24 files changed, 224 insertions, 221 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 1b46e6e74881..6afae32571ca 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -516,7 +516,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	}
 
 	if (ret & VM_FAULT_RETRY) {
-		if (nonblocking)
+		if (nonblocking && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
 			*nonblocking = 0;
 		return -EBUSY;
 	}
@@ -890,7 +890,10 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 				break;
 		}
 		if (*locked) {
-			/* VM_FAULT_RETRY didn't trigger */
+			/*
+			 * VM_FAULT_RETRY didn't trigger or it was a
+			 * FOLL_NOWAIT.
+			 */
 			if (!pages_done)
 				pages_done = ret;
 			break;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 87ab9b8f56b5..5a68730eebd6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -555,7 +555,8 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) {
+	if (mem_cgroup_try_charge(page, vma->vm_mm, gfp | __GFP_NORETRY, &memcg,
+				  true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -1316,7 +1317,7 @@ alloc:
 	}
 
 	if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm,
-					huge_gfp, &memcg, true))) {
+				huge_gfp | __GFP_NORETRY, &memcg, true))) {
 		put_page(new_page);
 		split_huge_pmd(vma, vmf->pmd, vmf->address);
 		if (page)
@@ -2783,11 +2784,13 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 
 	list_for_each_safe(pos, next, &list) {
 		page = list_entry((void *)pos, struct page, mapping);
-		lock_page(page);
+		if (!trylock_page(page))
+			goto next;
 		/* split_huge_page() removes page from list on success */
 		if (!split_huge_page(page))
 			split++;
 		unlock_page(page);
+next:
 		put_page(page);
 	}
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7c204e3d132b..976bbc5646fe 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -18,6 +18,7 @@
 #include <linux/bootmem.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
+#include <linux/mmdebug.h>
 #include <linux/sched/signal.h>
 #include <linux/rmap.h>
 #include <linux/string_helpers.h>
@@ -1583,7 +1584,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
 		page = NULL;
 	} else {
 		h->surplus_huge_pages++;
-		h->nr_huge_pages_node[page_to_nid(page)]++;
+		h->surplus_huge_pages_node[page_to_nid(page)]++;
 	}
 
 out_unlock:
@@ -4374,6 +4375,12 @@ int hugetlb_reserve_pages(struct inode *inode,
 	struct resv_map *resv_map;
 	long gbl_reserve;
 
+	/* This should never happen */
+	if (from > to) {
+		VM_WARN(1, "%s called with a negative range\n", __func__);
+		return -EINVAL;
+	}
+
 	/*
 	 * Only apply hugepage reservation if asked. At fault time, an
 	 * attempt will be made for VM_NORESERVE to allocate a page
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b7e2268dfc9a..e42568284e06 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -530,7 +530,12 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 			goto out;
 		}
 
-		VM_BUG_ON_PAGE(PageCompound(page), page);
+		/* TODO: teach khugepaged to collapse THP mapped with pte */
+		if (PageCompound(page)) {
+			result = SCAN_PAGE_COMPOUND;
+			goto out;
+		}
+
 		VM_BUG_ON_PAGE(!PageAnon(page), page);
 
 		/*
@@ -960,7 +965,9 @@ static void collapse_huge_page(struct mm_struct *mm,
 		goto out_nolock;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {
+	/* Do not oom kill for khugepaged charges */
+	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY,
+					   &memcg, true))) {
 		result = SCAN_CGROUP_CHARGE_FAIL;
 		goto out_nolock;
 	}
@@ -1319,7 +1326,9 @@ static void collapse_shmem(struct mm_struct *mm,
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {
+	/* Do not oom kill for khugepaged charges */
+	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY,
+					   &memcg, true))) {
 		result = SCAN_CGROUP_CHARGE_FAIL;
 		goto out;
 	}
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index e83987c55a08..46c2290a08f1 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1657,8 +1657,7 @@ static void start_scan_thread(void)
 }
 
 /*
- * Stop the automatic memory scanning thread. This function must be called
- * with the scan_mutex held.
+ * Stop the automatic memory scanning thread.
  */
 static void stop_scan_thread(void)
 {
@@ -1921,12 +1920,15 @@ static void kmemleak_do_cleanup(struct work_struct *work)
 {
 	stop_scan_thread();
 
+	mutex_lock(&scan_mutex);
 	/*
-	 * Once the scan thread has stopped, it is safe to no longer track
-	 * object freeing. Ordering of the scan thread stopping and the memory
-	 * accesses below is guaranteed by the kthread_stop() function.
+	 * Once it is made sure that kmemleak_scan has stopped, it is safe to no
+	 * longer track object freeing. Ordering of the scan thread stopping and
+	 * the memory accesses below is guaranteed by the kthread_stop()
+	 * function.
 	 */
 	kmemleak_free_enabled = 0;
+	mutex_unlock(&scan_mutex);
 
 	if (!kmemleak_found_leaks)
 		__kmemleak_do_cleanup();
diff --git a/mm/memblock.c b/mm/memblock.c
index 5a9ca2a1751b..48376bd33274 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1101,34 +1101,6 @@ 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);
-
-	if (right == type->cnt)
-		return max_pfn;
-	else
-		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
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 670e99b68aa6..9ec024b862ac 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -714,9 +714,9 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
  * invocations for reference counting, or use mem_cgroup_iter_break()
  * to cancel a hierarchy walk before the round-trip is complete.
  *
- * Reclaimers can specify a zone and a priority level in @reclaim to
+ * Reclaimers can specify a node and a priority level in @reclaim to
  * divide up the memcgs in the hierarchy among all concurrent
- * reclaimers operating on the same zone and priority.
+ * reclaimers operating on the same node and priority.
  */
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 				   struct mem_cgroup *prev,
@@ -2299,7 +2299,7 @@ void memcg_kmem_put_cache(struct kmem_cache *cachep)
 }
 
 /**
- * memcg_kmem_charge: charge a kmem page
+ * memcg_kmem_charge_memcg: charge a kmem page
  * @page: page to charge
  * @gfp: reclaim mode
  * @order: allocation order
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4b80ccee4535..8291b75f42c8 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1139,8 +1139,6 @@ int memory_failure(unsigned long pfn, int flags)
 		return 0;
 	}
 
-	arch_unmap_kpfn(pfn);
-
 	orig_head = hpage = compound_head(p);
 	num_poisoned_pages_inc();
 
diff --git a/mm/memory.c b/mm/memory.c
index dd8de96f5547..5fcfc24904d1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -80,7 +80,7 @@
 
 #include "internal.h"
 
-#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+#if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
 #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
 #endif
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d879f1d8a44a..32cba0332787 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2124,6 +2124,9 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 	case MPOL_INTERLEAVE:
 		return !!nodes_equal(a->v.nodes, b->v.nodes);
 	case MPOL_PREFERRED:
+		/* a's ->flags is the same as b's */
+		if (a->flags & MPOL_F_LOCAL)
+			return true;
 		return a->v.preferred_node == b->v.preferred_node;
 	default:
 		BUG();
diff --git a/mm/mlock.c b/mm/mlock.c
index 79398200e423..74e5a6547c3d 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -64,6 +64,12 @@ void clear_page_mlock(struct page *page)
 	mod_zone_page_state(page_zone(page), NR_MLOCK,
 			    -hpage_nr_pages(page));
 	count_vm_event(UNEVICTABLE_PGCLEARED);
+	/*
+	 * The previous TestClearPageMlocked() corresponds to the smp_mb()
+	 * in __pagevec_lru_add_fn().
+	 *
+	 * See __pagevec_lru_add_fn for more explanation.
+	 */
 	if (!isolate_lru_page(page)) {
 		putback_lru_page(page);
 	} else {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 81e18ceef579..1741dd23e7c1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -46,6 +46,7 @@
 #include <linux/stop_machine.h>
 #include <linux/sort.h>
 #include <linux/pfn.h>
+#include <xen/xen.h>
 #include <linux/backing-dev.h>
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
@@ -347,6 +348,9 @@ static inline bool update_defer_init(pg_data_t *pgdat,
 	/* Always populate low zones for address-constrained allocations */
 	if (zone_end < pgdat_end_pfn(pgdat))
 		return true;
+	/* Xen PV domains need page structures early */
+	if (xen_pv_domain())
+		return true;
 	(*nr_initialised)++;
 	if ((*nr_initialised > pgdat->static_init_pgcnt) &&
 	    (pfn & (PAGES_PER_SECTION - 1)) == 0) {
@@ -1906,7 +1910,9 @@ static int move_freepages(struct zone *zone,
 	 * Remove at a later date when no bug reports exist related to
 	 * grouping pages by mobility
 	 */
-	VM_BUG_ON(page_zone(start_page) != page_zone(end_page));
+	VM_BUG_ON(pfn_valid(page_to_pfn(start_page)) &&
+	          pfn_valid(page_to_pfn(end_page)) &&
+	          page_zone(start_page) != page_zone(end_page));
 #endif
 
 	if (num_movable)
@@ -3590,7 +3596,7 @@ static bool __need_fs_reclaim(gfp_t gfp_mask)
 		return false;
 
 	/* this guy won't enter reclaim */
-	if ((current->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC))
+	if (current->flags & PF_MEMALLOC)
 		return false;
 
 	/* We're only interested __GFP_FS allocations for now */
@@ -5350,17 +5356,8 @@ 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)) {
-#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
+		if (!early_pfn_valid(pfn))
 			continue;
-		}
 		if (!early_pfn_in_nid(pfn, nid))
 			continue;
 		if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised))
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 9886c6073828..7172e0a80e13 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -123,13 +123,13 @@ void __reset_page_owner(struct page *page, unsigned int order)
 static inline bool check_recursive_alloc(struct stack_trace *trace,
 					unsigned long ip)
 {
-	int i, count;
+	int i;
 
 	if (!trace->nr_entries)
 		return false;
 
-	for (i = 0, count = 0; i < trace->nr_entries; i++) {
-		if (trace->entries[i] == ip && ++count == 2)
+	for (i = 0; i < trace->nr_entries; i++) {
+		if (trace->entries[i] == ip)
 			return true;
 	}
 
diff --git a/mm/percpu-km.c b/mm/percpu-km.c
index d2a76642c4ae..38de70ab1a0d 100644
--- a/mm/percpu-km.c
+++ b/mm/percpu-km.c
@@ -34,7 +34,7 @@
 #include <linux/log2.h>
 
 static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
-			       int page_start, int page_end)
+			       int page_start, int page_end, gfp_t gfp)
 {
 	return 0;
 }
@@ -45,18 +45,18 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
 	/* nada */
 }
 
-static struct pcpu_chunk *pcpu_create_chunk(void)
+static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
 {
 	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;
 	struct pcpu_chunk *chunk;
 	struct page *pages;
 	int i;
 
-	chunk = pcpu_alloc_chunk();
+	chunk = pcpu_alloc_chunk(gfp);
 	if (!chunk)
 		return NULL;
 
-	pages = alloc_pages(GFP_KERNEL, order_base_2(nr_pages));
+	pages = alloc_pages(gfp, order_base_2(nr_pages));
 	if (!pages) {
 		pcpu_free_chunk(chunk);
 		return NULL;
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 9158e5a81391..d8078de912de 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -37,7 +37,7 @@ static struct page **pcpu_get_pages(void)
 	lockdep_assert_held(&pcpu_alloc_mutex);
 
 	if (!pages)
-		pages = pcpu_mem_zalloc(pages_size);
+		pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL);
 	return pages;
 }
 
@@ -73,18 +73,21 @@ static void pcpu_free_pages(struct pcpu_chunk *chunk,
  * @pages: array to put the allocated pages into, indexed by pcpu_page_idx()
  * @page_start: page index of the first page to be allocated
  * @page_end: page index of the last page to be allocated + 1
+ * @gfp: allocation flags passed to the underlying allocator
  *
  * Allocate pages [@page_start,@page_end) into @pages for all units.
  * The allocation is for @chunk.  Percpu core doesn't care about the
  * content of @pages and will pass it verbatim to pcpu_map_pages().
  */
 static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
-			    struct page **pages, int page_start, int page_end)
+			    struct page **pages, int page_start, int page_end,
+			    gfp_t gfp)
 {
-	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM;
 	unsigned int cpu, tcpu;
 	int i;
 
+	gfp |= __GFP_HIGHMEM;
+
 	for_each_possible_cpu(cpu) {
 		for (i = page_start; i < page_end; i++) {
 			struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
@@ -262,6 +265,7 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
  * @chunk: chunk of interest
  * @page_start: the start page
  * @page_end: the end page
+ * @gfp: allocation flags passed to the underlying memory allocator
  *
  * For each cpu, populate and map pages [@page_start,@page_end) into
  * @chunk.
@@ -270,7 +274,7 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
  * pcpu_alloc_mutex, does GFP_KERNEL allocation.
  */
 static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
-			       int page_start, int page_end)
+			       int page_start, int page_end, gfp_t gfp)
 {
 	struct page **pages;
 
@@ -278,7 +282,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
 	if (!pages)
 		return -ENOMEM;
 
-	if (pcpu_alloc_pages(chunk, pages, page_start, page_end))
+	if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp))
 		return -ENOMEM;
 
 	if (pcpu_map_pages(chunk, pages, page_start, page_end)) {
@@ -325,12 +329,12 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
 	pcpu_free_pages(chunk, pages, page_start, page_end);
 }
 
-static struct pcpu_chunk *pcpu_create_chunk(void)
+static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
 {
 	struct pcpu_chunk *chunk;
 	struct vm_struct **vms;
 
-	chunk = pcpu_alloc_chunk();
+	chunk = pcpu_alloc_chunk(gfp);
 	if (!chunk)
 		return NULL;
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 50e7fdf84055..9297098519a6 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -80,6 +80,7 @@
 #include <linux/vmalloc.h>
 #include <linux/workqueue.h>
 #include <linux/kmemleak.h>
+#include <linux/sched.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
@@ -447,26 +448,25 @@ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits,
 /**
  * pcpu_mem_zalloc - allocate memory
  * @size: bytes to allocate
+ * @gfp: allocation flags
  *
  * Allocate @size bytes.  If @size is smaller than PAGE_SIZE,
- * kzalloc() is used; otherwise, vzalloc() is used.  The returned
- * memory is always zeroed.
- *
- * CONTEXT:
- * Does GFP_KERNEL allocation.
+ * kzalloc() is used; otherwise, the equivalent of vzalloc() is used.
+ * This is to facilitate passing through whitelisted flags.  The
+ * returned memory is always zeroed.
  *
  * RETURNS:
  * Pointer to the allocated area on success, NULL on failure.
  */
-static void *pcpu_mem_zalloc(size_t size)
+static void *pcpu_mem_zalloc(size_t size, gfp_t gfp)
 {
 	if (WARN_ON_ONCE(!slab_is_available()))
 		return NULL;
 
 	if (size <= PAGE_SIZE)
-		return kzalloc(size, GFP_KERNEL);
+		return kzalloc(size, gfp);
 	else
-		return vzalloc(size);
+		return __vmalloc(size, gfp | __GFP_ZERO, PAGE_KERNEL);
 }
 
 /**
@@ -1154,12 +1154,12 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 	return chunk;
 }
 
-static struct pcpu_chunk *pcpu_alloc_chunk(void)
+static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp)
 {
 	struct pcpu_chunk *chunk;
 	int region_bits;
 
-	chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
+	chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp);
 	if (!chunk)
 		return NULL;
 
@@ -1168,17 +1168,17 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	region_bits = pcpu_chunk_map_bits(chunk);
 
 	chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) *
-					   sizeof(chunk->alloc_map[0]));
+					   sizeof(chunk->alloc_map[0]), gfp);
 	if (!chunk->alloc_map)
 		goto alloc_map_fail;
 
 	chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) *
-					   sizeof(chunk->bound_map[0]));
+					   sizeof(chunk->bound_map[0]), gfp);
 	if (!chunk->bound_map)
 		goto bound_map_fail;
 
 	chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) *
-					   sizeof(chunk->md_blocks[0]));
+					   sizeof(chunk->md_blocks[0]), gfp);
 	if (!chunk->md_blocks)
 		goto md_blocks_fail;
 
@@ -1277,9 +1277,11 @@ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk,
  * pcpu_addr_to_page		- translate address to physical address
  * pcpu_verify_alloc_info	- check alloc_info is acceptable during init
  */
-static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size);
-static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size);
-static struct pcpu_chunk *pcpu_create_chunk(void);
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
+			       int page_start, int page_end, gfp_t gfp);
+static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
+				  int page_start, int page_end);
+static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp);
 static void pcpu_destroy_chunk(struct pcpu_chunk *chunk);
 static struct page *pcpu_addr_to_page(void *addr);
 static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai);
@@ -1339,6 +1341,8 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 				 gfp_t gfp)
 {
+	/* whitelisted flags that can be passed to the backing allocators */
+	gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
 	bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
 	bool do_warn = !(gfp & __GFP_NOWARN);
 	static int warn_limit = 10;
@@ -1369,8 +1373,17 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 		return NULL;
 	}
 
-	if (!is_atomic)
-		mutex_lock(&pcpu_alloc_mutex);
+	if (!is_atomic) {
+		/*
+		 * pcpu_balance_workfn() allocates memory under this mutex,
+		 * and it may wait for memory reclaim. Allow current task
+		 * to become OOM victim, in case of memory pressure.
+		 */
+		if (gfp & __GFP_NOFAIL)
+			mutex_lock(&pcpu_alloc_mutex);
+		else if (mutex_lock_killable(&pcpu_alloc_mutex))
+			return NULL;
+	}
 
 	spin_lock_irqsave(&pcpu_lock, flags);
 
@@ -1421,7 +1434,7 @@ restart:
 	}
 
 	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
-		chunk = pcpu_create_chunk();
+		chunk = pcpu_create_chunk(pcpu_gfp);
 		if (!chunk) {
 			err = "failed to allocate new chunk";
 			goto fail;
@@ -1450,7 +1463,7 @@ area_found:
 					   page_start, page_end) {
 			WARN_ON(chunk->immutable);
 
-			ret = pcpu_populate_chunk(chunk, rs, re);
+			ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp);
 
 			spin_lock_irqsave(&pcpu_lock, flags);
 			if (ret) {
@@ -1561,10 +1574,17 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
  * pcpu_balance_workfn - manage the amount of free chunks and populated pages
  * @work: unused
  *
- * Reclaim all fully free chunks except for the first one.
+ * Reclaim all fully free chunks except for the first one.  This is also
+ * responsible for maintaining the pool of empty populated pages.  However,
+ * it is possible that this is called when physical memory is scarce causing
+ * OOM killer to be triggered.  We should avoid doing so until an actual
+ * allocation causes the failure as it is possible that requests can be
+ * serviced from already backed regions.
  */
 static void pcpu_balance_workfn(struct work_struct *work)
 {
+	/* gfp flags passed to underlying allocators */
+	const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
 	LIST_HEAD(to_free);
 	struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
 	struct pcpu_chunk *chunk, *next;
@@ -1600,6 +1620,7 @@ static void pcpu_balance_workfn(struct work_struct *work)
 			spin_unlock_irq(&pcpu_lock);
 		}
 		pcpu_destroy_chunk(chunk);
+		cond_resched();
 	}
 
 	/*
@@ -1645,7 +1666,7 @@ retry_pop:
 					   chunk->nr_pages) {
 			int nr = min(re - rs, nr_to_pop);
 
-			ret = pcpu_populate_chunk(chunk, rs, rs + nr);
+			ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp);
 			if (!ret) {
 				nr_to_pop -= nr;
 				spin_lock_irq(&pcpu_lock);
@@ -1662,7 +1683,7 @@ retry_pop:
 
 	if (nr_to_pop) {
 		/* ran out of chunks to populate, create a new one and retry */
-		chunk = pcpu_create_chunk();
+		chunk = pcpu_create_chunk(gfp);
 		if (chunk) {
 			spin_lock_irq(&pcpu_lock);
 			pcpu_chunk_relocate(chunk, -1);
diff --git a/mm/shmem.c b/mm/shmem.c
index 1907688b75ee..b85919243399 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -493,36 +493,45 @@ next:
 		info = list_entry(pos, struct shmem_inode_info, shrinklist);
 		inode = &info->vfs_inode;
 
-		if (nr_to_split && split >= nr_to_split) {
-			iput(inode);
-			continue;
-		}
+		if (nr_to_split && split >= nr_to_split)
+			goto leave;
 
-		page = find_lock_page(inode->i_mapping,
+		page = find_get_page(inode->i_mapping,
 				(inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT);
 		if (!page)
 			goto drop;
 
+		/* No huge page at the end of the file: nothing to split */
 		if (!PageTransHuge(page)) {
-			unlock_page(page);
 			put_page(page);
 			goto drop;
 		}
 
+		/*
+		 * Leave the inode on the list if we failed to lock
+		 * the page at this time.
+		 *
+		 * Waiting for the lock may lead to deadlock in the
+		 * reclaim path.
+		 */
+		if (!trylock_page(page)) {
+			put_page(page);
+			goto leave;
+		}
+
 		ret = split_huge_page(page);
 		unlock_page(page);
 		put_page(page);
 
-		if (ret) {
-			/* split failed: leave it on the list */
-			iput(inode);
-			continue;
-		}
+		/* If split failed leave the inode on the list */
+		if (ret)
+			goto leave;
 
 		split++;
 drop:
 		list_del_init(&info->shrinklist);
 		removed++;
+leave:
 		iput(inode);
 	}
 
diff --git a/mm/slab.c b/mm/slab.c
index 324446621b3e..9095c3945425 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1283,6 +1283,7 @@ void __init kmem_cache_init(void)
 				  nr_node_ids * sizeof(struct kmem_cache_node *),
 				  SLAB_HWCACHE_ALIGN, 0, 0);
 	list_add(&kmem_cache->list, &slab_caches);
+	memcg_link_cache(kmem_cache);
 	slab_state = PARTIAL;
 
 	/*
diff --git a/mm/swap.c b/mm/swap.c
index 567a7b96e41d..0f17330dd0e5 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -446,30 +446,6 @@ void lru_cache_add(struct page *page)
 }
 
 /**
- * add_page_to_unevictable_list - add a page to the unevictable list
- * @page:  the page to be added to the unevictable list
- *
- * Add page directly to its zone's unevictable list.  To avoid races with
- * tasks that might be making the page evictable, through eg. munlock,
- * munmap or exit, while it's not on the lru, we want to add the page
- * while it's locked or otherwise "invisible" to other tasks.  This is
- * difficult to do when using the pagevec cache, so bypass that.
- */
-void add_page_to_unevictable_list(struct page *page)
-{
-	struct pglist_data *pgdat = page_pgdat(page);
-	struct lruvec *lruvec;
-
-	spin_lock_irq(&pgdat->lru_lock);
-	lruvec = mem_cgroup_page_lruvec(page, pgdat);
-	ClearPageActive(page);
-	SetPageUnevictable(page);
-	SetPageLRU(page);
-	add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE);
-	spin_unlock_irq(&pgdat->lru_lock);
-}
-
-/**
  * lru_cache_add_active_or_unevictable
  * @page:  the page to be added to LRU
  * @vma:   vma in which page is mapped for determining reclaimability
@@ -484,13 +460,9 @@ void lru_cache_add_active_or_unevictable(struct page *page,
 {
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 
-	if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) {
+	if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED))
 		SetPageActive(page);
-		lru_cache_add(page);
-		return;
-	}
-
-	if (!TestSetPageMlocked(page)) {
+	else if (!TestSetPageMlocked(page)) {
 		/*
 		 * We use the irq-unsafe __mod_zone_page_stat because this
 		 * counter is not modified from interrupt context, and the pte
@@ -500,7 +472,7 @@ void lru_cache_add_active_or_unevictable(struct page *page,
 				    hpage_nr_pages(page));
 		count_vm_event(UNEVICTABLE_PGMLOCKED);
 	}
-	add_page_to_unevictable_list(page);
+	lru_cache_add(page);
 }
 
 /*
@@ -886,15 +858,55 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
 static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
 				 void *arg)
 {
-	int file = page_is_file_cache(page);
-	int active = PageActive(page);
-	enum lru_list lru = page_lru(page);
+	enum lru_list lru;
+	int was_unevictable = TestClearPageUnevictable(page);
 
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 
 	SetPageLRU(page);
+	/*
+	 * Page becomes evictable in two ways:
+	 * 1) Within LRU lock [munlock_vma_pages() and __munlock_pagevec()].
+	 * 2) Before acquiring LRU lock to put the page to correct LRU and then
+	 *   a) do PageLRU check with lock [check_move_unevictable_pages]
+	 *   b) do PageLRU check before lock [clear_page_mlock]
+	 *
+	 * (1) & (2a) are ok as LRU lock will serialize them. For (2b), we need
+	 * following strict ordering:
+	 *
+	 * #0: __pagevec_lru_add_fn		#1: clear_page_mlock
+	 *
+	 * SetPageLRU()				TestClearPageMlocked()
+	 * smp_mb() // explicit ordering	// above provides strict
+	 *					// ordering
+	 * PageMlocked()			PageLRU()
+	 *
+	 *
+	 * if '#1' does not observe setting of PG_lru by '#0' and fails
+	 * isolation, the explicit barrier will make sure that page_evictable
+	 * check will put the page in correct LRU. Without smp_mb(), SetPageLRU
+	 * can be reordered after PageMlocked check and can make '#1' to fail
+	 * the isolation of the page whose Mlocked bit is cleared (#0 is also
+	 * looking at the same page) and the evictable page will be stranded
+	 * in an unevictable LRU.
+	 */
+	smp_mb();
+
+	if (page_evictable(page)) {
+		lru = page_lru(page);
+		update_page_reclaim_stat(lruvec, page_is_file_cache(page),
+					 PageActive(page));
+		if (was_unevictable)
+			count_vm_event(UNEVICTABLE_PGRESCUED);
+	} else {
+		lru = LRU_UNEVICTABLE;
+		ClearPageActive(page);
+		SetPageUnevictable(page);
+		if (!was_unevictable)
+			count_vm_event(UNEVICTABLE_PGCULLED);
+	}
+
 	add_page_to_lru_list(page, lruvec, lru);
-	update_page_reclaim_stat(lruvec, file, active);
 	trace_mm_lru_insertion(page, lru);
 }
 
@@ -913,7 +925,7 @@ EXPORT_SYMBOL(__pagevec_lru_add);
  * @pvec:	Where the resulting entries are placed
  * @mapping:	The address_space to search
  * @start:	The starting entry index
- * @nr_pages:	The maximum number of pages
+ * @nr_entries:	The maximum number of pages
  * @indices:	The cache indices corresponding to the entries in @pvec
  *
  * pagevec_lookup_entries() will search for and return a group of up
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 673942094328..ebff729cc956 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1943,11 +1943,15 @@ void *vmalloc_exec(unsigned long size)
 }
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
-#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL
+#define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL)
 #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA)
-#define GFP_VMALLOC32 GFP_DMA | GFP_KERNEL
+#define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL)
 #else
-#define GFP_VMALLOC32 GFP_KERNEL
+/*
+ * 64b systems should always have either DMA or DMA32 zones. For others
+ * GFP_DMA32 should do the right thing and use the normal zone.
+ */
+#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL
 #endif
 
 /**
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 444749669187..cd5dc3faaa57 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -769,64 +769,7 @@ int remove_mapping(struct address_space *mapping, struct page *page)
  */
 void putback_lru_page(struct page *page)
 {
-	bool is_unevictable;
-	int was_unevictable = PageUnevictable(page);
-
-	VM_BUG_ON_PAGE(PageLRU(page), page);
-
-redo:
-	ClearPageUnevictable(page);
-
-	if (page_evictable(page)) {
-		/*
-		 * For evictable pages, we can use the cache.
-		 * In event of a race, worst case is we end up with an
-		 * unevictable page on [in]active list.
-		 * We know how to handle that.
-		 */
-		is_unevictable = false;
-		lru_cache_add(page);
-	} else {
-		/*
-		 * Put unevictable pages directly on zone's unevictable
-		 * list.
-		 */
-		is_unevictable = true;
-		add_page_to_unevictable_list(page);
-		/*
-		 * When racing with an mlock or AS_UNEVICTABLE clearing
-		 * (page is unlocked) make sure that if the other thread
-		 * does not observe our setting of PG_lru and fails
-		 * isolation/check_move_unevictable_pages,
-		 * we see PG_mlocked/AS_UNEVICTABLE cleared below and move
-		 * the page back to the evictable list.
-		 *
-		 * The other side is TestClearPageMlocked() or shmem_lock().
-		 */
-		smp_mb();
-	}
-
-	/*
-	 * page's status can change while we move it among lru. If an evictable
-	 * page is on unevictable list, it never be freed. To avoid that,
-	 * check after we added it to the list, again.
-	 */
-	if (is_unevictable && page_evictable(page)) {
-		if (!isolate_lru_page(page)) {
-			put_page(page);
-			goto redo;
-		}
-		/* This means someone else dropped this page from LRU
-		 * So, it will be freed or putback to LRU again. There is
-		 * nothing to do here.
-		 */
-	}
-
-	if (was_unevictable && !is_unevictable)
-		count_vm_event(UNEVICTABLE_PGRESCUED);
-	else if (!was_unevictable && is_unevictable)
-		count_vm_event(UNEVICTABLE_PGCULLED);
-
+	lru_cache_add(page);
 	put_page(page);		/* drop ref from isolate */
 }
 
@@ -1837,6 +1780,20 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		set_bit(PGDAT_WRITEBACK, &pgdat->flags);
 
 	/*
+	 * If dirty pages are scanned that are not queued for IO, it
+	 * 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.
+	 */
+	if (stat.nr_unqueued_dirty == nr_taken)
+		wakeup_flusher_threads(WB_REASON_VMSCAN);
+
+	/*
 	 * Legacy memcg will stall in page writeback so avoid forcibly
 	 * stalling here.
 	 */
@@ -1848,22 +1805,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		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 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 (stat.nr_unqueued_dirty == nr_taken) {
-			wakeup_flusher_threads(WB_REASON_VMSCAN);
+		/* Allow kswapd to start writing pages during reclaim. */
+		if (stat.nr_unqueued_dirty == nr_taken)
 			set_bit(PGDAT_DIRTY, &pgdat->flags);
-		}
 
 		/*
 		 * If kswapd scans pages marked marked for immediate
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 40b2db6db6b1..33581be705f0 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1839,9 +1839,11 @@ static void vmstat_update(struct work_struct *w)
 		 * to occur in the future. Keep on running the
 		 * update worker thread.
 		 */
+		preempt_disable();
 		queue_delayed_work_on(smp_processor_id(), mm_percpu_wq,
 				this_cpu_ptr(&vmstat_work),
 				round_jiffies_relative(sysctl_stat_interval));
+		preempt_enable();
 	}
 }
 
diff --git a/mm/zpool.c b/mm/zpool.c
index f8cb83e7699b..01a771e304fa 100644
--- a/mm/zpool.c
+++ b/mm/zpool.c
@@ -360,7 +360,7 @@ u64 zpool_get_total_size(struct zpool *zpool)
 
 /**
  * zpool_evictable() - Test if zpool is potentially evictable
- * @pool	The zpool to test
+ * @zpool:	The zpool to test
  *
  * Zpool is only potentially evictable when it's created with struct
  * zpool_ops.evict and its driver implements struct zpool_driver.shrink.
diff --git a/mm/zswap.c b/mm/zswap.c
index c004aa4fd3f4..61a5c41972db 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1007,6 +1007,12 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 	u8 *src, *dst;
 	struct zswap_header zhdr = { .swpentry = swp_entry(type, offset) };
 
+	/* THP isn't supported */
+	if (PageTransHuge(page)) {
+		ret = -EINVAL;
+		goto reject;
+	}
+
 	if (!zswap_enabled || !tree) {
 		ret = -ENODEV;
 		goto reject;