16 files changed, 323 insertions, 140 deletions

diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h
index 12a1764f612b..9a62937c56ca 100644
--- a/include/asm-generic/cputime.h
+++ b/include/asm-generic/cputime.h
@@ -4,71 +4,66 @@
 #include <linux/time.h>
 #include <linux/jiffies.h>
 
-typedef unsigned long cputime_t;
+typedef unsigned long __nocast cputime_t;
 
-#define cputime_zero                    (0UL)
 #define cputime_one_jiffy               jiffies_to_cputime(1)
-#define cputime_max                     ((~0UL >> 1) - 1)
-#define cputime_add(__a, __b)           ((__a) +  (__b))
-#define cputime_sub(__a, __b)           ((__a) -  (__b))
-#define cputime_div(__a, __n)           ((__a) /  (__n))
-#define cputime_halve(__a)              ((__a) >> 1)
-#define cputime_eq(__a, __b)            ((__a) == (__b))
-#define cputime_gt(__a, __b)            ((__a) >  (__b))
-#define cputime_ge(__a, __b)            ((__a) >= (__b))
-#define cputime_lt(__a, __b)            ((__a) <  (__b))
-#define cputime_le(__a, __b)            ((__a) <= (__b))
-#define cputime_to_jiffies(__ct)        (__ct)
+#define cputime_to_jiffies(__ct)        (__force unsigned long)(__ct)
 #define cputime_to_scaled(__ct)         (__ct)
-#define jiffies_to_cputime(__hz)        (__hz)
+#define jiffies_to_cputime(__hz)        (__force cputime_t)(__hz)
 
-typedef u64 cputime64_t;
+typedef u64 __nocast cputime64_t;
 
-#define cputime64_zero (0ULL)
-#define cputime64_add(__a, __b)         ((__a) + (__b))
-#define cputime64_sub(__a, __b)         ((__a) - (__b))
-#define cputime64_to_jiffies64(__ct)    (__ct)
-#define jiffies64_to_cputime64(__jif)   (__jif)
-#define cputime_to_cputime64(__ct)      ((u64) __ct)
-#define cputime64_gt(__a, __b)          ((__a) >  (__b))
+#define cputime64_to_jiffies64(__ct)    (__force u64)(__ct)
+#define jiffies64_to_cputime64(__jif)   (__force cputime64_t)(__jif)
 
-#define nsecs_to_cputime64(__ct)        nsecs_to_jiffies64(__ct)
+#define nsecs_to_cputime64(__ct)        \
+        jiffies64_to_cputime64(nsecs_to_jiffies64(__ct))
 
 
 /*
  * Convert cputime to microseconds and back.
  */
-#define cputime_to_usecs(__ct)          jiffies_to_usecs(__ct)
-#define usecs_to_cputime(__msecs)       usecs_to_jiffies(__msecs)
-#define usecs_to_cputime64(__msecs)     nsecs_to_jiffies64((__msecs) * 1000)
+#define cputime_to_usecs(__ct)          \
+        jiffies_to_usecs(cputime_to_jiffies(__ct))
+#define usecs_to_cputime(__usec)        \
+        jiffies_to_cputime(usecs_to_jiffies(__usec))
+#define usecs_to_cputime64(__usec)      \
+        jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000))
 
 /*
  * Convert cputime to seconds and back.
  */
-#define cputime_to_secs(jif)            ((jif) / HZ)
-#define secs_to_cputime(sec)            ((sec) * HZ)
+#define cputime_to_secs(jif)            (cputime_to_jiffies(jif) / HZ)
+#define secs_to_cputime(sec)            jiffies_to_cputime((sec) * HZ)
 
 /*
  * Convert cputime to timespec and back.
  */
-#define timespec_to_cputime(__val)      timespec_to_jiffies(__val)
-#define cputime_to_timespec(__ct,__val) jiffies_to_timespec(__ct,__val)
+#define timespec_to_cputime(__val)      \
+        jiffies_to_cputime(timespec_to_jiffies(__val))
+#define cputime_to_timespec(__ct,__val) \
+        jiffies_to_timespec(cputime_to_jiffies(__ct),__val)
 
 /*
  * Convert cputime to timeval and back.
  */
-#define timeval_to_cputime(__val)       timeval_to_jiffies(__val)
-#define cputime_to_timeval(__ct,__val)  jiffies_to_timeval(__ct,__val)
+#define timeval_to_cputime(__val)       \
+        jiffies_to_cputime(timeval_to_jiffies(__val))
+#define cputime_to_timeval(__ct,__val)  \
+        jiffies_to_timeval(cputime_to_jiffies(__ct),__val)
 
 /*
  * Convert cputime to clock and back.
  */
-#define cputime_to_clock_t(__ct)        jiffies_to_clock_t(__ct)
-#define clock_t_to_cputime(__x)         clock_t_to_jiffies(__x)
+#define cputime_to_clock_t(__ct)        \
+        jiffies_to_clock_t(cputime_to_jiffies(__ct))
+#define clock_t_to_cputime(__x)         \
+        jiffies_to_cputime(clock_t_to_jiffies(__x))
 
 /*
  * Convert cputime64 to clock.
  */
-#define cputime64_to_clock_t(__ct)      jiffies_64_to_clock_t(__ct)
+#define cputime64_to_clock_t(__ct)      \
+        jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct))
 
 #endif
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index a3ef66a2a083..3c1063acb2ab 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -22,8 +22,14 @@ extern unsigned long __sw_hweight64(__u64 w);
 #include <asm/bitops.h>
 
 #define for_each_set_bit(bit, addr, size) \
-        for ((bit) = find_first_bit((addr), (size)); \
-             (bit) < (size); \
+        for ((bit) = find_first_bit((addr), (size));            \
+             (bit) < (size);                                    \
+             (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+/* same as for_each_set_bit() but use bit as value to start with */
+#define for_each_set_bit_cont(bit, addr, size) \
+        for ((bit) = find_next_bit((addr), (size), (bit));      \
+             (bit) < (size);                                    \
              (bit) = find_next_bit((addr), (size), (bit) + 1))
 
 static __inline__ int get_bitmask_order(unsigned int count)
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index ab344a521105..66d3e954eb6c 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -44,7 +44,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat,
                                        unsigned long endpfn);
 extern unsigned long init_bootmem(unsigned long addr, unsigned long memend);
 
-unsigned long free_all_memory_core_early(int nodeid);
+extern unsigned long free_low_memory_core_early(int nodeid);
 extern unsigned long free_all_bootmem_node(pg_data_t *pgdat);
 extern unsigned long free_all_bootmem(void);
 
diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 65970b811e22..0e5f5785d9f2 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -46,6 +46,8 @@ struct debug_obj {
  *                      fails
  * @fixup_free:         fixup function, which is called when the free check
  *                      fails
+ * @fixup_assert_init:  fixup function, which is called when the assert_init
+ *                      check fails
  */
 struct debug_obj_descr {
         const char              *name;
@@ -54,6 +56,7 @@ struct debug_obj_descr {
         int (*fixup_activate)   (void *addr, enum debug_obj_state state);
         int (*fixup_destroy)    (void *addr, enum debug_obj_state state);
         int (*fixup_free)       (void *addr, enum debug_obj_state state);
+        int (*fixup_assert_init)(void *addr, enum debug_obj_state state);
 };
 
 #ifdef CONFIG_DEBUG_OBJECTS
@@ -64,6 +67,7 @@ extern void debug_object_activate  (void *addr, struct debug_obj_descr *descr);
 extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr);
 extern void debug_object_destroy   (void *addr, struct debug_obj_descr *descr);
 extern void debug_object_free      (void *addr, struct debug_obj_descr *descr);
+extern void debug_object_assert_init(void *addr, struct debug_obj_descr *descr);
 
 /*
  * Active state:
@@ -89,6 +93,8 @@ static inline void
 debug_object_destroy   (void *addr, struct debug_obj_descr *descr) { }
 static inline void
 debug_object_free      (void *addr, struct debug_obj_descr *descr) { }
+static inline void
+debug_object_assert_init(void *addr, struct debug_obj_descr *descr) { }
 
 static inline void debug_objects_early_init(void) { }
 static inline void debug_objects_mem_init(void) { }
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 388b0d425b50..5ce8b140428f 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <linux/workqueue.h>
 
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
 
@@ -14,6 +15,12 @@ struct jump_label_key {
 #endif
 };
 
+struct jump_label_key_deferred {
+        struct jump_label_key key;
+        unsigned long timeout;
+        struct delayed_work work;
+};
+
 # include <asm/jump_label.h>
 # define HAVE_JUMP_LABEL
 #endif  /* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */
@@ -51,8 +58,11 @@ extern void arch_jump_label_transform_static(struct jump_entry *entry,
 extern int jump_label_text_reserved(void *start, void *end);
 extern void jump_label_inc(struct jump_label_key *key);
 extern void jump_label_dec(struct jump_label_key *key);
+extern void jump_label_dec_deferred(struct jump_label_key_deferred *key);
 extern bool jump_label_enabled(struct jump_label_key *key);
 extern void jump_label_apply_nops(struct module *mod);
+extern void jump_label_rate_limit(struct jump_label_key_deferred *key,
+                unsigned long rl);
 
 #else  /* !HAVE_JUMP_LABEL */
 
@@ -68,6 +78,10 @@ static __always_inline void jump_label_init(void)
 {
 }
 
+struct jump_label_key_deferred {
+        struct jump_label_key  key;
+};
+
 static __always_inline bool static_branch(struct jump_label_key *key)
 {
         if (unlikely(atomic_read(&key->enabled)))
@@ -85,6 +99,11 @@ static inline void jump_label_dec(struct jump_label_key *key)
         atomic_dec(&key->enabled);
 }
 
+static inline void jump_label_dec_deferred(struct jump_label_key_deferred *key)
+{
+        jump_label_dec(&key->key);
+}
+
 static inline int jump_label_text_reserved(void *start, void *end)
 {
         return 0;
@@ -102,6 +121,14 @@ static inline int jump_label_apply_nops(struct module *mod)
 {
         return 0;
 }
+
+static inline void jump_label_rate_limit(struct jump_label_key_deferred *key,
+                unsigned long rl)
+{
+}
 #endif  /* HAVE_JUMP_LABEL */
 
+#define jump_label_key_enabled  ((struct jump_label_key){ .enabled = ATOMIC_INIT(1), })
+#define jump_label_key_disabled ((struct jump_label_key){ .enabled = ATOMIC_INIT(0), })
+
 #endif  /* _LINUX_JUMP_LABEL_H */
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 0cce2db580c3..2fbd9053c2df 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -6,6 +6,7 @@
 #include <linux/percpu.h>
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
+#include <linux/sched.h>
 #include <asm/irq.h>
 #include <asm/cputime.h>
 
@@ -15,21 +16,25 @@
  * used by rstatd/perfmeter
  */
 
-struct cpu_usage_stat {
-        cputime64_t user;
-        cputime64_t nice;
-        cputime64_t system;
-        cputime64_t softirq;
-        cputime64_t irq;
-        cputime64_t idle;
-        cputime64_t iowait;
-        cputime64_t steal;
-        cputime64_t guest;
-        cputime64_t guest_nice;
+enum cpu_usage_stat {
+        CPUTIME_USER,
+        CPUTIME_NICE,
+        CPUTIME_SYSTEM,
+        CPUTIME_SOFTIRQ,
+        CPUTIME_IRQ,
+        CPUTIME_IDLE,
+        CPUTIME_IOWAIT,
+        CPUTIME_STEAL,
+        CPUTIME_GUEST,
+        CPUTIME_GUEST_NICE,
+        NR_STATS,
+};
+
+struct kernel_cpustat {
+        u64 cpustat[NR_STATS];
 };
 
 struct kernel_stat {
-        struct cpu_usage_stat   cpustat;
 #ifndef CONFIG_GENERIC_HARDIRQS
        unsigned int irqs[NR_IRQS];
 #endif
@@ -38,10 +43,13 @@ struct kernel_stat {
 };
 
 DECLARE_PER_CPU(struct kernel_stat, kstat);
+DECLARE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
 
-#define kstat_cpu(cpu)  per_cpu(kstat, cpu)
 /* Must have preemption disabled for this to be meaningful. */
-#define kstat_this_cpu  __get_cpu_var(kstat)
+#define kstat_this_cpu (&__get_cpu_var(kstat))
+#define kcpustat_this_cpu (&__get_cpu_var(kernel_cpustat))
+#define kstat_cpu(cpu) per_cpu(kstat, cpu)
+#define kcpustat_cpu(cpu) per_cpu(kernel_cpustat, cpu)
 
 extern unsigned long long nr_context_switches(void);
 
diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h
index b0e99898527c..e23121f9d82a 100644
--- a/include/linux/latencytop.h
+++ b/include/linux/latencytop.h
@@ -10,6 +10,8 @@
 #define _INCLUDE_GUARD_LATENCYTOP_H_
 
 #include <linux/compiler.h>
+struct task_struct;
+
 #ifdef CONFIG_LATENCYTOP
 
 #define LT_SAVECOUNT            32
@@ -23,7 +25,6 @@ struct latency_record {
 };
 
 
-struct task_struct;
 
 extern int latencytop_enabled;
 void __account_scheduler_latency(struct task_struct *task, int usecs, int inter);
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index b6a56e37284c..d36619ead3ba 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -343,6 +343,8 @@ extern void lockdep_trace_alloc(gfp_t mask);
 
 #define lockdep_assert_held(l)  WARN_ON(debug_locks && !lockdep_is_held(l))
 
+#define lockdep_recursing(tsk)  ((tsk)->lockdep_recursion)
+
 #else /* !LOCKDEP */
 
 static inline void lockdep_off(void)
@@ -392,6 +394,8 @@ struct lock_class_key { };
 
 #define lockdep_assert_held(l)                  do { } while (0)
 
+#define lockdep_recursing(tsk)                  (0)
+
 #endif /* !LOCKDEP */
 
 #ifdef CONFIG_LOCK_STAT
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index e6b843e16e81..a6bb10235148 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -2,8 +2,6 @@
 #define _LINUX_MEMBLOCK_H
 #ifdef __KERNEL__
 
-#define MEMBLOCK_ERROR  0
-
 #ifdef CONFIG_HAVE_MEMBLOCK
 /*
  * Logical memory blocks.
@@ -19,81 +17,161 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 
-#include <asm/memblock.h>
-
 #define INIT_MEMBLOCK_REGIONS   128
 
 struct memblock_region {
         phys_addr_t base;
         phys_addr_t size;
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+        int nid;
+#endif
 };
 
 struct memblock_type {
         unsigned long cnt;      /* number of regions */
         unsigned long max;      /* size of the allocated array */
+        phys_addr_t total_size; /* size of all regions */
         struct memblock_region *regions;
 };
 
 struct memblock {
         phys_addr_t current_limit;
-        phys_addr_t memory_size;        /* Updated by memblock_analyze() */
         struct memblock_type memory;
         struct memblock_type reserved;
 };
 
 extern struct memblock memblock;
 extern int memblock_debug;
-extern int memblock_can_resize;
 
 #define memblock_dbg(fmt, ...) \
         if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
 
-u64 memblock_find_in_range(u64 start, u64 end, u64 size, u64 align);
+phys_addr_t memblock_find_in_range_node(phys_addr_t start, phys_addr_t end,
+                                phys_addr_t size, phys_addr_t align, int nid);
+phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
+                                   phys_addr_t size, phys_addr_t align);
 int memblock_free_reserved_regions(void);
 int memblock_reserve_reserved_regions(void);
 
-extern void memblock_init(void);
-extern void memblock_analyze(void);
-extern long memblock_add(phys_addr_t base, phys_addr_t size);
-extern long memblock_remove(phys_addr_t base, phys_addr_t size);
-extern long memblock_free(phys_addr_t base, phys_addr_t size);
-extern long memblock_reserve(phys_addr_t base, phys_addr_t size);
+void memblock_allow_resize(void);
+int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid);
+int memblock_add(phys_addr_t base, phys_addr_t size);
+int memblock_remove(phys_addr_t base, phys_addr_t size);
+int memblock_free(phys_addr_t base, phys_addr_t size);
+int memblock_reserve(phys_addr_t base, phys_addr_t size);
+
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
+                          unsigned long *out_end_pfn, int *out_nid);
+
+/**
+ * for_each_mem_pfn_range - early memory pfn range iterator
+ * @i: an integer used as loop variable
+ * @nid: node selector, %MAX_NUMNODES for all nodes
+ * @p_start: ptr to ulong for start pfn of the range, can be %NULL
+ * @p_end: ptr to ulong for end pfn of the range, can be %NULL
+ * @p_nid: ptr to int for nid of the range, can be %NULL
+ *
+ * Walks over configured memory ranges.  Available after early_node_map is
+ * populated.
+ */
+#define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid)           \
+        for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \
+             i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid))
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+
+void __next_free_mem_range(u64 *idx, int nid, phys_addr_t *out_start,
+                           phys_addr_t *out_end, int *out_nid);
+
+/**
+ * for_each_free_mem_range - iterate through free memblock areas
+ * @i: u64 used as loop variable
+ * @nid: node selector, %MAX_NUMNODES for all nodes
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ * @p_nid: ptr to int for nid of the range, can be %NULL
+ *
+ * Walks over free (memory && !reserved) areas of memblock.  Available as
+ * soon as memblock is initialized.
+ */
+#define for_each_free_mem_range(i, nid, p_start, p_end, p_nid)          \
+        for (i = 0,                                                     \
+             __next_free_mem_range(&i, nid, p_start, p_end, p_nid);     \
+             i != (u64)ULLONG_MAX;                                      \
+             __next_free_mem_range(&i, nid, p_start, p_end, p_nid))
+
+void __next_free_mem_range_rev(u64 *idx, int nid, phys_addr_t *out_start,
+                               phys_addr_t *out_end, int *out_nid);
 
-/* The numa aware allocator is only available if
- * CONFIG_ARCH_POPULATES_NODE_MAP is set
+/**
+ * for_each_free_mem_range_reverse - rev-iterate through free memblock areas
+ * @i: u64 used as loop variable
+ * @nid: node selector, %MAX_NUMNODES for all nodes
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ * @p_nid: ptr to int for nid of the range, can be %NULL
+ *
+ * Walks over free (memory && !reserved) areas of memblock in reverse
+ * order.  Available as soon as memblock is initialized.
  */
-extern phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align,
-                                        int nid);
-extern phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align,
-                                            int nid);
+#define for_each_free_mem_range_reverse(i, nid, p_start, p_end, p_nid)  \
+        for (i = (u64)ULLONG_MAX,                                       \
+             __next_free_mem_range_rev(&i, nid, p_start, p_end, p_nid); \
+             i != (u64)ULLONG_MAX;                                      \
+             __next_free_mem_range_rev(&i, nid, p_start, p_end, p_nid))
 
-extern phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align);
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+int memblock_set_node(phys_addr_t base, phys_addr_t size, int nid);
+
+static inline void memblock_set_region_node(struct memblock_region *r, int nid)
+{
+        r->nid = nid;
+}
+
+static inline int memblock_get_region_node(const struct memblock_region *r)
+{
+        return r->nid;
+}
+#else
+static inline void memblock_set_region_node(struct memblock_region *r, int nid)
+{
+}
+
+static inline int memblock_get_region_node(const struct memblock_region *r)
+{
+        return 0;
+}
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+
+phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid);
+phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid);
+
+phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align);
 
 /* Flags for memblock_alloc_base() amd __memblock_alloc_base() */
 #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0)
 #define MEMBLOCK_ALLOC_ACCESSIBLE       0
 
-extern phys_addr_t memblock_alloc_base(phys_addr_t size,
-                                         phys_addr_t align,
-                                         phys_addr_t max_addr);
-extern phys_addr_t __memblock_alloc_base(phys_addr_t size,
-                                           phys_addr_t align,
-                                           phys_addr_t max_addr);
-extern phys_addr_t memblock_phys_mem_size(void);
-extern phys_addr_t memblock_start_of_DRAM(void);
-extern phys_addr_t memblock_end_of_DRAM(void);
-extern void memblock_enforce_memory_limit(phys_addr_t memory_limit);
-extern int memblock_is_memory(phys_addr_t addr);
-extern int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
-extern int memblock_is_reserved(phys_addr_t addr);
-extern int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
-
-extern void memblock_dump_all(void);
-
-/* Provided by the architecture */
-extern phys_addr_t memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid);
-extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
-                                   phys_addr_t addr2, phys_addr_t size2);
+phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align,
+                                phys_addr_t max_addr);
+phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align,
+                                  phys_addr_t max_addr);
+phys_addr_t memblock_phys_mem_size(void);
+phys_addr_t memblock_start_of_DRAM(void);
+phys_addr_t memblock_end_of_DRAM(void);
+void memblock_enforce_memory_limit(phys_addr_t memory_limit);
+int memblock_is_memory(phys_addr_t addr);
+int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
+int memblock_is_reserved(phys_addr_t addr);
+int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
+
+extern void __memblock_dump_all(void);
+
+static inline void memblock_dump_all(void)
+{
+        if (memblock_debug)
+                __memblock_dump_all();
+}
 
 /**
  * memblock_set_current_limit - Set the current allocation limit to allow
@@ -101,7 +179,7 @@ extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
  *                         accessible during boot
  * @limit: New limit value (physical address)
  */
-extern void memblock_set_current_limit(phys_addr_t limit);
+void memblock_set_current_limit(phys_addr_t limit);
 
 
 /*
@@ -154,9 +232,9 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
              region++)
 
 
-#ifdef ARCH_DISCARD_MEMBLOCK
-#define __init_memblock __init
-#define __initdata_memblock __initdata
+#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+#define __init_memblock __meminit
+#define __initdata_memblock __meminitdata
 #else
 #define __init_memblock
 #define __initdata_memblock
@@ -165,7 +243,7 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
 #else
 static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
-        return MEMBLOCK_ERROR;
+        return 0;
 }
 
 #endif /* CONFIG_HAVE_MEMBLOCK */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4baadd18f4ad..5d9b4c9813bd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1253,41 +1253,34 @@ static inline void pgtable_page_dtor(struct page *page)
 extern void free_area_init(unsigned long * zones_size);
 extern void free_area_init_node(int nid, unsigned long * zones_size,
                 unsigned long zone_start_pfn, unsigned long *zholes_size);
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 /*
- * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its
+ * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its
  * zones, allocate the backing mem_map and account for memory holes in a more
  * architecture independent manner. This is a substitute for creating the
  * zone_sizes[] and zholes_size[] arrays and passing them to
  * free_area_init_node()
  *
  * An architecture is expected to register range of page frames backed by
- * physical memory with add_active_range() before calling
+ * physical memory with memblock_add[_node]() before calling
  * free_area_init_nodes() passing in the PFN each zone ends at. At a basic
  * usage, an architecture is expected to do something like
  *
  * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn,
  *                                                       max_highmem_pfn};
  * for_each_valid_physical_page_range()
- *      add_active_range(node_id, start_pfn, end_pfn)
+ *      memblock_add_node(base, size, nid)
  * free_area_init_nodes(max_zone_pfns);
  *
- * If the architecture guarantees that there are no holes in the ranges
- * registered with add_active_range(), free_bootmem_active_regions()
- * will call free_bootmem_node() for each registered physical page range.
- * Similarly sparse_memory_present_with_active_regions() calls
- * memory_present() for each range when SPARSEMEM is enabled.
+ * free_bootmem_with_active_regions() calls free_bootmem_node() for each
+ * registered physical page range.  Similarly
+ * sparse_memory_present_with_active_regions() calls memory_present() for
+ * each range when SPARSEMEM is enabled.
  *
  * See mm/page_alloc.c for more information on each function exposed by
- * CONFIG_ARCH_POPULATES_NODE_MAP
+ * CONFIG_HAVE_MEMBLOCK_NODE_MAP.
  */
 extern void free_area_init_nodes(unsigned long *max_zone_pfn);
-extern void add_active_range(unsigned int nid, unsigned long start_pfn,
-                                        unsigned long end_pfn);
-extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
-                                        unsigned long end_pfn);
-extern void remove_all_active_ranges(void);
-void sort_node_map(void);
 unsigned long node_map_pfn_alignment(void);
 unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn,
                                                 unsigned long end_pfn);
@@ -1300,14 +1293,11 @@ extern void free_bootmem_with_active_regions(int nid,
                                                 unsigned long max_low_pfn);
 int add_from_early_node_map(struct range *range, int az,
                                    int nr_range, int nid);
-u64 __init find_memory_core_early(int nid, u64 size, u64 align,
-                                        u64 goal, u64 limit);
-typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
-extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
 extern void sparse_memory_present_with_active_regions(int nid);
-#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
 
-#if !defined(CONFIG_ARCH_POPULATES_NODE_MAP) && \
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+
+#if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \
     !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID)
 static inline int __early_pfn_to_nid(unsigned long pfn)
 {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 188cb2ffe8db..3ac040f19369 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -598,13 +598,13 @@ struct zonelist {
 #endif
 };
 
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 struct node_active_region {
         unsigned long start_pfn;
         unsigned long end_pfn;
         int nid;
 };
-#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 #ifndef CONFIG_DISCONTIGMEM
 /* The array of struct pages - for discontigmem use pgdat->lmem_map */
@@ -720,7 +720,7 @@ extern int movable_zone;
 
 static inline int zone_movable_is_highmem(void)
 {
-#if defined(CONFIG_HIGHMEM) && defined(CONFIG_ARCH_POPULATES_NODE_MAP)
+#if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE)
         return movable_zone == ZONE_HIGHMEM;
 #else
         return 0;
@@ -938,7 +938,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 #endif
 
 #if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \
-        !defined(CONFIG_ARCH_POPULATES_NODE_MAP)
+        !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
 static inline unsigned long early_pfn_to_nid(unsigned long pfn)
 {
         return 0;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b1f89122bf6a..08855613ceb3 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -54,6 +54,7 @@ enum perf_hw_id {
         PERF_COUNT_HW_BUS_CYCLES                = 6,
         PERF_COUNT_HW_STALLED_CYCLES_FRONTEND   = 7,
         PERF_COUNT_HW_STALLED_CYCLES_BACKEND    = 8,
+        PERF_COUNT_HW_REF_CPU_CYCLES            = 9,
 
         PERF_COUNT_HW_MAX,                      /* non-ABI */
 };
@@ -890,6 +891,7 @@ struct perf_event_context {
         int                             nr_active;
         int                             is_active;
         int                             nr_stat;
+        int                             nr_freq;
         int                             rotate_disable;
         atomic_t                        refcount;
         struct task_struct              *task;
@@ -1063,12 +1065,12 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
         }
 }
 
-extern struct jump_label_key perf_sched_events;
+extern struct jump_label_key_deferred perf_sched_events;
 
 static inline void perf_event_task_sched_in(struct task_struct *prev,
                                             struct task_struct *task)
 {
-        if (static_branch(&perf_sched_events))
+        if (static_branch(&perf_sched_events.key))
                 __perf_event_task_sched_in(prev, task);
 }
 
@@ -1077,7 +1079,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
 {
         perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
 
-        if (static_branch(&perf_sched_events))
+        if (static_branch(&perf_sched_events.key))
                 __perf_event_task_sched_out(prev, next);
 }
 
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 79159de0e341..2110a81c5e2a 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -40,12 +40,6 @@
 #define RED_INACTIVE    0x09F911029D74E35BULL   /* when obj is inactive */
 #define RED_ACTIVE      0xD84156C5635688C0ULL   /* when obj is active */
 
-#ifdef CONFIG_PHYS_ADDR_T_64BIT
-#define MEMBLOCK_INACTIVE       0x3a84fb0144c9e71bULL
-#else
-#define MEMBLOCK_INACTIVE       0x44c9e71bUL
-#endif
-
 #define SLUB_RED_INACTIVE       0xbb
 #define SLUB_RED_ACTIVE         0xcc
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 56fa25a5b1eb..40d84481a1c9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -273,9 +273,11 @@ extern int runqueue_is_locked(int cpu);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
 extern void select_nohz_load_balancer(int stop_tick);
+extern void set_cpu_sd_state_idle(void);
 extern int get_nohz_timer_target(void);
 #else
 static inline void select_nohz_load_balancer(int stop_tick) { }
+static inline void set_cpu_sd_state_idle(void) { }
 #endif
 
 /*
@@ -483,8 +485,8 @@ struct task_cputime {
 
 #define INIT_CPUTIME    \
         (struct task_cputime) {                                 \
-                .utime = cputime_zero,                          \
-                .stime = cputime_zero,                          \
+                .utime = 0,                                     \
+                .stime = 0,                                     \
                 .sum_exec_runtime = 0,                          \
         }
 
@@ -901,6 +903,10 @@ struct sched_group_power {
          * single CPU.
          */
         unsigned int power, power_orig;
+        /*
+         * Number of busy cpus in this group.
+         */
+        atomic_t nr_busy_cpus;
 };
 
 struct sched_group {
@@ -925,6 +931,15 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
         return to_cpumask(sg->cpumask);
 }
 
+/**
+ * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
+ * @group: The group whose first cpu is to be returned.
+ */
+static inline unsigned int group_first_cpu(struct sched_group *group)
+{
+        return cpumask_first(sched_group_cpus(group));
+}
+
 struct sched_domain_attr {
         int relax_domain_level;
 };
@@ -1315,8 +1330,8 @@ struct task_struct {
          * older sibling, respectively.  (p->father can be replaced with 
          * p->real_parent->pid)
          */
-        struct task_struct *real_parent; /* real parent process */
-        struct task_struct *parent; /* recipient of SIGCHLD, wait4() reports */
+        struct task_struct __rcu *real_parent; /* real parent process */
+        struct task_struct __rcu *parent; /* recipient of SIGCHLD, wait4() reports */
         /*
          * children/sibling forms the list of my natural children
          */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 3efc9f3f43a0..a9ce45e8501c 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -77,13 +77,13 @@ struct task_struct;
 #define __WAIT_BIT_KEY_INITIALIZER(word, bit)                           \
         { .flags = word, .bit_nr = bit, }
 
-extern void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *);
+extern void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *);
 
 #define init_waitqueue_head(q)                          \
         do {                                            \
                 static struct lock_class_key __key;     \
                                                         \
-                __init_waitqueue_head((q), &__key);     \
+                __init_waitqueue_head((q), #q, &__key); \
         } while (0)
 
 #ifdef CONFIG_LOCKDEP
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 959ff18b63b6..6ba596b07a72 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -331,6 +331,13 @@ DEFINE_EVENT(sched_stat_template, sched_stat_iowait,
              TP_ARGS(tsk, delay));
 
 /*
+ * Tracepoint for accounting blocked time (time the task is in uninterruptible).
+ */
+DEFINE_EVENT(sched_stat_template, sched_stat_blocked,
+             TP_PROTO(struct task_struct *tsk, u64 delay),
+             TP_ARGS(tsk, delay));
+
+/*
  * Tracepoint for accounting runtime (time the task is executing
  * on a CPU).
  */
@@ -363,6 +370,56 @@ TRACE_EVENT(sched_stat_runtime,
                         (unsigned long long)__entry->vruntime)
 );
 
+#ifdef CREATE_TRACE_POINTS
+static inline u64 trace_get_sleeptime(struct task_struct *tsk)
+{
+#ifdef CONFIG_SCHEDSTATS
+        u64 block, sleep;
+
+        block = tsk->se.statistics.block_start;
+        sleep = tsk->se.statistics.sleep_start;
+        tsk->se.statistics.block_start = 0;
+        tsk->se.statistics.sleep_start = 0;
+
+        return block ? block : sleep ? sleep : 0;
+#else
+        return 0;
+#endif
+}
+#endif
+
+/*
+ * Tracepoint for accounting sleeptime (time the task is sleeping
+ * or waiting for I/O).
+ */
+TRACE_EVENT(sched_stat_sleeptime,
+
+        TP_PROTO(struct task_struct *tsk, u64 now),
+
+        TP_ARGS(tsk, now),
+
+        TP_STRUCT__entry(
+                __array( char,  comm,   TASK_COMM_LEN   )
+                __field( pid_t, pid                     )
+                __field( u64,   sleeptime               )
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+                __entry->pid            = tsk->pid;
+                __entry->sleeptime = trace_get_sleeptime(tsk);
+                __entry->sleeptime = __entry->sleeptime ?
+                                now - __entry->sleeptime : 0;
+        )
+        TP_perf_assign(
+                __perf_count(__entry->sleeptime);
+        ),
+
+        TP_printk("comm=%s pid=%d sleeptime=%Lu [ns]",
+                        __entry->comm, __entry->pid,
+                        (unsigned long long)__entry->sleeptime)
+);
+
 /*
  * Tracepoint for showing priority inheritance modifying a tasks
  * priority.