26 files changed, 226 insertions, 194 deletions

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index aa8f61c..4cd4ddf 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -15,7 +15,8 @@
 /* For more detailed tracepoint output */
 #define COMPACT_NO_SUITABLE_PAGE	5
 #define COMPACT_NOT_SUITABLE_ZONE	6
-/* When adding new state, please change compaction_status_string, too */
+#define COMPACT_CONTENDED		7
+/* When adding new states, please adjust include/trace/events/compaction.h */
 
 /* Used to signal whether compaction detected need_sched() or lock contention */
 /* No contention detected */
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 8efb40e..0e3110a 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -210,6 +210,23 @@
 #define __visible	__attribute__((externally_visible))
 #endif
 
+
+#if GCC_VERSION >= 40900 && !defined(__CHECKER__)
+/*
+ * __assume_aligned(n, k): Tell the optimizer that the returned
+ * pointer can be assumed to be k modulo n. The second argument is
+ * optional (default 0), so we use a variadic macro to make the
+ * shorthand.
+ *
+ * Beware: Do not apply this to functions which may return
+ * ERR_PTRs. Also, it is probably unwise to apply it to functions
+ * returning extra information in the low bits (but in that case the
+ * compiler should see some alignment anyway, when the return value is
+ * massaged by 'flags = ptr & 3; ptr &= ~3;').
+ */
+#define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__)))
+#endif
+
 /*
  * GCC 'asm goto' miscompiles certain code sequences:
  *
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 52a459f..4dac103 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -417,6 +417,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 #define __visible
 #endif
 
+/*
+ * Assume alignment of return value.
+ */
+#ifndef __assume_aligned
+#define __assume_aligned(a, ...)
+#endif
+
+
 /* Are two types/vars the same type (ignoring qualifiers)? */
 #ifndef __same_type
 # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 1b35799..5a13119 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -93,7 +93,7 @@ extern int current_cpuset_is_being_rebound(void);
 
 extern void rebuild_sched_domains(void);
 
-extern void cpuset_print_task_mems_allowed(struct task_struct *p);
+extern void cpuset_print_current_mems_allowed(void);
 
 /*
  * read_mems_allowed_begin is required when making decisions involving
@@ -219,7 +219,7 @@ static inline void rebuild_sched_domains(void)
 	partition_sched_domains(1, NULL, NULL);
 }
 
-static inline void cpuset_print_task_mems_allowed(struct task_struct *p)
+static inline void cpuset_print_current_mems_allowed(void)
 {
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4974968..9a1cb8c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2409,6 +2409,7 @@ extern int write_inode_now(struct inode *, int);
 extern int filemap_fdatawrite(struct address_space *);
 extern int filemap_flush(struct address_space *);
 extern int filemap_fdatawait(struct address_space *);
+extern void filemap_fdatawait_keep_errors(struct address_space *);
 extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
 				   loff_t lend);
 extern int filemap_write_and_wait(struct address_space *mapping);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 5e35379..685c262 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -483,6 +483,17 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 #define hugepages_supported() (HPAGE_SHIFT != 0)
 #endif
 
+void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm);
+
+static inline void hugetlb_count_add(long l, struct mm_struct *mm)
+{
+	atomic_long_add(l, &mm->hugetlb_usage);
+}
+
+static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
+{
+	atomic_long_sub(l, &mm->hugetlb_usage);
+}
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page(v, a, r) NULL
@@ -519,6 +530,14 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 {
 	return &mm->page_table_lock;
 }
+
+static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m)
+{
+}
+
+static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
+{
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index c518eb5..24daf8f 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -89,10 +89,6 @@ int memblock_add_range(struct memblock_type *type,
 		       phys_addr_t base, phys_addr_t size,
 		       int nid, unsigned long flags);
 
-int memblock_remove_range(struct memblock_type *type,
-			  phys_addr_t base,
-			  phys_addr_t size);
-
 void __next_mem_range(u64 *idx, int nid, ulong flags,
 		      struct memblock_type *type_a,
 		      struct memblock_type *type_b, phys_addr_t *out_start,
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 27251ed..cd0e241 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -301,8 +301,7 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg);
 void mem_cgroup_uncharge(struct page *page);
 void mem_cgroup_uncharge_list(struct list_head *page_list);
 
-void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
-			bool lrucare);
+void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage);
 
 struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
@@ -384,7 +383,7 @@ unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 	return mz->lru_size[lru];
 }
 
-static inline int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
+static inline bool mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 {
 	unsigned long inactive_ratio;
 	unsigned long inactive;
@@ -403,24 +402,26 @@ static inline int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 	return inactive * inactive_ratio < active;
 }
 
+void mem_cgroup_handle_over_high(void);
+
 void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 				struct task_struct *p);
 
 static inline void mem_cgroup_oom_enable(void)
 {
-	WARN_ON(current->memcg_oom.may_oom);
-	current->memcg_oom.may_oom = 1;
+	WARN_ON(current->memcg_may_oom);
+	current->memcg_may_oom = 1;
 }
 
 static inline void mem_cgroup_oom_disable(void)
 {
-	WARN_ON(!current->memcg_oom.may_oom);
-	current->memcg_oom.may_oom = 0;
+	WARN_ON(!current->memcg_may_oom);
+	current->memcg_may_oom = 0;
 }
 
 static inline bool task_in_memcg_oom(struct task_struct *p)
 {
-	return p->memcg_oom.memcg;
+	return p->memcg_in_oom;
 }
 
 bool mem_cgroup_oom_synchronize(bool wait);
@@ -537,9 +538,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
 {
 }
 
-static inline void mem_cgroup_migrate(struct page *oldpage,
-				      struct page *newpage,
-				      bool lrucare)
+static inline void mem_cgroup_replace_page(struct page *old, struct page *new)
 {
 }
 
@@ -585,10 +584,10 @@ static inline bool mem_cgroup_disabled(void)
 	return true;
 }
 
-static inline int
+static inline bool
 mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 {
-	return 1;
+	return true;
 }
 
 static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
@@ -622,6 +621,10 @@ static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
 {
 }
 
+static inline void mem_cgroup_handle_over_high(void)
+{
+}
+
 static inline void mem_cgroup_oom_enable(void)
 {
 }
@@ -748,11 +751,10 @@ static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
  * conditions, but because they are pretty simple, they are expected to be
  * fast.
  */
-bool __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg,
-					int order);
-void __memcg_kmem_commit_charge(struct page *page,
-				       struct mem_cgroup *memcg, int order);
-void __memcg_kmem_uncharge_pages(struct page *page, int order);
+int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
+			      struct mem_cgroup *memcg);
+int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
+void __memcg_kmem_uncharge(struct page *page, int order);
 
 /*
  * helper for acessing a memcg's index. It will be used as an index in the
@@ -767,77 +769,42 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
 void __memcg_kmem_put_cache(struct kmem_cache *cachep);
 
-struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr);
-
-int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
-		      unsigned long nr_pages);
-void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages);
-
-/**
- * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
- * @gfp: the gfp allocation flags.
- * @memcg: a pointer to the memcg this was charged against.
- * @order: allocation order.
- *
- * returns true if the memcg where the current task belongs can hold this
- * allocation.
- *
- * We return true automatically if this allocation is not to be accounted to
- * any memcg.
- */
-static inline bool
-memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
+static inline bool __memcg_kmem_bypass(gfp_t gfp)
 {
 	if (!memcg_kmem_enabled())
 		return true;
-
 	if (gfp & __GFP_NOACCOUNT)
 		return true;
-	/*
-	 * __GFP_NOFAIL allocations will move on even if charging is not
-	 * possible. Therefore we don't even try, and have this allocation
-	 * unaccounted. We could in theory charge it forcibly, but we hope
-	 * those allocations are rare, and won't be worth the trouble.
-	 */
-	if (gfp & __GFP_NOFAIL)
-		return true;
 	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
 		return true;
-
-	/* If the test is dying, just let it go. */
-	if (unlikely(fatal_signal_pending(current)))
-		return true;
-
-	return __memcg_kmem_newpage_charge(gfp, memcg, order);
+	return false;
 }
 
 /**
- * memcg_kmem_uncharge_pages: uncharge pages from memcg
- * @page: pointer to struct page being freed
- * @order: allocation order.
+ * memcg_kmem_charge: charge a kmem page
+ * @page: page to charge
+ * @gfp: reclaim mode
+ * @order: allocation order
+ *
+ * Returns 0 on success, an error code on failure.
  */
-static inline void
-memcg_kmem_uncharge_pages(struct page *page, int order)
+static __always_inline int memcg_kmem_charge(struct page *page,
+					     gfp_t gfp, int order)
 {
-	if (memcg_kmem_enabled())
-		__memcg_kmem_uncharge_pages(page, order);
+	if (__memcg_kmem_bypass(gfp))
+		return 0;
+	return __memcg_kmem_charge(page, gfp, order);
 }
 
 /**
- * memcg_kmem_commit_charge: embeds correct memcg in a page
- * @page: pointer to struct page recently allocated
- * @memcg: the memcg structure we charged against
- * @order: allocation order.
- *
- * Needs to be called after memcg_kmem_newpage_charge, regardless of success or
- * failure of the allocation. if @page is NULL, this function will revert the
- * charges. Otherwise, it will commit @page to @memcg.
+ * memcg_kmem_uncharge: uncharge a kmem page
+ * @page: page to uncharge
+ * @order: allocation order
  */
-static inline void
-memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
+static __always_inline void memcg_kmem_uncharge(struct page *page, int order)
 {
-	if (memcg_kmem_enabled() && memcg)
-		__memcg_kmem_commit_charge(page, memcg, order);
+	if (memcg_kmem_enabled())
+		__memcg_kmem_uncharge(page, order);
 }
 
 /**
@@ -850,17 +817,8 @@ memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
 static __always_inline struct kmem_cache *
 memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
-	if (!memcg_kmem_enabled())
-		return cachep;
-	if (gfp & __GFP_NOACCOUNT)
-		return cachep;
-	if (gfp & __GFP_NOFAIL)
-		return cachep;
-	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
+	if (__memcg_kmem_bypass(gfp))
 		return cachep;
-	if (unlikely(fatal_signal_pending(current)))
-		return cachep;
-
 	return __memcg_kmem_get_cache(cachep);
 }
 
@@ -869,13 +827,6 @@ static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
 	if (memcg_kmem_enabled())
 		__memcg_kmem_put_cache(cachep);
 }
-
-static __always_inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
-{
-	if (!memcg_kmem_enabled())
-		return NULL;
-	return __mem_cgroup_from_kmem(ptr);
-}
 #else
 #define for_each_memcg_cache_index(_idx)	\
 	for (; NULL; )
@@ -890,18 +841,12 @@ static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
 	return false;
 }
 
-static inline bool
-memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
-{
-	return true;
-}
-
-static inline void memcg_kmem_uncharge_pages(struct page *page, int order)
+static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 {
+	return 0;
 }
 
-static inline void
-memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
+static inline void memcg_kmem_uncharge(struct page *page, int order)
 {
 }
 
@@ -927,11 +872,5 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
 {
 }
-
-static inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
-{
-	return NULL;
-}
 #endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
-
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80001de..906c46a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -139,6 +139,7 @@ extern unsigned int kobjsize(const void *objp);
 
 #define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
 #define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
+#define VM_LOCKONFAULT	0x00080000	/* Lock the pages covered when they are faulted in */
 #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
 #define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
@@ -202,6 +203,9 @@ extern unsigned int kobjsize(const void *objp);
 /* This mask defines which mm->def_flags a process can inherit its parent */
 #define VM_INIT_DEF_MASK	VM_NOHUGEPAGE
 
+/* This mask is used to clear all the VMA flags used by mlock */
+#define VM_LOCKED_CLEAR_MASK	(~(VM_LOCKED | VM_LOCKONFAULT))
+
 /*
  * mapping from the currently active vm_flags protection bits (the
  * low four bits) to a page protection mask..
@@ -1606,8 +1610,10 @@ static inline void pgtable_init(void)
 
 static inline bool pgtable_page_ctor(struct page *page)
 {
+	if (!ptlock_init(page))
+		return false;
 	inc_zone_page_state(page, NR_PAGETABLE);
-	return ptlock_init(page);
+	return true;
 }
 
 static inline void pgtable_page_dtor(struct page *page)
@@ -2036,8 +2042,6 @@ void page_cache_async_readahead(struct address_space *mapping,
 				pgoff_t offset,
 				unsigned long size);
 
-unsigned long max_sane_readahead(unsigned long nr);
-
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
 
@@ -2137,6 +2141,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */
 #define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
+#define FOLL_MLOCK	0x1000	/* lock present pages */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3d6baa7..0a85da2 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -486,6 +486,9 @@ struct mm_struct {
 	/* address of the bounds directory */
 	void __user *bd_addr;
 #endif
+#ifdef CONFIG_HUGETLB_PAGE
+	atomic_long_t hugetlb_usage;
+#endif
 };
 
 static inline void mm_init_cpumask(struct mm_struct *mm)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d943477..2d7e660 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -823,8 +823,7 @@ enum memmap_context {
 	MEMMAP_HOTPLUG,
 };
 extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
-				     unsigned long size,
-				     enum memmap_context context);
+				     unsigned long size);
 
 extern void lruvec_init(struct lruvec *lruvec);
 
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 78488e0..7ec5b86 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -73,6 +73,7 @@ extern int watchdog_user_enabled;
 extern int watchdog_thresh;
 extern unsigned long *watchdog_cpumask_bits;
 extern int sysctl_softlockup_all_cpu_backtrace;
+extern int sysctl_hardlockup_all_cpu_backtrace;
 struct ctl_table;
 extern int proc_watchdog(struct ctl_table *, int ,
 			 void __user *, size_t *, loff_t *);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 416509e..a525e50 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -256,7 +256,7 @@ PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim)
  * Must use a macro here due to header dependency issues. page_zone() is not
  * available at this point.
  */
-#define PageHighMem(__p) is_highmem(page_zone(__p))
+#define PageHighMem(__p) is_highmem_idx(page_zonenum(__p))
 #else
 PAGEFLAG_FALSE(HighMem)
 #endif
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index 17fa4f8..7e62920 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -36,9 +36,9 @@ static inline unsigned long page_counter_read(struct page_counter *counter)
 
 void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages);
 void page_counter_charge(struct page_counter *counter, unsigned long nr_pages);
-int page_counter_try_charge(struct page_counter *counter,
-			    unsigned long nr_pages,
-			    struct page_counter **fail);
+bool page_counter_try_charge(struct page_counter *counter,
+			     unsigned long nr_pages,
+			     struct page_counter **fail);
 void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
 int page_counter_limit(struct page_counter *counter, unsigned long limit);
 int page_counter_memparse(const char *buf, const char *max,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4effb10..eeb5066 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -384,6 +384,7 @@ extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
 				  void __user *buffer,
 				  size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
+extern unsigned int  hardlockup_panic;
 void lockup_detector_init(void);
 #else
 static inline void touch_softlockup_watchdog(void)
@@ -1460,7 +1461,9 @@ struct task_struct {
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
 	unsigned sched_migrated:1;
-
+#ifdef CONFIG_MEMCG
+	unsigned memcg_may_oom:1;
+#endif
 #ifdef CONFIG_MEMCG_KMEM
 	unsigned memcg_kmem_skip_account:1;
 #endif
@@ -1791,12 +1794,12 @@ struct task_struct {
 	unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
 #ifdef CONFIG_MEMCG
-	struct memcg_oom_info {
-		struct mem_cgroup *memcg;
-		gfp_t gfp_mask;
-		int order;
-		unsigned int may_oom:1;
-	} memcg_oom;
+	struct mem_cgroup *memcg_in_oom;
+	gfp_t memcg_oom_gfp_mask;
+	int memcg_oom_order;
+
+	/* number of pages to reclaim on returning to userland */
+	unsigned int memcg_nr_pages_over_high;
 #endif
 #ifdef CONFIG_UPROBES
 	struct uprobe_task *utask;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 7e37d44..7c82e3b 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -111,7 +111,7 @@ struct mem_cgroup;
  * struct kmem_cache related prototypes
  */
 void __init kmem_cache_init(void);
-int slab_is_available(void);
+bool slab_is_available(void);
 
 struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			unsigned long,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a460e2e..a156b82 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -887,4 +887,6 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename,
 
 asmlinkage long sys_membarrier(int cmd, int flags);
 
+asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
+
 #endif
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 84d4972..26c1521 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -50,6 +50,7 @@
 #include <linux/ptrace.h>
 #include <linux/security.h>
 #include <linux/task_work.h>
+#include <linux/memcontrol.h>
 struct linux_binprm;
 
 /*
@@ -188,6 +189,8 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 	smp_mb__after_atomic();
 	if (unlikely(current->task_works))
 		task_work_run();
+
+	mem_cgroup_handle_over_high();
 }
 
 #endif	/* <linux/tracehook.h> */
diff --git a/include/linux/types.h b/include/linux/types.h
index c314989..70d8500 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -205,11 +205,25 @@ struct ustat {
  * struct callback_head - callback structure for use with RCU and task_work
  * @next: next update requests in a list
  * @func: actual update function to call after the grace period.
+ *
+ * The struct is aligned to size of pointer. On most architectures it happens
+ * naturally due ABI requirements, but some architectures (like CRIS) have
+ * weird ABI and we need to ask it explicitly.
+ *
+ * The alignment is required to guarantee that bits 0 and 1 of @next will be
+ * clear under normal conditions -- as long as we use call_rcu(),
+ * call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback.
+ *
+ * This guarantee is important for few reasons:
+ *  - future call_rcu_lazy() will make use of lower bits in the pointer;
+ *  - the structure shares storage spacer in struct page with @compound_head,
+ *    which encode PageTail() in bit 0. The guarantee is needed to avoid
+ *    false-positive PageTail().
  */
 struct callback_head {
 	struct callback_head *next;
 	void (*func)(struct callback_head *head);
-};
+} __attribute__((aligned(sizeof(void *))));
 #define rcu_head callback_head
 
 typedef void (*rcu_callback_t)(struct rcu_head *head);
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index d6f2c2c..558129a 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -75,36 +75,6 @@ static inline unsigned long __copy_from_user_nocache(void *to,
 
 #endif		/* ARCH_HAS_NOCACHE_UACCESS */
 
-/**
- * probe_kernel_address(): safely attempt to read from a location
- * @addr: address to read from - its type is type typeof(retval)*
- * @retval: read into this variable
- *
- * Safely read from address @addr into variable @revtal.  If a kernel fault
- * happens, handle that and return -EFAULT.
- * We ensure that the __get_user() is executed in atomic context so that
- * do_page_fault() doesn't attempt to take mmap_sem.  This makes
- * probe_kernel_address() suitable for use within regions where the caller
- * already holds mmap_sem, or other locks which nest inside mmap_sem.
- * This must be a macro because __get_user() needs to know the types of the
- * args.
- *
- * We don't include enough header files to be able to do the set_fs().  We
- * require that the probe_kernel_address() caller will do that.
- */
-#define probe_kernel_address(addr, retval)		\
-	({						\
-		long ret;				\
-		mm_segment_t old_fs = get_fs();		\
-							\
-		set_fs(KERNEL_DS);			\
-		pagefault_disable();			\
-		ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval));		\
-		pagefault_enable();			\
-		set_fs(old_fs);				\
-		ret;					\
-	})
-
 /*
  * probe_kernel_read(): safely attempt to read from a location
  * @dst: pointer to the buffer that shall take the data
@@ -131,4 +101,14 @@ extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size
 
 extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
 
+/**
+ * probe_kernel_address(): safely attempt to read from a location
+ * @addr: address to read from
+ * @retval: read into this variable
+ *
+ * Returns 0 on success, or -EFAULT.
+ */
+#define probe_kernel_address(addr, retval)		\
+	probe_kernel_read(&retval, addr, sizeof(retval))
+
 #endif		/* __LINUX_UACCESS_H__ */
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 9246d32..e623d39 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -14,12 +14,12 @@
 #endif
 
 #ifdef CONFIG_HIGHMEM
-#define HIGHMEM_ZONE(xx) , xx##_HIGH
+#define HIGHMEM_ZONE(xx) xx##_HIGH,
 #else
 #define HIGHMEM_ZONE(xx)
 #endif
 
-#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL HIGHMEM_ZONE(xx) , xx##_MOVABLE
+#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, HIGHMEM_ZONE(xx) xx##_MOVABLE
 
 enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGALLOC),
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 82e7db7..5dbc8b0 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -161,30 +161,8 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
 }
 
 #ifdef CONFIG_NUMA
-/*
- * Determine the per node value of a stat item. This function
- * is called frequently in a NUMA machine, so try to be as
- * frugal as possible.
- */
-static inline unsigned long node_page_state(int node,
-				 enum zone_stat_item item)
-{
-	struct zone *zones = NODE_DATA(node)->node_zones;
-
-	return
-#ifdef CONFIG_ZONE_DMA
-		zone_page_state(&zones[ZONE_DMA], item) +
-#endif
-#ifdef CONFIG_ZONE_DMA32
-		zone_page_state(&zones[ZONE_DMA32], item) +
-#endif
-#ifdef CONFIG_HIGHMEM
-		zone_page_state(&zones[ZONE_HIGHMEM], item) +
-#endif
-		zone_page_state(&zones[ZONE_NORMAL], item) +
-		zone_page_state(&zones[ZONE_MOVABLE], item);
-}
 
+extern unsigned long node_page_state(int node, enum zone_stat_item item);
 extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp);
 
 #else
@@ -269,7 +247,6 @@ static inline void __dec_zone_page_state(struct page *page,
 
 #define set_pgdat_percpu_threshold(pgdat, callback) { }
 
-static inline void refresh_cpu_vm_stats(int cpu) { }
 static inline void refresh_zone_stat_thresholds(void) { }
 static inline void cpu_vm_stats_fold(int cpu) { }
 
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index 9a6a3fe..c92d1e1 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -9,6 +9,62 @@
 #include <linux/tracepoint.h>
 #include <trace/events/gfpflags.h>
 
+#define COMPACTION_STATUS					\
+	EM( COMPACT_DEFERRED,		"deferred")		\
+	EM( COMPACT_SKIPPED,		"skipped")		\
+	EM( COMPACT_CONTINUE,		"continue")		\
+	EM( COMPACT_PARTIAL,		"partial")		\
+	EM( COMPACT_COMPLETE,		"complete")		\
+	EM( COMPACT_NO_SUITABLE_PAGE,	"no_suitable_page")	\
+	EM( COMPACT_NOT_SUITABLE_ZONE,	"not_suitable_zone")	\
+	EMe(COMPACT_CONTENDED,		"contended")
+
+#ifdef CONFIG_ZONE_DMA
+#define IFDEF_ZONE_DMA(X) X
+#else
+#define IFDEF_ZONE_DMA(X)
+#endif
+
+#ifdef CONFIG_ZONE_DMA32
+#define IFDEF_ZONE_DMA32(X) X
+#else
+#define IFDEF_ZONE_DMA32(X)
+#endif
+
+#ifdef CONFIG_HIGHMEM
+#define IFDEF_ZONE_HIGHMEM(X) X
+#else
+#define IFDEF_ZONE_HIGHMEM(X)
+#endif
+
+#define ZONE_TYPE						\
+	IFDEF_ZONE_DMA(		EM (ZONE_DMA,	 "DMA"))	\
+	IFDEF_ZONE_DMA32(	EM (ZONE_DMA32,	 "DMA32"))	\
+				EM (ZONE_NORMAL, "Normal")	\
+	IFDEF_ZONE_HIGHMEM(	EM (ZONE_HIGHMEM,"HighMem"))	\
+				EMe(ZONE_MOVABLE,"Movable")
+
+/*
+ * First define the enums in the above macros to be exported to userspace
+ * via TRACE_DEFINE_ENUM().
+ */
+#undef EM
+#undef EMe
+#define EM(a, b)	TRACE_DEFINE_ENUM(a);
+#define EMe(a, b)	TRACE_DEFINE_ENUM(a);
+
+COMPACTION_STATUS
+ZONE_TYPE
+
+/*
+ * Now redefine the EM() and EMe() macros to map the enums to the strings
+ * that will be printed in the output.
+ */
+#undef EM
+#undef EMe
+#define EM(a, b)	{a, b},
+#define EMe(a, b)	{a, b}
+
 DECLARE_EVENT_CLASS(mm_compaction_isolate_template,
 
 	TP_PROTO(
@@ -161,7 +217,7 @@ TRACE_EVENT(mm_compaction_end,
 		__entry->free_pfn,
 		__entry->zone_end,
 		__entry->sync ? "sync" : "async",
-		compaction_status_string[__entry->status])
+		__print_symbolic(__entry->status, COMPACTION_STATUS))
 );
 
 TRACE_EVENT(mm_compaction_try_to_compact_pages,
@@ -201,23 +257,23 @@ DECLARE_EVENT_CLASS(mm_compaction_suitable_template,
 
 	TP_STRUCT__entry(
 		__field(int, nid)
-		__field(char *, name)
+		__field(enum zone_type, idx)
 		__field(int, order)
 		__field(int, ret)
 	),
 
 	TP_fast_assign(
 		__entry->nid = zone_to_nid(zone);
-		__entry->name = (char *)zone->name;
+		__entry->idx = zone_idx(zone);
 		__entry->order = order;
 		__entry->ret = ret;
 	),
 
 	TP_printk("node=%d zone=%-8s order=%d ret=%s",
 		__entry->nid,
-		__entry->name,
+		__print_symbolic(__entry->idx, ZONE_TYPE),
 		__entry->order,
-		compaction_status_string[__entry->ret])
+		__print_symbolic(__entry->ret, COMPACTION_STATUS))
 );
 
 DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_finished,
@@ -247,7 +303,7 @@ DECLARE_EVENT_CLASS(mm_compaction_defer_template,
 
 	TP_STRUCT__entry(
 		__field(int, nid)
-		__field(char *, name)
+		__field(enum zone_type, idx)
 		__field(int, order)
 		__field(unsigned int, considered)
 		__field(unsigned int, defer_shift)
@@ -256,7 +312,7 @@ DECLARE_EVENT_CLASS(mm_compaction_defer_template,
 
 	TP_fast_assign(
 		__entry->nid = zone_to_nid(zone);
-		__entry->name = (char *)zone->name;
+		__entry->idx = zone_idx(zone);
 		__entry->order = order;
 		__entry->considered = zone->compact_considered;
 		__entry->defer_shift = zone->compact_defer_shift;
@@ -265,7 +321,7 @@ DECLARE_EVENT_CLASS(mm_compaction_defer_template,
 
 	TP_printk("node=%d zone=%-8s order=%d order_failed=%d consider=%u limit=%lu",
 		__entry->nid,
-		__entry->name,
+		__print_symbolic(__entry->idx, ZONE_TYPE),
 		__entry->order,
 		__entry->order_failed,
 		__entry->considered,
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index ddc3b36..a74dd84 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -25,6 +25,11 @@
 # define MAP_UNINITIALIZED 0x0		/* Don't support this flag */
 #endif
 
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
+
 #define MS_ASYNC	1		/* sync memory asynchronously */
 #define MS_INVALIDATE	2		/* invalidate the caches */
 #define MS_SYNC		4		/* synchronous memory sync */
diff --git a/include/uapi/asm-generic/mman.h b/include/uapi/asm-generic/mman.h
index e9fe6fd..7162cd4 100644
--- a/include/uapi/asm-generic/mman.h
+++ b/include/uapi/asm-generic/mman.h
@@ -17,5 +17,6 @@
 
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
 
 #endif /* __ASM_GENERIC_MMAN_H */
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index ee12400..1324b02 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -713,9 +713,11 @@ __SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
 __SYSCALL(__NR_userfaultfd, sys_userfaultfd)
 #define __NR_membarrier 283
 __SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 284
+__SYSCALL(__NR_mlock2, sys_mlock2)
 
 #undef __NR_syscalls
-#define __NR_syscalls 284
+#define __NR_syscalls 285
 
 /*
  * All syscalls below here should go away really,