struct mm_struct *mm,
  * - under NOMMU conditions the chunk to be unmapped must be backed by a single
  *   VMA, though it need not cover the whole VMA
  */
-int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
+int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf)
 {
 	struct vm_area_struct *vma;
 	unsigned long end;
@@ -1643,7 +1644,7 @@ int vm_munmap(unsigned long addr, size_t len)
 	int ret;
 
 	down_write(&mm->mmap_sem);
-	ret = do_munmap(mm, addr, len);
+	ret = do_munmap(mm, addr, len, NULL);
 	up_write(&mm->mmap_sem);
 	return ret;
 }
@@ -1794,7 +1795,7 @@ void unmap_mapping_range(struct address_space *mapping,
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
-int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+int filemap_fault(struct vm_fault *vmf)
 {
 	BUG();
 	return 0;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ec9f11d4f094..578321f1c070 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -403,12 +403,14 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 
 static void dump_header(struct oom_control *oc, struct task_struct *p)
 {
-	nodemask_t *nm = (oc->nodemask) ? oc->nodemask : &cpuset_current_mems_allowed;
-
-	pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=%*pbl, order=%d, oom_score_adj=%hd\n",
-		current->comm, oc->gfp_mask, &oc->gfp_mask,
-		nodemask_pr_args(nm), oc->order,
-		current->signal->oom_score_adj);
+	pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=",
+		current->comm, oc->gfp_mask, &oc->gfp_mask);
+	if (oc->nodemask)
+		pr_cont("%*pbl", nodemask_pr_args(oc->nodemask));
+	else
+		pr_cont("(null)");
+	pr_cont(",  order=%d, oom_score_adj=%hd\n",
+		oc->order, current->signal->oom_score_adj);
 	if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order)
 		pr_warn("COMPACTION is disabled!!!\n");
 
@@ -417,7 +419,7 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
 	if (oc->memcg)
 		mem_cgroup_print_oom_info(oc->memcg, p);
 	else
-		show_mem(SHOW_MEM_FILTER_NODES);
+		show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask);
 	if (sysctl_oom_dump_tasks)
 		dump_tasks(oc->memcg, oc->nodemask);
 }
@@ -465,8 +467,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 {
 	struct mmu_gather tlb;
 	struct vm_area_struct *vma;
-	struct zap_details details = {.check_swap_entries = true,
-				      .ignore_dirty = true};
 	bool ret = true;
 
 	/*
@@ -510,14 +510,7 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 
 	tlb_gather_mmu(&tlb, mm, 0, -1);
 	for (vma = mm->mmap ; vma; vma = vma->vm_next) {
-		if (is_vm_hugetlb_page(vma))
-			continue;
-
-		/*
-		 * mlocked VMAs require explicit munlocking before unmap.
-		 * Let's keep it simple here and skip such VMAs.
-		 */
-		if (vma->vm_flags & VM_LOCKED)
+		if (!can_madv_dontneed_vma(vma))
 			continue;
 
 		/*
@@ -532,7 +525,7 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 		 */
 		if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED))
 			unmap_page_range(&tlb, vma, vma->vm_start, vma->vm_end,
-					 &details);
+					 NULL);
 	}
 	tlb_finish_mmu(&tlb, 0, -1);
 	pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
@@ -1013,7 +1006,7 @@ bool out_of_memory(struct oom_control *oc)
 	 * make sure exclude 0 mask - all other users should have at least
 	 * ___GFP_DIRECT_RECLAIM to get here.
 	 */
-	if (oc->gfp_mask && !(oc->gfp_mask & (__GFP_FS|__GFP_NOFAIL)))
+	if (oc->gfp_mask && !(oc->gfp_mask & __GFP_FS))
 		return true;
 
 	/*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 216449825859..ae6e601f0a58 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -580,7 +580,7 @@ static void wb_domain_writeout_inc(struct wb_domain *dom,
 	__fprop_inc_percpu_max(&dom->completions, completions,
 			       max_prop_frac);
 	/* First event after period switching was turned off? */
-	if (!unlikely(dom->period_time)) {
+	if (unlikely(!dom->period_time)) {
 		/*
 		 * We can race with other __bdi_writeout_inc calls here but
 		 * it does not cause any harm since the resulting time when
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f3e0c69a97b7..0aba4dfc0e57 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -55,10 +55,10 @@
 #include <linux/kmemleak.h>
 #include <linux/compaction.h>
 #include <trace/events/kmem.h>
+#include <trace/events/oom.h>
 #include <linux/prefetch.h>
 #include <linux/mm_inline.h>
 #include <linux/migrate.h>
-#include <linux/page_ext.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
 #include <linux/page_owner.h>
@@ -91,6 +91,10 @@ EXPORT_PER_CPU_SYMBOL(_numa_mem_);
 int _node_numa_mem_[MAX_NUMNODES];
 #endif
 
+/* work_structs for global per-cpu drains */
+DEFINE_MUTEX(pcpu_drain_mutex);
+DEFINE_PER_CPU(struct work_struct, pcpu_drain);
+
 #ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
 volatile unsigned long latent_entropy __latent_entropy;
 EXPORT_SYMBOL(latent_entropy);
@@ -352,7 +356,7 @@ static inline unsigned long *get_pageblock_bitmap(struct page *page,
 							unsigned long pfn)
 {
 #ifdef CONFIG_SPARSEMEM
-	return __pfn_to_section(pfn)->pageblock_flags;
+	return section_to_usemap(__pfn_to_section(pfn));
 #else
 	return page_zone(page)->pageblock_flags;
 #endif /* CONFIG_SPARSEMEM */
@@ -714,7 +718,7 @@ static inline void rmv_page_order(struct page *page)
 /*
  * This function checks whether a page is free && is the buddy
  * we can do coalesce a page and its buddy if
- * (a) the buddy is not in a hole &&
+ * (a) the buddy is not in a hole (check before calling!) &&
  * (b) the buddy is in the buddy system &&
  * (c) a page and its buddy have the same order &&
  * (d) a page and its buddy are in the same zone.
@@ -729,9 +733,6 @@ static inline void rmv_page_order(struct page *page)
 static inline int page_is_buddy(struct page *page, struct page *buddy,
 							unsigned int order)
 {
-	if (!pfn_valid_within(page_to_pfn(buddy)))
-		return 0;
-
 	if (page_is_guard(buddy) && page_order(buddy) == order) {
 		if (page_zone_id(page) != page_zone_id(buddy))
 			return 0;
@@ -787,9 +788,8 @@ static inline void __free_one_page(struct page *page,
 		struct zone *zone, unsigned int order,
 		int migratetype)
 {
-	unsigned long page_idx;
-	unsigned long combined_idx;
-	unsigned long uninitialized_var(buddy_idx);
+	unsigned long combined_pfn;
+	unsigned long uninitialized_var(buddy_pfn);
 	struct page *buddy;
 	unsigned int max_order;
 
@@ -802,15 +802,16 @@ static inline void __free_one_page(struct page *page,
 	if (likely(!is_migrate_isolate(migratetype)))
 		__mod_zone_freepage_state(zone, 1 << order, migratetype);
 
-	page_idx = pfn & ((1 << MAX_ORDER) - 1);
-
-	VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page);
+	VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page);
 	VM_BUG_ON_PAGE(bad_range(zone, page), page);
 
 continue_merging:
 	while (order < max_order - 1) {
-		buddy_idx = __find_buddy_index(page_idx, order);
-		buddy = page + (buddy_idx - page_idx);
+		buddy_pfn = __find_buddy_pfn(pfn, order);
+		buddy = page + (buddy_pfn - pfn);
+
+		if (!pfn_valid_within(buddy_pfn))
+			goto done_merging;
 		if (!page_is_buddy(page, buddy, order))
 			goto done_merging;
 		/*
@@ -824,9 +825,9 @@ continue_merging:
 			zone->free_area[order].nr_free--;
 			rmv_page_order(buddy);
 		}
-		combined_idx = buddy_idx & page_idx;
-		page = page + (combined_idx - page_idx);
-		page_idx = combined_idx;
+		combined_pfn = buddy_pfn & pfn;
+		page = page + (combined_pfn - pfn);
+		pfn = combined_pfn;
 		order++;
 	}
 	if (max_order < MAX_ORDER) {
@@ -841,8 +842,8 @@ continue_merging:
 		if (unlikely(has_isolate_pageblock(zone))) {
 			int buddy_mt;
 
-			buddy_idx = __find_buddy_index(page_idx, order);
-			buddy = page + (buddy_idx - page_idx);
+			buddy_pfn = __find_buddy_pfn(pfn, order);
+			buddy = page + (buddy_pfn - pfn);
 			buddy_mt = get_pageblock_migratetype(buddy);
 
 			if (migratetype != buddy_mt
@@ -865,12 +866,12 @@ done_merging:
 	 * so it's less likely to be used soon and more likely to be merged
 	 * as a higher order page
 	 */
-	if ((order < MAX_ORDER-2) && pfn_valid_within(page_to_pfn(buddy))) {
+	if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)) {
 		struct page *higher_page, *higher_buddy;
-		combined_idx = buddy_idx & page_idx;
-		higher_page = page + (combined_idx - page_idx);
-		buddy_idx = __find_buddy_index(combined_idx, order + 1);
-		higher_buddy = higher_page + (buddy_idx - combined_idx);
+		combined_pfn = buddy_pfn & pfn;
+		higher_page = page + (combined_pfn - pfn);
+		buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
+		higher_buddy = higher_page + (buddy_pfn - combined_pfn);
 		if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
 			list_add_tail(&page->lru,
 				&zone->free_area[order].free_list[migratetype]);
@@ -1087,10 +1088,10 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 {
 	int migratetype = 0;
 	int batch_free = 0;
-	unsigned long nr_scanned;
+	unsigned long nr_scanned, flags;
 	bool isolated_pageblocks;
 
-	spin_lock(&zone->lock);
+	spin_lock_irqsave(&zone->lock, flags);
 	isolated_pageblocks = has_isolate_pageblock(zone);
 	nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
 	if (nr_scanned)
@@ -1139,7 +1140,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 			trace_mm_page_pcpu_drain(page, 0, mt);
 		} while (--count && --batch_free && !list_empty(list));
 	}
-	spin_unlock(&zone->lock);
+	spin_unlock_irqrestore(&zone->lock, flags);
 }
 
 static void free_one_page(struct zone *zone,
@@ -1147,8 +1148,9 @@ static void free_one_page(struct zone *zone,
 				unsigned int order,
 				int migratetype)
 {
-	unsigned long nr_scanned;
-	spin_lock(&zone->lock);
+	unsigned long nr_scanned, flags;
+	spin_lock_irqsave(&zone->lock, flags);
+	__count_vm_events(PGFREE, 1 << order);
 	nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
 	if (nr_scanned)
 		__mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned);
@@ -1158,7 +1160,7 @@ static void free_one_page(struct zone *zone,
 		migratetype = get_pfnblock_migratetype(page, pfn);
 	}
 	__free_one_page(page, pfn, zone, order, migratetype);
-	spin_unlock(&zone->lock);
+	spin_unlock_irqrestore(&zone->lock, flags);
 }
 
 static void __meminit __init_single_page(struct page *page, unsigned long pfn,
@@ -1236,7 +1238,6 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
 
 static void __free_pages_ok(struct page *page, unsigned int order)
 {
-	unsigned long flags;
 	int migratetype;
 	unsigned long pfn = page_to_pfn(page);
 
@@ -1244,10 +1245,7 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 		return;
 
 	migratetype = get_pfnblock_migratetype(page, pfn);
-	local_irq_save(flags);
-	__count_vm_events(PGFREE, 1 << order);
 	free_one_page(page_zone(page), page, pfn, order, migratetype);
-	local_irq_restore(flags);
 }
 
 static void __init __free_pages_boot_core(struct page *page, unsigned int order)
@@ -2219,8 +2217,9 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			int migratetype, bool cold)
 {
 	int i, alloced = 0;
+	unsigned long flags;
 
-	spin_lock(&zone->lock);
+	spin_lock_irqsave(&zone->lock, flags);
 	for (i = 0; i < count; ++i) {
 		struct page *page = __rmqueue(zone, order, migratetype);
 		if (unlikely(page == NULL))
@@ -2256,7 +2255,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 	 * pages added to the pcp list.
 	 */
 	__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
-	spin_unlock(&zone->lock);
+	spin_unlock_irqrestore(&zone->lock, flags);
 	return alloced;
 }
 
@@ -2341,16 +2340,26 @@ void drain_local_pages(struct zone *zone)
 		drain_pages(cpu);
 }
 
+static void drain_local_pages_wq(struct work_struct *work)
+{
+	/*
+	 * drain_all_pages doesn't use proper cpu hotplug protection so
+	 * we can race with cpu offline when the WQ can move this from
+	 * a cpu pinned worker to an unbound one. We can operate on a different
+	 * cpu which is allright but we also have to make sure to not move to
+	 * a different one.
+	 */
+	preempt_disable();
+	drain_local_pages(NULL);
+	preempt_enable();
+}
+
 /*
  * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
  *
  * When zone parameter is non-NULL, spill just the single zone's pages.
  *
- * Note that this code is protected against sending an IPI to an offline
- * CPU but does not guarantee sending an IPI to newly hotplugged CPUs:
- * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but
- * nothing keeps CPUs from showing up after we populated the cpumask and
- * before the call to on_each_cpu_mask().
+ * Note that this can be extremely slow as the draining happens in a workqueue.
  */
 void drain_all_pages(struct zone *zone)
 {
@@ -2362,6 +2371,21 @@ void drain_all_pages(struct zone *zone)
 	 */
 	static cpumask_t cpus_with_pcps;
 
+	/* Workqueues cannot recurse */
+	if (current->flags & PF_WQ_WORKER)
+		return;
+
+	/*
+	 * Do not drain if one is already in progress unless it's specific to
+	 * a zone. Such callers are primarily CMA and memory hotplug and need
+	 * the drain to be complete when the call returns.
+	 */
+	if (unlikely(!mutex_trylock(&pcpu_drain_mutex))) {
+		if (!zone)
+			return;
+		mutex_lock(&pcpu_drain_mutex);
+	}
+
 	/*
 	 * We don't care about racing with CPU hotplug event
 	 * as offline notification will cause the notified
@@ -2392,8 +2416,16 @@ void drain_all_pages(struct zone *zone)
 		else
 			cpumask_clear_cpu(cpu, &cpus_with_pcps);
 	}
-	on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages,
-								zone, 1);
+
+	for_each_cpu(cpu, &cpus_with_pcps) {
+		struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu);
+		INIT_WORK(work, drain_local_pages_wq);
+		schedule_work_on(cpu, work);
+	}
+	for_each_cpu(cpu, &cpus_with_pcps)
+		flush_work(per_cpu_ptr(&pcpu_drain, cpu));
+
+	mutex_unlock(&pcpu_drain_mutex);
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -2444,17 +2476,20 @@ void free_hot_cold_page(struct page *page, bool cold)
 {
 	struct zone *zone = page_zone(page);
 	struct per_cpu_pages *pcp;
-	unsigned long flags;
 	unsigned long pfn = page_to_pfn(page);
 	int migratetype;
 
+	if (in_interrupt()) {
+		__free_pages_ok(page, 0);
+		return;
+	}
+
 	if (!free_pcp_prepare(page))
 		return;
 
 	migratetype = get_pfnblock_migratetype(page, pfn);
 	set_pcppage_migratetype(page, migratetype);
-	local_irq_save(flags);
-	__count_vm_event(PGFREE);
+	preempt_disable();
 
 	/*
 	 * We only track unmovable, reclaimable and movable on pcp lists.
@@ -2471,6 +2506,7 @@ void free_hot_cold_page(struct page *page, bool cold)
 		migratetype = MIGRATE_MOVABLE;
 	}
 
+	__count_vm_event(PGFREE);
 	pcp = &this_cpu_ptr(zone->pageset)->pcp;
 	if (!cold)
 		list_add(&page->lru, &pcp->lists[migratetype]);
@@ -2484,7 +2520,7 @@ void free_hot_cold_page(struct page *page, bool cold)
 	}
 
 out:
-	local_irq_restore(flags);
+	preempt_enable_no_resched();
 }
 
 /*
@@ -2602,74 +2638,105 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
 #endif
 }
 
+/* Remove page from the per-cpu list, caller must protect the list */
+static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype,
+			bool cold, struct per_cpu_pages *pcp,
+			struct list_head *list)
+{
+	struct page *page;
+
+	VM_BUG_ON(in_interrupt());
+
+	do {
+		if (list_empty(list)) {
+			pcp->count += rmqueue_bulk(zone, 0,
+					pcp->batch, list,
+					migratetype, cold);
+			if (unlikely(list_empty(list)))
+				return NULL;
+		}
+
+		if (cold)
+			page = list_last_entry(list, struct page, lru);
+		else
+			page = list_first_entry(list, struct page, lru);
+
+		list_del(&page->lru);
+		pcp->count--;
+	} while (check_new_pcp(page));
+
+	return page;
+}
+
+/* Lock and remove page from the per-cpu list */
+static struct page *rmqueue_pcplist(struct zone *preferred_zone,
+			struct zone *zone, unsigned int order,
+			gfp_t gfp_flags, int migratetype)
+{
+	struct per_cpu_pages *pcp;
+	struct list_head *list;
+	bool cold = ((gfp_flags & __GFP_COLD) != 0);
+	struct page *page;
+
+	preempt_disable();
+	pcp = &this_cpu_ptr(zone->pageset)->pcp;
+	list = &pcp->lists[migratetype];
+	page = __rmqueue_pcplist(zone,  migratetype, cold, pcp, list);
+	if (page) {
+		__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
+		zone_statistics(preferred_zone, zone);
+	}
+	preempt_enable_no_resched();
+	return page;
+}
+
 /*
  * Allocate a page from the given zone. Use pcplists for order-0 allocations.
  */
 static inline
-struct page *buffered_rmqueue(struct zone *preferred_zone,
+struct page *rmqueue(struct zone *preferred_zone,
 			struct zone *zone, unsigned int order,
 			gfp_t gfp_flags, unsigned int alloc_flags,
 			int migratetype)
 {
 	unsigned long flags;
 	struct page *page;
-	bool cold = ((gfp_flags & __GFP_COLD) != 0);
-
-	if (likely(order == 0)) {
-		struct per_cpu_pages *pcp;
-		struct list_head *list;
 
-		local_irq_save(flags);
-		do {
-			pcp = &this_cpu_ptr(zone->pageset)->pcp;
-			list = &pcp->lists[migratetype];
-			if (list_empty(list)) {
-				pcp->count += rmqueue_bulk(zone, 0,
-						pcp->batch, list,
-						migratetype, cold);
-				if (unlikely(list_empty(list)))
-					goto failed;
-			}
-
-			if (cold)
-				page = list_last_entry(list, struct page, lru);
-			else
-				page = list_first_entry(list, struct page, lru);
-
-			list_del(&page->lru);
-			pcp->count--;
+	if (likely(order == 0) && !in_interrupt()) {
+		page = rmqueue_pcplist(preferred_zone, zone, order,
+				gfp_flags, migratetype);
+		goto out;
+	}
 
-		} while (check_new_pcp(page));
-	} else {
-		/*
-		 * We most definitely don't want callers attempting to
-		 * allocate greater than order-1 page units with __GFP_NOFAIL.
-		 */
-		WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
-		spin_lock_irqsave(&zone->lock, flags);
+	/*
+	 * We most definitely don't want callers attempting to
+	 * allocate greater than order-1 page units with __GFP_NOFAIL.
+	 */
+	WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
+	spin_lock_irqsave(&zone->lock, flags);
 
-		do {
-			page = NULL;
-			if (alloc_flags & ALLOC_HARDER) {
-				page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
-				if (page)
-					trace_mm_page_alloc_zone_locked(page, order, migratetype);
-			}
-			if (!page)
-				page = __rmqueue(zone, order, migratetype);
-		} while (page && check_new_pages(page, order));
-		spin_unlock(&zone->lock);
+	do {
+		page = NULL;
+		if (alloc_flags & ALLOC_HARDER) {
+			page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
+			if (page)
+				trace_mm_page_alloc_zone_locked(page, order, migratetype);
+		}
 		if (!page)
-			goto failed;
-		__mod_zone_freepage_state(zone, -(1 << order),
-					  get_pcppage_migratetype(page));
-	}
+			page = __rmqueue(zone, order, migratetype);
+	} while (page && check_new_pages(page, order));
+	spin_unlock(&zone->lock);
+	if (!page)
+		goto failed;
+	__mod_zone_freepage_state(zone, -(1 << order),
+				  get_pcppage_migratetype(page));
 
 	__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
 	zone_statistics(preferred_zone, zone);
 	local_irq_restore(flags);
 
-	VM_BUG_ON_PAGE(bad_range(zone, page), page);
+out:
+	VM_BUG_ON_PAGE(page && bad_range(zone, page), page);
 	return page;
 
 failed:
@@ -2974,7 +3041,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 		}
 
 try_this_zone:
-		page = buffered_rmqueue(ac->preferred_zoneref->zone, zone, order,
+		page = rmqueue(ac->preferred_zoneref->zone, zone, order,
 				gfp_mask, alloc_flags, ac->migratetype);
 		if (page) {
 			prep_new_page(page, order, gfp_mask, alloc_flags);
@@ -3007,18 +3074,12 @@ static inline bool should_suppress_show_mem(void)
 	return ret;
 }
 
-static DEFINE_RATELIMIT_STATE(nopage_rs,
-		DEFAULT_RATELIMIT_INTERVAL,
-		DEFAULT_RATELIMIT_BURST);
-
-void warn_alloc(gfp_t gfp_mask, const char *fmt, ...)
+static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
 {
 	unsigned int filter = SHOW_MEM_FILTER_NODES;
-	struct va_format vaf;
-	va_list args;
+	static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1);
 
-	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) ||
-	    debug_guardpage_minorder() > 0)
+	if (should_suppress_show_mem() || !__ratelimit(&show_mem_rs))
 		return;
 
 	/*
@@ -3033,6 +3094,20 @@ void warn_alloc(gfp_t gfp_mask, const char *fmt, ...)
 	if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
 		filter &= ~SHOW_MEM_FILTER_NODES;
 
+	show_mem(filter, nodemask);
+}
+
+void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+
+	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) ||
+	    debug_guardpage_minorder() > 0)
+		return;
+
 	pr_warn("%s: ", current->comm);
 
 	va_start(args, fmt);
@@ -3041,11 +3116,36 @@ void warn_alloc(gfp_t gfp_mask, const char *fmt, ...)
 	pr_cont("%pV", &vaf);
 	va_end(args);
 
-	pr_cont(", mode:%#x(%pGg)\n", gfp_mask, &gfp_mask);
+	pr_cont(", mode:%#x(%pGg), nodemask=", gfp_mask, &gfp_mask);
+	if (nodemask)
+		pr_cont("%*pbl\n", nodemask_pr_args(nodemask));
+	else
+		pr_cont("(null)\n");
+
+	cpuset_print_current_mems_allowed();
 
 	dump_stack();
-	if (!should_suppress_show_mem())
-		show_mem(filter);
+	warn_alloc_show_mem(gfp_mask, nodemask);
+}
+
+static inline struct page *
+__alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order,
+			      unsigned int alloc_flags,
+			      const struct alloc_context *ac)
+{
+	struct page *page;
+
+	page = get_page_from_freelist(gfp_mask, order,
+			alloc_flags|ALLOC_CPUSET, ac);
+	/*
+	 * fallback to ignore cpuset restriction if our nodes
+	 * are depleted
+	 */
+	if (!page)
+		page = get_page_from_freelist(gfp_mask, order,
+				alloc_flags, ac);
+
+	return page;
 }
 
 static inline struct page *
@@ -3083,47 +3183,42 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	if (page)
 		goto out;
 
-	if (!(gfp_mask & __GFP_NOFAIL)) {
-		/* Coredumps can quickly deplete all memory reserves */
-		if (current->flags & PF_DUMPCORE)
-			goto out;
-		/* The OOM killer will not help higher order allocs */
-		if (order > PAGE_ALLOC_COSTLY_ORDER)
-			goto out;
-		/* The OOM killer does not needlessly kill tasks for lowmem */
-		if (ac->high_zoneidx < ZONE_NORMAL)
-			goto out;
-		if (pm_suspended_storage())
-			goto out;
-		/*
-		 * XXX: GFP_NOFS allocations should rather fail than rely on
-		 * other request to make a forward progress.
-		 * We are in an unfortunate situation where out_of_memory cannot
-		 * do much for this context but let's try it to at least get
-		 * access to memory reserved if the current task is killed (see
-		 * out_of_memory). Once filesystems are ready to handle allocation
-		 * failures more gracefully we should just bail out here.
-		 */
+	/* Coredumps can quickly deplete all memory reserves */
+	if (current->flags & PF_DUMPCORE)
+		goto out;
+	/* The OOM killer will not help higher order allocs */
+	if (order > PAGE_ALLOC_COSTLY_ORDER)
+		goto out;
+	/* The OOM killer does not needlessly kill tasks for lowmem */
+	if (ac->high_zoneidx < ZONE_NORMAL)
+		goto out;
+	if (pm_suspended_storage())
+		goto out;
+	/*
+	 * XXX: GFP_NOFS allocations should rather fail than rely on
+	 * other request to make a forward progress.
+	 * We are in an unfortunate situation where out_of_memory cannot
+	 * do much for this context but let's try it to at least get
+	 * access to memory reserved if the current task is killed (see
+	 * out_of_memory). Once filesystems are ready to handle allocation
+	 * failures more gracefully we should just bail out here.
+	 */
+
+	/* The OOM killer may not free memory on a specific node */
+	if (gfp_mask & __GFP_THISNODE)
+		goto out;
 
-		/* The OOM killer may not free memory on a specific node */
-		if (gfp_mask & __GFP_THISNODE)
-			goto out;
-	}
 	/* Exhausted what can be done so it's blamo time */
 	if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
 		*did_some_progress = 1;
 
-		if (gfp_mask & __GFP_NOFAIL) {
-			page = get_page_from_freelist(gfp_mask, order,
-					ALLOC_NO_WATERMARKS|ALLOC_CPUSET, ac);
-			/*
-			 * fallback to ignore cpuset restriction if our nodes
-			 * are depleted
-			 */
-			if (!page)
-				page = get_page_from_freelist(gfp_mask, order,
+		/*
+		 * Help non-failing allocations by giving them access to memory
+		 * reserves
+		 */
+		if (gfp_mask & __GFP_NOFAIL)
+			page = __alloc_pages_cpuset_fallback(gfp_mask, order,
 					ALLOC_NO_WATERMARKS, ac);
-		}
 	}
 out:
 	mutex_unlock(&oom_lock);
@@ -3192,6 +3287,9 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
 {
 	int max_retries = MAX_COMPACT_RETRIES;
 	int min_priority;
+	bool ret = false;
+	int retries = *compaction_retries;
+	enum compact_priority priority = *compact_priority;
 
 	if (!order)
 		return false;
@@ -3213,8 +3311,10 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
 	 * But do not retry if the given zonelist is not suitable for
 	 * compaction.
 	 */
-	if (compaction_withdrawn(compact_result))
-		return compaction_zonelist_suitable(ac, order, alloc_flags);
+	if (compaction_withdrawn(compact_result)) {
+		ret = compaction_zonelist_suitable(ac, order, alloc_flags);
+		goto out;
+	}
 
 	/*
 	 * !costly requests are much more important than __GFP_REPEAT
@@ -3226,8 +3326,10 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
 	 */
 	if (order > PAGE_ALLOC_COSTLY_ORDER)
 		max_retries /= 4;
-	if (*compaction_retries <= max_retries)
-		return true;
+	if (*compaction_retries <= max_retries) {
+		ret = true;
+		goto out;
+	}
 
 	/*
 	 * Make sure there are attempts at the highest priority if we exhausted
@@ -3236,12 +3338,15 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
 check_priority:
 	min_priority = (order > PAGE_ALLOC_COSTLY_ORDER) ?
 			MIN_COMPACT_COSTLY_PRIORITY : MIN_COMPACT_PRIORITY;
+
 	if (*compact_priority > min_priority) {
 		(*compact_priority)--;
 		*compaction_retries = 0;
-		return true;
+		ret = true;
 	}
-	return false;
+out:
+	trace_compact_retry(order, priority, compact_result, retries, max_retries, ret);
+	return ret;
 }
 #else
 static inline struct page *
@@ -3464,6 +3569,8 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
 					ac->nodemask) {
 		unsigned long available;
 		unsigned long reclaimable;
+		unsigned long min_wmark = min_wmark_pages(zone);
+		bool wmark;
 
 		available = reclaimable = zone_reclaimable_pages(zone);
 		available -= DIV_ROUND_UP((*no_progress_loops) * available,
@@ -3474,8 +3581,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
 		 * Would the allocation succeed if we reclaimed the whole
 		 * available?
 		 */
-		if (__zone_watermark_ok(zone, order, min_wmark_pages(zone),
-				ac_classzone_idx(ac), alloc_flags, available)) {
+		wmark = __zone_watermark_ok(zone, order, min_wmark,
+				ac_classzone_idx(ac), alloc_flags, available);
+		trace_reclaim_retry_zone(z, order, reclaimable,
+				available, min_wmark, *no_progress_loops, wmark);
+		if (wmark) {
 			/*
 			 * If we didn't make any progress and have a lot of
 			 * dirty + writeback pages then we should wait for
@@ -3555,6 +3665,14 @@ retry_cpuset:
 	no_progress_loops = 0;
 	compact_priority = DEF_COMPACT_PRIORITY;
 	cpuset_mems_cookie = read_mems_allowed_begin();
+
+	/*
+	 * The fast path uses conservative alloc_flags to succeed only until
+	 * kswapd needs to be woken up, and to avoid the cost of setting up
+	 * alloc_flags precisely. So we do that now.
+	 */
+	alloc_flags = gfp_to_alloc_flags(gfp_mask);
+
 	/*
 	 * We need to recalculate the starting point for the zonelist iterator
 	 * because we might have used different nodemask in the fast path, or
@@ -3566,14 +3684,6 @@ retry_cpuset:
 	if (!ac->preferred_zoneref->zone)
 		goto nopage;
 
-
-	/*
-	 * The fast path uses conservative alloc_flags to succeed only until
-	 * kswapd needs to be woken up, and to avoid the cost of setting up
-	 * alloc_flags precisely. So we do that now.
-	 */
-	alloc_flags = gfp_to_alloc_flags(gfp_mask);
-
 	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
 		wake_all_kswapds(order, ac);
 
@@ -3650,35 +3760,21 @@ retry:
 		goto got_pg;
 
 	/* Caller is not willing to reclaim, we can't balance anything */
-	if (!can_direct_reclaim) {
-		/*
-		 * All existing users of the __GFP_NOFAIL are blockable, so warn
-		 * of any new users that actually allow this type of allocation
-		 * to fail.
-		 */
-		WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL);
+	if (!can_direct_reclaim)
 		goto nopage;
-	}
 
-	/* Avoid recursion of direct reclaim */
-	if (current->flags & PF_MEMALLOC) {
-		/*
-		 * __GFP_NOFAIL request from this context is rather bizarre
-		 * because we cannot reclaim anything and only can loop waiting
-		 * for somebody to do a work for us.
-		 */
-		if (WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
-			cond_resched();
-			goto retry;
-		}
-		goto nopage;
+	/* Make sure we know about allocations which stall for too long */
+	if (time_after(jiffies, alloc_start + stall_timeout)) {
+		warn_alloc(gfp_mask, ac->nodemask,
+			"page allocation stalls for %ums, order:%u",
+			jiffies_to_msecs(jiffies-alloc_start), order);
+		stall_timeout += 10 * HZ;
 	}
 
-	/* Avoid allocations with no watermarks from looping endlessly */
-	if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
+	/* Avoid recursion of direct reclaim */
+	if (current->flags & PF_MEMALLOC)
 		goto nopage;
 
-
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac,
 							&did_some_progress);
@@ -3702,14 +3798,6 @@ retry:
 	if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_REPEAT))
 		goto nopage;
 
-	/* Make sure we know about allocations which stall for too long */
-	if (time_after(jiffies, alloc_start + stall_timeout)) {
-		warn_alloc(gfp_mask,
-			"page allocation stalls for %ums, order:%u",
-			jiffies_to_msecs(jiffies-alloc_start), order);
-		stall_timeout += 10 * HZ;
-	}
-
 	if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
 				 did_some_progress > 0, &no_progress_loops))
 		goto retry;
@@ -3738,6 +3826,10 @@ retry:
 	if (page)
 		goto got_pg;
 
+	/* Avoid allocations with no watermarks from looping endlessly */
+	if (test_thread_flag(TIF_MEMDIE))
+		goto nopage;
+
 	/* Retry as long as the OOM killer is making progress */
 	if (did_some_progress) {
 		no_progress_loops = 0;
@@ -3755,82 +3847,123 @@ nopage:
 	if (read_mems_allowed_retry(cpuset_mems_cookie))
 		goto retry_cpuset;
 
-	warn_alloc(gfp_mask,
+	/*
+	 * Make sure that __GFP_NOFAIL request doesn't leak out and make sure
+	 * we always retry
+	 */
+	if (gfp_mask & __GFP_NOFAIL) {
+		/*
+		 * All existing users of the __GFP_NOFAIL are blockable, so warn
+		 * of any new users that actually require GFP_NOWAIT
+		 */
+		if (WARN_ON_ONCE(!can_direct_reclaim))
+			goto fail;
+
+		/*
+		 * PF_MEMALLOC request from this context is rather bizarre
+		 * because we cannot reclaim anything and only can loop waiting
+		 * for somebody to do a work for us
+		 */
+		WARN_ON_ONCE(current->flags & PF_MEMALLOC);
+
+		/*
+		 * non failing costly orders are a hard requirement which we
+		 * are not prepared for much so let's warn about these users
+		 * so that we can identify them and convert them to something
+		 * else.
+		 */
+		WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER);
+
+		/*
+		 * Help non-failing allocations by giving them access to memory
+		 * reserves but do not use ALLOC_NO_WATERMARKS because this
+		 * could deplete whole memory reserves which would just make
+		 * the situation worse
+		 */
+		page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
+		if (page)
+			goto got_pg;
+
+		cond_resched();
+		goto retry;
+	}
+fail:
+	warn_alloc(gfp_mask, ac->nodemask,
 			"page allocation failure: order:%u", order);
 got_pg:
 	return page;
 }
 
-/*
- * This is the 'heart' of the zoned buddy allocator.
- */
-struct page *
-__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
-			struct zonelist *zonelist, nodemask_t *nodemask)
+static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
+		struct zonelist *zonelist, nodemask_t *nodemask,
+		struct alloc_context *ac, gfp_t *alloc_mask,
+		unsigned int *alloc_flags)
 {
-	struct page *page;
-	unsigned int alloc_flags = ALLOC_WMARK_LOW;
-	gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
-	struct alloc_context ac = {
-		.high_zoneidx = gfp_zone(gfp_mask),
-		.zonelist = zonelist,
-		.nodemask = nodemask,
-		.migratetype = gfpflags_to_migratetype(gfp_mask),
-	};
+	ac->high_zoneidx = gfp_zone(gfp_mask);
+	ac->zonelist = zonelist;
+	ac->nodemask = nodemask;
+	ac->migratetype = gfpflags_to_migratetype(gfp_mask);
 
 	if (cpusets_enabled()) {
-		alloc_mask |= __GFP_HARDWALL;
-		alloc_flags |= ALLOC_CPUSET;
-		if (!ac.nodemask)
-			ac.nodemask = &cpuset_current_mems_allowed;
+		*alloc_mask |= __GFP_HARDWALL;
+		if (!ac->nodemask)
+			ac->nodemask = &cpuset_current_mems_allowed;
+		else
+			*alloc_flags |= ALLOC_CPUSET;
 	}
 
-	gfp_mask &= gfp_allowed_mask;
-
 	lockdep_trace_alloc(gfp_mask);
 
 	might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
 
 	if (should_fail_alloc_page(gfp_mask, order))
-		return NULL;
+		return false;
 
-	/*
-	 * Check the zones suitable for the gfp_mask contain at least one
-	 * valid zone. It's possible to have an empty zonelist as a result
-	 * of __GFP_THISNODE and a memoryless node
-	 */
-	if (unlikely(!zonelist->_zonerefs->zone))
-		return NULL;
+	if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
+		*alloc_flags |= ALLOC_CMA;
 
-	if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE)
-		alloc_flags |= ALLOC_CMA;
+	return true;
+}
 
+/* Determine whether to spread dirty pages and what the first usable zone */
+static inline void finalise_ac(gfp_t gfp_mask,
+		unsigned int order, struct alloc_context *ac)
+{
 	/* Dirty zone balancing only done in the fast path */
-	ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
+	ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
 	/*
 	 * The preferred zone is used for statistics but crucially it is
 	 * also used as the starting point for the zonelist iterator. It
 	 * may get reset for allocations that ignore memory policies.
 	 */
-	ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
-					ac.high_zoneidx, ac.nodemask);
-	if (!ac.preferred_zoneref->zone) {
-		page = NULL;
-		/*
-		 * This might be due to race with cpuset_current_mems_allowed
-		 * update, so make sure we retry with original nodemask in the
-		 * slow path.
-		 */
-		goto no_zone;
-	}
+	ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+					ac->high_zoneidx, ac->nodemask);
+}
+
+/*
+ * This is the 'heart' of the zoned buddy allocator.
+ */
+struct page *
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
+			struct zonelist *zonelist, nodemask_t *nodemask)
+{
+	struct page *page;
+	unsigned int alloc_flags = ALLOC_WMARK_LOW;
+	gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
+	struct alloc_context ac = { };
+
+	gfp_mask &= gfp_allowed_mask;
+	if (!prepare_alloc_pages(gfp_mask, order, zonelist, nodemask, &ac, &alloc_mask, &alloc_flags))
+		return NULL;
+
+	finalise_ac(gfp_mask, order, &ac);
 
 	/* First allocation attempt */
 	page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
 	if (likely(page))
 		goto out;
 
-no_zone:
 	/*
 	 * Runtime PM, block IO and its error handling path can deadlock
 	 * because I/O on the device might not complete.
@@ -4252,20 +4385,20 @@ void si_meminfo_node(struct sysinfo *val, int nid)
  * Determine whether the node should be displayed or not, depending on whether
  * SHOW_MEM_FILTER_NODES was passed to show_free_areas().
  */
-bool skip_free_areas_node(unsigned int flags, int nid)
+static bool show_mem_node_skip(unsigned int flags, int nid, nodemask_t *nodemask)
 {
-	bool ret = false;
-	unsigned int cpuset_mems_cookie;
-
 	if (!(flags & SHOW_MEM_FILTER_NODES))
-		goto out;
+		return false;
 
-	do {
-		cpuset_mems_cookie = read_mems_allowed_begin();
-		ret = !node_isset(nid, cpuset_current_mems_allowed);
-	} while (read_mems_allowed_retry(cpuset_mems_cookie));
-out:
-	return ret;
+	/*
+	 * no node mask - aka implicit memory numa policy. Do not bother with
+	 * the synchronization - read_mems_allowed_begin - because we do not
+	 * have to be precise here.
+	 */
+	if (!nodemask)
+		nodemask = &cpuset_current_mems_allowed;
+
+	return !node_isset(nid, *nodemask);
 }
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
@@ -4306,7 +4439,7 @@ static void show_migration_types(unsigned char type)
  * SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's
  *   cpuset.
  */
-void show_free_areas(unsigned int filter)
+void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 {
 	unsigned long free_pcp = 0;
 	int cpu;
@@ -4314,7 +4447,7 @@ void show_free_areas(unsigned int filter)
 	pg_data_t *pgdat;
 
 	for_each_populated_zone(zone) {
-		if (skip_free_areas_node(filter, zone_to_nid(zone)))
+		if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
 			continue;
 
 		for_each_online_cpu(cpu)
@@ -4348,6 +4481,9 @@ void show_free_areas(unsigned int filter)
 		global_page_state(NR_FREE_CMA_PAGES));
 
 	for_each_online_pgdat(pgdat) {
+		if (show_mem_node_skip(filter, pgdat->node_id, nodemask))
+			continue;
+
 		printk("Node %d"
 			" active_anon:%lukB"
 			" inactive_anon:%lukB"
@@ -4397,7 +4533,7 @@ void show_free_areas(unsigned int filter)
 	for_each_populated_zone(zone) {
 		int i;
 
-		if (skip_free_areas_node(filter, zone_to_nid(zone)))
+		if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
 			continue;
 
 		free_pcp = 0;
@@ -4462,7 +4598,7 @@ void show_free_areas(unsigned int filter)
 		unsigned long nr[MAX_ORDER], flags, total = 0;
 		unsigned char types[MAX_ORDER];
 
-		if (skip_free_areas_node(filter, zone_to_nid(zone)))
+		if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
 			continue;
 		show_node(zone);
 		printk(KERN_CONT "%s: ", zone->name);
@@ -5083,8 +5219,17 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		if (context != MEMMAP_EARLY)
 			goto not_early;
 
-		if (!early_pfn_valid(pfn))
+		if (!early_pfn_valid(pfn)) {
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+			/*
+			 * Skip to the pfn preceding the next valid one (or
+			 * end_pfn), such that we hit a valid pfn (or end_pfn)
+			 * on our next iteration of the loop.
+			 */
+			pfn = memblock_next_valid_pfn(pfn, end_pfn) - 1;
+#endif
 			continue;
+		}
 		if (!early_pfn_in_nid(pfn, nid))
 			continue;
 		if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised))
@@ -5591,6 +5736,11 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
 	adjust_zone_range_for_zone_movable(nid, zone_type,
 			node_start_pfn, node_end_pfn,
 			&zone_start_pfn, &zone_end_pfn);
+
+	/* If this node has no page within this zone, return 0. */
+	if (zone_start_pfn == zone_end_pfn)
+		return 0;
+
 	nr_absent = __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
 
 	/*
@@ -6378,10 +6528,12 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 
 	/* Print out the early node map */
 	pr_info("Early memory node ranges\n");
-	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
 		pr_info("  node %3d: [mem %#018Lx-%#018Lx]\n", nid,
 			(u64)start_pfn << PAGE_SHIFT,
 			((u64)end_pfn << PAGE_SHIFT) - 1);
+		section_active_init(start_pfn, end_pfn - start_pfn);
+	}
 
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
@@ -7081,8 +7233,9 @@ void *__init alloc_large_system_hash(const char *tablename,
  * If @count is not zero, it is okay to include less @count unmovable pages
  *
  * PageLRU check without isolation or lru_lock could race so that
- * MIGRATE_MOVABLE block might include unmovable pages. It means you can't
- * expect this function should be exact.
+ * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
+ * check without lock_page also may miss some movable non-lru pages at
+ * race condition. So you can't expect this function should be exact.
  */
 bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 			 bool skip_hwpoisoned_pages)
@@ -7138,6 +7291,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		if (skip_hwpoisoned_pages && PageHWPoison(page))
 			continue;
 
+		if (__PageMovable(page))
+			continue;
+
 		if (!PageLRU(page))
 			found++;
 		/*
@@ -7249,6 +7405,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
  *			#MIGRATE_MOVABLE or #MIGRATE_CMA).  All pageblocks
  *			in range must have the same migratetype and it must
  *			be either of the two.
+ * @gfp_mask:	GFP mask to use during compaction
  *
  * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
  * aligned, however it's the caller's responsibility to guarantee that
@@ -7262,7 +7419,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
  * need to be freed with free_contig_range().
  */
 int alloc_contig_range(unsigned long start, unsigned long end,
-		       unsigned migratetype)
+		       unsigned migratetype, gfp_t gfp_mask)
 {
 	unsigned long outer_start, outer_end;
 	unsigned int order;
@@ -7274,7 +7431,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		.zone = page_zone(pfn_to_page(start)),
 		.mode = MIGRATE_SYNC,
 		.ignore_skip_hint = true,
-		.gfp_mask = GFP_KERNEL,
+		.gfp_mask = memalloc_noio_flags(gfp_mask),
 	};
 	INIT_LIST_HEAD(&cc.migratepages);
 
diff --git a/mm/page_idle.c b/mm/page_idle.c
index ae11aa914e55..b0ee56c56b58 100644
--- a/mm/page_idle.c
+++ b/mm/page_idle.c
@@ -54,27 +54,27 @@ static int page_idle_clear_pte_refs_one(struct page *page,
 					struct vm_area_struct *vma,
 					unsigned long addr, void *arg)
 {
-	struct mm_struct *mm = vma->vm_mm;
-	pmd_t *pmd;
-	pte_t *pte;
-	spinlock_t *ptl;
+	struct page_vma_mapped_walk pvmw = {
+		.page = page,
+		.vma = vma,
+		.address = addr,
+	};
 	bool referenced = false;
 
-	if (!page_check_address_transhuge(page, mm, addr, &pmd, &pte, &ptl))
-		return SWAP_AGAIN;
-
-	if (pte) {
-		referenced = ptep_clear_young_notify(vma, addr, pte);
-		pte_unmap(pte);
-	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
-		referenced = pmdp_clear_young_notify(vma, addr, pmd);
-	} else {
-		/* unexpected pmd-mapped page? */
-		WARN_ON_ONCE(1);
+	while (page_vma_mapped_walk(&pvmw)) {
+		addr = pvmw.address;
+		if (pvmw.pte) {
+			referenced = ptep_clear_young_notify(vma, addr,
+					pvmw.pte);
+		} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
+			referenced = pmdp_clear_young_notify(vma, addr,
+					pvmw.pmd);
+		} else {
+			/* unexpected pmd-mapped page? */
+			WARN_ON_ONCE(1);
+		}
 	}
 
-	spin_unlock(ptl);
-
 	if (referenced) {
 		clear_page_idle(page);
 		/*
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index a5594bfcc5ed..f4e17a57926a 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -83,7 +83,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 	unsigned long flags, nr_pages;
 	bool isolated_page = false;
 	unsigned int order;
-	unsigned long page_idx, buddy_idx;
+	unsigned long pfn, buddy_pfn;
 	struct page *buddy;
 
 	zone = page_zone(page);
@@ -102,11 +102,11 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 	if (PageBuddy(page)) {
 		order = page_order(page);
 		if (order >= pageblock_order) {
-			page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
-			buddy_idx = __find_buddy_index(page_idx, order);
-			buddy = page + (buddy_idx - page_idx);
+			pfn = page_to_pfn(page);
+			buddy_pfn = __find_buddy_pfn(pfn, order);
+			buddy = page + (buddy_pfn - pfn);
 
-			if (pfn_valid_within(page_to_pfn(buddy)) &&
+			if (pfn_valid_within(buddy_pfn) &&
 			    !is_migrate_isolate_page(buddy)) {
 				__isolate_free_page(page, order);
 				isolated_page = true;
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 60634dc53a88..c3cee247f2e6 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -261,7 +261,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 	 */
 	for (; pfn < end_pfn; ) {
 		if (!pfn_valid(pfn)) {
-			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
+			pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 			continue;
 		}
 
@@ -527,7 +527,7 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
 	 */
 	for (; pfn < end_pfn; ) {
 		if (!pfn_valid(pfn)) {
-			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
+			pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 			continue;
 		}
 
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
new file mode 100644
index 000000000000..a23001a22c15
--- /dev/null
+++ b/mm/page_vma_mapped.c
@@ -0,0 +1,218 @@
+#include <linux/mm.h>
+#include <linux/rmap.h>
+#include <linux/hugetlb.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+
+#include "internal.h"
+
+static inline bool check_pmd(struct page_vma_mapped_walk *pvmw)
+{
+	pmd_t pmde;
+	/*
+	 * Make sure we don't re-load pmd between present and !trans_huge check.
+	 * We need a consistent view.
+	 */
+	pmde = READ_ONCE(*pvmw->pmd);
+	return pmd_present(pmde) && !pmd_trans_huge(pmde);
+}
+
+static inline bool not_found(struct page_vma_mapped_walk *pvmw)
+{
+	page_vma_mapped_walk_done(pvmw);
+	return false;
+}
+
+static bool map_pte(struct page_vma_mapped_walk *pvmw)
+{
+	pvmw->pte = pte_offset_map(pvmw->pmd, pvmw->address);
+	if (!(pvmw->flags & PVMW_SYNC)) {
+		if (pvmw->flags & PVMW_MIGRATION) {
+			if (!is_swap_pte(*pvmw->pte))
+				return false;
+		} else {
+			if (!pte_present(*pvmw->pte))
+				return false;
+		}
+	}
+	pvmw->ptl = pte_lockptr(pvmw->vma->vm_mm, pvmw->pmd);
+	spin_lock(pvmw->ptl);
+	return true;
+}
+
+static bool check_pte(struct page_vma_mapped_walk *pvmw)
+{
+	if (pvmw->flags & PVMW_MIGRATION) {
+#ifdef CONFIG_MIGRATION
+		swp_entry_t entry;
+		if (!is_swap_pte(*pvmw->pte))
+			return false;
+		entry = pte_to_swp_entry(*pvmw->pte);
+		if (!is_migration_entry(entry))
+			return false;
+		if (migration_entry_to_page(entry) - pvmw->page >=
+				hpage_nr_pages(pvmw->page)) {
+			return false;
+		}
+		if (migration_entry_to_page(entry) < pvmw->page)
+			return false;
+#else
+		WARN_ON_ONCE(1);
+#endif
+	} else {
+		if (!pte_present(*pvmw->pte))
+			return false;
+
+		/* THP can be referenced by any subpage */
+		if (pte_page(*pvmw->pte) - pvmw->page >=
+				hpage_nr_pages(pvmw->page)) {
+			return false;
+		}
+		if (pte_page(*pvmw->pte) < pvmw->page)
+			return false;
+	}
+
+	return true;
+}
+
+/**
+ * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at
+ * @pvmw->address
+ * @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags
+ * must be set. pmd, pte and ptl must be NULL.
+ *
+ * Returns true if the page is mapped in the vma. @pvmw->pmd and @pvmw->pte point
+ * to relevant page table entries. @pvmw->ptl is locked. @pvmw->address is
+ * adjusted if needed (for PTE-mapped THPs).
+ *
+ * If @pvmw->pmd is set but @pvmw->pte is not, you have found PMD-mapped page
+ * (usually THP). For PTE-mapped THP, you should run page_vma_mapped_walk() in
+ * a loop to find all PTEs that map the THP.
+ *
+ * For HugeTLB pages, @pvmw->pte is set to the relevant page table entry
+ * regardless of which page table level the page is mapped at. @pvmw->pmd is
+ * NULL.
+ *
+ * Retruns false if there are no more page table entries for the page in
+ * the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped.
+ *
+ * If you need to stop the walk before page_vma_mapped_walk() returned false,
+ * use page_vma_mapped_walk_done(). It will do the housekeeping.
+ */
+bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+{
+	struct mm_struct *mm = pvmw->vma->vm_mm;
+	struct page *page = pvmw->page;
+	pgd_t *pgd;
+	pud_t *pud;
+
+	/* The only possible pmd mapping has been handled on last iteration */
+	if (pvmw->pmd && !pvmw->pte)
+		return not_found(pvmw);
+
+	/* Only for THP, seek to next pte entry makes sense */
+	if (pvmw->pte) {
+		if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
+			return not_found(pvmw);
+		goto next_pte;
+	}
+
+	if (unlikely(PageHuge(pvmw->page))) {
+		/* when pud is not present, pte will be NULL */
+		pvmw->pte = huge_pte_offset(mm, pvmw->address);
+		if (!pvmw->pte)
+			return false;
+
+		pvmw->ptl = huge_pte_lockptr(page_hstate(page), mm, pvmw->pte);
+		spin_lock(pvmw->ptl);
+		if (!check_pte(pvmw))
+			return not_found(pvmw);
+		return true;
+	}
+restart:
+	pgd = pgd_offset(mm, pvmw->address);
+	if (!pgd_present(*pgd))
+		return false;
+	pud = pud_offset(pgd, pvmw->address);
+	if (!pud_present(*pud))
+		return false;
+	pvmw->pmd = pmd_offset(pud, pvmw->address);
+	if (pmd_trans_huge(*pvmw->pmd)) {
+		pvmw->ptl = pmd_lock(mm, pvmw->pmd);
+		if (!pmd_present(*pvmw->pmd))
+			return not_found(pvmw);
+		if (likely(pmd_trans_huge(*pvmw->pmd))) {
+			if (pvmw->flags & PVMW_MIGRATION)
+				return not_found(pvmw);
+			if (pmd_page(*pvmw->pmd) != page)
+				return not_found(pvmw);
+			return true;
+		} else {
+			/* THP pmd was split under us: handle on pte level */
+			spin_unlock(pvmw->ptl);
+			pvmw->ptl = NULL;
+		}
+	} else {
+		if (!check_pmd(pvmw))
+			return false;
+	}
+	if (!map_pte(pvmw))
+		goto next_pte;
+	while (1) {
+		if (check_pte(pvmw))
+			return true;
+next_pte:	do {
+			pvmw->address += PAGE_SIZE;
+			if (pvmw->address >=
+					__vma_address(pvmw->page, pvmw->vma) +
+					hpage_nr_pages(pvmw->page) * PAGE_SIZE)
+				return not_found(pvmw);
+			/* Did we cross page table boundary? */
+			if (pvmw->address % PMD_SIZE == 0) {
+				pte_unmap(pvmw->pte);
+				if (pvmw->ptl) {
+					spin_unlock(pvmw->ptl);
+					pvmw->ptl = NULL;
+				}
+				goto restart;
+			} else {
+				pvmw->pte++;
+			}
+		} while (pte_none(*pvmw->pte));
+
+		if (!pvmw->ptl) {
+			pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
+			spin_lock(pvmw->ptl);
+		}
+	}
+}
+
+/**
+ * page_mapped_in_vma - check whether a page is really mapped in a VMA
+ * @page: the page to test
+ * @vma: the VMA to test
+ *
+ * Returns 1 if the page is mapped into the page tables of the VMA, 0
+ * if the page is not mapped into the page tables of this VMA.  Only
+ * valid for normal file or anonymous VMAs.
+ */
+int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
+{
+	struct page_vma_mapped_walk pvmw = {
+		.page = page,
+		.vma = vma,
+		.flags = PVMW_SYNC,
+	};
+	unsigned long start, end;
+
+	start = __vma_address(page, vma);
+	end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1);
+
+	if (unlikely(end < vma->vm_start || start >= vma->vm_end))
+		return 0;
+	pvmw.address = max(start, vma->vm_start);
+	if (!page_vma_mapped_walk(&pvmw))
+		return 0;
+	page_vma_mapped_walk_done(&pvmw);
+	return 1;
+}
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 207244489a68..03761577ae86 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -78,14 +78,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 
 	pud = pud_offset(pgd, addr);
 	do {
+ again:
 		next = pud_addr_end(addr, end);
-		if (pud_none_or_clear_bad(pud)) {
+		if (pud_none(*pud) || !walk->vma) {
 			if (walk->pte_hole)
 				err = walk->pte_hole(addr, next, walk);
 			if (err)
 				break;
 			continue;
 		}
+
+		if (walk->pud_entry) {
+			spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma);
+
+			if (ptl) {
+				err = walk->pud_entry(pud, addr, next, walk);
+				spin_unlock(ptl);
+				if (err)
+					break;
+				continue;
+			}
+		}
+
+		split_huge_pud(walk->vma, pud, addr);
+		if (pud_none(*pud))
+			goto again;
+
 		if (walk->pmd_entry || walk->pte_entry)
 			err = walk_pmd_range(pud, addr, next, walk);
 		if (err)
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 71c5f9109f2a..4ed5908c65b0 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -123,6 +123,20 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
 	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return pmd;
 }
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
+			    pud_t *pudp)
+{
+	pud_t pud;
+
+	VM_BUG_ON(address & ~HPAGE_PUD_MASK);
+	VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp));
+	pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp);
+	flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
+	return pud;
+}
+#endif
 #endif
 
 #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
diff --git a/mm/rmap.c b/mm/rmap.c
index 91619fd70939..8774791e2809 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -607,8 +607,7 @@ void try_to_unmap_flush_dirty(void)
 		try_to_unmap_flush();
 }
 
-static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
-		struct page *page, bool writable)
+static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
 {
 	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
 
@@ -643,8 +642,7 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
 	return should_defer;
 }
 #else
-static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
-		struct page *page, bool writable)
+static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
 {
 }
 
@@ -710,170 +708,6 @@ out:
 	return pmd;
 }
 
-/*
- * Check that @page is mapped at @address into @mm.
- *
- * If @sync is false, page_check_address may perform a racy check to avoid
- * the page table lock when the pte is not present (helpful when reclaiming
- * highly shared pages).
- *
- * On success returns with pte mapped and locked.
- */
-pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
-			  unsigned long address, spinlock_t **ptlp, int sync)
-{
-	pmd_t *pmd;
-	pte_t *pte;
-	spinlock_t *ptl;
-
-	if (unlikely(PageHuge(page))) {
-		/* when pud is not present, pte will be NULL */
-		pte = huge_pte_offset(mm, address);
-		if (!pte)
-			return NULL;
-
-		ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
-		goto check;
-	}
-
-	pmd = mm_find_pmd(mm, address);
-	if (!pmd)
-		return NULL;
-
-	pte = pte_offset_map(pmd, address);
-	/* Make a quick check before getting the lock */
-	if (!sync && !pte_present(*pte)) {
-		pte_unmap(pte);
-		return NULL;
-	}
-
-	ptl = pte_lockptr(mm, pmd);
-check:
-	spin_lock(ptl);
-	if (pte_present(*pte) && page_to_pfn(page) == pte_pfn(*pte)) {
-		*ptlp = ptl;
-		return pte;
-	}
-	pte_unmap_unlock(pte, ptl);
-	return NULL;
-}
-
-/**
- * page_mapped_in_vma - check whether a page is really mapped in a VMA
- * @page: the page to test
- * @vma: the VMA to test
- *
- * Returns 1 if the page is mapped into the page tables of the VMA, 0
- * if the page is not mapped into the page tables of this VMA.  Only
- * valid for normal file or anonymous VMAs.
- */
-int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
-{
-	unsigned long address;
-	pte_t *pte;
-	spinlock_t *ptl;
-
-	address = __vma_address(page, vma);
-	if (unlikely(address < vma->vm_start || address >= vma->vm_end))
-		return 0;
-	pte = page_check_address(page, vma->vm_mm, address, &ptl, 1);
-	if (!pte)			/* the page is not in this mm */
-		return 0;
-	pte_unmap_unlock(pte, ptl);
-
-	return 1;
-}
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-/*
- * Check that @page is mapped at @address into @mm. In contrast to
- * page_check_address(), this function can handle transparent huge pages.
- *
- * On success returns true with pte mapped and locked. For PMD-mapped
- * transparent huge pages *@ptep is set to NULL.
- */
-bool page_check_address_transhuge(struct page *page, struct mm_struct *mm,
-				  unsigned long address, pmd_t **pmdp,
-				  pte_t **ptep, spinlock_t **ptlp)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-	spinlock_t *ptl;
-
-	if (unlikely(PageHuge(page))) {
-		/* when pud is not present, pte will be NULL */
-		pte = huge_pte_offset(mm, address);
-		if (!pte)
-			return false;
-
-		ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
-		pmd = NULL;
-		goto check_pte;
-	}
-
-	pgd = pgd_offset(mm, address);
-	if (!pgd_present(*pgd))
-		return false;
-	pud = pud_offset(pgd, address);
-	if (!pud_present(*pud))
-		return false;
-	pmd = pmd_offset(pud, address);
-
-	if (pmd_trans_huge(*pmd)) {
-		ptl = pmd_lock(mm, pmd);
-		if (!pmd_present(*pmd))
-			goto unlock_pmd;
-		if (unlikely(!pmd_trans_huge(*pmd))) {
-			spin_unlock(ptl);
-			goto map_pte;
-		}
-
-		if (pmd_page(*pmd) != page)
-			goto unlock_pmd;
-
-		pte = NULL;
-		goto found;
-unlock_pmd:
-		spin_unlock(ptl);
-		return false;
-	} else {
-		pmd_t pmde = *pmd;
-
-		barrier();
-		if (!pmd_present(pmde) || pmd_trans_huge(pmde))
-			return false;
-	}
-map_pte:
-	pte = pte_offset_map(pmd, address);
-	if (!pte_present(*pte)) {
-		pte_unmap(pte);
-		return false;
-	}
-
-	ptl = pte_lockptr(mm, pmd);
-check_pte:
-	spin_lock(ptl);
-
-	if (!pte_present(*pte)) {
-		pte_unmap_unlock(pte, ptl);
-		return false;
-	}
-
-	/* THP can be referenced by any subpage */
-	if (pte_pfn(*pte) - page_to_pfn(page) >= hpage_nr_pages(page)) {
-		pte_unmap_unlock(pte, ptl);
-		return false;
-	}
-found:
-	*ptep = pte;
-	*pmdp = pmd;
-	*ptlp = ptl;
-	return true;
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
 struct page_referenced_arg {
 	int mapcount;
 	int referenced;
@@ -886,45 +720,48 @@ struct page_referenced_arg {
 static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 			unsigned long address, void *arg)
 {
-	struct mm_struct *mm = vma->vm_mm;
 	struct page_referenced_arg *pra = arg;
-	pmd_t *pmd;
-	pte_t *pte;
-	spinlock_t *ptl;
+	struct page_vma_mapped_walk pvmw = {
+		.page = page,
+		.vma = vma,
+		.address = address,
+	};
 	int referenced = 0;
 
-	if (!page_check_address_transhuge(page, mm, address, &pmd, &pte, &ptl))
-		return SWAP_AGAIN;
+	while (page_vma_mapped_walk(&pvmw)) {
+		address = pvmw.address;
 
-	if (vma->vm_flags & VM_LOCKED) {
-		if (pte)
-			pte_unmap(pte);
-		spin_unlock(ptl);
-		pra->vm_flags |= VM_LOCKED;
-		return SWAP_FAIL; /* To break the loop */
-	}
+		if (vma->vm_flags & VM_LOCKED) {
+			page_vma_mapped_walk_done(&pvmw);
+			pra->vm_flags |= VM_LOCKED;
+			return SWAP_FAIL; /* To break the loop */
+		}
 
-	if (pte) {
-		if (ptep_clear_flush_young_notify(vma, address, pte)) {
-			/*
-			 * Don't treat a reference through a sequentially read
-			 * mapping as such.  If the page has been used in
-			 * another mapping, we will catch it; if this other
-			 * mapping is already gone, the unmap path will have
-			 * set PG_referenced or activated the page.
-			 */
-			if (likely(!(vma->vm_flags & VM_SEQ_READ)))
+		if (pvmw.pte) {
+			if (ptep_clear_flush_young_notify(vma, address,
+						pvmw.pte)) {
+				/*
+				 * Don't treat a reference through
+				 * a sequentially read mapping as such.
+				 * If the page has been used in another mapping,
+				 * we will catch it; if this other mapping is
+				 * already gone, the unmap path will have set
+				 * PG_referenced or activated the page.
+				 */
+				if (likely(!(vma->vm_flags & VM_SEQ_READ)))
+					referenced++;
+			}
+		} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
+			if (pmdp_clear_flush_young_notify(vma, address,
+						pvmw.pmd))
 				referenced++;
+		} else {
+			/* unexpected pmd-mapped page? */
+			WARN_ON_ONCE(1);
 		}
-		pte_unmap(pte);
-	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
-		if (pmdp_clear_flush_young_notify(vma, address, pmd))
-			referenced++;
-	} else {
-		/* unexpected pmd-mapped page? */
-		WARN_ON_ONCE(1);
+
+		pra->mapcount--;
 	}
-	spin_unlock(ptl);
 
 	if (referenced)
 		clear_page_idle(page);
@@ -936,7 +773,6 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		pra->vm_flags |= vma->vm_flags;
 	}
 
-	pra->mapcount--;
 	if (!pra->mapcount)
 		return SWAP_SUCCESS; /* To break the loop */
 
@@ -1015,34 +851,56 @@ int page_referenced(struct page *page,
 static int page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 			    unsigned long address, void *arg)
 {
-	struct mm_struct *mm = vma->vm_mm;
-	pte_t *pte;
-	spinlock_t *ptl;
-	int ret = 0;
+	struct page_vma_mapped_walk pvmw = {
+		.page = page,
+		.vma = vma,
+		.address = address,
+		.flags = PVMW_SYNC,
+	};
 	int *cleaned = arg;
 
-	pte = page_check_address(page, mm, address, &ptl, 1);
-	if (!pte)
-		goto out;
-
-	if (pte_dirty(*pte) || pte_write(*pte)) {
-		pte_t entry;
+	while (page_vma_mapped_walk(&pvmw)) {
+		int ret = 0;
+		address = pvmw.address;
+		if (pvmw.pte) {
+			pte_t entry;
+			pte_t *pte = pvmw.pte;
+
+			if (!pte_dirty(*pte) && !pte_write(*pte))
+				continue;
+
+			flush_cache_page(vma, address, pte_pfn(*pte));
+			entry = ptep_clear_flush(vma, address, pte);
+			entry = pte_wrprotect(entry);
+			entry = pte_mkclean(entry);
+			set_pte_at(vma->vm_mm, address, pte, entry);
+			ret = 1;
+		} else {
+#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
+			pmd_t *pmd = pvmw.pmd;
+			pmd_t entry;
+
+			if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
+				continue;
+
+			flush_cache_page(vma, address, page_to_pfn(page));
+			entry = pmdp_huge_clear_flush(vma, address, pmd);
+			entry = pmd_wrprotect(entry);
+			entry = pmd_mkclean(entry);
+			set_pmd_at(vma->vm_mm, address, pmd, entry);
+			ret = 1;
+#else
+			/* unexpected pmd-mapped page? */
+			WARN_ON_ONCE(1);
+#endif
+		}
 
-		flush_cache_page(vma, address, pte_pfn(*pte));
-		entry = ptep_clear_flush(vma, address, pte);
-		entry = pte_wrprotect(entry);
-		entry = pte_mkclean(entry);
-		set_pte_at(mm, address, pte, entry);
-		ret = 1;
+		if (ret) {
+			mmu_notifier_invalidate_page(vma->vm_mm, address);
+			(*cleaned)++;
+		}
 	}
 
-	pte_unmap_unlock(pte, ptl);
-
-	if (ret) {
-		mmu_notifier_invalidate_page(mm, address);
-		(*cleaned)++;
-	}
-out:
 	return SWAP_AGAIN;
 }
 
@@ -1435,155 +1293,163 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		     unsigned long address, void *arg)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	pte_t *pte;
+	struct page_vma_mapped_walk pvmw = {
+		.page = page,
+		.vma = vma,
+		.address = address,
+	};
 	pte_t pteval;
-	spinlock_t *ptl;
+	struct page *subpage;
 	int ret = SWAP_AGAIN;
 	struct rmap_private *rp = arg;
 	enum ttu_flags flags = rp->flags;
 
 	/* munlock has nothing to gain from examining un-locked vmas */
 	if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
-		goto out;
+		return SWAP_AGAIN;
 
 	if (flags & TTU_SPLIT_HUGE_PMD) {
 		split_huge_pmd_address(vma, address,
 				flags & TTU_MIGRATION, page);
-		/* check if we have anything to do after split */
-		if (page_mapcount(page) == 0)
-			goto out;
 	}
 
-	pte = page_check_address(page, mm, address, &ptl,
-				 PageTransCompound(page));
-	if (!pte)
-		goto out;
+	while (page_vma_mapped_walk(&pvmw)) {
+		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+		address = pvmw.address;
 
-	/*
-	 * If the page is mlock()d, we cannot swap it out.
-	 * If it's recently referenced (perhaps page_referenced
-	 * skipped over this mm) then we should reactivate it.
-	 */
-	if (!(flags & TTU_IGNORE_MLOCK)) {
-		if (vma->vm_flags & VM_LOCKED) {
-			/* PTE-mapped THP are never mlocked */
-			if (!PageTransCompound(page)) {
-				/*
-				 * Holding pte lock, we do *not* need
-				 * mmap_sem here
-				 */
-				mlock_vma_page(page);
-			}
-			ret = SWAP_MLOCK;
-			goto out_unmap;
-		}
-		if (flags & TTU_MUNLOCK)
-			goto out_unmap;
-	}
-	if (!(flags & TTU_IGNORE_ACCESS)) {
-		if (ptep_clear_flush_young_notify(vma, address, pte)) {
-			ret = SWAP_FAIL;
-			goto out_unmap;
-		}
-  	}
+		/* Unexpected PMD-mapped THP? */
+		VM_BUG_ON_PAGE(!pvmw.pte, page);
 
-	/* Nuke the page table entry. */
-	flush_cache_page(vma, address, page_to_pfn(page));
-	if (should_defer_flush(mm, flags)) {
 		/*
-		 * We clear the PTE but do not flush so potentially a remote
-		 * CPU could still be writing to the page. If the entry was
-		 * previously clean then the architecture must guarantee that
-		 * a clear->dirty transition on a cached TLB entry is written
-		 * through and traps if the PTE is unmapped.
+		 * If the page is mlock()d, we cannot swap it out.
+		 * If it's recently referenced (perhaps page_referenced
+		 * skipped over this mm) then we should reactivate it.
 		 */
-		pteval = ptep_get_and_clear(mm, address, pte);
-
-		set_tlb_ubc_flush_pending(mm, page, pte_dirty(pteval));
-	} else {
-		pteval = ptep_clear_flush(vma, address, pte);
-	}
+		if (!(flags & TTU_IGNORE_MLOCK)) {
+			if (vma->vm_flags & VM_LOCKED) {
+				/* PTE-mapped THP are never mlocked */
+				if (!PageTransCompound(page)) {
+					/*
+					 * Holding pte lock, we do *not* need
+					 * mmap_sem here
+					 */
+					mlock_vma_page(page);
+				}
+				ret = SWAP_MLOCK;
+				page_vma_mapped_walk_done(&pvmw);
+				break;
+			}
+			if (flags & TTU_MUNLOCK)
+				continue;
+		}
 
-	/* Move the dirty bit to the physical page now the pte is gone. */
-	if (pte_dirty(pteval))
-		set_page_dirty(page);
+		if (!(flags & TTU_IGNORE_ACCESS)) {
+			if (ptep_clear_flush_young_notify(vma, address,
+						pvmw.pte)) {
+				ret = SWAP_FAIL;
+				page_vma_mapped_walk_done(&pvmw);
+				break;
+			}
+		}
 
-	/* Update high watermark before we lower rss */
-	update_hiwater_rss(mm);
+		/* Nuke the page table entry. */
+		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+		if (should_defer_flush(mm, flags)) {
+			/*
+			 * We clear the PTE but do not flush so potentially
+			 * a remote CPU could still be writing to the page.
+			 * If the entry was previously clean then the
+			 * architecture must guarantee that a clear->dirty
+			 * transition on a cached TLB entry is written through
+			 * and traps if the PTE is unmapped.
+			 */
+			pteval = ptep_get_and_clear(mm, address, pvmw.pte);
 
-	if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
-		if (PageHuge(page)) {
-			hugetlb_count_sub(1 << compound_order(page), mm);
+			set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
 		} else {
-			dec_mm_counter(mm, mm_counter(page));
+			pteval = ptep_clear_flush(vma, address, pvmw.pte);
 		}
-		set_pte_at(mm, address, pte,
-			   swp_entry_to_pte(make_hwpoison_entry(page)));
-	} else if (pte_unused(pteval)) {
-		/*
-		 * The guest indicated that the page content is of no
-		 * interest anymore. Simply discard the pte, vmscan
-		 * will take care of the rest.
-		 */
-		dec_mm_counter(mm, mm_counter(page));
-	} else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) {
-		swp_entry_t entry;
-		pte_t swp_pte;
-		/*
-		 * Store the pfn of the page in a special migration
-		 * pte. do_swap_page() will wait until the migration
-		 * pte is removed and then restart fault handling.
-		 */
-		entry = make_migration_entry(page, pte_write(pteval));
-		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);
-	} else if (PageAnon(page)) {
-		swp_entry_t entry = { .val = page_private(page) };
-		pte_t swp_pte;
-		/*
-		 * Store the swap location in the pte.
-		 * See handle_pte_fault() ...
-		 */
-		VM_BUG_ON_PAGE(!PageSwapCache(page), page);
 
-		if (!PageDirty(page) && (flags & TTU_LZFREE)) {
-			/* It's a freeable page by MADV_FREE */
-			dec_mm_counter(mm, MM_ANONPAGES);
-			rp->lazyfreed++;
-			goto discard;
-		}
+		/* Move the dirty bit to the page. Now the pte is gone. */
+		if (pte_dirty(pteval))
+			set_page_dirty(page);
 
-		if (swap_duplicate(entry) < 0) {
-			set_pte_at(mm, address, pte, pteval);
-			ret = SWAP_FAIL;
-			goto out_unmap;
-		}
-		if (list_empty(&mm->mmlist)) {
-			spin_lock(&mmlist_lock);
-			if (list_empty(&mm->mmlist))
-				list_add(&mm->mmlist, &init_mm.mmlist);
-			spin_unlock(&mmlist_lock);
-		}
-		dec_mm_counter(mm, MM_ANONPAGES);
-		inc_mm_counter(mm, MM_SWAPENTS);
-		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);
-	} else
-		dec_mm_counter(mm, mm_counter_file(page));
+		/* Update high watermark before we lower rss */
+		update_hiwater_rss(mm);
 
-discard:
-	page_remove_rmap(page, PageHuge(page));
-	put_page(page);
+		if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
+			if (PageHuge(page)) {
+				int nr = 1 << compound_order(page);
+				hugetlb_count_sub(nr, mm);
+			} else {
+				dec_mm_counter(mm, mm_counter(page));
+			}
+
+			pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
+			set_pte_at(mm, address, pvmw.pte, pteval);
+		} else if (pte_unused(pteval)) {
+			/*
+			 * The guest indicated that the page content is of no
+			 * interest anymore. Simply discard the pte, vmscan
+			 * will take care of the rest.
+			 */
+			dec_mm_counter(mm, mm_counter(page));
+		} else if (IS_ENABLED(CONFIG_MIGRATION) &&
+				(flags & TTU_MIGRATION)) {
+			swp_entry_t entry;
+			pte_t swp_pte;
+			/*
+			 * Store the pfn of the page in a special migration
+			 * pte. do_swap_page() will wait until the migration
+			 * pte is removed and then restart fault handling.
+			 */
+			entry = make_migration_entry(subpage,
+					pte_write(pteval));
+			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, pvmw.pte, swp_pte);
+		} else if (PageAnon(page)) {
+			swp_entry_t entry = { .val = page_private(subpage) };
+			pte_t swp_pte;
+			/*
+			 * Store the swap location in the pte.
+			 * See handle_pte_fault() ...
+			 */
+			VM_BUG_ON_PAGE(!PageSwapCache(page), page);
+
+			if (!PageDirty(page) && (flags & TTU_LZFREE)) {
+				/* It's a freeable page by MADV_FREE */
+				dec_mm_counter(mm, MM_ANONPAGES);
+				rp->lazyfreed++;
+				goto discard;
+			}
 
-out_unmap:
-	pte_unmap_unlock(pte, ptl);
-	if (ret != SWAP_FAIL && ret != SWAP_MLOCK && !(flags & TTU_MUNLOCK))
+			if (swap_duplicate(entry) < 0) {
+				set_pte_at(mm, address, pvmw.pte, pteval);
+				ret = SWAP_FAIL;
+				page_vma_mapped_walk_done(&pvmw);
+				break;
+			}
+			if (list_empty(&mm->mmlist)) {
+				spin_lock(&mmlist_lock);
+				if (list_empty(&mm->mmlist))
+					list_add(&mm->mmlist, &init_mm.mmlist);
+				spin_unlock(&mmlist_lock);
+			}
+			dec_mm_counter(mm, MM_ANONPAGES);
+			inc_mm_counter(mm, MM_SWAPENTS);
+			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, pvmw.pte, swp_pte);
+		} else
+			dec_mm_counter(mm, mm_counter_file(page));
+discard:
+		page_remove_rmap(subpage, PageHuge(page));
+		put_page(page);
 		mmu_notifier_invalidate_page(mm, address);
-out:
+	}
 	return ret;
 }
 
@@ -1608,7 +1474,7 @@ static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg)
 
 static int page_mapcount_is_zero(struct page *page)
 {
-	return !page_mapcount(page);
+	return !total_mapcount(page);
 }
 
 /**
@@ -1755,7 +1621,7 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc,
 		bool locked)
 {
 	struct anon_vma *anon_vma;
-	pgoff_t pgoff;
+	pgoff_t pgoff_start, pgoff_end;
 	struct anon_vma_chain *avc;
 	int ret = SWAP_AGAIN;
 
@@ -1769,8 +1635,10 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc,
 	if (!anon_vma)
 		return ret;
 
-	pgoff = page_to_pgoff(page);
-	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {
+	pgoff_start = page_to_pgoff(page);
+	pgoff_end = pgoff_start + hpage_nr_pages(page) - 1;
+	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
+			pgoff_start, pgoff_end) {
 		struct vm_area_struct *vma = avc->vma;
 		unsigned long address = vma_address(page, vma);
 
@@ -1808,7 +1676,7 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc,
 		bool locked)
 {
 	struct address_space *mapping = page_mapping(page);
-	pgoff_t pgoff;
+	pgoff_t pgoff_start, pgoff_end;
 	struct vm_area_struct *vma;
 	int ret = SWAP_AGAIN;
 
@@ -1823,10 +1691,12 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc,
 	if (!mapping)
 		return ret;
 
-	pgoff = page_to_pgoff(page);
+	pgoff_start = page_to_pgoff(page);
+	pgoff_end = pgoff_start + hpage_nr_pages(page) - 1;
 	if (!locked)
 		i_mmap_lock_read(mapping);
-	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
+	vma_interval_tree_foreach(vma, &mapping->i_mmap,
+			pgoff_start, pgoff_end) {
 		unsigned long address = vma_address(page, vma);
 
 		cond_resched();
diff --git a/mm/rodata_test.c b/mm/rodata_test.c
new file mode 100644
index 000000000000..0fd21670b513
--- /dev/null
+++ b/mm/rodata_test.c
@@ -0,0 +1,56 @@
+/*
+ * rodata_test.c: functional test for mark_rodata_ro function
+ *
+ * (C) Copyright 2008 Intel Corporation
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#include <linux/uaccess.h>
+#include <asm/sections.h>
+
+const int rodata_test_data = 0xC3;
+EXPORT_SYMBOL_GPL(rodata_test_data);
+
+void rodata_test(void)
+{
+	unsigned long start, end;
+	int zero = 0;
+
+	/* test 1: read the value */
+	/* If this test fails, some previous testrun has clobbered the state */
+	if (!rodata_test_data) {
+		pr_err("rodata_test: test 1 fails (start data)\n");
+		return;
+	}
+
+	/* test 2: write to the variable; this should fault */
+	if (!probe_kernel_write((void *)&rodata_test_data,
+						(void *)&zero, sizeof(zero))) {
+		pr_err("rodata_test: test data was not read only\n");
+		return;
+	}
+
+	/* test 3: check the value hasn't changed */
+	if (rodata_test_data == zero) {
+		pr_err("rodata_test: test data was changed\n");
+		return;
+	}
+
+	/* test 4: check if the rodata section is PAGE_SIZE aligned */
+	start = (unsigned long)__start_rodata;
+	end = (unsigned long)__end_rodata;
+	if (start & (PAGE_SIZE - 1)) {
+		pr_err("rodata_test: start of .rodata is not page size aligned\n");
+		return;
+	}
+	if (end & (PAGE_SIZE - 1)) {
+		pr_err("rodata_test: end of .rodata is not page size aligned\n");
+		return;
+	}
+
+	pr_info("rodata_test: all tests were successful\n");
+}
diff --git a/mm/shmem.c b/mm/shmem.c
index 3a7587a0314d..a26649a6633f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -34,6 +34,8 @@
 #include <linux/uio.h>
 #include <linux/khugepaged.h>
 
+#include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */
+
 static struct vfsmount *shm_mnt;
 
 #ifdef CONFIG_SHMEM
@@ -70,6 +72,8 @@ static struct vfsmount *shm_mnt;
 #include <linux/syscalls.h>
 #include <linux/fcntl.h>
 #include <uapi/linux/memfd.h>
+#include <linux/userfaultfd_k.h>
+#include <linux/rmap.h>
 
 #include <linux/uaccess.h>
 #include <asm/pgtable.h>
@@ -115,13 +119,14 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 				struct shmem_inode_info *info, pgoff_t index);
 static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 		struct page **pagep, enum sgp_type sgp,
-		gfp_t gfp, struct mm_struct *fault_mm, int *fault_type);
+		gfp_t gfp, struct vm_area_struct *vma,
+		struct vm_fault *vmf, int *fault_type);
 
 int shmem_getpage(struct inode *inode, pgoff_t index,
 		struct page **pagep, enum sgp_type sgp)
 {
 	return shmem_getpage_gfp(inode, index, pagep, sgp,
-		mapping_gfp_mask(inode->i_mapping), NULL, NULL);
+		mapping_gfp_mask(inode->i_mapping), NULL, NULL, NULL);
 }
 
 static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb)
@@ -190,6 +195,11 @@ static const struct inode_operations shmem_special_inode_operations;
 static const struct vm_operations_struct shmem_vm_ops;
 static struct file_system_type shmem_fs_type;
 
+bool vma_is_shmem(struct vm_area_struct *vma)
+{
+	return vma->vm_ops == &shmem_vm_ops;
+}
+
 static LIST_HEAD(shmem_swaplist);
 static DEFINE_MUTEX(shmem_swaplist_mutex);
 
@@ -1570,7 +1580,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
  */
 static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	struct page **pagep, enum sgp_type sgp, gfp_t gfp,
-	struct mm_struct *fault_mm, int *fault_type)
+	struct vm_area_struct *vma, struct vm_fault *vmf, int *fault_type)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct shmem_inode_info *info = SHMEM_I(inode);
@@ -1624,7 +1634,7 @@ repeat:
 	 * bring it back from swap or allocate.
 	 */
 	sbinfo = SHMEM_SB(inode->i_sb);
-	charge_mm = fault_mm ? : current->mm;
+	charge_mm = vma ? vma->vm_mm : current->mm;
 
 	if (swap.val) {
 		/* Look it up and read it in.. */
@@ -1634,7 +1644,8 @@ repeat:
 			if (fault_type) {
 				*fault_type |= VM_FAULT_MAJOR;
 				count_vm_event(PGMAJFAULT);
-				mem_cgroup_count_vm_event(fault_mm, PGMAJFAULT);
+				mem_cgroup_count_vm_event(charge_mm,
+							  PGMAJFAULT);
 			}
 			/* Here we actually start the io */
 			page = shmem_swapin(swap, gfp, info, index);
@@ -1703,6 +1714,11 @@ repeat:
 		swap_free(swap);
 
 	} else {
+		if (vma && userfaultfd_missing(vma)) {
+			*fault_type = handle_userfault(vmf, VM_UFFD_MISSING);
+			return 0;
+		}
+
 		/* shmem_symlink() */
 		if (mapping->a_ops != &shmem_aops)
 			goto alloc_nohuge;
@@ -1892,8 +1908,9 @@ static int synchronous_wake_function(wait_queue_t *wait, unsigned mode, int sync
 	return ret;
 }
 
-static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int shmem_fault(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = file_inode(vma->vm_file);
 	gfp_t gfp = mapping_gfp_mask(inode->i_mapping);
 	enum sgp_type sgp;
@@ -1965,7 +1982,7 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		sgp = SGP_NOHUGE;
 
 	error = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp,
-				  gfp, vma->vm_mm, &ret);
+				  gfp, vma, vmf, &ret);
 	if (error)
 		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
 	return ret;
@@ -2175,10 +2192,123 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 
 bool shmem_mapping(struct address_space *mapping)
 {
-	if (!mapping->host)
-		return false;
+	return mapping->a_ops == &shmem_aops;
+}
 
-	return mapping->host->i_sb->s_op == &shmem_ops;
+int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm,
+			   pmd_t *dst_pmd,
+			   struct vm_area_struct *dst_vma,
+			   unsigned long dst_addr,
+			   unsigned long src_addr,
+			   struct page **pagep)
+{
+	struct inode *inode = file_inode(dst_vma->vm_file);
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+	struct address_space *mapping = inode->i_mapping;
+	gfp_t gfp = mapping_gfp_mask(mapping);
+	pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
+	struct mem_cgroup *memcg;
+	spinlock_t *ptl;
+	void *page_kaddr;
+	struct page *page;
+	pte_t _dst_pte, *dst_pte;
+	int ret;
+
+	ret = -ENOMEM;
+	if (shmem_acct_block(info->flags, 1))
+		goto out;
+	if (sbinfo->max_blocks) {
+		if (percpu_counter_compare(&sbinfo->used_blocks,
+					   sbinfo->max_blocks) >= 0)
+			goto out_unacct_blocks;
+		percpu_counter_inc(&sbinfo->used_blocks);
+	}
+
+	if (!*pagep) {
+		page = shmem_alloc_page(gfp, info, pgoff);
+		if (!page)
+			goto out_dec_used_blocks;
+
+		page_kaddr = kmap_atomic(page);
+		ret = copy_from_user(page_kaddr, (const void __user *)src_addr,
+				     PAGE_SIZE);
+		kunmap_atomic(page_kaddr);
+
+		/* fallback to copy_from_user outside mmap_sem */
+		if (unlikely(ret)) {
+			*pagep = page;
+			if (sbinfo->max_blocks)
+				percpu_counter_add(&sbinfo->used_blocks, -1);
+			shmem_unacct_blocks(info->flags, 1);
+			/* don't free the page */
+			return -EFAULT;
+		}
+	} else {
+		page = *pagep;
+		*pagep = NULL;
+	}
+
+	VM_BUG_ON(PageLocked(page) || PageSwapBacked(page));
+	__SetPageLocked(page);
+	__SetPageSwapBacked(page);
+	__SetPageUptodate(page);
+
+	ret = mem_cgroup_try_charge(page, dst_mm, gfp, &memcg, false);
+	if (ret)
+		goto out_release;
+
+	ret = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK);
+	if (!ret) {
+		ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL);
+		radix_tree_preload_end();
+	}
+	if (ret)
+		goto out_release_uncharge;
+
+	mem_cgroup_commit_charge(page, memcg, false, false);
+
+	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
+	if (dst_vma->vm_flags & VM_WRITE)
+		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
+
+	ret = -EEXIST;
+	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+	if (!pte_none(*dst_pte))
+		goto out_release_uncharge_unlock;
+
+	lru_cache_add_anon(page);
+
+	spin_lock(&info->lock);
+	info->alloced++;
+	inode->i_blocks += BLOCKS_PER_PAGE;
+	shmem_recalc_inode(inode);
+	spin_unlock(&info->lock);
+
+	inc_mm_counter(dst_mm, mm_counter_file(page));
+	page_add_file_rmap(page, false);
+	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+
+	/* No need to invalidate - it was non-present before */
+	update_mmu_cache(dst_vma, dst_addr, dst_pte);
+	unlock_page(page);
+	pte_unmap_unlock(dst_pte, ptl);
+	ret = 0;
+out:
+	return ret;
+out_release_uncharge_unlock:
+	pte_unmap_unlock(dst_pte, ptl);
+out_release_uncharge:
+	mem_cgroup_cancel_charge(page, memcg, false);
+out_release:
+	unlock_page(page);
+	put_page(page);
+out_dec_used_blocks:
+	if (sbinfo->max_blocks)
+		percpu_counter_add(&sbinfo->used_blocks, -1);
+out_unacct_blocks:
+	shmem_unacct_blocks(info->flags, 1);
+	goto out;
 }
 
 #ifdef CONFIG_TMPFS
@@ -2201,7 +2331,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 	pgoff_t index = pos >> PAGE_SHIFT;
 
 	/* i_mutex is held by caller */
-	if (unlikely(info->seals)) {
+	if (unlikely(info->seals & (F_SEAL_WRITE | F_SEAL_GROW))) {
 		if (info->seals & F_SEAL_WRITE)
 			return -EPERM;
 		if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size)
@@ -4140,7 +4270,7 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 
 	BUG_ON(mapping->a_ops != &shmem_aops);
 	error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE,
-				  gfp, NULL, NULL);
+				  gfp, NULL, NULL, NULL);
 	if (error)
 		page = ERR_PTR(error);
 	else
diff --git a/mm/slab.c b/mm/slab.c
index 4f2ec6bb46eb..31335e713ffb 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1288,7 +1288,8 @@ void __init kmem_cache_init(void)
 	 * Initialize the caches that provide memory for the  kmem_cache_node
 	 * structures first.  Without this, further allocations will bug.
 	 */
-	kmalloc_caches[INDEX_NODE] = create_kmalloc_cache("kmalloc-node",
+	kmalloc_caches[INDEX_NODE] = create_kmalloc_cache(
+				get_kmalloc_cache_name(INDEX_NODE),
 				kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS);
 	slab_state = PARTIAL_NODE;
 	setup_kmalloc_cache_index_table();
@@ -2332,6 +2333,13 @@ int __kmem_cache_shrink(struct kmem_cache *cachep)
 	return (ret ? 1 : 0);
 }
 
+#ifdef CONFIG_MEMCG
+void __kmemcg_cache_deactivate(struct kmem_cache *cachep)
+{
+	__kmem_cache_shrink(cachep);
+}
+#endif
+
 int __kmem_cache_shutdown(struct kmem_cache *cachep)
 {
 	return __kmem_cache_shrink(cachep);
diff --git a/mm/slab.h b/mm/slab.h
index de6579dc362c..360f157b1da2 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -78,6 +78,7 @@ unsigned long calculate_alignment(unsigned long flags,
 /* Kmalloc array related functions */
 void setup_kmalloc_cache_index_table(void);
 void create_kmalloc_caches(unsigned long);
+const char *get_kmalloc_cache_name(int index);
 
 /* Find the kmalloc slab corresponding for a certain size */
 struct kmem_cache *kmalloc_slab(size_t, gfp_t);
@@ -162,6 +163,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size,
 int __kmem_cache_shutdown(struct kmem_cache *);
 void __kmem_cache_release(struct kmem_cache *);
 int __kmem_cache_shrink(struct kmem_cache *);
+void __kmemcg_cache_deactivate(struct kmem_cache *s);
 void slab_kmem_cache_release(struct kmem_cache *);
 
 struct seq_file;
@@ -195,17 +197,22 @@ void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
 int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
 
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
+
+/* List of all root caches. */
+extern struct list_head		slab_root_caches;
+#define root_caches_node	memcg_params.__root_caches_node
+
 /*
  * Iterate over all memcg caches of the given root cache. The caller must hold
  * slab_mutex.
  */
 #define for_each_memcg_cache(iter, root) \
-	list_for_each_entry(iter, &(root)->memcg_params.list, \
-			    memcg_params.list)
+	list_for_each_entry(iter, &(root)->memcg_params.children, \
+			    memcg_params.children_node)
 
 static inline bool is_root_cache(struct kmem_cache *s)
 {
-	return s->memcg_params.is_root_cache;
+	return !s->memcg_params.root_cache;
 }
 
 static inline bool slab_equal_or_root(struct kmem_cache *s,
@@ -294,9 +301,16 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order,
 }
 
 extern void slab_init_memcg_params(struct kmem_cache *);
+extern void memcg_link_cache(struct kmem_cache *s);
+extern void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
+				void (*deact_fn)(struct kmem_cache *));
 
 #else /* CONFIG_MEMCG && !CONFIG_SLOB */
 
+/* If !memcg, all caches are root. */
+#define slab_root_caches	slab_caches
+#define root_caches_node	list
+
 #define for_each_memcg_cache(iter, root) \
 	for ((void)(iter), (void)(root); 0; )
 
@@ -341,6 +355,11 @@ static inline void memcg_uncharge_slab(struct page *page, int order,
 static inline void slab_init_memcg_params(struct kmem_cache *s)
 {
 }
+
+static inline void memcg_link_cache(struct kmem_cache *s)
+{
+}
+
 #endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
@@ -488,6 +507,9 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 void *slab_start(struct seq_file *m, loff_t *pos);
 void *slab_next(struct seq_file *m, void *p, loff_t *pos);
 void slab_stop(struct seq_file *m, void *p);
+void *memcg_slab_start(struct seq_file *m, loff_t *pos);
+void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos);
+void memcg_slab_stop(struct seq_file *m, void *p);
 int memcg_slab_show(struct seq_file *m, void *p);
 
 void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
diff --git a/mm/slab_common.c b/mm/slab_common.c
index ae323841adb1..16b39eeb208a 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -30,6 +30,11 @@ LIST_HEAD(slab_caches);
 DEFINE_MUTEX(slab_mutex);
 struct kmem_cache *kmem_cache;
 
+static LIST_HEAD(slab_caches_to_rcu_destroy);
+static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work);
+static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
+		    slab_caches_to_rcu_destroy_workfn);
+
 /*
  * Set of flags that will prevent slab merging
  */
@@ -133,11 +138,14 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
 }
 
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
+
+LIST_HEAD(slab_root_caches);
+
 void slab_init_memcg_params(struct kmem_cache *s)
 {
-	s->memcg_params.is_root_cache = true;
-	INIT_LIST_HEAD(&s->memcg_params.list);
+	s->memcg_params.root_cache = NULL;
 	RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
+	INIT_LIST_HEAD(&s->memcg_params.children);
 }
 
 static int init_memcg_params(struct kmem_cache *s,
@@ -145,10 +153,11 @@ static int init_memcg_params(struct kmem_cache *s,
 {
 	struct memcg_cache_array *arr;
 
-	if (memcg) {
-		s->memcg_params.is_root_cache = false;
-		s->memcg_params.memcg = memcg;
+	if (root_cache) {
 		s->memcg_params.root_cache = root_cache;
+		s->memcg_params.memcg = memcg;
+		INIT_LIST_HEAD(&s->memcg_params.children_node);
+		INIT_LIST_HEAD(&s->memcg_params.kmem_caches_node);
 		return 0;
 	}
 
@@ -177,9 +186,6 @@ static int update_memcg_params(struct kmem_cache *s, int new_array_size)
 {
 	struct memcg_cache_array *old, *new;
 
-	if (!is_root_cache(s))
-		return 0;
-
 	new = kzalloc(sizeof(struct memcg_cache_array) +
 		      new_array_size * sizeof(void *), GFP_KERNEL);
 	if (!new)
@@ -203,7 +209,7 @@ int memcg_update_all_caches(int num_memcgs)
 	int ret = 0;
 
 	mutex_lock(&slab_mutex);
-	list_for_each_entry(s, &slab_caches, list) {
+	list_for_each_entry(s, &slab_root_caches, root_caches_node) {
 		ret = update_memcg_params(s, num_memcgs);
 		/*
 		 * Instead of freeing the memory, we'll just leave the caches
@@ -215,6 +221,28 @@ int memcg_update_all_caches(int num_memcgs)
 	mutex_unlock(&slab_mutex);
 	return ret;
 }
+
+void memcg_link_cache(struct kmem_cache *s)
+{
+	if (is_root_cache(s)) {
+		list_add(&s->root_caches_node, &slab_root_caches);
+	} else {
+		list_add(&s->memcg_params.children_node,
+			 &s->memcg_params.root_cache->memcg_params.children);
+		list_add(&s->memcg_params.kmem_caches_node,
+			 &s->memcg_params.memcg->kmem_caches);
+	}
+}
+
+static void memcg_unlink_cache(struct kmem_cache *s)
+{
+	if (is_root_cache(s)) {
+		list_del(&s->root_caches_node);
+	} else {
+		list_del(&s->memcg_params.children_node);
+		list_del(&s->memcg_params.kmem_caches_node);
+	}
+}
 #else
 static inline int init_memcg_params(struct kmem_cache *s,
 		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
@@ -225,6 +253,10 @@ static inline int init_memcg_params(struct kmem_cache *s,
 static inline void destroy_memcg_params(struct kmem_cache *s)
 {
 }
+
+static inline void memcg_unlink_cache(struct kmem_cache *s)
+{
+}
 #endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
 /*
@@ -255,7 +287,7 @@ struct kmem_cache *find_mergeable(size_t size, size_t align,
 {
 	struct kmem_cache *s;
 
-	if (slab_nomerge || (flags & SLAB_NEVER_MERGE))
+	if (slab_nomerge)
 		return NULL;
 
 	if (ctor)
@@ -266,7 +298,10 @@ struct kmem_cache *find_mergeable(size_t size, size_t align,
 	size = ALIGN(size, align);
 	flags = kmem_cache_flags(size, flags, name, NULL);
 
-	list_for_each_entry_reverse(s, &slab_caches, list) {
+	if (flags & SLAB_NEVER_MERGE)
+		return NULL;
+
+	list_for_each_entry_reverse(s, &slab_root_caches, root_caches_node) {
 		if (slab_unmergeable(s))
 			continue;
 
@@ -350,6 +385,7 @@ static struct kmem_cache *create_cache(const char *name,
 
 	s->refcount = 1;
 	list_add(&s->list, &slab_caches);
+	memcg_link_cache(s);
 out:
 	if (err)
 		return ERR_PTR(err);
@@ -458,33 +494,61 @@ out_unlock:
 }
 EXPORT_SYMBOL(kmem_cache_create);
 
-static int shutdown_cache(struct kmem_cache *s,
-		struct list_head *release, bool *need_rcu_barrier)
+static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
 {
-	if (__kmem_cache_shutdown(s) != 0)
-		return -EBUSY;
+	LIST_HEAD(to_destroy);
+	struct kmem_cache *s, *s2;
 
-	if (s->flags & SLAB_DESTROY_BY_RCU)
-		*need_rcu_barrier = true;
+	/*
+	 * On destruction, SLAB_DESTROY_BY_RCU kmem_caches are put on the
+	 * @slab_caches_to_rcu_destroy list.  The slab pages are freed
+	 * through RCU and and the associated kmem_cache are dereferenced
+	 * while freeing the pages, so the kmem_caches should be freed only
+	 * after the pending RCU operations are finished.  As rcu_barrier()
+	 * is a pretty slow operation, we batch all pending destructions
+	 * asynchronously.
+	 */
+	mutex_lock(&slab_mutex);
+	list_splice_init(&slab_caches_to_rcu_destroy, &to_destroy);
+	mutex_unlock(&slab_mutex);
 
-	list_move(&s->list, release);
-	return 0;
+	if (list_empty(&to_destroy))
+		return;
+
+	rcu_barrier();
+
+	list_for_each_entry_safe(s, s2, &to_destroy, list) {
+#ifdef SLAB_SUPPORTS_SYSFS
+		sysfs_slab_release(s);
+#else
+		slab_kmem_cache_release(s);
+#endif
+	}
 }
 
-static void release_caches(struct list_head *release, bool need_rcu_barrier)
+static int shutdown_cache(struct kmem_cache *s)
 {
-	struct kmem_cache *s, *s2;
+	/* free asan quarantined objects */
+	kasan_cache_shutdown(s);
+
+	if (__kmem_cache_shutdown(s) != 0)
+		return -EBUSY;
 
-	if (need_rcu_barrier)
-		rcu_barrier();
+	memcg_unlink_cache(s);
+	list_del(&s->list);
 
-	list_for_each_entry_safe(s, s2, release, list) {
+	if (s->flags & SLAB_DESTROY_BY_RCU) {
+		list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
+		schedule_work(&slab_caches_to_rcu_destroy_work);
+	} else {
 #ifdef SLAB_SUPPORTS_SYSFS
-		sysfs_slab_remove(s);
+		sysfs_slab_release(s);
 #else
 		slab_kmem_cache_release(s);
 #endif
 	}
+
+	return 0;
 }
 
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
@@ -551,8 +615,6 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 		goto out_unlock;
 	}
 
-	list_add(&s->memcg_params.list, &root_cache->memcg_params.list);
-
 	/*
 	 * Since readers won't lock (see cache_from_memcg_idx()), we need a
 	 * barrier here to ensure nobody will see the kmem_cache partially
@@ -568,6 +630,66 @@ out_unlock:
 	put_online_cpus();
 }
 
+static void kmemcg_deactivate_workfn(struct work_struct *work)
+{
+	struct kmem_cache *s = container_of(work, struct kmem_cache,
+					    memcg_params.deact_work);
+
+	get_online_cpus();
+	get_online_mems();
+
+	mutex_lock(&slab_mutex);
+
+	s->memcg_params.deact_fn(s);
+
+	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
+	put_online_cpus();
+
+	/* done, put the ref from slab_deactivate_memcg_cache_rcu_sched() */
+	css_put(&s->memcg_params.memcg->css);
+}
+
+static void kmemcg_deactivate_rcufn(struct rcu_head *head)
+{
+	struct kmem_cache *s = container_of(head, struct kmem_cache,
+					    memcg_params.deact_rcu_head);
+
+	/*
+	 * We need to grab blocking locks.  Bounce to ->deact_work.  The
+	 * work item shares the space with the RCU head and can't be
+	 * initialized eariler.
+	 */
+	INIT_WORK(&s->memcg_params.deact_work, kmemcg_deactivate_workfn);
+	queue_work(memcg_kmem_cache_wq, &s->memcg_params.deact_work);
+}
+
+/**
+ * slab_deactivate_memcg_cache_rcu_sched - schedule deactivation after a
+ *					   sched RCU grace period
+ * @s: target kmem_cache
+ * @deact_fn: deactivation function to call
+ *
+ * Schedule @deact_fn to be invoked with online cpus, mems and slab_mutex
+ * held after a sched RCU grace period.  The slab is guaranteed to stay
+ * alive until @deact_fn is finished.  This is to be used from
+ * __kmemcg_cache_deactivate().
+ */
+void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
+					   void (*deact_fn)(struct kmem_cache *))
+{
+	if (WARN_ON_ONCE(is_root_cache(s)) ||
+	    WARN_ON_ONCE(s->memcg_params.deact_fn))
+		return;
+
+	/* pin memcg so that @s doesn't get destroyed in the middle */
+	css_get(&s->memcg_params.memcg->css);
+
+	s->memcg_params.deact_fn = deact_fn;
+	call_rcu_sched(&s->memcg_params.deact_rcu_head, kmemcg_deactivate_rcufn);
+}
+
 void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
 {
 	int idx;
@@ -579,41 +701,15 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
 	get_online_cpus();
 	get_online_mems();
 
-#ifdef CONFIG_SLUB
-	/*
-	 * In case of SLUB, we need to disable empty slab caching to
-	 * avoid pinning the offline memory cgroup by freeable kmem
-	 * pages charged to it. SLAB doesn't need this, as it
-	 * periodically purges unused slabs.
-	 */
 	mutex_lock(&slab_mutex);
-	list_for_each_entry(s, &slab_caches, list) {
-		c = is_root_cache(s) ? cache_from_memcg_idx(s, idx) : NULL;
-		if (c) {
-			c->cpu_partial = 0;
-			c->min_partial = 0;
-		}
-	}
-	mutex_unlock(&slab_mutex);
-	/*
-	 * kmem_cache->cpu_partial is checked locklessly (see
-	 * put_cpu_partial()). Make sure the change is visible.
-	 */
-	synchronize_sched();
-#endif
-
-	mutex_lock(&slab_mutex);
-	list_for_each_entry(s, &slab_caches, list) {
-		if (!is_root_cache(s))
-			continue;
-
+	list_for_each_entry(s, &slab_root_caches, root_caches_node) {
 		arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
 						lockdep_is_held(&slab_mutex));
 		c = arr->entries[idx];
 		if (!c)
 			continue;
 
-		__kmem_cache_shrink(c);
+		__kmemcg_cache_deactivate(c);
 		arr->entries[idx] = NULL;
 	}
 	mutex_unlock(&slab_mutex);
@@ -622,47 +718,29 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
 	put_online_cpus();
 }
 
-static int __shutdown_memcg_cache(struct kmem_cache *s,
-		struct list_head *release, bool *need_rcu_barrier)
-{
-	BUG_ON(is_root_cache(s));
-
-	if (shutdown_cache(s, release, need_rcu_barrier))
-		return -EBUSY;
-
-	list_del(&s->memcg_params.list);
-	return 0;
-}
-
 void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
 {
-	LIST_HEAD(release);
-	bool need_rcu_barrier = false;
 	struct kmem_cache *s, *s2;
 
 	get_online_cpus();
 	get_online_mems();
 
 	mutex_lock(&slab_mutex);
-	list_for_each_entry_safe(s, s2, &slab_caches, list) {
-		if (is_root_cache(s) || s->memcg_params.memcg != memcg)
-			continue;
+	list_for_each_entry_safe(s, s2, &memcg->kmem_caches,
+				 memcg_params.kmem_caches_node) {
 		/*
 		 * The cgroup is about to be freed and therefore has no charges
 		 * left. Hence, all its caches must be empty by now.
 		 */
-		BUG_ON(__shutdown_memcg_cache(s, &release, &need_rcu_barrier));
+		BUG_ON(shutdown_cache(s));
 	}
 	mutex_unlock(&slab_mutex);
 
 	put_online_mems();
 	put_online_cpus();
-
-	release_caches(&release, need_rcu_barrier);
 }
 
-static int shutdown_memcg_caches(struct kmem_cache *s,
-		struct list_head *release, bool *need_rcu_barrier)
+static int shutdown_memcg_caches(struct kmem_cache *s)
 {
 	struct memcg_cache_array *arr;
 	struct kmem_cache *c, *c2;
@@ -681,13 +759,13 @@ static int shutdown_memcg_caches(struct kmem_cache *s,
 		c = arr->entries[i];
 		if (!c)
 			continue;
-		if (__shutdown_memcg_cache(c, release, need_rcu_barrier))
+		if (shutdown_cache(c))
 			/*
 			 * The cache still has objects. Move it to a temporary
 			 * list so as not to try to destroy it for a second
 			 * time while iterating over inactive caches below.
 			 */
-			list_move(&c->memcg_params.list, &busy);
+			list_move(&c->memcg_params.children_node, &busy);
 		else
 			/*
 			 * The cache is empty and will be destroyed soon. Clear
@@ -702,23 +780,22 @@ static int shutdown_memcg_caches(struct kmem_cache *s,
 	 * Second, shutdown all caches left from memory cgroups that are now
 	 * offline.
 	 */
-	list_for_each_entry_safe(c, c2, &s->memcg_params.list,
-				 memcg_params.list)
-		__shutdown_memcg_cache(c, release, need_rcu_barrier);
+	list_for_each_entry_safe(c, c2, &s->memcg_params.children,
+				 memcg_params.children_node)
+		shutdown_cache(c);
 
-	list_splice(&busy, &s->memcg_params.list);
+	list_splice(&busy, &s->memcg_params.children);
 
 	/*
 	 * A cache being destroyed must be empty. In particular, this means
 	 * that all per memcg caches attached to it must be empty too.
 	 */
-	if (!list_empty(&s->memcg_params.list))
+	if (!list_empty(&s->memcg_params.children))
 		return -EBUSY;
 	return 0;
 }
 #else
-static inline int shutdown_memcg_caches(struct kmem_cache *s,
-		struct list_head *release, bool *need_rcu_barrier)
+static inline int shutdown_memcg_caches(struct kmem_cache *s)
 {
 	return 0;
 }
@@ -734,8 +811,6 @@ void slab_kmem_cache_release(struct kmem_cache *s)
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
-	LIST_HEAD(release);
-	bool need_rcu_barrier = false;
 	int err;
 
 	if (unlikely(!s))
@@ -744,16 +819,15 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	get_online_cpus();
 	get_online_mems();
 
-	kasan_cache_destroy(s);
 	mutex_lock(&slab_mutex);
 
 	s->refcount--;
 	if (s->refcount)
 		goto out_unlock;
 
-	err = shutdown_memcg_caches(s, &release, &need_rcu_barrier);
+	err = shutdown_memcg_caches(s);
 	if (!err)
-		err = shutdown_cache(s, &release, &need_rcu_barrier);
+		err = shutdown_cache(s);
 
 	if (err) {
 		pr_err("kmem_cache_destroy %s: Slab cache still has objects\n",
@@ -765,8 +839,6 @@ out_unlock:
 
 	put_online_mems();
 	put_online_cpus();
-
-	release_caches(&release, need_rcu_barrier);
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
@@ -828,6 +900,7 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
 
 	create_boot_cache(s, name, size, flags);
 	list_add(&s->list, &slab_caches);
+	memcg_link_cache(s);
 	s->refcount = 1;
 	return s;
 }
@@ -932,6 +1005,11 @@ static struct {
 	{"kmalloc-67108864", 67108864}
 };
 
+const char * __init get_kmalloc_cache_name(int index)
+{
+	return kmalloc_info[index].name;
+}
+
 /*
  * Patch up the size_index table if we have strange large alignment
  * requirements for the kmalloc array. This is only the case for
@@ -1138,12 +1216,12 @@ static void print_slabinfo_header(struct seq_file *m)
 void *slab_start(struct seq_file *m, loff_t *pos)
 {
 	mutex_lock(&slab_mutex);
-	return seq_list_start(&slab_caches, *pos);
+	return seq_list_start(&slab_root_caches, *pos);
 }
 
 void *slab_next(struct seq_file *m, void *p, loff_t *pos)
 {
-	return seq_list_next(p, &slab_caches, pos);
+	return seq_list_next(p, &slab_root_caches, pos);
 }
 
 void slab_stop(struct seq_file *m, void *p)
@@ -1195,25 +1273,44 @@ static void cache_show(struct kmem_cache *s, struct seq_file *m)
 
 static int slab_show(struct seq_file *m, void *p)
 {
-	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
+	struct kmem_cache *s = list_entry(p, struct kmem_cache, root_caches_node);
 
-	if (p == slab_caches.next)
+	if (p == slab_root_caches.next)
 		print_slabinfo_header(m);
-	if (is_root_cache(s))
-		cache_show(s, m);
+	cache_show(s, m);
 	return 0;
 }
 
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
+void *memcg_slab_start(struct seq_file *m, loff_t *pos)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+
+	mutex_lock(&slab_mutex);
+	return seq_list_start(&memcg->kmem_caches, *pos);
+}
+
+void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+
+	return seq_list_next(p, &memcg->kmem_caches, pos);
+}
+
+void memcg_slab_stop(struct seq_file *m, void *p)
+{
+	mutex_unlock(&slab_mutex);
+}
+
 int memcg_slab_show(struct seq_file *m, void *p)
 {
-	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
+	struct kmem_cache *s = list_entry(p, struct kmem_cache,
+					  memcg_params.kmem_caches_node);
 	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
 
-	if (p == slab_caches.next)
+	if (p == memcg->kmem_caches.next)
 		print_slabinfo_header(m);
-	if (!is_root_cache(s) && s->memcg_params.memcg == memcg)
-		cache_show(s, m);
+	cache_show(s, m);
 	return 0;
 }
 #endif
diff --git a/mm/slub.c b/mm/slub.c
index 7ec0a965c6a3..7f4bc7027ed5 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -214,11 +214,13 @@ enum track_item { TRACK_ALLOC, TRACK_FREE };
 static int sysfs_slab_add(struct kmem_cache *);
 static int sysfs_slab_alias(struct kmem_cache *, const char *);
 static void memcg_propagate_slab_attrs(struct kmem_cache *s);
+static void sysfs_slab_remove(struct kmem_cache *s);
 #else
 static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
 static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
 							{ return 0; }
 static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
+static inline void sysfs_slab_remove(struct kmem_cache *s) { }
 #endif
 
 static inline void stat(const struct kmem_cache *s, enum stat_item si)
@@ -1630,6 +1632,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 		flags &= ~GFP_SLAB_BUG_MASK;
 		pr_warn("Unexpected gfp: %#x (%pGg). Fixing up to gfp: %#x (%pGg). Fix your code!\n",
 				invalid_mask, &invalid_mask, flags, &flags);
+		dump_stack();
 	}
 
 	return allocate_slab(s,
@@ -3686,6 +3689,7 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
 		if (n->nr_partial || slabs_node(s, node))
 			return 1;
 	}
+	sysfs_slab_remove(s);
 	return 0;
 }
 
@@ -3952,6 +3956,42 @@ int __kmem_cache_shrink(struct kmem_cache *s)
 	return ret;
 }
 
+#ifdef CONFIG_MEMCG
+static void kmemcg_cache_deact_after_rcu(struct kmem_cache *s)
+{
+	/*
+	 * Called with all the locks held after a sched RCU grace period.
+	 * Even if @s becomes empty after shrinking, we can't know that @s
+	 * doesn't have allocations already in-flight and thus can't
+	 * destroy @s until the associated memcg is released.
+	 *
+	 * However, let's remove the sysfs files for empty caches here.
+	 * Each cache has a lot of interface files which aren't
+	 * particularly useful for empty draining caches; otherwise, we can
+	 * easily end up with millions of unnecessary sysfs files on
+	 * systems which have a lot of memory and transient cgroups.
+	 */
+	if (!__kmem_cache_shrink(s))
+		sysfs_slab_remove(s);
+}
+
+void __kmemcg_cache_deactivate(struct kmem_cache *s)
+{
+	/*
+	 * Disable empty slabs caching. Used to avoid pinning offline
+	 * memory cgroups by kmem pages that can be freed.
+	 */
+	s->cpu_partial = 0;
+	s->min_partial = 0;
+
+	/*
+	 * s->cpu_partial is checked locklessly (see put_cpu_partial), so
+	 * we have to make sure the change is visible before shrinking.
+	 */
+	slab_deactivate_memcg_cache_rcu_sched(s, kmemcg_cache_deact_after_rcu);
+}
+#endif
+
 static int slab_mem_going_offline_callback(void *arg)
 {
 	struct kmem_cache *s;
@@ -4108,6 +4148,7 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
 	}
 	slab_init_memcg_params(s);
 	list_add(&s->list, &slab_caches);
+	memcg_link_cache(s);
 	return s;
 }
 
@@ -4667,6 +4708,22 @@ enum slab_stat_type {
 #define SO_OBJECTS	(1 << SL_OBJECTS)
 #define SO_TOTAL	(1 << SL_TOTAL)
 
+#ifdef CONFIG_MEMCG
+static bool memcg_sysfs_enabled = IS_ENABLED(CONFIG_SLUB_MEMCG_SYSFS_ON);
+
+static int __init setup_slub_memcg_sysfs(char *str)
+{
+	int v;
+
+	if (get_option(&str, &v) > 0)
+		memcg_sysfs_enabled = v;
+
+	return 1;
+}
+
+__setup("slub_memcg_sysfs=", setup_slub_memcg_sysfs);
+#endif
+
 static ssize_t show_slab_objects(struct kmem_cache *s,
 			    char *buf, unsigned long flags)
 {
@@ -5570,8 +5627,14 @@ static int sysfs_slab_add(struct kmem_cache *s)
 {
 	int err;
 	const char *name;
+	struct kset *kset = cache_kset(s);
 	int unmergeable = slab_unmergeable(s);
 
+	if (!kset) {
+		kobject_init(&s->kobj, &slab_ktype);
+		return 0;
+	}
+
 	if (unmergeable) {
 		/*
 		 * Slabcache can never be merged so we can use the name proper.
@@ -5588,7 +5651,7 @@ static int sysfs_slab_add(struct kmem_cache *s)
 		name = create_unique_id(s);
 	}
 
-	s->kobj.kset = cache_kset(s);
+	s->kobj.kset = kset;
 	err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
 	if (err)
 		goto out;
@@ -5598,7 +5661,7 @@ static int sysfs_slab_add(struct kmem_cache *s)
 		goto out_del_kobj;
 
 #ifdef CONFIG_MEMCG
-	if (is_root_cache(s)) {
+	if (is_root_cache(s) && memcg_sysfs_enabled) {
 		s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj);
 		if (!s->memcg_kset) {
 			err = -ENOMEM;
@@ -5621,7 +5684,7 @@ out_del_kobj:
 	goto out;
 }
 
-void sysfs_slab_remove(struct kmem_cache *s)
+static void sysfs_slab_remove(struct kmem_cache *s)
 {
 	if (slab_state < FULL)
 		/*
@@ -5630,12 +5693,26 @@ void sysfs_slab_remove(struct kmem_cache *s)
 		 */
 		return;
 
+	if (!s->kobj.state_in_sysfs)
+		/*
+		 * For a memcg cache, this may be called during
+		 * deactivation and again on shutdown.  Remove only once.
+		 * A cache is never shut down before deactivation is
+		 * complete, so no need to worry about synchronization.
+		 */
+		return;
+
 #ifdef CONFIG_MEMCG
 	kset_unregister(s->memcg_kset);
 #endif
 	kobject_uevent(&s->kobj, KOBJ_REMOVE);
 	kobject_del(&s->kobj);
-	kobject_put(&s->kobj);
+}
+
+void sysfs_slab_release(struct kmem_cache *s)
+{
+	if (slab_state >= FULL)
+		kobject_put(&s->kobj);
 }
 
 /*
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 574c67b663fe..8679d4a81b98 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -248,20 +248,28 @@ int __meminit vmemmap_populate_basepages(unsigned long start,
 	return 0;
 }
 
-struct page * __meminit sparse_mem_map_populate(unsigned long pnum, int nid)
+struct page * __meminit __populate_section_memmap(unsigned long pfn,
+		unsigned long nr_pages, int nid)
 {
 	unsigned long start;
 	unsigned long end;
-	struct page *map;
 
-	map = pfn_to_page(pnum * PAGES_PER_SECTION);
-	start = (unsigned long)map;
-	end = (unsigned long)(map + PAGES_PER_SECTION);
+	/*
+	 * The minimum granularity of memmap extensions is
+	 * SECTION_ACTIVE_SIZE as allocations are tracked in the
+	 * 'map_active' bitmap of the section.
+	 */
+	end = ALIGN(pfn + nr_pages, PHYS_PFN(SECTION_ACTIVE_SIZE));
+	pfn &= PHYS_PFN(SECTION_ACTIVE_MASK);
+	nr_pages = end - pfn;
+
+	start = (unsigned long) pfn_to_page(pfn);
+	end = start + nr_pages * sizeof(struct page);
 
 	if (vmemmap_populate(start, end, nid))
 		return NULL;
 
-	return map;
+	return pfn_to_page(pfn);
 }
 
 void __init sparse_mem_maps_populate_node(struct page **map_map,
@@ -284,11 +292,13 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 
 	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
 		struct mem_section *ms;
+		unsigned long pfn = section_nr_to_pfn(pnum);
 
 		if (!present_section_nr(pnum))
 			continue;
 
-		map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
+		map_map[pnum] = __populate_section_memmap(pfn,
+				PAGES_PER_SECTION, nodeid);
 		if (map_map[pnum])
 			continue;
 		ms = __nr_to_section(pnum);
diff --git a/mm/sparse.c b/mm/sparse.c
index 1e168bf2779a..3e0c1c73f814 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -24,6 +24,7 @@
 #ifdef CONFIG_SPARSEMEM_EXTREME
 struct mem_section *mem_section[NR_SECTION_ROOTS]
 	____cacheline_internodealigned_in_smp;
+static DEFINE_SPINLOCK(mem_section_lock); /* atomically instantiate new entries */
 #else
 struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
 	____cacheline_internodealigned_in_smp;
@@ -89,7 +90,22 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid)
 	if (!section)
 		return -ENOMEM;
 
-	mem_section[root] = section;
+	spin_lock(&mem_section_lock);
+	if (mem_section[root] == NULL) {
+		mem_section[root] = section;
+		section = NULL;
+	}
+	spin_unlock(&mem_section_lock);
+
+	/*
+	 * The only time we expect adding a section may race is during
+	 * post-meminit hotplug. So, there is no expectation that 'section'
+	 * leaks in the !slab_is_available() case.
+	 */
+	if (section && slab_is_available()) {
+		kfree(section);
+		return -EEXIST;
+	}
 
 	return 0;
 }
@@ -168,6 +184,66 @@ void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
 	}
 }
 
+static int __init section_active_index(phys_addr_t phys)
+{
+	return (phys & ~(PA_SECTION_MASK)) / SECTION_ACTIVE_SIZE;
+}
+
+static unsigned long section_active_mask(unsigned long pfn,
+					 unsigned long nr_pages)
+{
+	int idx_start, idx_size;
+	phys_addr_t start, size;
+
+	WARN_ON((pfn & ~PAGE_SECTION_MASK) + nr_pages > PAGES_PER_SECTION);
+	if (!nr_pages)
+		return 0;
+
+	/*
+	 * The size is the number of pages left in the section or
+	 * nr_pages, whichever is smaller. The size will be rounded up
+	 * to the next SECTION_ACTIVE_SIZE boundary, the start will be
+	 * rounded down.
+	 */
+	start = PFN_PHYS(pfn);
+	size = PFN_PHYS(min_not_zero(nr_pages, PAGES_PER_SECTION
+				- (pfn & ~PAGE_SECTION_MASK)));
+	size = ALIGN(size, SECTION_ACTIVE_SIZE);
+
+	idx_start = section_active_index(start);
+	idx_size = section_active_index(size);
+
+	if (idx_size == 0)
+		return ULONG_MAX; /* full section */
+	return ((1UL << idx_size) - 1) << idx_start;
+}
+
+void __init section_active_init(unsigned long pfn, unsigned long nr_pages)
+{
+	int end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
+	int i, start_sec = pfn_to_section_nr(pfn);
+
+	if (!nr_pages)
+		return;
+
+	for (i = start_sec; i <= end_sec; i++) {
+		struct mem_section *ms;
+		unsigned long mask;
+		unsigned long pfns;
+
+		pfns = min(nr_pages, PAGES_PER_SECTION
+				- (pfn & ~PAGE_SECTION_MASK));
+		mask = section_active_mask(pfn, pfns);
+
+		ms = __nr_to_section(i);
+		pr_debug("%s: sec: %d mask: %#018lx\n", __func__, i, mask);
+		ms->usage->map_active = mask;
+
+		pfn += pfns;
+		nr_pages -= pfns;
+	}
+}
+
 /* Record a memory area against a node. */
 void __init memory_present(int nid, unsigned long start, unsigned long end)
 {
@@ -231,19 +307,23 @@ struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pn
 	return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
 }
 
-static int __meminit sparse_init_one_section(struct mem_section *ms,
+static void __meminit sparse_init_one_section(struct mem_section *ms,
 		unsigned long pnum, struct page *mem_map,
-		unsigned long *pageblock_bitmap)
+		struct mem_section_usage *usage)
 {
-	if (!present_section(ms))
-		return -EINVAL;
+	/*
+	 * Given that SPARSEMEM_VMEMMAP=y supports sub-section hotplug,
+	 * ->section_mem_map can not be guaranteed to point to a full
+	 *  section's worth of memory.  The field is only valid / used
+	 *  in the SPARSEMEM_VMEMMAP=n case.
+	 */
+	if (IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP))
+		mem_map = NULL;
 
 	ms->section_mem_map &= ~SECTION_MAP_MASK;
 	ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum) |
-							SECTION_HAS_MEM_MAP;
- 	ms->pageblock_flags = pageblock_bitmap;
-
-	return 1;
+		SECTION_HAS_MEM_MAP;
+	ms->usage = usage;
 }
 
 unsigned long usemap_size(void)
@@ -255,9 +335,13 @@ unsigned long usemap_size(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-static unsigned long *__kmalloc_section_usemap(void)
+static struct mem_section_usage *__alloc_section_usage(void)
 {
-	return kmalloc(usemap_size(), GFP_KERNEL);
+	struct mem_section_usage *usage;
+
+	usage = kzalloc(sizeof(*usage) + usemap_size(), GFP_KERNEL);
+	/* TODO: allocate the map_active bitmap */
+	return usage;
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
@@ -293,7 +377,8 @@ again:
 	return p;
 }
 
-static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
+static void __init check_usemap_section_nr(int nid,
+		struct mem_section_usage *usage)
 {
 	unsigned long usemap_snr, pgdat_snr;
 	static unsigned long old_usemap_snr = NR_MEM_SECTIONS;
@@ -301,7 +386,7 @@ static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
 	struct pglist_data *pgdat = NODE_DATA(nid);
 	int usemap_nid;
 
-	usemap_snr = pfn_to_section_nr(__pa(usemap) >> PAGE_SHIFT);
+	usemap_snr = pfn_to_section_nr(__pa(usage) >> PAGE_SHIFT);
 	pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
 	if (usemap_snr == pgdat_snr)
 		return;
@@ -336,7 +421,8 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 	return memblock_virt_alloc_node_nopanic(size, pgdat->node_id);
 }
 
-static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
+static void __init check_usemap_section_nr(int nid,
+		struct mem_section_usage *usage)
 {
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
@@ -344,31 +430,33 @@ static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
 static void __init sparse_early_usemaps_alloc_node(void *data,
 				 unsigned long pnum_begin,
 				 unsigned long pnum_end,
-				 unsigned long usemap_count, int nodeid)
+				 unsigned long usage_count, int nodeid)
 {
-	void *usemap;
+	void *usage;
 	unsigned long pnum;
-	unsigned long **usemap_map = (unsigned long **)data;
-	int size = usemap_size();
+	struct mem_section_usage **usage_map = data;
+	int size = sizeof(struct mem_section_usage) + usemap_size();
 
-	usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
-							  size * usemap_count);
-	if (!usemap) {
+	usage = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
+							  size * usage_count);
+	if (!usage) {
 		pr_warn("%s: allocation failed\n", __func__);
 		return;
 	}
 
+	memset(usage, 0, size * usage_count);
 	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
 		if (!present_section_nr(pnum))
 			continue;
-		usemap_map[pnum] = usemap;
-		usemap += size;
-		check_usemap_section_nr(nodeid, usemap_map[pnum]);
+		usage_map[pnum] = usage;
+		usage += size;
+		check_usemap_section_nr(nodeid, usage_map[pnum]);
 	}
 }
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
-struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid)
+struct page __init *__populate_section_memmap(unsigned long pfn,
+		unsigned long nr_pages, int nid)
 {
 	struct page *map;
 	unsigned long size;
@@ -420,10 +508,12 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 	/* fallback */
 	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
 		struct mem_section *ms;
+		unsigned long pfn = section_nr_to_pfn(pnum);
 
 		if (!present_section_nr(pnum))
 			continue;
-		map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
+		map_map[pnum] = __populate_section_memmap(pfn,
+				PAGES_PER_SECTION, nodeid);
 		if (map_map[pnum])
 			continue;
 		ms = __nr_to_section(pnum);
@@ -451,7 +541,8 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 	struct mem_section *ms = __nr_to_section(pnum);
 	int nid = sparse_early_nid(ms);
 
-	map = sparse_mem_map_populate(pnum, nid);
+	map = __populate_section_memmap(section_nr_to_pfn(pnum),
+			PAGES_PER_SECTION, nid);
 	if (map)
 		return map;
 
@@ -468,7 +559,7 @@ void __weak __meminit vmemmap_populate_print_last(void)
 
 /**
  *  alloc_usemap_and_memmap - memory alloction for pageblock flags and vmemmap
- *  @map: usemap_map for pageblock flags or mmap_map for vmemmap
+ *  @map: usage_map for mem_section_usage or mmap_map for vmemmap
  */
 static void __init alloc_usemap_and_memmap(void (*alloc_func)
 					(void *, unsigned long, unsigned long,
@@ -521,10 +612,9 @@ static void __init alloc_usemap_and_memmap(void (*alloc_func)
  */
 void __init sparse_init(void)
 {
+	struct mem_section_usage *usage, **usage_map;
 	unsigned long pnum;
 	struct page *map;
-	unsigned long *usemap;
-	unsigned long **usemap_map;
 	int size;
 #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
 	int size2;
@@ -539,21 +629,21 @@ void __init sparse_init(void)
 
 	/*
 	 * map is using big page (aka 2M in x86 64 bit)
-	 * usemap is less one page (aka 24 bytes)
+	 * usage is less one page (aka 24 bytes)
 	 * so alloc 2M (with 2M align) and 24 bytes in turn will
 	 * make next 2M slip to one more 2M later.
 	 * then in big system, the memory will have a lot of holes...
 	 * here try to allocate 2M pages continuously.
 	 *
 	 * powerpc need to call sparse_init_one_section right after each
-	 * sparse_early_mem_map_alloc, so allocate usemap_map at first.
+	 * sparse_early_mem_map_alloc, so allocate usage_map at first.
 	 */
-	size = sizeof(unsigned long *) * NR_MEM_SECTIONS;
-	usemap_map = memblock_virt_alloc(size, 0);
-	if (!usemap_map)
-		panic("can not allocate usemap_map\n");
+	size = sizeof(struct mem_section_usage *) * NR_MEM_SECTIONS;
+	usage_map = memblock_virt_alloc(size, 0);
+	if (!usage_map)
+		panic("can not allocate usage_map\n");
 	alloc_usemap_and_memmap(sparse_early_usemaps_alloc_node,
-							(void *)usemap_map);
+							(void *)usage_map);
 
 #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
 	size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
@@ -568,8 +658,8 @@ void __init sparse_init(void)
 		if (!present_section_nr(pnum))
 			continue;
 
-		usemap = usemap_map[pnum];
-		if (!usemap)
+		usage = usage_map[pnum];
+		if (!usage)
 			continue;
 
 #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
@@ -581,7 +671,7 @@ void __init sparse_init(void)
 			continue;
 
 		sparse_init_one_section(__nr_to_section(pnum), pnum, map,
-								usemap);
+								usage);
 	}
 
 	vmemmap_populate_print_last();
@@ -589,20 +679,21 @@ void __init sparse_init(void)
 #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
 	memblock_free_early(__pa(map_map), size2);
 #endif
-	memblock_free_early(__pa(usemap_map), size);
+	memblock_free_early(__pa(usage_map), size);
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
+static struct page *populate_section_memmap(unsigned long pfn,
+		unsigned long nr_pages, int nid)
 {
-	/* This will make the necessary allocations eventually. */
-	return sparse_mem_map_populate(pnum, nid);
+	return __populate_section_memmap(pfn, nr_pages, nid);
 }
-static void __kfree_section_memmap(struct page *memmap)
+
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages)
 {
-	unsigned long start = (unsigned long)memmap;
-	unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
+	unsigned long start = (unsigned long) pfn_to_page(pfn);
+	unsigned long end = start + nr_pages * sizeof(struct page);
 
 	vmemmap_free(start, end);
 }
@@ -616,11 +707,18 @@ static void free_map_bootmem(struct page *memmap)
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 #else
-static struct page *__kmalloc_section_memmap(void)
+struct page *populate_section_memmap(unsigned long pfn,
+		unsigned long nr_pages, int nid)
 {
 	struct page *page, *ret;
 	unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
 
+	if ((pfn & ~PAGE_SECTION_MASK) || nr_pages != PAGES_PER_SECTION) {
+		WARN(1, "%s: called with section unaligned parameters\n",
+				__func__);
+		return NULL;
+	}
+
 	page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
 	if (page)
 		goto got_map_page;
@@ -637,13 +735,16 @@ got_map_ptr:
 	return ret;
 }
 
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages)
 {
-	return __kmalloc_section_memmap();
-}
+	struct page *memmap = pfn_to_page(pfn);
+
+	if ((pfn & ~PAGE_SECTION_MASK) || nr_pages != PAGES_PER_SECTION) {
+		WARN(1, "%s: called with section unaligned parameters\n",
+				__func__);
+		return;
+	}
 
-static void __kfree_section_memmap(struct page *memmap)
-{
 	if (is_vmalloc_addr(memmap))
 		vfree(memmap);
 	else
@@ -662,12 +763,12 @@ static void free_map_bootmem(struct page *memmap)
 		>> PAGE_SHIFT;
 
 	for (i = 0; i < nr_pages; i++, page++) {
-		magic = (unsigned long) page->lru.next;
+		magic = (unsigned long) page->freelist;
 
 		BUG_ON(magic == NODE_INFO);
 
 		maps_section_nr = pfn_to_section_nr(page_to_pfn(page));
-		removing_section_nr = page->private;
+		removing_section_nr = page_private(page);
 
 		/*
 		 * When this function is called, the removing section is
@@ -684,18 +785,179 @@ static void free_map_bootmem(struct page *memmap)
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
-/*
- * returns the number of sections whose mem_maps were properly
- * set.  If this is <=0, then that means that the passed-in
- * map was not consumed and must be freed.
+static bool is_early_section(struct mem_section *ms)
+{
+	struct page *usemap_page;
+
+	usemap_page = virt_to_page(ms->usage->pageblock_flags);
+	if (PageSlab(usemap_page) || PageCompound(usemap_page))
+		return false;
+	else
+		return true;
+
+}
+
+#ifndef CONFIG_MEMORY_HOTREMOVE
+static void free_map_bootmem(struct page *memmap)
+{
+}
+#endif
+
+static void section_deactivate(struct pglist_data *pgdat, unsigned long pfn,
+                unsigned long nr_pages)
+{
+	bool early_section;
+	struct page *memmap = NULL;
+	struct mem_section_usage *usage = NULL;
+	int section_nr = pfn_to_section_nr(pfn);
+	struct mem_section *ms = __nr_to_section(section_nr);
+	unsigned long mask = section_active_mask(pfn, nr_pages), flags;
+
+	pgdat_resize_lock(pgdat, &flags);
+	if (!ms->usage ||
+	    WARN((ms->usage->map_active & mask) != mask,
+		 "section already deactivated active: %#lx mask: %#lx\n",
+			ms->usage->map_active, mask)) {
+		pgdat_resize_unlock(pgdat, &flags);
+		return;
+	}
+
+	early_section = is_early_section(ms);
+	ms->usage->map_active ^= mask;
+	if (ms->usage->map_active == 0) {
+		usage = ms->usage;
+		ms->usage = NULL;
+		memmap = sparse_decode_mem_map(ms->section_mem_map,
+				section_nr);
+		ms->section_mem_map = 0;
+	}
+
+	pgdat_resize_unlock(pgdat, &flags);
+
+	/*
+	 * There are 3 cases to handle across two configurations
+	 * (SPARSEMEM_VMEMMAP={y,n}):
+	 *
+	 * 1/ deactivation of a partial hot-added section (only possible
+	 * in the SPARSEMEM_VMEMMAP=y case).
+	 *    a/ section was present at memory init
+	 *    b/ section was hot-added post memory init
+	 * 2/ deactivation of a complete hot-added section
+	 * 3/ deactivation of a complete section from memory init
+	 *
+	 * For 1/, when map_active does not go to zero we will not be
+	 * freeing the usage map, but still need to free the vmemmap
+	 * range.
+	 *
+	 * For 2/ and 3/ the SPARSEMEM_VMEMMAP={y,n} cases are unified
+	 */
+	if (!mask)
+		return;
+	if (nr_pages < PAGES_PER_SECTION) {
+		if (!IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) {
+			WARN(1, "partial memory section removal not supported\n");
+			return;
+		}
+		if (!early_section)
+			depopulate_section_memmap(pfn, nr_pages);
+		memmap = 0;
+	}
+
+	if (usage) {
+		if (!early_section) {
+			/*
+			 * 'memmap' may be zero in the SPARSEMEM_VMEMMAP=y case
+			 * (see sparse_init_one_section()), so we can't rely on
+			 * it to determine if we need to depopulate the memmap.
+			 * Instead, we uncoditionally depopulate due to 'usage'
+			 * being valid.
+			 */
+			if (memmap || (nr_pages >= PAGES_PER_SECTION
+					&& IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)))
+				depopulate_section_memmap(pfn, nr_pages);
+			kfree(usage);
+			return;
+		}
+	}
+
+	/*
+	 * The usemap came from bootmem. This is packed with other usemaps
+	 * on the section which has pgdat at boot time. Just keep it as is now.
+	 */
+	if (memmap)
+		free_map_bootmem(memmap);
+}
+
+static struct page * __meminit section_activate(struct pglist_data *pgdat,
+		unsigned long pfn, unsigned nr_pages)
+{
+	struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn));
+	unsigned long mask = section_active_mask(pfn, nr_pages), flags;
+	struct mem_section_usage *usage;
+	bool early_section = false;
+	struct page *memmap;
+	int rc = 0;
+
+	usage = __alloc_section_usage();
+	if (!usage)
+		return ERR_PTR(-ENOMEM);
+
+	pgdat_resize_lock(pgdat, &flags);
+	if (!ms->usage) {
+		ms->usage = usage;
+		usage = NULL;
+	} else
+		early_section = is_early_section(ms);
+
+	if (!mask)
+		rc = -EINVAL;
+	else if (mask & ms->usage->map_active)
+		rc = -EBUSY;
+	else
+		ms->usage->map_active |= mask;
+	pgdat_resize_unlock(pgdat, &flags);
+
+	kfree(usage);
+
+	if (rc)
+		return ERR_PTR(rc);
+
+
+	/*
+	 * The early init code does not consider partially populated
+	 * initial sections, it simply assumes that memory will never be
+	 * referenced.  If we hot-add memory into such a section then we
+	 * do not need to populate the memmap and can simply reuse what
+	 * is already there.
+	 */
+	if (nr_pages < PAGES_PER_SECTION && early_section)
+		return pfn_to_page(pfn);
+
+	memmap = populate_section_memmap(pfn, nr_pages, pgdat->node_id);
+	if (!memmap) {
+		section_deactivate(pgdat, pfn, nr_pages);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return memmap;
+}
+
+/**
+ * sparse_add_section() - create a new memmap section, or populate an
+ * existing one
+ * @zone: host zone for the new memory mapping
+ * @start_pfn: first pfn to add (section aligned if zone != ZONE_DEVICE)
+ * @nr_pages: number of new pages to add
+ *
+ * Returns 0 on success.
  */
-int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn)
+int __meminit sparse_add_section(struct zone *zone, unsigned long start_pfn,
+		unsigned long nr_pages)
 {
 	unsigned long section_nr = pfn_to_section_nr(start_pfn);
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	struct mem_section *ms;
 	struct page *memmap;
-	unsigned long *usemap;
 	unsigned long flags;
 	int ret;
 
@@ -706,36 +968,28 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn)
 	ret = sparse_index_init(section_nr, pgdat->node_id);
 	if (ret < 0 && ret != -EEXIST)
 		return ret;
-	memmap = kmalloc_section_memmap(section_nr, pgdat->node_id);
-	if (!memmap)
-		return -ENOMEM;
-	usemap = __kmalloc_section_usemap();
-	if (!usemap) {
-		__kfree_section_memmap(memmap);
-		return -ENOMEM;
-	}
 
-	pgdat_resize_lock(pgdat, &flags);
+	memmap = section_activate(pgdat, start_pfn, nr_pages);
+	if (IS_ERR(memmap))
+		return PTR_ERR(memmap);
 
+	pgdat_resize_lock(pgdat, &flags);
 	ms = __pfn_to_section(start_pfn);
-	if (ms->section_mem_map & SECTION_MARKED_PRESENT) {
-		ret = -EEXIST;
+	if (nr_pages == PAGES_PER_SECTION && (ms->section_mem_map
+				& SECTION_MARKED_PRESENT)) {
+		ret = -EBUSY;
 		goto out;
 	}
-
-	memset(memmap, 0, sizeof(struct page) * PAGES_PER_SECTION);
-
 	ms->section_mem_map |= SECTION_MARKED_PRESENT;
-
-	ret = sparse_init_one_section(ms, section_nr, memmap, usemap);
-
+	sparse_init_one_section(ms, section_nr, memmap, ms->usage);
 out:
 	pgdat_resize_unlock(pgdat, &flags);
-	if (ret <= 0) {
-		kfree(usemap);
-		__kfree_section_memmap(memmap);
+	if (nr_pages == PAGES_PER_SECTION && ret < 0 && ret != -EEXIST) {
+		section_deactivate(pgdat, start_pfn, nr_pages);
+		return ret;
 	}
-	return ret;
+	memset(memmap, 0, sizeof(struct page) * nr_pages);
+	return 0;
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
@@ -760,53 +1014,15 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 }
 #endif
 
-static void free_section_usemap(struct page *memmap, unsigned long *usemap)
-{
-	struct page *usemap_page;
-
-	if (!usemap)
-		return;
-
-	usemap_page = virt_to_page(usemap);
-	/*
-	 * Check to see if allocation came from hot-plug-add
-	 */
-	if (PageSlab(usemap_page) || PageCompound(usemap_page)) {
-		kfree(usemap);
-		if (memmap)
-			__kfree_section_memmap(memmap);
-		return;
-	}
-
-	/*
-	 * The usemap came from bootmem. This is packed with other usemaps
-	 * on the section which has pgdat at boot time. Just keep it as is now.
-	 */
-
-	if (memmap)
-		free_map_bootmem(memmap);
-}
-
-void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
+void sparse_remove_section(struct zone *zone, struct mem_section *ms,
+		unsigned long pfn, unsigned long nr_pages,
 		unsigned long map_offset)
 {
-	struct page *memmap = NULL;
-	unsigned long *usemap = NULL, flags;
 	struct pglist_data *pgdat = zone->zone_pgdat;
 
-	pgdat_resize_lock(pgdat, &flags);
-	if (ms->section_mem_map) {
-		usemap = ms->pageblock_flags;
-		memmap = sparse_decode_mem_map(ms->section_mem_map,
-						__section_nr(ms));
-		ms->section_mem_map = 0;
-		ms->pageblock_flags = NULL;
-	}
-	pgdat_resize_unlock(pgdat, &flags);
-
-	clear_hwpoisoned_pages(memmap + map_offset,
-			PAGES_PER_SECTION - map_offset);
-	free_section_usemap(memmap, usemap);
+	clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset,
+			nr_pages - map_offset);
+	section_deactivate(pgdat, pfn, nr_pages);
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 #endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/mm/swap.c b/mm/swap.c
index 844baedd2429..c4910f14f957 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -209,9 +209,10 @@ static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec,
 {
 	int *pgmoved = arg;
 
-	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
-		enum lru_list lru = page_lru_base_type(page);
-		list_move_tail(&page->lru, &lruvec->lists[lru]);
+	if (PageLRU(page) && !PageUnevictable(page)) {
+		del_page_from_lru_list(page, lruvec, page_lru(page));
+		ClearPageActive(page);
+		add_page_to_lru_list_tail(page, lruvec, page_lru(page));
 		(*pgmoved)++;
 	}
 }
@@ -235,7 +236,7 @@ static void pagevec_move_tail(struct pagevec *pvec)
  */
 void rotate_reclaimable_page(struct page *page)
 {
-	if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) &&
+	if (!PageLocked(page) && !PageDirty(page) &&
 	    !PageUnevictable(page) && PageLRU(page)) {
 		struct pagevec *pvec;
 		unsigned long flags;
@@ -971,12 +972,6 @@ EXPORT_SYMBOL(pagevec_lookup_tag);
 void __init swap_setup(void)
 {
 	unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT);
-#ifdef CONFIG_SWAP
-	int i;
-
-	for (i = 0; i < MAX_SWAPFILES; i++)
-		spin_lock_init(&swapper_spaces[i].tree_lock);
-#endif
 
 	/* Use a smaller cluster for small-memory machines */
 	if (megs < 16)
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
new file mode 100644
index 000000000000..9b5bc86f96ad
--- /dev/null
+++ b/mm/swap_slots.c
@@ -0,0 +1,342 @@
+/*
+ * Manage cache of swap slots to be used for and returned from
+ * swap.
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * We allocate the swap slots from the global pool and put
+ * it into local per cpu caches.  This has the advantage
+ * of no needing to acquire the swap_info lock every time
+ * we need a new slot.
+ *
+ * There is also opportunity to simply return the slot
+ * to local caches without needing to acquire swap_info
+ * lock.  We do not reuse the returned slots directly but
+ * move them back to the global pool in a batch.  This
+ * allows the slots to coaellesce and reduce fragmentation.
+ *
+ * The swap entry allocated is marked with SWAP_HAS_CACHE
+ * flag in map_count that prevents it from being allocated
+ * again from the global pool.
+ *
+ * The swap slots cache is protected by a mutex instead of
+ * a spin lock as when we search for slots with scan_swap_map,
+ * we can possibly sleep.
+ */
+
+#include <linux/swap_slots.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/vmalloc.h>
+#include <linux/mutex.h>
+
+#ifdef CONFIG_SWAP
+
+static DEFINE_PER_CPU(struct swap_slots_cache, swp_slots);
+static bool	swap_slot_cache_active;
+bool	swap_slot_cache_enabled;
+static bool	swap_slot_cache_initialized;
+DEFINE_MUTEX(swap_slots_cache_mutex);
+/* Serialize swap slots cache enable/disable operations */
+DEFINE_MUTEX(swap_slots_cache_enable_mutex);
+
+static void __drain_swap_slots_cache(unsigned int type);
+static void deactivate_swap_slots_cache(void);
+static void reactivate_swap_slots_cache(void);
+
+#define use_swap_slot_cache (swap_slot_cache_active && \
+		swap_slot_cache_enabled && swap_slot_cache_initialized)
+#define SLOTS_CACHE 0x1
+#define SLOTS_CACHE_RET 0x2
+
+static void deactivate_swap_slots_cache(void)
+{
+	mutex_lock(&swap_slots_cache_mutex);
+	swap_slot_cache_active = false;
+	__drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET);
+	mutex_unlock(&swap_slots_cache_mutex);
+}
+
+static void reactivate_swap_slots_cache(void)
+{
+	mutex_lock(&swap_slots_cache_mutex);
+	swap_slot_cache_active = true;
+	mutex_unlock(&swap_slots_cache_mutex);
+}
+
+/* Must not be called with cpu hot plug lock */
+void disable_swap_slots_cache_lock(void)
+{
+	mutex_lock(&swap_slots_cache_enable_mutex);
+	swap_slot_cache_enabled = false;
+	if (swap_slot_cache_initialized) {
+		/* serialize with cpu hotplug operations */
+		get_online_cpus();
+		__drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET);
+		put_online_cpus();
+	}
+}
+
+static void __reenable_swap_slots_cache(void)
+{
+	swap_slot_cache_enabled = has_usable_swap();
+}
+
+void reenable_swap_slots_cache_unlock(void)
+{
+	__reenable_swap_slots_cache();
+	mutex_unlock(&swap_slots_cache_enable_mutex);
+}
+
+static bool check_cache_active(void)
+{
+	long pages;
+
+	if (!swap_slot_cache_enabled || !swap_slot_cache_initialized)
+		return false;
+
+	pages = get_nr_swap_pages();
+	if (!swap_slot_cache_active) {
+		if (pages > num_online_cpus() *
+		    THRESHOLD_ACTIVATE_SWAP_SLOTS_CACHE)
+			reactivate_swap_slots_cache();
+		goto out;
+	}
+
+	/* if global pool of slot caches too low, deactivate cache */
+	if (pages < num_online_cpus() * THRESHOLD_DEACTIVATE_SWAP_SLOTS_CACHE)
+		deactivate_swap_slots_cache();
+out:
+	return swap_slot_cache_active;
+}
+
+static int alloc_swap_slot_cache(unsigned int cpu)
+{
+	struct swap_slots_cache *cache;
+	swp_entry_t *slots, *slots_ret;
+
+	/*
+	 * Do allocation outside swap_slots_cache_mutex
+	 * as vzalloc could trigger reclaim and get_swap_page,
+	 * which can lock swap_slots_cache_mutex.
+	 */
+	slots = vzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE);
+	if (!slots)
+		return -ENOMEM;
+
+	slots_ret = vzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE);
+	if (!slots_ret) {
+		vfree(slots);
+		return -ENOMEM;
+	}
+
+	mutex_lock(&swap_slots_cache_mutex);
+	cache = &per_cpu(swp_slots, cpu);
+	if (cache->slots || cache->slots_ret)
+		/* cache already allocated */
+		goto out;
+	if (!cache->lock_initialized) {
+		mutex_init(&cache->alloc_lock);
+		spin_lock_init(&cache->free_lock);
+		cache->lock_initialized = true;
+	}
+	cache->nr = 0;
+	cache->cur = 0;
+	cache->n_ret = 0;
+	cache->slots = slots;
+	slots = NULL;
+	cache->slots_ret = slots_ret;
+	slots_ret = NULL;
+out:
+	mutex_unlock(&swap_slots_cache_mutex);
+	if (slots)
+		vfree(slots);
+	if (slots_ret)
+		vfree(slots_ret);
+	return 0;
+}
+
+static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type,
+				  bool free_slots)
+{
+	struct swap_slots_cache *cache;
+	swp_entry_t *slots = NULL;
+
+	cache = &per_cpu(swp_slots, cpu);
+	if ((type & SLOTS_CACHE) && cache->slots) {
+		mutex_lock(&cache->alloc_lock);
+		swapcache_free_entries(cache->slots + cache->cur, cache->nr);
+		cache->cur = 0;
+		cache->nr = 0;
+		if (free_slots && cache->slots) {
+			vfree(cache->slots);
+			cache->slots = NULL;
+		}
+		mutex_unlock(&cache->alloc_lock);
+	}
+	if ((type & SLOTS_CACHE_RET) && cache->slots_ret) {
+		spin_lock_irq(&cache->free_lock);
+		swapcache_free_entries(cache->slots_ret, cache->n_ret);
+		cache->n_ret = 0;
+		if (free_slots && cache->slots_ret) {
+			slots = cache->slots_ret;
+			cache->slots_ret = NULL;
+		}
+		spin_unlock_irq(&cache->free_lock);
+		if (slots)
+			vfree(slots);
+	}
+}
+
+static void __drain_swap_slots_cache(unsigned int type)
+{
+	unsigned int cpu;
+
+	/*
+	 * This function is called during
+	 *	1) swapoff, when we have to make sure no
+	 *	   left over slots are in cache when we remove
+	 *	   a swap device;
+	 *      2) disabling of swap slot cache, when we run low
+	 *	   on swap slots when allocating memory and need
+	 *	   to return swap slots to global pool.
+	 *
+	 * We cannot acquire cpu hot plug lock here as
+	 * this function can be invoked in the cpu
+	 * hot plug path:
+	 * cpu_up -> lock cpu_hotplug -> cpu hotplug state callback
+	 *   -> memory allocation -> direct reclaim -> get_swap_page
+	 *   -> drain_swap_slots_cache
+	 *
+	 * Hence the loop over current online cpu below could miss cpu that
+	 * is being brought online but not yet marked as online.
+	 * That is okay as we do not schedule and run anything on a
+	 * cpu before it has been marked online. Hence, we will not
+	 * fill any swap slots in slots cache of such cpu.
+	 * There are no slots on such cpu that need to be drained.
+	 */
+	for_each_online_cpu(cpu)
+		drain_slots_cache_cpu(cpu, type, false);
+}
+
+static int free_slot_cache(unsigned int cpu)
+{
+	mutex_lock(&swap_slots_cache_mutex);
+	drain_slots_cache_cpu(cpu, SLOTS_CACHE | SLOTS_CACHE_RET, true);
+	mutex_unlock(&swap_slots_cache_mutex);
+	return 0;
+}
+
+int enable_swap_slots_cache(void)
+{
+	int ret = 0;
+
+	mutex_lock(&swap_slots_cache_enable_mutex);
+	if (swap_slot_cache_initialized) {
+		__reenable_swap_slots_cache();
+		goto out_unlock;
+	}
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "swap_slots_cache",
+				alloc_swap_slot_cache, free_slot_cache);
+	if (ret < 0)
+		goto out_unlock;
+	swap_slot_cache_initialized = true;
+	__reenable_swap_slots_cache();
+out_unlock:
+	mutex_unlock(&swap_slots_cache_enable_mutex);
+	return 0;
+}
+
+/* called with swap slot cache's alloc lock held */
+static int refill_swap_slots_cache(struct swap_slots_cache *cache)
+{
+	if (!use_swap_slot_cache || cache->nr)
+		return 0;
+
+	cache->cur = 0;
+	if (swap_slot_cache_active)
+		cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE, cache->slots);
+
+	return cache->nr;
+}
+
+int free_swap_slot(swp_entry_t entry)
+{
+	struct swap_slots_cache *cache;
+
+	BUG_ON(!swap_slot_cache_initialized);
+
+	cache = &get_cpu_var(swp_slots);
+	if (use_swap_slot_cache && cache->slots_ret) {
+		spin_lock_irq(&cache->free_lock);
+		/* Swap slots cache may be deactivated before acquiring lock */
+		if (!use_swap_slot_cache) {
+			spin_unlock_irq(&cache->free_lock);
+			goto direct_free;
+		}
+		if (cache->n_ret >= SWAP_SLOTS_CACHE_SIZE) {
+			/*
+			 * Return slots to global pool.
+			 * The current swap_map value is SWAP_HAS_CACHE.
+			 * Set it to 0 to indicate it is available for
+			 * allocation in global pool
+			 */
+			swapcache_free_entries(cache->slots_ret, cache->n_ret);
+			cache->n_ret = 0;
+		}
+		cache->slots_ret[cache->n_ret++] = entry;
+		spin_unlock_irq(&cache->free_lock);
+	} else {
+direct_free:
+		swapcache_free_entries(&entry, 1);
+	}
+	put_cpu_var(swp_slots);
+
+	return 0;
+}
+
+swp_entry_t get_swap_page(void)
+{
+	swp_entry_t entry, *pentry;
+	struct swap_slots_cache *cache;
+
+	/*
+	 * Preemption is allowed here, because we may sleep
+	 * in refill_swap_slots_cache().  But it is safe, because
+	 * accesses to the per-CPU data structure are protected by the
+	 * mutex cache->alloc_lock.
+	 *
+	 * The alloc path here does not touch cache->slots_ret
+	 * so cache->free_lock is not taken.
+	 */
+	cache = raw_cpu_ptr(&swp_slots);
+
+	entry.val = 0;
+	if (check_cache_active()) {
+		mutex_lock(&cache->alloc_lock);
+		if (cache->slots) {
+repeat:
+			if (cache->nr) {
+				pentry = &cache->slots[cache->cur++];
+				entry = *pentry;
+				pentry->val = 0;
+				cache->nr--;
+			} else {
+				if (refill_swap_slots_cache(cache))
+					goto repeat;
+			}
+		}
+		mutex_unlock(&cache->alloc_lock);
+		if (entry.val)
+			return entry;
+	}
+
+	get_swap_pages(1, &entry);
+
+	return entry;
+}
+
+#endif /* CONFIG_SWAP */
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 35d7e0ee1c77..2126e9ba23b2 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -17,6 +17,8 @@
 #include <linux/blkdev.h>
 #include <linux/pagevec.h>
 #include <linux/migrate.h>
+#include <linux/vmalloc.h>
+#include <linux/swap_slots.h>
 
 #include <asm/pgtable.h>
 
@@ -32,15 +34,8 @@ static const struct address_space_operations swap_aops = {
 #endif
 };
 
-struct address_space swapper_spaces[MAX_SWAPFILES] = {
-	[0 ... MAX_SWAPFILES - 1] = {
-		.page_tree	= RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
-		.i_mmap_writable = ATOMIC_INIT(0),
-		.a_ops		= &swap_aops,
-		/* swap cache doesn't use writeback related tags */
-		.flags		= 1 << AS_NO_WRITEBACK_TAGS,
-	}
-};
+struct address_space *swapper_spaces[MAX_SWAPFILES];
+static unsigned int nr_swapper_spaces[MAX_SWAPFILES];
 
 #define INC_CACHE_INFO(x)	do { swap_cache_info.x++; } while (0)
 
@@ -53,11 +48,26 @@ static struct {
 
 unsigned long total_swapcache_pages(void)
 {
-	int i;
+	unsigned int i, j, nr;
 	unsigned long ret = 0;
+	struct address_space *spaces;
 
-	for (i = 0; i < MAX_SWAPFILES; i++)
-		ret += swapper_spaces[i].nrpages;
+	rcu_read_lock();
+	for (i = 0; i < MAX_SWAPFILES; i++) {
+		/*
+		 * The corresponding entries in nr_swapper_spaces and
+		 * swapper_spaces will be reused only after at least
+		 * one grace period.  So it is impossible for them
+		 * belongs to different usage.
+		 */
+		nr = nr_swapper_spaces[i];
+		spaces = rcu_dereference(swapper_spaces[i]);
+		if (!nr || !spaces)
+			continue;
+		for (j = 0; j < nr; j++)
+			ret += spaces[j].nrpages;
+	}
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -315,6 +325,17 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			break;
 
 		/*
+		 * Just skip read ahead for unused swap slot.
+		 * During swap_off when swap_slot_cache is disabled,
+		 * we have to handle the race between putting
+		 * swap entry in swap cache and marking swap slot
+		 * as SWAP_HAS_CACHE.  That's done in later part of code or
+		 * else swap_off will be aborted if we return NULL.
+		 */
+		if (!__swp_swapcount(entry) && swap_slot_cache_enabled)
+			return NULL;
+
+		/*
 		 * Get a new page to read into from swap.
 		 */
 		if (!new_page) {
@@ -505,3 +526,38 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 skip:
 	return read_swap_cache_async(entry, gfp_mask, vma, addr);
 }
+
+int init_swap_address_space(unsigned int type, unsigned long nr_pages)
+{
+	struct address_space *spaces, *space;
+	unsigned int i, nr;
+
+	nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES);
+	spaces = vzalloc(sizeof(struct address_space) * nr);
+	if (!spaces)
+		return -ENOMEM;
+	for (i = 0; i < nr; i++) {
+		space = spaces + i;
+		INIT_RADIX_TREE(&space->page_tree, GFP_ATOMIC|__GFP_NOWARN);
+		atomic_set(&space->i_mmap_writable, 0);
+		space->a_ops = &swap_aops;
+		/* swap cache doesn't use writeback related tags */
+		mapping_set_no_writeback_tags(space);
+		spin_lock_init(&space->tree_lock);
+	}
+	nr_swapper_spaces[type] = nr;
+	rcu_assign_pointer(swapper_spaces[type], spaces);
+
+	return 0;
+}
+
+void exit_swap_address_space(unsigned int type)
+{
+	struct address_space *spaces;
+
+	spaces = swapper_spaces[type];
+	nr_swapper_spaces[type] = 0;
+	rcu_assign_pointer(swapper_spaces[type], NULL);
+	synchronize_rcu();
+	kvfree(spaces);
+}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4761701d1721..50b64f6dd580 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -34,6 +34,7 @@
 #include <linux/frontswap.h>
 #include <linux/swapfile.h>
 #include <linux/export.h>
+#include <linux/swap_slots.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -257,6 +258,52 @@ static inline void cluster_set_null(struct swap_cluster_info *info)
 	info->data = 0;
 }
 
+static inline void __lock_cluster(struct swap_cluster_info *ci)
+{
+	spin_lock(&ci->lock);
+}
+
+static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
+						     unsigned long offset)
+{
+	struct swap_cluster_info *ci;
+
+	ci = si->cluster_info;
+	if (ci) {
+		ci += offset / SWAPFILE_CLUSTER;
+		__lock_cluster(ci);
+	}
+	return ci;
+}
+
+static inline void unlock_cluster(struct swap_cluster_info *ci)
+{
+	if (ci)
+		spin_unlock(&ci->lock);
+}
+
+static inline struct swap_cluster_info *lock_cluster_or_swap_info(
+	struct swap_info_struct *si,
+	unsigned long offset)
+{
+	struct swap_cluster_info *ci;
+
+	ci = lock_cluster(si, offset);
+	if (!ci)
+		spin_lock(&si->lock);
+
+	return ci;
+}
+
+static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si,
+					       struct swap_cluster_info *ci)
+{
+	if (ci)
+		unlock_cluster(ci);
+	else
+		spin_unlock(&si->lock);
+}
+
 static inline bool cluster_list_empty(struct swap_cluster_list *list)
 {
 	return cluster_is_null(&list->head);
@@ -281,9 +328,17 @@ static void cluster_list_add_tail(struct swap_cluster_list *list,
 		cluster_set_next_flag(&list->head, idx, 0);
 		cluster_set_next_flag(&list->tail, idx, 0);
 	} else {
+		struct swap_cluster_info *ci_tail;
 		unsigned int tail = cluster_next(&list->tail);
 
-		cluster_set_next(&ci[tail], idx);
+		/*
+		 * Nested cluster lock, but both cluster locks are
+		 * only acquired when we held swap_info_struct->lock
+		 */
+		ci_tail = ci + tail;
+		__lock_cluster(ci_tail);
+		cluster_set_next(ci_tail, idx);
+		unlock_cluster(ci_tail);
 		cluster_set_next_flag(&list->tail, idx, 0);
 	}
 }
@@ -328,7 +383,7 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si,
 */
 static void swap_do_scheduled_discard(struct swap_info_struct *si)
 {
-	struct swap_cluster_info *info;
+	struct swap_cluster_info *info, *ci;
 	unsigned int idx;
 
 	info = si->cluster_info;
@@ -341,10 +396,14 @@ static void swap_do_scheduled_discard(struct swap_info_struct *si)
 				SWAPFILE_CLUSTER);
 
 		spin_lock(&si->lock);
-		cluster_set_flag(&info[idx], CLUSTER_FLAG_FREE);
+		ci = lock_cluster(si, idx * SWAPFILE_CLUSTER);
+		cluster_set_flag(ci, CLUSTER_FLAG_FREE);
+		unlock_cluster(ci);
 		cluster_list_add_tail(&si->free_clusters, info, idx);
+		ci = lock_cluster(si, idx * SWAPFILE_CLUSTER);
 		memset(si->swap_map + idx * SWAPFILE_CLUSTER,
 				0, SWAPFILE_CLUSTER);
+		unlock_cluster(ci);
 	}
 }
 
@@ -443,12 +502,13 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
  * Try to get a swap entry from current cpu's swap entry pool (a cluster). This
  * might involve allocating a new cluster for current CPU too.
  */
-static void scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
+static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
 	unsigned long *offset, unsigned long *scan_base)
 {
 	struct percpu_cluster *cluster;
+	struct swap_cluster_info *ci;
 	bool found_free;
-	unsigned long tmp;
+	unsigned long tmp, max;
 
 new_cluster:
 	cluster = this_cpu_ptr(si->percpu_cluster);
@@ -466,7 +526,7 @@ new_cluster:
 			*scan_base = *offset = si->cluster_next;
 			goto new_cluster;
 		} else
-			return;
+			return false;
 	}
 
 	found_free = false;
@@ -476,14 +536,21 @@ new_cluster:
 	 * check if there is still free entry in the cluster
 	 */
 	tmp = cluster->next;
-	while (tmp < si->max && tmp < (cluster_next(&cluster->index) + 1) *
-	       SWAPFILE_CLUSTER) {
+	max = min_t(unsigned long, si->max,
+		    (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER);
+	if (tmp >= max) {
+		cluster_set_null(&cluster->index);
+		goto new_cluster;
+	}
+	ci = lock_cluster(si, tmp);
+	while (tmp < max) {
 		if (!si->swap_map[tmp]) {
 			found_free = true;
 			break;
 		}
 		tmp++;
 	}
+	unlock_cluster(ci);
 	if (!found_free) {
 		cluster_set_null(&cluster->index);
 		goto new_cluster;
@@ -491,15 +558,22 @@ new_cluster:
 	cluster->next = tmp + 1;
 	*offset = tmp;
 	*scan_base = tmp;
+	return found_free;
 }
 
-static unsigned long scan_swap_map(struct swap_info_struct *si,
-				   unsigned char usage)
+static int scan_swap_map_slots(struct swap_info_struct *si,
+			       unsigned char usage, int nr,
+			       swp_entry_t slots[])
 {
+	struct swap_cluster_info *ci;
 	unsigned long offset;
 	unsigned long scan_base;
 	unsigned long last_in_cluster = 0;
 	int latency_ration = LATENCY_LIMIT;
+	int n_ret = 0;
+
+	if (nr > SWAP_BATCH)
+		nr = SWAP_BATCH;
 
 	/*
 	 * We try to cluster swap pages by allocating them sequentially
@@ -517,8 +591,10 @@ static unsigned long scan_swap_map(struct swap_info_struct *si,
 
 	/* SSD algorithm */
 	if (si->cluster_info) {
-		scan_swap_map_try_ssd_cluster(si, &offset, &scan_base);
-		goto checks;
+		if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
+			goto checks;
+		else
+			goto scan;
 	}
 
 	if (unlikely(!si->cluster_nr--)) {
@@ -562,8 +638,14 @@ static unsigned long scan_swap_map(struct swap_info_struct *si,
 
 checks:
 	if (si->cluster_info) {
-		while (scan_swap_map_ssd_cluster_conflict(si, offset))
-			scan_swap_map_try_ssd_cluster(si, &offset, &scan_base);
+		while (scan_swap_map_ssd_cluster_conflict(si, offset)) {
+		/* take a break if we already got some slots */
+			if (n_ret)
+				goto done;
+			if (!scan_swap_map_try_ssd_cluster(si, &offset,
+							&scan_base))
+				goto scan;
+		}
 	}
 	if (!(si->flags & SWP_WRITEOK))
 		goto no_page;
@@ -572,9 +654,11 @@ checks:
 	if (offset > si->highest_bit)
 		scan_base = offset = si->lowest_bit;
 
+	ci = lock_cluster(si, offset);
 	/* reuse swap entry of cache-only swap if not busy. */
 	if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
 		int swap_was_freed;
+		unlock_cluster(ci);
 		spin_unlock(&si->lock);
 		swap_was_freed = __try_to_reclaim_swap(si, offset);
 		spin_lock(&si->lock);
@@ -584,8 +668,13 @@ checks:
 		goto scan; /* check next one */
 	}
 
-	if (si->swap_map[offset])
-		goto scan;
+	if (si->swap_map[offset]) {
+		unlock_cluster(ci);
+		if (!n_ret)
+			goto scan;
+		else
+			goto done;
+	}
 
 	if (offset == si->lowest_bit)
 		si->lowest_bit++;
@@ -601,10 +690,45 @@ checks:
 	}
 	si->swap_map[offset] = usage;
 	inc_cluster_info_page(si, si->cluster_info, offset);
+	unlock_cluster(ci);
 	si->cluster_next = offset + 1;
-	si->flags -= SWP_SCANNING;
+	slots[n_ret++] = swp_entry(si->type, offset);
+
+	/* got enough slots or reach max slots? */
+	if ((n_ret == nr) || (offset >= si->highest_bit))
+		goto done;
+
+	/* search for next available slot */
+
+	/* time to take a break? */
+	if (unlikely(--latency_ration < 0)) {
+		if (n_ret)
+			goto done;
+		spin_unlock(&si->lock);
+		cond_resched();
+		spin_lock(&si->lock);
+		latency_ration = LATENCY_LIMIT;
+	}
+
+	/* try to get more slots in cluster */
+	if (si->cluster_info) {
+		if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
+			goto checks;
+		else
+			goto done;
+	}
+	/* non-ssd case */
+	++offset;
 
-	return offset;
+	/* non-ssd case, still more slots in cluster? */
+	if (si->cluster_nr && !si->swap_map[offset]) {
+		--si->cluster_nr;
+		goto checks;
+	}
+
+done:
+	si->flags -= SWP_SCANNING;
+	return n_ret;
 
 scan:
 	spin_unlock(&si->lock);
@@ -642,17 +766,41 @@ scan:
 
 no_page:
 	si->flags -= SWP_SCANNING;
-	return 0;
+	return n_ret;
 }
 
-swp_entry_t get_swap_page(void)
+static unsigned long scan_swap_map(struct swap_info_struct *si,
+				   unsigned char usage)
+{
+	swp_entry_t entry;
+	int n_ret;
+
+	n_ret = scan_swap_map_slots(si, usage, 1, &entry);
+
+	if (n_ret)
+		return swp_offset(entry);
+	else
+		return 0;
+
+}
+
+int get_swap_pages(int n_goal, swp_entry_t swp_entries[])
 {
 	struct swap_info_struct *si, *next;
-	pgoff_t offset;
+	long avail_pgs;
+	int n_ret = 0;
 
-	if (atomic_long_read(&nr_swap_pages) <= 0)
+	avail_pgs = atomic_long_read(&nr_swap_pages);
+	if (avail_pgs <= 0)
 		goto noswap;
-	atomic_long_dec(&nr_swap_pages);
+
+	if (n_goal > SWAP_BATCH)
+		n_goal = SWAP_BATCH;
+
+	if (n_goal > avail_pgs)
+		n_goal = avail_pgs;
+
+	atomic_long_sub(n_goal, &nr_swap_pages);
 
 	spin_lock(&swap_avail_lock);
 
@@ -678,14 +826,14 @@ start_over:
 			spin_unlock(&si->lock);
 			goto nextsi;
 		}
-
-		/* This is called for allocating swap entry for cache */
-		offset = scan_swap_map(si, SWAP_HAS_CACHE);
+		n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
+					    n_goal, swp_entries);
 		spin_unlock(&si->lock);
-		if (offset)
-			return swp_entry(si->type, offset);
+		if (n_ret)
+			goto check_out;
 		pr_debug("scan_swap_map of si %d failed to find offset\n",
-		       si->type);
+			si->type);
+
 		spin_lock(&swap_avail_lock);
 nextsi:
 		/*
@@ -696,7 +844,8 @@ nextsi:
 		 * up between us dropping swap_avail_lock and taking si->lock.
 		 * Since we dropped the swap_avail_lock, the swap_avail_head
 		 * list may have been modified; so if next is still in the
-		 * swap_avail_head list then try it, otherwise start over.
+		 * swap_avail_head list then try it, otherwise start over
+		 * if we have not gotten any slots.
 		 */
 		if (plist_node_empty(&next->avail_list))
 			goto start_over;
@@ -704,9 +853,11 @@ nextsi:
 
 	spin_unlock(&swap_avail_lock);
 
-	atomic_long_inc(&nr_swap_pages);
+check_out:
+	if (n_ret < n_goal)
+		atomic_long_add((long) (n_goal-n_ret), &nr_swap_pages);
 noswap:
-	return (swp_entry_t) {0};
+	return n_ret;
 }
 
 /* The only caller of this function is now suspend routine */
@@ -731,7 +882,7 @@ swp_entry_t get_swap_page_of_type(int type)
 	return (swp_entry_t) {0};
 }
 
-static struct swap_info_struct *swap_info_get(swp_entry_t entry)
+static struct swap_info_struct *__swap_info_get(swp_entry_t entry)
 {
 	struct swap_info_struct *p;
 	unsigned long offset, type;
@@ -747,34 +898,76 @@ static struct swap_info_struct *swap_info_get(swp_entry_t entry)
 	offset = swp_offset(entry);
 	if (offset >= p->max)
 		goto bad_offset;
-	if (!p->swap_map[offset])
-		goto bad_free;
-	spin_lock(&p->lock);
 	return p;
 
-bad_free:
-	pr_err("swap_free: %s%08lx\n", Unused_offset, entry.val);
-	goto out;
 bad_offset:
-	pr_err("swap_free: %s%08lx\n", Bad_offset, entry.val);
+	pr_err("swap_info_get: %s%08lx\n", Bad_offset, entry.val);
 	goto out;
 bad_device:
-	pr_err("swap_free: %s%08lx\n", Unused_file, entry.val);
+	pr_err("swap_info_get: %s%08lx\n", Unused_file, entry.val);
 	goto out;
 bad_nofile:
-	pr_err("swap_free: %s%08lx\n", Bad_file, entry.val);
+	pr_err("swap_info_get: %s%08lx\n", Bad_file, entry.val);
+out:
+	return NULL;
+}
+
+static struct swap_info_struct *_swap_info_get(swp_entry_t entry)
+{
+	struct swap_info_struct *p;
+
+	p = __swap_info_get(entry);
+	if (!p)
+		goto out;
+	if (!p->swap_map[swp_offset(entry)])
+		goto bad_free;
+	return p;
+
+bad_free:
+	pr_err("swap_info_get: %s%08lx\n", Unused_offset, entry.val);
+	goto out;
 out:
 	return NULL;
 }
 
-static unsigned char swap_entry_free(struct swap_info_struct *p,
-				     swp_entry_t entry, unsigned char usage)
+static struct swap_info_struct *swap_info_get(swp_entry_t entry)
 {
+	struct swap_info_struct *p;
+
+	p = _swap_info_get(entry);
+	if (p)
+		spin_lock(&p->lock);
+	return p;
+}
+
+static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry,
+					struct swap_info_struct *q)
+{
+	struct swap_info_struct *p;
+
+	p = _swap_info_get(entry);
+
+	if (p != q) {
+		if (q != NULL)
+			spin_unlock(&q->lock);
+		if (p != NULL)
+			spin_lock(&p->lock);
+	}
+	return p;
+}
+
+static unsigned char __swap_entry_free(struct swap_info_struct *p,
+				       swp_entry_t entry, unsigned char usage)
+{
+	struct swap_cluster_info *ci;
 	unsigned long offset = swp_offset(entry);
 	unsigned char count;
 	unsigned char has_cache;
 
+	ci = lock_cluster_or_swap_info(p, offset);
+
 	count = p->swap_map[offset];
+
 	has_cache = count & SWAP_HAS_CACHE;
 	count &= ~SWAP_HAS_CACHE;
 
@@ -798,38 +991,52 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
 	}
 
 	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;
-		if (offset > p->highest_bit) {
-			bool was_full = !p->highest_bit;
-			p->highest_bit = offset;
-			if (was_full && (p->flags & SWP_WRITEOK)) {
-				spin_lock(&swap_avail_lock);
-				WARN_ON(!plist_node_empty(&p->avail_list));
-				if (plist_node_empty(&p->avail_list))
-					plist_add(&p->avail_list,
-						  &swap_avail_head);
-				spin_unlock(&swap_avail_lock);
-			}
-		}
-		atomic_long_inc(&nr_swap_pages);
-		p->inuse_pages--;
-		frontswap_invalidate_page(p->type, offset);
-		if (p->flags & SWP_BLKDEV) {
-			struct gendisk *disk = p->bdev->bd_disk;
-			if (disk->fops->swap_slot_free_notify)
-				disk->fops->swap_slot_free_notify(p->bdev,
-								  offset);
+	p->swap_map[offset] = usage ? : SWAP_HAS_CACHE;
+
+	unlock_cluster_or_swap_info(p, ci);
+
+	return usage;
+}
+
+static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry)
+{
+	struct swap_cluster_info *ci;
+	unsigned long offset = swp_offset(entry);
+	unsigned char count;
+
+	ci = lock_cluster(p, offset);
+	count = p->swap_map[offset];
+	VM_BUG_ON(count != SWAP_HAS_CACHE);
+	p->swap_map[offset] = 0;
+	dec_cluster_info_page(p, p->cluster_info, offset);
+	unlock_cluster(ci);
+
+	mem_cgroup_uncharge_swap(entry);
+	if (offset < p->lowest_bit)
+		p->lowest_bit = offset;
+	if (offset > p->highest_bit) {
+		bool was_full = !p->highest_bit;
+
+		p->highest_bit = offset;
+		if (was_full && (p->flags & SWP_WRITEOK)) {
+			spin_lock(&swap_avail_lock);
+			WARN_ON(!plist_node_empty(&p->avail_list));
+			if (plist_node_empty(&p->avail_list))
+				plist_add(&p->avail_list,
+					  &swap_avail_head);
+			spin_unlock(&swap_avail_lock);
 		}
 	}
+	atomic_long_inc(&nr_swap_pages);
+	p->inuse_pages--;
+	frontswap_invalidate_page(p->type, offset);
+	if (p->flags & SWP_BLKDEV) {
+		struct gendisk *disk = p->bdev->bd_disk;
 
-	return usage;
+		if (disk->fops->swap_slot_free_notify)
+			disk->fops->swap_slot_free_notify(p->bdev,
+							  offset);
+	}
 }
 
 /*
@@ -840,10 +1047,10 @@ void swap_free(swp_entry_t entry)
 {
 	struct swap_info_struct *p;
 
-	p = swap_info_get(entry);
+	p = _swap_info_get(entry);
 	if (p) {
-		swap_entry_free(p, entry, 1);
-		spin_unlock(&p->lock);
+		if (!__swap_entry_free(p, entry, 1))
+			free_swap_slot(entry);
 	}
 }
 
@@ -854,11 +1061,33 @@ void swapcache_free(swp_entry_t entry)
 {
 	struct swap_info_struct *p;
 
-	p = swap_info_get(entry);
+	p = _swap_info_get(entry);
 	if (p) {
-		swap_entry_free(p, entry, SWAP_HAS_CACHE);
-		spin_unlock(&p->lock);
+		if (!__swap_entry_free(p, entry, SWAP_HAS_CACHE))
+			free_swap_slot(entry);
+	}
+}
+
+void swapcache_free_entries(swp_entry_t *entries, int n)
+{
+	struct swap_info_struct *p, *prev;
+	int i;
+
+	if (n <= 0)
+		return;
+
+	prev = NULL;
+	p = NULL;
+	for (i = 0; i < n; ++i) {
+		p = swap_info_get_cont(entries[i], prev);
+		if (p)
+			swap_entry_free(p, entries[i]);
+		else
+			break;
+		prev = p;
 	}
+	if (p)
+		spin_unlock(&p->lock);
 }
 
 /*
@@ -870,13 +1099,39 @@ int page_swapcount(struct page *page)
 {
 	int count = 0;
 	struct swap_info_struct *p;
+	struct swap_cluster_info *ci;
 	swp_entry_t entry;
+	unsigned long offset;
 
 	entry.val = page_private(page);
-	p = swap_info_get(entry);
+	p = _swap_info_get(entry);
 	if (p) {
-		count = swap_count(p->swap_map[swp_offset(entry)]);
-		spin_unlock(&p->lock);
+		offset = swp_offset(entry);
+		ci = lock_cluster_or_swap_info(p, offset);
+		count = swap_count(p->swap_map[offset]);
+		unlock_cluster_or_swap_info(p, ci);
+	}
+	return count;
+}
+
+/*
+ * How many references to @entry are currently swapped out?
+ * This does not give an exact answer when swap count is continued,
+ * but does include the high COUNT_CONTINUED flag to allow for that.
+ */
+int __swp_swapcount(swp_entry_t entry)
+{
+	int count = 0;
+	pgoff_t offset;
+	struct swap_info_struct *si;
+	struct swap_cluster_info *ci;
+
+	si = __swap_info_get(entry);
+	if (si) {
+		offset = swp_offset(entry);
+		ci = lock_cluster_or_swap_info(si, offset);
+		count = swap_count(si->swap_map[offset]);
+		unlock_cluster_or_swap_info(si, ci);
 	}
 	return count;
 }
@@ -889,22 +1144,26 @@ int swp_swapcount(swp_entry_t entry)
 {
 	int count, tmp_count, n;
 	struct swap_info_struct *p;
+	struct swap_cluster_info *ci;
 	struct page *page;
 	pgoff_t offset;
 	unsigned char *map;
 
-	p = swap_info_get(entry);
+	p = _swap_info_get(entry);
 	if (!p)
 		return 0;
 
-	count = swap_count(p->swap_map[swp_offset(entry)]);
+	offset = swp_offset(entry);
+
+	ci = lock_cluster_or_swap_info(p, offset);
+
+	count = swap_count(p->swap_map[offset]);
 	if (!(count & COUNT_CONTINUED))
 		goto out;
 
 	count &= ~COUNT_CONTINUED;
 	n = SWAP_MAP_MAX + 1;
 
-	offset = swp_offset(entry);
 	page = vmalloc_to_page(p->swap_map + offset);
 	offset &= ~PAGE_MASK;
 	VM_BUG_ON(page_private(page) != SWP_CONTINUED);
@@ -919,7 +1178,7 @@ int swp_swapcount(swp_entry_t entry)
 		n *= (SWAP_CONT_MAX + 1);
 	} while (tmp_count & COUNT_CONTINUED);
 out:
-	spin_unlock(&p->lock);
+	unlock_cluster_or_swap_info(p, ci);
 	return count;
 }
 
@@ -1011,21 +1270,23 @@ int free_swap_and_cache(swp_entry_t entry)
 {
 	struct swap_info_struct *p;
 	struct page *page = NULL;
+	unsigned char count;
 
 	if (non_swap_entry(entry))
 		return 1;
 
-	p = swap_info_get(entry);
+	p = _swap_info_get(entry);
 	if (p) {
-		if (swap_entry_free(p, entry, 1) == SWAP_HAS_CACHE) {
+		count = __swap_entry_free(p, entry, 1);
+		if (count == SWAP_HAS_CACHE) {
 			page = find_get_page(swap_address_space(entry),
 					     swp_offset(entry));
 			if (page && !trylock_page(page)) {
 				put_page(page);
 				page = NULL;
 			}
-		}
-		spin_unlock(&p->lock);
+		} else if (!count)
+			free_swap_slot(entry);
 	}
 	if (page) {
 		/*
@@ -1853,6 +2114,17 @@ static void reinsert_swap_info(struct swap_info_struct *p)
 	spin_unlock(&swap_lock);
 }
 
+bool has_usable_swap(void)
+{
+	bool ret = true;
+
+	spin_lock(&swap_lock);
+	if (plist_head_empty(&swap_active_head))
+		ret = false;
+	spin_unlock(&swap_lock);
+	return ret;
+}
+
 SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 {
 	struct swap_info_struct *p = NULL;
@@ -1923,6 +2195,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 
+	disable_swap_slots_cache_lock();
+
 	set_current_oom_origin();
 	err = try_to_unuse(p->type, false, 0); /* force unuse all pages */
 	clear_current_oom_origin();
@@ -1930,9 +2204,12 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	if (err) {
 		/* re-insert swap space back into swap_list */
 		reinsert_swap_info(p);
+		reenable_swap_slots_cache_unlock();
 		goto out_dput;
 	}
 
+	reenable_swap_slots_cache_unlock();
+
 	flush_work(&p->discard_work);
 
 	destroy_swap_extents(p);
@@ -1975,6 +2252,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	vfree(frontswap_map);
 	/* Destroy swap account information */
 	swap_cgroup_swapoff(p->type);
+	exit_swap_address_space(p->type);
 
 	inode = mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
@@ -2298,6 +2576,13 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
 	return maxpages;
 }
 
+#define SWAP_CLUSTER_INFO_COLS						\
+	DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info))
+#define SWAP_CLUSTER_SPACE_COLS						\
+	DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER)
+#define SWAP_CLUSTER_COLS						\
+	max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS)
+
 static int setup_swap_map_and_extents(struct swap_info_struct *p,
 					union swap_header *swap_header,
 					unsigned char *swap_map,
@@ -2305,11 +2590,12 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p,
 					unsigned long maxpages,
 					sector_t *span)
 {
-	int i;
+	unsigned int j, k;
 	unsigned int nr_good_pages;
 	int nr_extents;
 	unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER);
-	unsigned long idx = p->cluster_next / SWAPFILE_CLUSTER;
+	unsigned long col = p->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS;
+	unsigned long i, idx;
 
 	nr_good_pages = maxpages - 1;	/* omit header page */
 
@@ -2357,15 +2643,23 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p,
 	if (!cluster_info)
 		return nr_extents;
 
-	for (i = 0; i < nr_clusters; i++) {
-		if (!cluster_count(&cluster_info[idx])) {
+
+	/*
+	 * Reduce false cache line sharing between cluster_info and
+	 * sharing same address space.
+	 */
+	for (k = 0; k < SWAP_CLUSTER_COLS; k++) {
+		j = (k + col) % SWAP_CLUSTER_COLS;
+		for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) {
+			idx = i * SWAP_CLUSTER_COLS + j;
+			if (idx >= nr_clusters)
+				continue;
+			if (cluster_count(&cluster_info[idx]))
+				continue;
 			cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE);
 			cluster_list_add_tail(&p->free_clusters, cluster_info,
 					      idx);
 		}
-		idx++;
-		if (idx == nr_clusters)
-			idx = 0;
 	}
 	return nr_extents;
 }
@@ -2468,6 +2762,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 
 	if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) {
 		int cpu;
+		unsigned long ci, nr_cluster;
 
 		p->flags |= SWP_SOLIDSTATE;
 		/*
@@ -2475,13 +2770,17 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		 * SSD
 		 */
 		p->cluster_next = 1 + (prandom_u32() % p->highest_bit);
+		nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER);
 
-		cluster_info = vzalloc(DIV_ROUND_UP(maxpages,
-			SWAPFILE_CLUSTER) * sizeof(*cluster_info));
+		cluster_info = vzalloc(nr_cluster * sizeof(*cluster_info));
 		if (!cluster_info) {
 			error = -ENOMEM;
 			goto bad_swap;
 		}
+
+		for (ci = 0; ci < nr_cluster; ci++)
+			spin_lock_init(&((cluster_info + ci)->lock));
+
 		p->percpu_cluster = alloc_percpu(struct percpu_cluster);
 		if (!p->percpu_cluster) {
 			error = -ENOMEM;
@@ -2538,6 +2837,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		}
 	}
 
+	error = init_swap_address_space(p->type, maxpages);
+	if (error)
+		goto bad_swap;
+
 	mutex_lock(&swapon_mutex);
 	prio = -1;
 	if (swap_flags & SWAP_FLAG_PREFER)
@@ -2593,6 +2896,8 @@ out:
 		putname(name);
 	if (inode && S_ISREG(inode->i_mode))
 		inode_unlock(inode);
+	if (!error)
+		enable_swap_slots_cache();
 	return error;
 }
 
@@ -2627,6 +2932,7 @@ void si_swapinfo(struct sysinfo *val)
 static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 {
 	struct swap_info_struct *p;
+	struct swap_cluster_info *ci;
 	unsigned long offset, type;
 	unsigned char count;
 	unsigned char has_cache;
@@ -2640,10 +2946,10 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 		goto bad_file;
 	p = swap_info[type];
 	offset = swp_offset(entry);
-
-	spin_lock(&p->lock);
 	if (unlikely(offset >= p->max))
-		goto unlock_out;
+		goto out;
+
+	ci = lock_cluster_or_swap_info(p, offset);
 
 	count = p->swap_map[offset];
 
@@ -2686,7 +2992,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 	p->swap_map[offset] = count | has_cache;
 
 unlock_out:
-	spin_unlock(&p->lock);
+	unlock_cluster_or_swap_info(p, ci);
 out:
 	return err;
 
@@ -2775,6 +3081,7 @@ EXPORT_SYMBOL_GPL(__page_file_index);
 int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 {
 	struct swap_info_struct *si;
+	struct swap_cluster_info *ci;
 	struct page *head;
 	struct page *page;
 	struct page *list_page;
@@ -2798,6 +3105,9 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	}
 
 	offset = swp_offset(entry);
+
+	ci = lock_cluster(si, offset);
+
 	count = si->swap_map[offset] & ~SWAP_HAS_CACHE;
 
 	if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) {
@@ -2810,6 +3120,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	}
 
 	if (!page) {
+		unlock_cluster(ci);
 		spin_unlock(&si->lock);
 		return -ENOMEM;
 	}
@@ -2858,6 +3169,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	list_add_tail(&page->lru, &head->lru);
 	page = NULL;			/* now it's attached, don't free it */
 out:
+	unlock_cluster(ci);
 	spin_unlock(&si->lock);
 outer:
 	if (page)
@@ -2871,7 +3183,8 @@ outer:
  * into, carry if so, or else fail until a new continuation page is allocated;
  * when the original swap_map count is decremented from 0 with continuation,
  * borrow from the continuation and report whether it still holds more.
- * Called while __swap_duplicate() or swap_entry_free() holds swap_lock.
+ * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster
+ * lock.
  */
 static bool swap_count_continued(struct swap_info_struct *si,
 				 pgoff_t offset, unsigned char count)
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index af817e5060fb..cf4345603490 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -14,6 +14,9 @@
 #include <linux/swapops.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/mmu_notifier.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/shmem_fs.h>
 #include <asm/tlbflush.h>
 #include "internal.h"
 
@@ -139,6 +142,200 @@ static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
 	return pmd;
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * __mcopy_atomic processing for HUGETLB vmas.  Note that this routine is
+ * called with mmap_sem held, it will release mmap_sem before returning.
+ */
+static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
+					      struct vm_area_struct *dst_vma,
+					      unsigned long dst_start,
+					      unsigned long src_start,
+					      unsigned long len,
+					      bool zeropage)
+{
+	ssize_t err;
+	pte_t *dst_pte;
+	unsigned long src_addr, dst_addr;
+	long copied;
+	struct page *page;
+	struct hstate *h;
+	unsigned long vma_hpagesize;
+	pgoff_t idx;
+	u32 hash;
+	struct address_space *mapping;
+
+	/*
+	 * There is no default zero huge page for all huge page sizes as
+	 * supported by hugetlb.  A PMD_SIZE huge pages may exist as used
+	 * by THP.  Since we can not reliably insert a zero page, this
+	 * feature is not supported.
+	 */
+	if (zeropage) {
+		up_read(&dst_mm->mmap_sem);
+		return -EINVAL;
+	}
+
+	src_addr = src_start;
+	dst_addr = dst_start;
+	copied = 0;
+	page = NULL;
+	vma_hpagesize = vma_kernel_pagesize(dst_vma);
+
+	/*
+	 * Validate alignment based on huge page size
+	 */
+	err = -EINVAL;
+	if (dst_start & (vma_hpagesize - 1) || len & (vma_hpagesize - 1))
+		goto out_unlock;
+
+retry:
+	/*
+	 * On routine entry dst_vma is set.  If we had to drop mmap_sem and
+	 * retry, dst_vma will be set to NULL and we must lookup again.
+	 */
+	if (!dst_vma) {
+		err = -ENOENT;
+		dst_vma = find_vma(dst_mm, dst_start);
+		if (!dst_vma || !is_vm_hugetlb_page(dst_vma))
+			goto out_unlock;
+		/*
+		 * Only allow __mcopy_atomic_hugetlb on userfaultfd
+		 * registered ranges.
+		 */
+		if (!dst_vma->vm_userfaultfd_ctx.ctx)
+			goto out_unlock;
+
+		if (dst_start < dst_vma->vm_start ||
+		    dst_start + len > dst_vma->vm_end)
+			goto out_unlock;
+
+		err = -EINVAL;
+		if (vma_hpagesize != vma_kernel_pagesize(dst_vma))
+			goto out_unlock;
+
+		/*
+		 * Make sure the vma is not shared, that the remaining dst
+		 * range is both valid and fully within a single existing vma.
+		 */
+		if (dst_vma->vm_flags & VM_SHARED)
+			goto out_unlock;
+	}
+
+	if (WARN_ON(dst_addr & (vma_hpagesize - 1) ||
+		    (len - copied) & (vma_hpagesize - 1)))
+		goto out_unlock;
+
+	/*
+	 * Ensure the dst_vma has a anon_vma.
+	 */
+	err = -ENOMEM;
+	if (unlikely(anon_vma_prepare(dst_vma)))
+		goto out_unlock;
+
+	h = hstate_vma(dst_vma);
+
+	while (src_addr < src_start + len) {
+		pte_t dst_pteval;
+
+		BUG_ON(dst_addr >= dst_start + len);
+		VM_BUG_ON(dst_addr & ~huge_page_mask(h));
+
+		/*
+		 * Serialize via hugetlb_fault_mutex
+		 */
+		idx = linear_page_index(dst_vma, dst_addr);
+		mapping = dst_vma->vm_file->f_mapping;
+		hash = hugetlb_fault_mutex_hash(h, dst_mm, dst_vma, mapping,
+								idx, dst_addr);
+		mutex_lock(&hugetlb_fault_mutex_table[hash]);
+
+		err = -ENOMEM;
+		dst_pte = huge_pte_alloc(dst_mm, dst_addr, huge_page_size(h));
+		if (!dst_pte) {
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			goto out_unlock;
+		}
+
+		err = -EEXIST;
+		dst_pteval = huge_ptep_get(dst_pte);
+		if (!huge_pte_none(dst_pteval)) {
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			goto out_unlock;
+		}
+
+		err = hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma,
+						dst_addr, src_addr, &page);
+
+		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+
+		cond_resched();
+
+		if (unlikely(err == -EFAULT)) {
+			up_read(&dst_mm->mmap_sem);
+			BUG_ON(!page);
+
+			err = copy_huge_page_from_user(page,
+						(const void __user *)src_addr,
+						pages_per_huge_page(h), true);
+			if (unlikely(err)) {
+				err = -EFAULT;
+				goto out;
+			}
+			down_read(&dst_mm->mmap_sem);
+
+			dst_vma = NULL;
+			goto retry;
+		} else
+			BUG_ON(page);
+
+		if (!err) {
+			dst_addr += vma_hpagesize;
+			src_addr += vma_hpagesize;
+			copied += vma_hpagesize;
+
+			if (fatal_signal_pending(current))
+				err = -EINTR;
+		}
+		if (err)
+			break;
+	}
+
+out_unlock:
+	up_read(&dst_mm->mmap_sem);
+out:
+	if (page) {
+		/*
+		 * We encountered an error and are about to free a newly
+		 * allocated huge page.  It is possible that there was a
+		 * reservation associated with the page that has been
+		 * consumed.  See the routine restore_reserve_on_error
+		 * for details.  Unfortunately, we can not call
+		 * restore_reserve_on_error now as it would require holding
+		 * mmap_sem.  Clear the PagePrivate flag so that the global
+		 * reserve count will not be incremented in free_huge_page.
+		 * The reservation map will still indicate the reservation
+		 * was consumed and possibly prevent later page allocation.
+		 * This is better than leaking a global reservation.
+		 */
+		ClearPagePrivate(page);
+		put_page(page);
+	}
+	BUG_ON(copied < 0);
+	BUG_ON(err > 0);
+	BUG_ON(!copied && !err);
+	return copied ? copied : err;
+}
+#else /* !CONFIG_HUGETLB_PAGE */
+/* fail at build time if gcc attempts to use this */
+extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
+				      struct vm_area_struct *dst_vma,
+				      unsigned long dst_start,
+				      unsigned long src_start,
+				      unsigned long len,
+				      bool zeropage);
+#endif /* CONFIG_HUGETLB_PAGE */
+
 static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 					      unsigned long dst_start,
 					      unsigned long src_start,
@@ -173,14 +370,10 @@ retry:
 	 * Make sure the vma is not shared, that the dst range is
 	 * both valid and fully within a single existing vma.
 	 */
-	err = -EINVAL;
+	err = -ENOENT;
 	dst_vma = find_vma(dst_mm, dst_start);
-	if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
+	if (!dst_vma)
 		goto out_unlock;
-	if (dst_start < dst_vma->vm_start ||
-	    dst_start + len > dst_vma->vm_end)
-		goto out_unlock;
-
 	/*
 	 * Be strict and only allow __mcopy_atomic on userfaultfd
 	 * registered ranges to prevent userland errors going
@@ -193,11 +386,22 @@ retry:
 	if (!dst_vma->vm_userfaultfd_ctx.ctx)
 		goto out_unlock;
 
+	if (dst_start < dst_vma->vm_start ||
+	    dst_start + len > dst_vma->vm_end)
+		goto out_unlock;
+
+	err = -EINVAL;
+	if (!vma_is_shmem(dst_vma) && dst_vma->vm_flags & VM_SHARED)
+		goto out_unlock;
+
 	/*
-	 * FIXME: only allow copying on anonymous vmas, tmpfs should
-	 * be added.
+	 * If this is a HUGETLB vma, pass off to appropriate routine
 	 */
-	if (dst_vma->vm_ops)
+	if (is_vm_hugetlb_page(dst_vma))
+		return  __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start,
+						src_start, len, zeropage);
+
+	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
 		goto out_unlock;
 
 	/*
@@ -206,7 +410,7 @@ retry:
 	 * dst_vma.
 	 */
 	err = -ENOMEM;
-	if (unlikely(anon_vma_prepare(dst_vma)))
+	if (vma_is_anonymous(dst_vma) && unlikely(anon_vma_prepare(dst_vma)))
 		goto out_unlock;
 
 	while (src_addr < src_start + len) {
@@ -243,12 +447,21 @@ retry:
 		BUG_ON(pmd_none(*dst_pmd));
 		BUG_ON(pmd_trans_huge(*dst_pmd));
 
-		if (!zeropage)
-			err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
-					       dst_addr, src_addr, &page);
-		else
-			err = mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma,
-						 dst_addr);
+		if (vma_is_anonymous(dst_vma)) {
+			if (!zeropage)
+				err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
+						       dst_addr, src_addr,
+						       &page);
+			else
+				err = mfill_zeropage_pte(dst_mm, dst_pmd,
+							 dst_vma, dst_addr);
+		} else {
+			err = -EINVAL; /* if zeropage is true return -EINVAL */
+			if (likely(!zeropage))
+				err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd,
+							     dst_vma, dst_addr,
+							     src_addr, &page);
+		}
 
 		cond_resched();
 
diff --git a/mm/util.c b/mm/util.c
index e91250dabf49..69bf18206e08 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -11,6 +11,7 @@
 #include <linux/mman.h>
 #include <linux/hugetlb.h>
 #include <linux/vmalloc.h>
+#include <linux/userfaultfd_k.h>
 
 #include <asm/sections.h>
 #include <linux/uaccess.h>
@@ -297,14 +298,16 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
 	unsigned long ret;
 	struct mm_struct *mm = current->mm;
 	unsigned long populate;
+	LIST_HEAD(uf);
 
 	ret = security_mmap_file(file, prot, flag);
 	if (!ret) {
 		if (down_write_killable(&mm->mmap_sem))
 			return -EINTR;
 		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
-				    &populate);
+				    &populate, &uf);
 		up_write(&mm->mmap_sem);
+		userfaultfd_unmap_complete(mm, &uf);
 		if (populate)
 			mm_populate(ret, populate);
 	}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3ca82d44edd3..011b446f8758 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1642,6 +1642,11 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	for (i = 0; i < area->nr_pages; i++) {
 		struct page *page;
 
+		if (fatal_signal_pending(current)) {
+			area->nr_pages = i;
+			goto fail;
+		}
+
 		if (node == NUMA_NO_NODE)
 			page = alloc_page(alloc_mask);
 		else
@@ -1662,7 +1667,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	return area->addr;
 
 fail:
-	warn_alloc(gfp_mask,
+	warn_alloc(gfp_mask, NULL,
 			  "vmalloc: allocation failure, allocated %ld of %ld bytes",
 			  (area->nr_pages*PAGE_SIZE), area->size);
 	vfree(area->addr);
@@ -1724,7 +1729,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	return addr;
 
 fail:
-	warn_alloc(gfp_mask,
+	warn_alloc(gfp_mask, NULL,
 			  "vmalloc: allocation failure: %lu bytes", real_size);
 	return NULL;
 }
@@ -2309,7 +2314,7 @@ EXPORT_SYMBOL_GPL(free_vm_area);
 #ifdef CONFIG_SMP
 static struct vmap_area *node_to_va(struct rb_node *n)
 {
-	return n ? rb_entry(n, struct vmap_area, rb_node) : NULL;
+	return rb_entry_safe(n, struct vmap_area, rb_node);
 }
 
 /**
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 532a2a750952..26c3b405ef34 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -87,6 +87,7 @@ struct scan_control {
 	/* The highest zone to isolate pages for reclaim from */
 	enum zone_type reclaim_idx;
 
+	/* Writepage batching in laptop mode; RECLAIM_WRITE */
 	unsigned int may_writepage:1;
 
 	/* Can mapped pages be reclaimed? */
@@ -234,22 +235,39 @@ bool pgdat_reclaimable(struct pglist_data *pgdat)
 		pgdat_reclaimable_pages(pgdat) * 6;
 }
 
-unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
+/**
+ * lruvec_lru_size -  Returns the number of pages on the given LRU list.
+ * @lruvec: lru vector
+ * @lru: lru to use
+ * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list)
+ */
+unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx)
 {
+	unsigned long lru_size;
+	int zid;
+
 	if (!mem_cgroup_disabled())
-		return mem_cgroup_get_lru_size(lruvec, lru);
+		lru_size = mem_cgroup_get_lru_size(lruvec, lru);
+	else
+		lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
 
-	return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
-}
+	for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) {
+		struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid];
+		unsigned long size;
 
-unsigned long lruvec_zone_lru_size(struct lruvec *lruvec, enum lru_list lru,
-				   int zone_idx)
-{
-	if (!mem_cgroup_disabled())
-		return mem_cgroup_get_zone_lru_size(lruvec, lru, zone_idx);
+		if (!managed_zone(zone))
+			continue;
+
+		if (!mem_cgroup_disabled())
+			size = mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
+		else
+			size = zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zid],
+				       NR_ZONE_LRU_BASE + lru);
+		lru_size -= min(size, lru_size);
+	}
+
+	return lru_size;
 
-	return zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zone_idx],
-			       NR_ZONE_LRU_BASE + lru);
 }
 
 /*
@@ -912,6 +930,17 @@ static void page_check_dirty_writeback(struct page *page,
 		mapping->a_ops->is_dirty_writeback(page, dirty, writeback);
 }
 
+struct reclaim_stat {
+	unsigned nr_dirty;
+	unsigned nr_unqueued_dirty;
+	unsigned nr_congested;
+	unsigned nr_writeback;
+	unsigned nr_immediate;
+	unsigned nr_activate;
+	unsigned nr_ref_keep;
+	unsigned nr_unmap_fail;
+};
+
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -919,22 +948,20 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				      struct pglist_data *pgdat,
 				      struct scan_control *sc,
 				      enum ttu_flags ttu_flags,
-				      unsigned long *ret_nr_dirty,
-				      unsigned long *ret_nr_unqueued_dirty,
-				      unsigned long *ret_nr_congested,
-				      unsigned long *ret_nr_writeback,
-				      unsigned long *ret_nr_immediate,
+				      struct reclaim_stat *stat,
 				      bool force_reclaim)
 {
 	LIST_HEAD(ret_pages);
 	LIST_HEAD(free_pages);
 	int pgactivate = 0;
-	unsigned long nr_unqueued_dirty = 0;
-	unsigned long nr_dirty = 0;
-	unsigned long nr_congested = 0;
-	unsigned long nr_reclaimed = 0;
-	unsigned long nr_writeback = 0;
-	unsigned long nr_immediate = 0;
+	unsigned nr_unqueued_dirty = 0;
+	unsigned nr_dirty = 0;
+	unsigned nr_congested = 0;
+	unsigned nr_reclaimed = 0;
+	unsigned nr_writeback = 0;
+	unsigned nr_immediate = 0;
+	unsigned nr_ref_keep = 0;
+	unsigned nr_unmap_fail = 0;
 
 	cond_resched();
 
@@ -1029,6 +1056,15 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 *    throttling so we could easily OOM just because too many
 		 *    pages are in writeback and there is nothing else to
 		 *    reclaim. Wait for the writeback to complete.
+		 *
+		 * In cases 1) and 2) we activate the pages to get them out of
+		 * the way while we continue scanning for clean pages on the
+		 * inactive list and refilling from the active list. The
+		 * observation here is that waiting for disk writes is more
+		 * expensive than potentially causing reloads down the line.
+		 * Since they're marked for immediate reclaim, they won't put
+		 * memory pressure on the cache working set any longer than it
+		 * takes to write them to disk.
 		 */
 		if (PageWriteback(page)) {
 			/* Case 1 above */
@@ -1036,7 +1072,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			    PageReclaim(page) &&
 			    test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {
 				nr_immediate++;
-				goto keep_locked;
+				goto activate_locked;
 
 			/* Case 2 above */
 			} else if (sane_reclaim(sc) ||
@@ -1054,7 +1090,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				 */
 				SetPageReclaim(page);
 				nr_writeback++;
-				goto keep_locked;
+				goto activate_locked;
 
 			/* Case 3 above */
 			} else {
@@ -1073,6 +1109,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		case PAGEREF_ACTIVATE:
 			goto activate_locked;
 		case PAGEREF_KEEP:
+			nr_ref_keep++;
 			goto keep_locked;
 		case PAGEREF_RECLAIM:
 		case PAGEREF_RECLAIM_CLEAN:
@@ -1110,6 +1147,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				(ttu_flags | TTU_BATCH_FLUSH | TTU_LZFREE) :
 				(ttu_flags | TTU_BATCH_FLUSH))) {
 			case SWAP_FAIL:
+				nr_unmap_fail++;
 				goto activate_locked;
 			case SWAP_AGAIN:
 				goto keep_locked;
@@ -1124,13 +1162,18 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 		if (PageDirty(page)) {
 			/*
-			 * Only kswapd can writeback filesystem pages to
-			 * avoid risk of stack overflow but only writeback
-			 * if many dirty pages have been encountered.
+			 * Only kswapd can writeback filesystem pages
+			 * to avoid risk of stack overflow. But avoid
+			 * injecting inefficient single-page IO into
+			 * flusher writeback as much as possible: only
+			 * write pages when we've encountered many
+			 * dirty pages, and when we've already scanned
+			 * the rest of the LRU for clean pages and see
+			 * the same dirty pages again (PageReclaim).
 			 */
 			if (page_is_file_cache(page) &&
-					(!current_is_kswapd() ||
-					 !test_bit(PGDAT_DIRTY, &pgdat->flags))) {
+			    (!current_is_kswapd() || !PageReclaim(page) ||
+			     !test_bit(PGDAT_DIRTY, &pgdat->flags))) {
 				/*
 				 * Immediately reclaim when written back.
 				 * Similar in principal to deactivate_page()
@@ -1140,7 +1183,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				inc_node_page_state(page, NR_VMSCAN_IMMEDIATE);
 				SetPageReclaim(page);
 
-				goto keep_locked;
+				goto activate_locked;
 			}
 
 			if (references == PAGEREF_RECLAIM_CLEAN)
@@ -1276,11 +1319,16 @@ keep:
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
 
-	*ret_nr_dirty += nr_dirty;
-	*ret_nr_congested += nr_congested;
-	*ret_nr_unqueued_dirty += nr_unqueued_dirty;
-	*ret_nr_writeback += nr_writeback;
-	*ret_nr_immediate += nr_immediate;
+	if (stat) {
+		stat->nr_dirty = nr_dirty;
+		stat->nr_congested = nr_congested;
+		stat->nr_unqueued_dirty = nr_unqueued_dirty;
+		stat->nr_writeback = nr_writeback;
+		stat->nr_immediate = nr_immediate;
+		stat->nr_activate = pgactivate;
+		stat->nr_ref_keep = nr_ref_keep;
+		stat->nr_unmap_fail = nr_unmap_fail;
+	}
 	return nr_reclaimed;
 }
 
@@ -1292,7 +1340,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 		.priority = DEF_PRIORITY,
 		.may_unmap = 1,
 	};
-	unsigned long ret, dummy1, dummy2, dummy3, dummy4, dummy5;
+	unsigned long ret;
 	struct page *page, *next;
 	LIST_HEAD(clean_pages);
 
@@ -1305,8 +1353,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 	}
 
 	ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
-			TTU_UNMAP|TTU_IGNORE_ACCESS,
-			&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
+			TTU_UNMAP|TTU_IGNORE_ACCESS, NULL, true);
 	list_splice(&clean_pages, page_list);
 	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret);
 	return ret;
@@ -1341,13 +1388,10 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 	 * wants to isolate pages it will be able to operate on without
 	 * blocking - clean pages for the most part.
 	 *
-	 * ISOLATE_CLEAN means that only clean pages should be isolated. This
-	 * is used by reclaim when it is cannot write to backing storage
-	 *
 	 * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages
 	 * that it is possible to migrate without blocking
 	 */
-	if (mode & (ISOLATE_CLEAN|ISOLATE_ASYNC_MIGRATE)) {
+	if (mode & ISOLATE_ASYNC_MIGRATE) {
 		/* All the caller can do on PageWriteback is block */
 		if (PageWriteback(page))
 			return ret;
@@ -1355,10 +1399,6 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 		if (PageDirty(page)) {
 			struct address_space *mapping;
 
-			/* ISOLATE_CLEAN means only clean pages */
-			if (mode & ISOLATE_CLEAN)
-				return ret;
-
 			/*
 			 * Only pages without mappings or that have a
 			 * ->migratepage callback are possible to migrate
@@ -1437,6 +1477,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	unsigned long nr_taken = 0;
 	unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
 	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
+	unsigned long skipped = 0, total_skipped = 0;
 	unsigned long scan, nr_pages;
 	LIST_HEAD(pages_skipped);
 
@@ -1488,14 +1529,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	 */
 	if (!list_empty(&pages_skipped)) {
 		int zid;
-		unsigned long total_skipped = 0;
 
 		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 			if (!nr_skipped[zid])
 				continue;
 
 			__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
-			total_skipped += nr_skipped[zid];
+			skipped += nr_skipped[zid];
 		}
 
 		/*
@@ -1503,13 +1543,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		 * close to unreclaimable. If the LRU list is empty, account
 		 * skipped pages as a full scan.
 		 */
-		scan += list_empty(src) ? total_skipped : total_skipped >> 2;
+		total_skipped = list_empty(src) ? skipped : skipped >> 2;
 
 		list_splice(&pages_skipped, src);
 	}
-	*nr_scanned = scan;
-	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
-				    nr_taken, mode, is_file_lru(lru));
+	*nr_scanned = scan + total_skipped;
+	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
+				    scan, skipped, nr_taken, mode, lru);
 	update_lru_sizes(lruvec, lru, nr_zone_taken);
 	return nr_taken;
 }
@@ -1669,30 +1709,6 @@ static int current_may_throttle(void)
 		bdi_write_congested(current->backing_dev_info);
 }
 
-static bool inactive_reclaimable_pages(struct lruvec *lruvec,
-				struct scan_control *sc, enum lru_list lru)
-{
-	int zid;
-	struct zone *zone;
-	int file = is_file_lru(lru);
-	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-
-	if (!global_reclaim(sc))
-		return true;
-
-	for (zid = sc->reclaim_idx; zid >= 0; zid--) {
-		zone = &pgdat->node_zones[zid];
-		if (!managed_zone(zone))
-			continue;
-
-		if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE +
-				LRU_FILE * file) >= SWAP_CLUSTER_MAX)
-			return true;
-	}
-
-	return false;
-}
-
 /*
  * shrink_inactive_list() is a helper for shrink_node().  It returns the number
  * of reclaimed pages
@@ -1705,19 +1721,12 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	unsigned long nr_scanned;
 	unsigned long nr_reclaimed = 0;
 	unsigned long nr_taken;
-	unsigned long nr_dirty = 0;
-	unsigned long nr_congested = 0;
-	unsigned long nr_unqueued_dirty = 0;
-	unsigned long nr_writeback = 0;
-	unsigned long nr_immediate = 0;
+	struct reclaim_stat stat = {};
 	isolate_mode_t isolate_mode = 0;
 	int file = is_file_lru(lru);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
 
-	if (!inactive_reclaimable_pages(lruvec, sc, lru))
-		return 0;
-
 	while (unlikely(too_many_isolated(pgdat, file, sc))) {
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
 
@@ -1730,8 +1739,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	if (!sc->may_unmap)
 		isolate_mode |= ISOLATE_UNMAPPED;
-	if (!sc->may_writepage)
-		isolate_mode |= ISOLATE_CLEAN;
 
 	spin_lock_irq(&pgdat->lru_lock);
 
@@ -1754,9 +1761,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		return 0;
 
 	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, TTU_UNMAP,
-				&nr_dirty, &nr_unqueued_dirty, &nr_congested,
-				&nr_writeback, &nr_immediate,
-				false);
+				&stat, false);
 
 	spin_lock_irq(&pgdat->lru_lock);
 
@@ -1790,7 +1795,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	 * of pages under pages flagged for immediate reclaim and stall if any
 	 * are encountered in the nr_immediate check below.
 	 */
-	if (nr_writeback && nr_writeback == nr_taken)
+	if (stat.nr_writeback && stat.nr_writeback == nr_taken)
 		set_bit(PGDAT_WRITEBACK, &pgdat->flags);
 
 	/*
@@ -1802,17 +1807,25 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		 * Tag a zone as congested if all the dirty pages scanned were
 		 * backed by a congested BDI and wait_iff_congested will stall.
 		 */
-		if (nr_dirty && nr_dirty == nr_congested)
+		if (stat.nr_dirty && stat.nr_dirty == stat.nr_congested)
 			set_bit(PGDAT_CONGESTED, &pgdat->flags);
 
 		/*
 		 * If dirty pages are scanned that are not queued for IO, it
-		 * implies that flushers are not keeping up. In this case, flag
-		 * the pgdat PGDAT_DIRTY and kswapd will start writing pages from
-		 * reclaim context.
+		 * implies that flushers are not doing their job. This can
+		 * happen when memory pressure pushes dirty pages to the end of
+		 * the LRU before the dirty limits are breached and the dirty
+		 * data has expired. It can also happen when the proportion of
+		 * dirty pages grows not through writes but through memory
+		 * pressure reclaiming all the clean cache. And in some cases,
+		 * the flushers simply cannot keep up with the allocation
+		 * rate. Nudge the flusher threads in case they are asleep, but
+		 * also allow kswapd to start writing pages during reclaim.
 		 */
-		if (nr_unqueued_dirty == nr_taken)
+		if (stat.nr_unqueued_dirty == nr_taken) {
+			wakeup_flusher_threads(0, WB_REASON_VMSCAN);
 			set_bit(PGDAT_DIRTY, &pgdat->flags);
+		}
 
 		/*
 		 * If kswapd scans pages marked marked for immediate
@@ -1820,7 +1833,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		 * that pages are cycling through the LRU faster than
 		 * they are written so also forcibly stall.
 		 */
-		if (nr_immediate && current_may_throttle())
+		if (stat.nr_immediate && current_may_throttle())
 			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 
@@ -1835,6 +1848,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
 			nr_scanned, nr_reclaimed,
+			stat.nr_dirty,  stat.nr_writeback,
+			stat.nr_congested, stat.nr_immediate,
+			stat.nr_activate, stat.nr_ref_keep,
+			stat.nr_unmap_fail,
 			sc->priority, file);
 	return nr_reclaimed;
 }
@@ -1855,17 +1872,19 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
  *
  * The downside is that we have to touch page->_refcount against each page.
  * But we had to alter page->flags anyway.
+ *
+ * Returns the number of pages moved to the given lru.
  */
 
-static void move_active_pages_to_lru(struct lruvec *lruvec,
+static unsigned move_active_pages_to_lru(struct lruvec *lruvec,
 				     struct list_head *list,
 				     struct list_head *pages_to_free,
 				     enum lru_list lru)
 {
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-	unsigned long pgmoved = 0;
 	struct page *page;
 	int nr_pages;
+	int nr_moved = 0;
 
 	while (!list_empty(list)) {
 		page = lru_to_page(list);
@@ -1877,7 +1896,6 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
 		nr_pages = hpage_nr_pages(page);
 		update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
 		list_move(&page->lru, &lruvec->lists[lru]);
-		pgmoved += nr_pages;
 
 		if (put_page_testzero(page)) {
 			__ClearPageLRU(page);
@@ -1891,11 +1909,15 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
 				spin_lock_irq(&pgdat->lru_lock);
 			} else
 				list_add(&page->lru, pages_to_free);
+		} else {
+			nr_moved += nr_pages;
 		}
 	}
 
 	if (!is_active_lru(lru))
-		__count_vm_events(PGDEACTIVATE, pgmoved);
+		__count_vm_events(PGDEACTIVATE, nr_moved);
+
+	return nr_moved;
 }
 
 static void shrink_active_list(unsigned long nr_to_scan,
@@ -1911,7 +1933,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	LIST_HEAD(l_inactive);
 	struct page *page;
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
-	unsigned long nr_rotated = 0;
+	unsigned nr_deactivate, nr_activate;
+	unsigned nr_rotated = 0;
 	isolate_mode_t isolate_mode = 0;
 	int file = is_file_lru(lru);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
@@ -1920,8 +1943,6 @@ static void shrink_active_list(unsigned long nr_to_scan,
 
 	if (!sc->may_unmap)
 		isolate_mode |= ISOLATE_UNMAPPED;
-	if (!sc->may_writepage)
-		isolate_mode |= ISOLATE_CLEAN;
 
 	spin_lock_irq(&pgdat->lru_lock);
 
@@ -1989,13 +2010,15 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	 */
 	reclaim_stat->recent_rotated[file] += nr_rotated;
 
-	move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
-	move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
+	nr_activate = move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
+	nr_deactivate = move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
 	spin_unlock_irq(&pgdat->lru_lock);
 
 	mem_cgroup_uncharge_list(&l_hold);
 	free_hot_cold_page_list(&l_hold, true);
+	trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
+			nr_deactivate, nr_rotated, sc->priority, file);
 }
 
 /*
@@ -2025,14 +2048,13 @@ static void shrink_active_list(unsigned long nr_to_scan,
  *   10TB     320        32GB
  */
 static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
-						struct scan_control *sc)
+						struct scan_control *sc, bool trace)
 {
 	unsigned long inactive_ratio;
-	unsigned long inactive;
-	unsigned long active;
+	unsigned long inactive, active;
+	enum lru_list inactive_lru = file * LRU_FILE;
+	enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
 	unsigned long gb;
-	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-	int zid;
 
 	/*
 	 * If we don't have swap space, anonymous page deactivation
@@ -2041,27 +2063,8 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 	if (!file && !total_swap_pages)
 		return false;
 
-	inactive = lruvec_lru_size(lruvec, file * LRU_FILE);
-	active = lruvec_lru_size(lruvec, file * LRU_FILE + LRU_ACTIVE);
-
-	/*
-	 * For zone-constrained allocations, it is necessary to check if
-	 * deactivations are required for lowmem to be reclaimed. This
-	 * calculates the inactive/active pages available in eligible zones.
-	 */
-	for (zid = sc->reclaim_idx + 1; zid < MAX_NR_ZONES; zid++) {
-		struct zone *zone = &pgdat->node_zones[zid];
-		unsigned long inactive_zone, active_zone;
-
-		if (!managed_zone(zone))
-			continue;
-
-		inactive_zone = lruvec_zone_lru_size(lruvec, file * LRU_FILE, zid);
-		active_zone = lruvec_zone_lru_size(lruvec, (file * LRU_FILE) + LRU_ACTIVE, zid);
-
-		inactive -= min(inactive, inactive_zone);
-		active -= min(active, active_zone);
-	}
+	inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
+	active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
 
 	gb = (inactive + active) >> (30 - PAGE_SHIFT);
 	if (gb)
@@ -2069,6 +2072,13 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 	else
 		inactive_ratio = 1;
 
+	if (trace)
+		trace_mm_vmscan_inactive_list_is_low(lruvec_pgdat(lruvec)->node_id,
+				sc->reclaim_idx,
+				lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive,
+				lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active,
+				inactive_ratio, file);
+
 	return inactive * inactive_ratio < active;
 }
 
@@ -2076,7 +2086,7 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 				 struct lruvec *lruvec, struct scan_control *sc)
 {
 	if (is_active_lru(lru)) {
-		if (inactive_list_is_low(lruvec, is_file_lru(lru), sc))
+		if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true))
 			shrink_active_list(nr_to_scan, lruvec, sc, lru);
 		return 0;
 	}
@@ -2207,8 +2217,8 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * lruvec even if it has plenty of old anonymous pages unless the
 	 * system is under heavy pressure.
 	 */
-	if (!inactive_list_is_low(lruvec, true, sc) &&
-	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) {
+	if (!inactive_list_is_low(lruvec, true, sc, false) &&
+	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
 		scan_balance = SCAN_FILE;
 		goto out;
 	}
@@ -2234,10 +2244,10 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * anon in [0], file in [1]
 	 */
 
-	anon  = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON) +
-		lruvec_lru_size(lruvec, LRU_INACTIVE_ANON);
-	file  = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) +
-		lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
+	anon  = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) +
+		lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES);
+	file  = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
+		lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES);
 
 	spin_lock_irq(&pgdat->lru_lock);
 	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
@@ -2275,7 +2285,7 @@ out:
 			unsigned long size;
 			unsigned long scan;
 
-			size = lruvec_lru_size(lruvec, lru);
+			size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
 			scan = size >> sc->priority;
 
 			if (!scan && pass && force_scan)
@@ -2432,7 +2442,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (inactive_list_is_low(lruvec, false, sc))
+	if (inactive_list_is_low(lruvec, false, sc, true))
 		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 				   sc, LRU_ACTIVE_ANON);
 }
@@ -2593,16 +2603,23 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 				    sc->nr_scanned - nr_scanned,
 				    node_lru_pages);
 
+		/*
+		 * Record the subtree's reclaim efficiency. The reclaimed
+		 * pages from slab is excluded here because the corresponding
+		 * scanned pages is not accounted. Moreover, freeing a page
+		 * by slab shrinking depends on each slab's object population,
+		 * making the cost model (i.e. scan:free) different from that
+		 * of LRU.
+		 */
+		vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
+			   sc->nr_scanned - nr_scanned,
+			   sc->nr_reclaimed - nr_reclaimed);
+
 		if (reclaim_state) {
 			sc->nr_reclaimed += reclaim_state->reclaimed_slab;
 			reclaim_state->reclaimed_slab = 0;
 		}
 
-		/* Record the subtree's reclaim efficiency */
-		vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
-			   sc->nr_scanned - nr_scanned,
-			   sc->nr_reclaimed - nr_reclaimed);
-
 		if (sc->nr_reclaimed - nr_reclaimed)
 			reclaimable = true;
 
@@ -2761,8 +2778,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 					  struct scan_control *sc)
 {
 	int initial_priority = sc->priority;
-	unsigned long total_scanned = 0;
-	unsigned long writeback_threshold;
 retry:
 	delayacct_freepages_start();
 
@@ -2775,7 +2790,6 @@ retry:
 		sc->nr_scanned = 0;
 		shrink_zones(zonelist, sc);
 
-		total_scanned += sc->nr_scanned;
 		if (sc->nr_reclaimed >= sc->nr_to_reclaim)
 			break;
 
@@ -2788,20 +2802,6 @@ retry:
 		 */
 		if (sc->priority < DEF_PRIORITY - 2)
 			sc->may_writepage = 1;
-
-		/*
-		 * Try to write back as many pages as we just scanned.  This
-		 * tends to cause slow streaming writers to write data to the
-		 * disk smoothly, at the dirtying rate, which is nice.   But
-		 * that's undesirable in laptop mode, where we *want* lumpy
-		 * writeout.  So in laptop mode, write out the whole world.
-		 */
-		writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2;
-		if (total_scanned > writeback_threshold) {
-			wakeup_flusher_threads(laptop_mode ? 0 : total_scanned,
-						WB_REASON_TRY_TO_FREE_PAGES);
-			sc->may_writepage = 1;
-		}
 	} while (--sc->priority >= 0);
 
 	delayacct_freepages_end();
@@ -3082,7 +3082,7 @@ static void age_active_anon(struct pglist_data *pgdat,
 	do {
 		struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
 
-		if (inactive_list_is_low(lruvec, false, sc))
+		if (inactive_list_is_low(lruvec, false, sc, true))
 			shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 					   sc, LRU_ACTIVE_ANON);
 
@@ -3103,6 +3103,7 @@ static bool zone_balanced(struct zone *zone, int order, int classzone_idx)
 	 */
 	clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags);
 	clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags);
+	clear_bit(PGDAT_WRITEBACK, &zone->zone_pgdat->flags);
 
 	return true;
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 7c28df36f50f..69f9aff39a2e 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1038,6 +1038,8 @@ const char * const vmstat_text[] = {
 	"compact_fail",
 	"compact_success",
 	"compact_daemon_wake",
+	"compact_daemon_migrate_scanned",
+	"compact_daemon_free_scanned",
 #endif
 
 #ifdef CONFIG_HUGETLB_PAGE
diff --git a/mm/workingset.c b/mm/workingset.c
index 80c913c89f11..c573cb24d1c5 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -267,7 +267,7 @@ bool workingset_refault(void *shadow)
 	}
 	lruvec = mem_cgroup_lruvec(pgdat, memcg);
 	refault = atomic_long_read(&lruvec->inactive_age);
-	active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE);
+	active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES);
 	rcu_read_unlock();
 
 	/*
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 8f9e89ca1d31..8970a2fd3b1a 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -34,28 +34,61 @@
 /*****************
  * Structures
 *****************/
+struct z3fold_pool;
+struct z3fold_ops {
+	int (*evict)(struct z3fold_pool *pool, unsigned long handle);
+};
+
+enum buddy {
+	HEADLESS = 0,
+	FIRST,
+	MIDDLE,
+	LAST,
+	BUDDIES_MAX
+};
+
+/*
+ * struct z3fold_header - z3fold page metadata occupying the first chunk of each
+ *			z3fold page, except for HEADLESS pages
+ * @buddy:	links the z3fold page into the relevant list in the pool
+ * @page_lock:		per-page lock
+ * @refcount:		reference cound for the z3fold page
+ * @first_chunks:	the size of the first buddy in chunks, 0 if free
+ * @middle_chunks:	the size of the middle buddy in chunks, 0 if free
+ * @last_chunks:	the size of the last buddy in chunks, 0 if free
+ * @first_num:		the starting number (for the first handle)
+ */
+struct z3fold_header {
+	struct list_head buddy;
+	spinlock_t page_lock;
+	struct kref refcount;
+	unsigned short first_chunks;
+	unsigned short middle_chunks;
+	unsigned short last_chunks;
+	unsigned short start_middle;
+	unsigned short first_num:2;
+};
+
 /*
  * NCHUNKS_ORDER determines the internal allocation granularity, effectively
  * adjusting internal fragmentation.  It also determines the number of
  * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the
- * allocation granularity will be in chunks of size PAGE_SIZE/64. As one chunk
- * in allocated page is occupied by z3fold header, NCHUNKS will be calculated
- * to 63 which shows the max number of free chunks in z3fold page, also there
- * will be 63 freelists per pool.
+ * allocation granularity will be in chunks of size PAGE_SIZE/64. Some chunks
+ * in the beginning of an allocated page are occupied by z3fold header, so
+ * NCHUNKS will be calculated to 63 (or 62 in case CONFIG_DEBUG_SPINLOCK=y),
+ * which shows the max number of free chunks in z3fold page, also there will
+ * be 63, or 62, respectively, freelists per pool.
  */
 #define NCHUNKS_ORDER	6
 
 #define CHUNK_SHIFT	(PAGE_SHIFT - NCHUNKS_ORDER)
 #define CHUNK_SIZE	(1 << CHUNK_SHIFT)
-#define ZHDR_SIZE_ALIGNED CHUNK_SIZE
+#define ZHDR_SIZE_ALIGNED round_up(sizeof(struct z3fold_header), CHUNK_SIZE)
+#define ZHDR_CHUNKS	(ZHDR_SIZE_ALIGNED >> CHUNK_SHIFT)
+#define TOTAL_CHUNKS	(PAGE_SIZE >> CHUNK_SHIFT)
 #define NCHUNKS		((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT)
 
-#define BUDDY_MASK	((1 << NCHUNKS_ORDER) - 1)
-
-struct z3fold_pool;
-struct z3fold_ops {
-	int (*evict)(struct z3fold_pool *pool, unsigned long handle);
-};
+#define BUDDY_MASK	(0x3)
 
 /**
  * struct z3fold_pool - stores metadata for each z3fold pool
@@ -64,8 +97,6 @@ struct z3fold_ops {
  * @unbuddied:	array of lists tracking z3fold pages that contain 2- buddies;
  *		the lists each z3fold page is added to depends on the size of
  *		its free region.
- * @buddied:	list tracking the z3fold pages that contain 3 buddies;
- *		these z3fold pages are full
  * @lru:	list tracking the z3fold pages in LRU order by most recently
  *		added buddy.
  * @pages_nr:	number of z3fold pages in the pool.
@@ -78,49 +109,22 @@ struct z3fold_ops {
 struct z3fold_pool {
 	spinlock_t lock;
 	struct list_head unbuddied[NCHUNKS];
-	struct list_head buddied;
 	struct list_head lru;
-	u64 pages_nr;
+	atomic64_t pages_nr;
 	const struct z3fold_ops *ops;
 	struct zpool *zpool;
 	const struct zpool_ops *zpool_ops;
 };
 
-enum buddy {
-	HEADLESS = 0,
-	FIRST,
-	MIDDLE,
-	LAST,
-	BUDDIES_MAX
-};
-
-/*
- * struct z3fold_header - z3fold page metadata occupying the first chunk of each
- *			z3fold page, except for HEADLESS pages
- * @buddy:	links the z3fold page into the relevant list in the pool
- * @first_chunks:	the size of the first buddy in chunks, 0 if free
- * @middle_chunks:	the size of the middle buddy in chunks, 0 if free
- * @last_chunks:	the size of the last buddy in chunks, 0 if free
- * @first_num:		the starting number (for the first handle)
- */
-struct z3fold_header {
-	struct list_head buddy;
-	unsigned short first_chunks;
-	unsigned short middle_chunks;
-	unsigned short last_chunks;
-	unsigned short start_middle;
-	unsigned short first_num:NCHUNKS_ORDER;
-};
-
 /*
  * Internal z3fold page flags
  */
 enum z3fold_page_flags {
-	UNDER_RECLAIM = 0,
-	PAGE_HEADLESS,
+	PAGE_HEADLESS = 0,
 	MIDDLE_CHUNK_MAPPED,
 };
 
+
 /*****************
  * Helpers
 *****************/
@@ -140,10 +144,11 @@ static struct z3fold_header *init_z3fold_page(struct page *page)
 	struct z3fold_header *zhdr = page_address(page);
 
 	INIT_LIST_HEAD(&page->lru);
-	clear_bit(UNDER_RECLAIM, &page->private);
 	clear_bit(PAGE_HEADLESS, &page->private);
 	clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
 
+	spin_lock_init(&zhdr->page_lock);
+	kref_init(&zhdr->refcount);
 	zhdr->first_chunks = 0;
 	zhdr->middle_chunks = 0;
 	zhdr->last_chunks = 0;
@@ -154,9 +159,36 @@ static struct z3fold_header *init_z3fold_page(struct page *page)
 }
 
 /* Resets the struct page fields and frees the page */
-static void free_z3fold_page(struct z3fold_header *zhdr)
+static void free_z3fold_page(struct page *page)
+{
+	__free_page(page);
+}
+
+static void release_z3fold_page(struct kref *ref)
+{
+	struct z3fold_header *zhdr;
+	struct page *page;
+
+	zhdr = container_of(ref, struct z3fold_header, refcount);
+	page = virt_to_page(zhdr);
+
+	if (!list_empty(&zhdr->buddy))
+		list_del(&zhdr->buddy);
+	if (!list_empty(&page->lru))
+		list_del(&page->lru);
+	free_z3fold_page(page);
+}
+
+/* Lock a z3fold page */
+static inline void z3fold_page_lock(struct z3fold_header *zhdr)
 {
-	__free_page(virt_to_page(zhdr));
+	spin_lock(&zhdr->page_lock);
+}
+
+/* Unlock a z3fold page */
+static inline void z3fold_page_unlock(struct z3fold_header *zhdr)
+{
+	spin_unlock(&zhdr->page_lock);
 }
 
 /*
@@ -179,7 +211,11 @@ static struct z3fold_header *handle_to_z3fold_header(unsigned long handle)
 	return (struct z3fold_header *)(handle & PAGE_MASK);
 }
 
-/* Returns buddy number */
+/*
+ * (handle & BUDDY_MASK) < zhdr->first_num is possible in encode_handle
+ *  but that doesn't matter. because the masking will result in the
+ *  correct buddy number.
+ */
 static enum buddy handle_to_buddy(unsigned long handle)
 {
 	struct z3fold_header *zhdr = handle_to_z3fold_header(handle);
@@ -200,9 +236,10 @@ static int num_free_chunks(struct z3fold_header *zhdr)
 	 */
 	if (zhdr->middle_chunks != 0) {
 		int nfree_before = zhdr->first_chunks ?
-			0 : zhdr->start_middle - 1;
+			0 : zhdr->start_middle - ZHDR_CHUNKS;
 		int nfree_after = zhdr->last_chunks ?
-			0 : NCHUNKS - zhdr->start_middle - zhdr->middle_chunks;
+			0 : TOTAL_CHUNKS -
+				(zhdr->start_middle + zhdr->middle_chunks);
 		nfree = max(nfree_before, nfree_after);
 	} else
 		nfree = NCHUNKS - zhdr->first_chunks - zhdr->last_chunks;
@@ -232,9 +269,8 @@ static struct z3fold_pool *z3fold_create_pool(gfp_t gfp,
 	spin_lock_init(&pool->lock);
 	for_each_unbuddied_list(i, 0)
 		INIT_LIST_HEAD(&pool->unbuddied[i]);
-	INIT_LIST_HEAD(&pool->buddied);
 	INIT_LIST_HEAD(&pool->lru);
-	pool->pages_nr = 0;
+	atomic64_set(&pool->pages_nr, 0);
 	pool->ops = ops;
 	return pool;
 }
@@ -250,25 +286,58 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool)
 	kfree(pool);
 }
 
+static inline void *mchunk_memmove(struct z3fold_header *zhdr,
+				unsigned short dst_chunk)
+{
+	void *beg = zhdr;
+	return memmove(beg + (dst_chunk << CHUNK_SHIFT),
+		       beg + (zhdr->start_middle << CHUNK_SHIFT),
+		       zhdr->middle_chunks << CHUNK_SHIFT);
+}
+
+#define BIG_CHUNK_GAP	3
 /* Has to be called with lock held */
 static int z3fold_compact_page(struct z3fold_header *zhdr)
 {
 	struct page *page = virt_to_page(zhdr);
-	void *beg = zhdr;
 
+	if (test_bit(MIDDLE_CHUNK_MAPPED, &page->private))
+		return 0; /* can't move middle chunk, it's used */
+
+	if (zhdr->middle_chunks == 0)
+		return 0; /* nothing to compact */
 
-	if (!test_bit(MIDDLE_CHUNK_MAPPED, &page->private) &&
-	    zhdr->middle_chunks != 0 &&
-	    zhdr->first_chunks == 0 && zhdr->last_chunks == 0) {
-		memmove(beg + ZHDR_SIZE_ALIGNED,
-			beg + (zhdr->start_middle << CHUNK_SHIFT),
-			zhdr->middle_chunks << CHUNK_SHIFT);
+	if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) {
+		/* move to the beginning */
+		mchunk_memmove(zhdr, ZHDR_CHUNKS);
 		zhdr->first_chunks = zhdr->middle_chunks;
 		zhdr->middle_chunks = 0;
 		zhdr->start_middle = 0;
 		zhdr->first_num++;
 		return 1;
 	}
+
+	/*
+	 * moving data is expensive, so let's only do that if
+	 * there's substantial gain (at least BIG_CHUNK_GAP chunks)
+	 */
+	if (zhdr->first_chunks != 0 && zhdr->last_chunks == 0 &&
+	    zhdr->start_middle - (zhdr->first_chunks + ZHDR_CHUNKS) >=
+			BIG_CHUNK_GAP) {
+		mchunk_memmove(zhdr, zhdr->first_chunks + ZHDR_CHUNKS);
+		zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS;
+		return 1;
+	} else if (zhdr->last_chunks != 0 && zhdr->first_chunks == 0 &&
+		   TOTAL_CHUNKS - (zhdr->last_chunks + zhdr->start_middle
+					+ zhdr->middle_chunks) >=
+			BIG_CHUNK_GAP) {
+		unsigned short new_start = TOTAL_CHUNKS - zhdr->last_chunks -
+			zhdr->middle_chunks;
+		mchunk_memmove(zhdr, new_start);
+		zhdr->start_middle = new_start;
+		return 1;
+	}
+
 	return 0;
 }
 
@@ -309,50 +378,63 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp,
 		bud = HEADLESS;
 	else {
 		chunks = size_to_chunks(size);
-		spin_lock(&pool->lock);
 
 		/* First, try to find an unbuddied z3fold page. */
 		zhdr = NULL;
 		for_each_unbuddied_list(i, chunks) {
-			if (!list_empty(&pool->unbuddied[i])) {
-				zhdr = list_first_entry(&pool->unbuddied[i],
+			spin_lock(&pool->lock);
+			zhdr = list_first_entry_or_null(&pool->unbuddied[i],
 						struct z3fold_header, buddy);
-				page = virt_to_page(zhdr);
-				if (zhdr->first_chunks == 0) {
-					if (zhdr->middle_chunks != 0 &&
-					    chunks >= zhdr->start_middle)
-						bud = LAST;
-					else
-						bud = FIRST;
-				} else if (zhdr->last_chunks == 0)
+			if (!zhdr) {
+				spin_unlock(&pool->lock);
+				continue;
+			}
+			kref_get(&zhdr->refcount);
+			list_del_init(&zhdr->buddy);
+			spin_unlock(&pool->lock);
+
+			page = virt_to_page(zhdr);
+			z3fold_page_lock(zhdr);
+			if (zhdr->first_chunks == 0) {
+				if (zhdr->middle_chunks != 0 &&
+				    chunks >= zhdr->start_middle)
 					bud = LAST;
-				else if (zhdr->middle_chunks == 0)
-					bud = MIDDLE;
-				else {
-					pr_err("No free chunks in unbuddied\n");
-					WARN_ON(1);
-					continue;
-				}
-				list_del(&zhdr->buddy);
-				goto found;
+				else
+					bud = FIRST;
+			} else if (zhdr->last_chunks == 0)
+				bud = LAST;
+			else if (zhdr->middle_chunks == 0)
+				bud = MIDDLE;
+			else {
+				z3fold_page_unlock(zhdr);
+				spin_lock(&pool->lock);
+				if (kref_put(&zhdr->refcount,
+					     release_z3fold_page))
+					atomic64_dec(&pool->pages_nr);
+				spin_unlock(&pool->lock);
+				pr_err("No free chunks in unbuddied\n");
+				WARN_ON(1);
+				continue;
 			}
+			goto found;
 		}
 		bud = FIRST;
-		spin_unlock(&pool->lock);
 	}
 
 	/* Couldn't find unbuddied z3fold page, create new one */
 	page = alloc_page(gfp);
 	if (!page)
 		return -ENOMEM;
-	spin_lock(&pool->lock);
-	pool->pages_nr++;
+
+	atomic64_inc(&pool->pages_nr);
 	zhdr = init_z3fold_page(page);
 
 	if (bud == HEADLESS) {
 		set_bit(PAGE_HEADLESS, &page->private);
+		spin_lock(&pool->lock);
 		goto headless;
 	}
+	z3fold_page_lock(zhdr);
 
 found:
 	if (bud == FIRST)
@@ -361,17 +443,15 @@ found:
 		zhdr->last_chunks = chunks;
 	else {
 		zhdr->middle_chunks = chunks;
-		zhdr->start_middle = zhdr->first_chunks + 1;
+		zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS;
 	}
 
+	spin_lock(&pool->lock);
 	if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0 ||
 			zhdr->middle_chunks == 0) {
 		/* Add to unbuddied list */
 		freechunks = num_free_chunks(zhdr);
 		list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
-	} else {
-		/* Add to buddied list */
-		list_add(&zhdr->buddy, &pool->buddied);
 	}
 
 headless:
@@ -383,6 +463,8 @@ headless:
 
 	*handle = encode_handle(zhdr, bud);
 	spin_unlock(&pool->lock);
+	if (bud != HEADLESS)
+		z3fold_page_unlock(zhdr);
 
 	return 0;
 }
@@ -404,7 +486,6 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 	struct page *page;
 	enum buddy bud;
 
-	spin_lock(&pool->lock);
 	zhdr = handle_to_z3fold_header(handle);
 	page = virt_to_page(zhdr);
 
@@ -412,6 +493,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		/* HEADLESS page stored */
 		bud = HEADLESS;
 	} else {
+		z3fold_page_lock(zhdr);
 		bud = handle_to_buddy(handle);
 
 		switch (bud) {
@@ -428,38 +510,36 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		default:
 			pr_err("%s: unknown bud %d\n", __func__, bud);
 			WARN_ON(1);
-			spin_unlock(&pool->lock);
+			z3fold_page_unlock(zhdr);
 			return;
 		}
 	}
 
-	if (test_bit(UNDER_RECLAIM, &page->private)) {
-		/* z3fold page is under reclaim, reclaim will free */
-		spin_unlock(&pool->lock);
-		return;
-	}
-
-	if (bud != HEADLESS) {
-		/* Remove from existing buddy list */
-		list_del(&zhdr->buddy);
-	}
-
-	if (bud == HEADLESS ||
-	    (zhdr->first_chunks == 0 && zhdr->middle_chunks == 0 &&
-			zhdr->last_chunks == 0)) {
-		/* z3fold page is empty, free */
+	if (bud == HEADLESS) {
+		spin_lock(&pool->lock);
 		list_del(&page->lru);
-		clear_bit(PAGE_HEADLESS, &page->private);
-		free_z3fold_page(zhdr);
-		pool->pages_nr--;
+		spin_unlock(&pool->lock);
+		free_z3fold_page(page);
+		atomic64_dec(&pool->pages_nr);
 	} else {
-		z3fold_compact_page(zhdr);
-		/* Add to the unbuddied list */
-		freechunks = num_free_chunks(zhdr);
-		list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
+		if (zhdr->first_chunks != 0 || zhdr->middle_chunks != 0 ||
+		    zhdr->last_chunks != 0) {
+			z3fold_compact_page(zhdr);
+			/* Add to the unbuddied list */
+			spin_lock(&pool->lock);
+			if (!list_empty(&zhdr->buddy))
+				list_del(&zhdr->buddy);
+			freechunks = num_free_chunks(zhdr);
+			list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
+			spin_unlock(&pool->lock);
+		}
+		z3fold_page_unlock(zhdr);
+		spin_lock(&pool->lock);
+		if (kref_put(&zhdr->refcount, release_z3fold_page))
+			atomic64_dec(&pool->pages_nr);
+		spin_unlock(&pool->lock);
 	}
 
-	spin_unlock(&pool->lock);
 }
 
 /**
@@ -506,20 +586,25 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 	unsigned long first_handle = 0, middle_handle = 0, last_handle = 0;
 
 	spin_lock(&pool->lock);
-	if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) ||
-			retries == 0) {
+	if (!pool->ops || !pool->ops->evict || retries == 0) {
 		spin_unlock(&pool->lock);
 		return -EINVAL;
 	}
 	for (i = 0; i < retries; i++) {
+		if (list_empty(&pool->lru)) {
+			spin_unlock(&pool->lock);
+			return -EINVAL;
+		}
 		page = list_last_entry(&pool->lru, struct page, lru);
-		list_del(&page->lru);
+		list_del_init(&page->lru);
 
-		/* Protect z3fold page against free */
-		set_bit(UNDER_RECLAIM, &page->private);
 		zhdr = page_address(page);
 		if (!test_bit(PAGE_HEADLESS, &page->private)) {
-			list_del(&zhdr->buddy);
+			if (!list_empty(&zhdr->buddy))
+				list_del_init(&zhdr->buddy);
+			kref_get(&zhdr->refcount);
+			spin_unlock(&pool->lock);
+			z3fold_page_lock(zhdr);
 			/*
 			 * We need encode the handles before unlocking, since
 			 * we can race with free that will set
@@ -534,13 +619,13 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 				middle_handle = encode_handle(zhdr, MIDDLE);
 			if (zhdr->last_chunks)
 				last_handle = encode_handle(zhdr, LAST);
+			z3fold_page_unlock(zhdr);
 		} else {
 			first_handle = encode_handle(zhdr, HEADLESS);
 			last_handle = middle_handle = 0;
+			spin_unlock(&pool->lock);
 		}
 
-		spin_unlock(&pool->lock);
-
 		/* Issue the eviction callback(s) */
 		if (middle_handle) {
 			ret = pool->ops->evict(pool, middle_handle);
@@ -558,36 +643,40 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 				goto next;
 		}
 next:
-		spin_lock(&pool->lock);
-		clear_bit(UNDER_RECLAIM, &page->private);
-		if ((test_bit(PAGE_HEADLESS, &page->private) && ret == 0) ||
-		    (zhdr->first_chunks == 0 && zhdr->last_chunks == 0 &&
-		     zhdr->middle_chunks == 0)) {
-			/*
-			 * All buddies are now free, free the z3fold page and
-			 * return success.
-			 */
-			clear_bit(PAGE_HEADLESS, &page->private);
-			free_z3fold_page(zhdr);
-			pool->pages_nr--;
-			spin_unlock(&pool->lock);
-			return 0;
-		}  else if (!test_bit(PAGE_HEADLESS, &page->private)) {
-			if (zhdr->first_chunks != 0 &&
-			    zhdr->last_chunks != 0 &&
-			    zhdr->middle_chunks != 0) {
-				/* Full, add to buddied list */
-				list_add(&zhdr->buddy, &pool->buddied);
+		if (test_bit(PAGE_HEADLESS, &page->private)) {
+			if (ret == 0) {
+				free_z3fold_page(page);
+				return 0;
 			} else {
+				spin_lock(&pool->lock);
+			}
+		} else {
+			z3fold_page_lock(zhdr);
+			if ((zhdr->first_chunks || zhdr->last_chunks ||
+			     zhdr->middle_chunks) &&
+			    !(zhdr->first_chunks && zhdr->last_chunks &&
+			      zhdr->middle_chunks)) {
 				z3fold_compact_page(zhdr);
 				/* add to unbuddied list */
+				spin_lock(&pool->lock);
 				freechunks = num_free_chunks(zhdr);
 				list_add(&zhdr->buddy,
 					 &pool->unbuddied[freechunks]);
+				spin_unlock(&pool->lock);
+			}
+			z3fold_page_unlock(zhdr);
+			spin_lock(&pool->lock);
+			if (kref_put(&zhdr->refcount, release_z3fold_page)) {
+				atomic64_dec(&pool->pages_nr);
+				return 0;
 			}
 		}
 
-		/* add to beginning of LRU */
+		/*
+		 * Add to the beginning of LRU.
+		 * Pool lock has to be kept here to ensure the page has
+		 * not already been released
+		 */
 		list_add(&page->lru, &pool->lru);
 	}
 	spin_unlock(&pool->lock);
@@ -611,7 +700,6 @@ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle)
 	void *addr;
 	enum buddy buddy;
 
-	spin_lock(&pool->lock);
 	zhdr = handle_to_z3fold_header(handle);
 	addr = zhdr;
 	page = virt_to_page(zhdr);
@@ -619,6 +707,7 @@ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle)
 	if (test_bit(PAGE_HEADLESS, &page->private))
 		goto out;
 
+	z3fold_page_lock(zhdr);
 	buddy = handle_to_buddy(handle);
 	switch (buddy) {
 	case FIRST:
@@ -637,8 +726,9 @@ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle)
 		addr = NULL;
 		break;
 	}
+
+	z3fold_page_unlock(zhdr);
 out:
-	spin_unlock(&pool->lock);
 	return addr;
 }
 
@@ -653,31 +743,28 @@ static void z3fold_unmap(struct z3fold_pool *pool, unsigned long handle)
 	struct page *page;
 	enum buddy buddy;
 
-	spin_lock(&pool->lock);
 	zhdr = handle_to_z3fold_header(handle);
 	page = virt_to_page(zhdr);
 
-	if (test_bit(PAGE_HEADLESS, &page->private)) {
-		spin_unlock(&pool->lock);
+	if (test_bit(PAGE_HEADLESS, &page->private))
 		return;
-	}
 
+	z3fold_page_lock(zhdr);
 	buddy = handle_to_buddy(handle);
 	if (buddy == MIDDLE)
 		clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
-	spin_unlock(&pool->lock);
+	z3fold_page_unlock(zhdr);
 }
 
 /**
  * z3fold_get_pool_size() - gets the z3fold pool size in pages
  * @pool:	pool whose size is being queried
  *
- * Returns: size in pages of the given pool.  The pool lock need not be
- * taken to access pages_nr.
+ * Returns: size in pages of the given pool.
  */
 static u64 z3fold_get_pool_size(struct z3fold_pool *pool)
 {
-	return pool->pages_nr;
+	return atomic64_read(&pool->pages_nr);
 }
 
 /*****************
@@ -776,8 +863,8 @@ MODULE_ALIAS("zpool-z3fold");
 
 static int __init init_z3fold(void)
 {
-	/* Make sure the z3fold header will fit in one chunk */
-	BUILD_BUG_ON(sizeof(struct z3fold_header) > ZHDR_SIZE_ALIGNED);
+	/* Make sure the z3fold header is not larger than the page size */
+	BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE);
 	zpool_register_driver(&z3fold_zpool_driver);
 
 	return 0;
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 9cc3c0b2c2c1..a1f24989ac23 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -25,7 +25,7 @@
  * Usage of struct page flags:
  *	PG_private: identifies the first component page
  *	PG_private2: identifies the last component page
- *	PG_owner_priv_1: indentifies the huge component page
+ *	PG_owner_priv_1: identifies the huge component page
  *
  */
 
@@ -364,7 +364,7 @@ static struct zspage *cache_alloc_zspage(struct zs_pool *pool, gfp_t flags)
 {
 	return kmem_cache_alloc(pool->zspage_cachep,
 			flags & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
-};
+}
 
 static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage)
 {
@@ -2383,7 +2383,7 @@ struct zs_pool *zs_create_pool(const char *name)
 		goto err;
 
 	/*
-	 * Iterate reversly, because, size of size_class that we want to use
+	 * Iterate reversely, because, size of size_class that we want to use
 	 * for merging should be larger or equal to current size.
 	 */
 	for (i = zs_size_classes - 1; i >= 0; i--) {
diff --git a/mm/zswap.c b/mm/zswap.c
index cabf09e0128b..eedc27894b10 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -76,6 +76,8 @@ static u64 zswap_duplicate_entry;
 * tunables
 **********************************/
 
+#define ZSWAP_PARAM_UNSET ""
+
 /* Enable/disable zswap (disabled by default) */
 static bool zswap_enabled;
 static int zswap_enabled_param_set(const char *,
@@ -185,6 +187,9 @@ static bool zswap_init_started;
 /* fatal error during init */
 static bool zswap_init_failed;
 
+/* init completed, but couldn't create the initial pool */
+static bool zswap_has_pool;
+
 /*********************************
 * helpers and fwd declarations
 **********************************/
@@ -424,7 +429,8 @@ static struct zswap_pool *__zswap_pool_current(void)
 	struct zswap_pool *pool;
 
 	pool = list_first_or_null_rcu(&zswap_pools, typeof(*pool), list);
-	WARN_ON(!pool);
+	WARN_ONCE(!pool && zswap_has_pool,
+		  "%s: no page storage pool!\n", __func__);
 
 	return pool;
 }
@@ -443,7 +449,7 @@ static struct zswap_pool *zswap_pool_current_get(void)
 	rcu_read_lock();
 
 	pool = __zswap_pool_current();
-	if (!pool || !zswap_pool_get(pool))
+	if (!zswap_pool_get(pool))
 		pool = NULL;
 
 	rcu_read_unlock();
@@ -459,7 +465,9 @@ static struct zswap_pool *zswap_pool_last_get(void)
 
 	list_for_each_entry_rcu(pool, &zswap_pools, list)
 		last = pool;
-	if (!WARN_ON(!last) && !zswap_pool_get(last))
+	WARN_ONCE(!last && zswap_has_pool,
+		  "%s: no page storage pool!\n", __func__);
+	if (!zswap_pool_get(last))
 		last = NULL;
 
 	rcu_read_unlock();
@@ -495,6 +503,17 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
 	int ret;
 
+	if (!zswap_has_pool) {
+		/* if either are unset, pool initialization failed, and we
+		 * need both params to be set correctly before trying to
+		 * create a pool.
+		 */
+		if (!strcmp(type, ZSWAP_PARAM_UNSET))
+			return NULL;
+		if (!strcmp(compressor, ZSWAP_PARAM_UNSET))
+			return NULL;
+	}
+
 	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
 	if (!pool) {
 		pr_err("pool alloc failed\n");
@@ -544,29 +563,41 @@ error:
 
 static __init struct zswap_pool *__zswap_pool_create_fallback(void)
 {
-	if (!crypto_has_comp(zswap_compressor, 0, 0)) {
-		if (!strcmp(zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT)) {
-			pr_err("default compressor %s not available\n",
-			       zswap_compressor);
-			return NULL;
-		}
+	bool has_comp, has_zpool;
+
+	has_comp = crypto_has_comp(zswap_compressor, 0, 0);
+	if (!has_comp && strcmp(zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT)) {
 		pr_err("compressor %s not available, using default %s\n",
 		       zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT);
 		param_free_charp(&zswap_compressor);
 		zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
+		has_comp = crypto_has_comp(zswap_compressor, 0, 0);
 	}
-	if (!zpool_has_pool(zswap_zpool_type)) {
-		if (!strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) {
-			pr_err("default zpool %s not available\n",
-			       zswap_zpool_type);
-			return NULL;
-		}
+	if (!has_comp) {
+		pr_err("default compressor %s not available\n",
+		       zswap_compressor);
+		param_free_charp(&zswap_compressor);
+		zswap_compressor = ZSWAP_PARAM_UNSET;
+	}
+
+	has_zpool = zpool_has_pool(zswap_zpool_type);
+	if (!has_zpool && strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) {
 		pr_err("zpool %s not available, using default %s\n",
 		       zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT);
 		param_free_charp(&zswap_zpool_type);
 		zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
+		has_zpool = zpool_has_pool(zswap_zpool_type);
+	}
+	if (!has_zpool) {
+		pr_err("default zpool %s not available\n",
+		       zswap_zpool_type);
+		param_free_charp(&zswap_zpool_type);
+		zswap_zpool_type = ZSWAP_PARAM_UNSET;
 	}
 
+	if (!has_comp || !has_zpool)
+		return NULL;
+
 	return zswap_pool_create(zswap_zpool_type, zswap_compressor);
 }
 
@@ -582,6 +613,9 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 
 static int __must_check zswap_pool_get(struct zswap_pool *pool)
 {
+	if (!pool)
+		return 0;
+
 	return kref_get_unless_zero(&pool->kref);
 }
 
@@ -639,7 +673,7 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp,
 	}
 
 	/* no change required */
-	if (!strcmp(s, *(char **)kp->arg))
+	if (!strcmp(s, *(char **)kp->arg) && zswap_has_pool)
 		return 0;
 
 	/* if this is load-time (pre-init) param setting,
@@ -670,21 +704,26 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp,
 	pool = zswap_pool_find_get(type, compressor);
 	if (pool) {
 		zswap_pool_debug("using existing", pool);
+		WARN_ON(pool == zswap_pool_current());
 		list_del_rcu(&pool->list);
-	} else {
-		spin_unlock(&zswap_pools_lock);
-		pool = zswap_pool_create(type, compressor);
-		spin_lock(&zswap_pools_lock);
 	}
 
+	spin_unlock(&zswap_pools_lock);
+
+	if (!pool)
+		pool = zswap_pool_create(type, compressor);
+
 	if (pool)
 		ret = param_set_charp(s, kp);
 	else
 		ret = -EINVAL;
 
+	spin_lock(&zswap_pools_lock);
+
 	if (!ret) {
 		put_pool = zswap_pool_current();
 		list_add_rcu(&pool->list, &zswap_pools);
+		zswap_has_pool = true;
 	} else if (pool) {
 		/* add the possibly pre-existing pool to the end of the pools
 		 * list; if it's new (and empty) then it'll be removed and
@@ -696,6 +735,17 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp,
 
 	spin_unlock(&zswap_pools_lock);
 
+	if (!zswap_has_pool && !pool) {
+		/* if initial pool creation failed, and this pool creation also
+		 * failed, maybe both compressor and zpool params were bad.
+		 * Allow changing this param, so pool creation will succeed
+		 * when the other param is changed. We already verified this
+		 * param is ok in the zpool_has_pool() or crypto_has_comp()
+		 * checks above.
+		 */
+		ret = param_set_charp(s, kp);
+	}
+
 	/* drop the ref from either the old current pool,
 	 * or the new pool we failed to add
 	 */
@@ -724,6 +774,10 @@ static int zswap_enabled_param_set(const char *val,
 		pr_err("can't enable, initialization failed\n");
 		return -ENODEV;
 	}
+	if (!zswap_has_pool && zswap_init_started) {
+		pr_err("can't enable, no pool configured\n");
+		return -ENODEV;
+	}
 
 	return param_set_bool(val, kp);
 }
@@ -1205,22 +1259,21 @@ static int __init init_zswap(void)
 		goto hp_fail;
 
 	pool = __zswap_pool_create_fallback();
-	if (!pool) {
+	if (pool) {
+		pr_info("loaded using pool %s/%s\n", pool->tfm_name,
+			zpool_get_type(pool->zpool));
+		list_add(&pool->list, &zswap_pools);
+		zswap_has_pool = true;
+	} else {
 		pr_err("pool creation failed\n");
-		goto pool_fail;
+		zswap_enabled = false;
 	}
-	pr_info("loaded using pool %s/%s\n", pool->tfm_name,
-		zpool_get_type(pool->zpool));
-
-	list_add(&pool->list, &zswap_pools);
 
 	frontswap_register_ops(&zswap_frontswap_ops);
 	if (zswap_debugfs_init())
 		pr_warn("debugfs initialization failed\n");
 	return 0;
 
-pool_fail:
-	cpuhp_remove_state_nocalls(CPUHP_MM_ZSWP_POOL_PREPARE);
 hp_fail:
 	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail: