Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few hotfixes

 - various misc updates

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (108 commits)
  mm, memory_hotplug: move movable_node to the hotplug proper
  mm, memory_hotplug: drop CONFIG_MOVABLE_NODE
  mm, memory_hotplug: drop artificial restriction on online/offline
  mm: memcontrol: account slab stats per lruvec
  mm: memcontrol: per-lruvec stats infrastructure
  mm: memcontrol: use generic mod_memcg_page_state for kmem pages
  mm: memcontrol: use the node-native slab memory counters
  mm: vmstat: move slab statistics from zone to node counters
  mm/zswap.c: delete an error message for a failed memory allocation in zswap_dstmem_prepare()
  mm/zswap.c: improve a size determination in zswap_frontswap_init()
  mm/zswap.c: delete an error message for a failed memory allocation in zswap_pool_create()
  mm/swapfile.c: sort swap entries before free
  mm/oom_kill: count global and memory cgroup oom kills
  mm: per-cgroup memory reclaim stats
  mm: kmemleak: treat vm_struct as alternative reference to vmalloc'ed objects
  mm: kmemleak: factor object reference updating out of scan_block()
  mm: kmemleak: slightly reduce the size of some structures on 64-bit architectures
  mm, mempolicy: don't check cpuset seqlock where it doesn't matter
  mm, cpuset: always use seqlock when changing task's nodemask
  mm, mempolicy: simplify rebinding mempolicies when updating cpusets
  ...

9 files changed, 25 insertions, 43 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index ae643412948a..ca8376e5008c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1038,40 +1038,25 @@ static void cpuset_post_attach(void)
  * @tsk: the task to change
  * @newmems: new nodes that the task will be set
  *
- * In order to avoid seeing no nodes if the old and new nodes are disjoint,
- * we structure updates as setting all new allowed nodes, then clearing newly
- * disallowed ones.
+ * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed
+ * and rebind an eventual tasks' mempolicy. If the task is allocating in
+ * parallel, it might temporarily see an empty intersection, which results in
+ * a seqlock check and retry before OOM or allocation failure.
  */
 static void cpuset_change_task_nodemask(struct task_struct *tsk,
 					nodemask_t *newmems)
 {
-	bool need_loop;
-
 	task_lock(tsk);
-	/*
-	 * Determine if a loop is necessary if another thread is doing
-	 * read_mems_allowed_begin().  If at least one node remains unchanged and
-	 * tsk does not have a mempolicy, then an empty nodemask will not be
-	 * possible when mems_allowed is larger than a word.
-	 */
-	need_loop = task_has_mempolicy(tsk) ||
-			!nodes_intersects(*newmems, tsk->mems_allowed);
 
-	if (need_loop) {
-		local_irq_disable();
-		write_seqcount_begin(&tsk->mems_allowed_seq);
-	}
+	local_irq_disable();
+	write_seqcount_begin(&tsk->mems_allowed_seq);
 
 	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
-	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
-
-	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
+	mpol_rebind_task(tsk, newmems);
 	tsk->mems_allowed = *newmems;
 
-	if (need_loop) {
-		write_seqcount_end(&tsk->mems_allowed_seq);
-		local_irq_enable();
-	}
+	write_seqcount_end(&tsk->mems_allowed_seq);
+	local_irq_enable();
 
 	task_unlock(tsk);
 }
diff --git a/kernel/exit.c b/kernel/exit.c
index b0cc86a2d00b..2bbc23273e2f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -51,7 +51,6 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/tracehook.h>
 #include <linux/fs_struct.h>
-#include <linux/userfaultfd_k.h>
 #include <linux/init_task.h>
 #include <linux/perf_event.h>
 #include <trace/events/sched.h>
diff --git a/kernel/extable.c b/kernel/extable.c
index 0fbdd8582f08..223df4a328a4 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -69,7 +69,7 @@ static inline int init_kernel_text(unsigned long addr)
 	return 0;
 }
 
-int core_kernel_text(unsigned long addr)
+int notrace core_kernel_text(unsigned long addr)
 {
 	if (addr >= (unsigned long)_stext &&
 	    addr < (unsigned long)_etext)
diff --git a/kernel/fork.c b/kernel/fork.c
index e53770d2bf95..aa01b810c0bd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -326,8 +326,8 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 		}
 
 		/* All stack pages belong to the same memcg. */
-		memcg_kmem_update_page_stat(vm->pages[0], MEMCG_KERNEL_STACK_KB,
-					    account * (THREAD_SIZE / 1024));
+		mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB,
+				     account * (THREAD_SIZE / 1024));
 	} else {
 		/*
 		 * All stack pages are in the same zone and belong to the
@@ -338,8 +338,8 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 		mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
 				    THREAD_SIZE / 1024 * account);
 
-		memcg_kmem_update_page_stat(first_page, MEMCG_KERNEL_STACK_KB,
-					    account * (THREAD_SIZE / 1024));
+		mod_memcg_page_state(first_page, MEMCG_KERNEL_STACK_KB,
+				     account * (THREAD_SIZE / 1024));
 	}
 }
 
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index e6b2f7ad3e51..4ccfcaae5b89 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -193,7 +193,8 @@ void __init __pv_init_lock_hash(void)
 	 */
 	pv_lock_hash = alloc_large_system_hash("PV qspinlock",
 					       sizeof(struct pv_hash_entry),
-					       pv_hash_size, 0, HASH_EARLY,
+					       pv_hash_size, 0,
+					       HASH_EARLY | HASH_ZERO,
 					       &pv_lock_hash_bits, NULL,
 					       pv_hash_size, pv_hash_size);
 }
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 23a6483c3666..124bed776532 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -358,7 +358,11 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 		goto err_pfn_remap;
 
 	mem_hotplug_begin();
-	error = arch_add_memory(nid, align_start, align_size, true);
+	error = arch_add_memory(nid, align_start, align_size, false);
+	if (!error)
+		move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
+					align_start >> PAGE_SHIFT,
+					align_size >> PAGE_SHIFT);
 	mem_hotplug_done();
 	if (error)
 		goto err_add_memory;
diff --git a/kernel/module.c b/kernel/module.c
index 1d958c6d5c24..b3dbdde82e80 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -49,9 +49,7 @@
 #include <linux/rculist.h>
 #include <linux/uaccess.h>
 #include <asm/cacheflush.h>
-#ifdef CONFIG_STRICT_MODULE_RWX
-#include <asm/set_memory.h>
-#endif
+#include <linux/set_memory.h>
 #include <asm/mmu_context.h>
 #include <linux/license.h>
 #include <asm/sections.h>
diff --git a/kernel/pid.c b/kernel/pid.c
index fd1cde1e4576..731c4e528f4e 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -575,16 +575,13 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
  */
 void __init pidhash_init(void)
 {
-	unsigned int i, pidhash_size;
+	unsigned int pidhash_size;
 
 	pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
-					   HASH_EARLY | HASH_SMALL,
+					   HASH_EARLY | HASH_SMALL | HASH_ZERO,
 					   &pidhash_shift, NULL,
 					   0, 4096);
 	pidhash_size = 1U << pidhash_shift;
-
-	for (i = 0; i < pidhash_size; i++)
-		INIT_HLIST_HEAD(&pid_hash[i]);
 }
 
 void __init pidmap_init(void)
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index b7708e319941..222317721c5a 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -30,15 +30,13 @@
 #include <linux/slab.h>
 #include <linux/compiler.h>
 #include <linux/ktime.h>
+#include <linux/set_memory.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/io.h>
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-#include <asm/set_memory.h>
-#endif
 
 #include "power.h"