Merge 'Linux v3.0' into Litmus

Some notes:
* Litmus^RT scheduling class is the topmost scheduling class
  (above stop_sched_class).
* scheduler_ipi() function (e.g., in smp_reschedule_interrupt())
  may increase IPI latencies.
* Added path into schedule() to quickly re-evaluate scheduling
  decision without becoming preemptive again. This used to be
  a standard path before the removal of BKL.

Conflicts:
	Makefile
	arch/arm/kernel/calls.S
	arch/arm/kernel/smp.c
	arch/x86/include/asm/unistd_32.h
	arch/x86/kernel/smp.c
	arch/x86/kernel/syscall_table_32.S
	include/linux/hrtimer.h
	kernel/printk.c
	kernel/sched.c
	kernel/sched_fair.c

1 files changed, 251 insertions, 102 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c9ac4fc837ba..9c990d13ae35 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -21,7 +21,8 @@
 #define CLONE_DETACHED          0x00400000      /* Unused, ignored */
 #define CLONE_UNTRACED          0x00800000      /* set if the tracing process can't force CLONE_PTRACE on this clone */
 #define CLONE_CHILD_SETTID      0x01000000      /* set the TID in the child */
-#define CLONE_STOPPED           0x02000000      /* Start in stopped state */
+/* 0x02000000 was previously the unused CLONE_STOPPED (Start in stopped state)
+   and is now available for re-use. */
 #define CLONE_NEWUTS            0x04000000      /* New utsname group? */
 #define CLONE_NEWIPC            0x08000000      /* New ipcs */
 #define CLONE_NEWUSER           0x10000000      /* New user namespace */
@@ -71,7 +72,6 @@ struct sched_param {
 #include <linux/smp.h>
 #include <linux/sem.h>
 #include <linux/signal.h>
-#include <linux/path.h>
 #include <linux/compiler.h>
 #include <linux/completion.h>
 #include <linux/pid.h>
@@ -89,7 +89,6 @@ struct sched_param {
 #include <linux/timer.h>
 #include <linux/hrtimer.h>
 #include <linux/task_io_accounting.h>
-#include <linux/kobject.h>
 #include <linux/latencytop.h>
 #include <linux/cred.h>
 
@@ -104,6 +103,7 @@ struct robust_list_head;
 struct bio_list;
 struct fs_struct;
 struct perf_event_context;
+struct blk_plug;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -147,7 +147,7 @@ extern unsigned long nr_iowait_cpu(int cpu);
 extern unsigned long this_cpu_load(void);
 
 
-extern void calc_global_load(void);
+extern void calc_global_load(unsigned long ticks);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -319,7 +319,7 @@ 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 int softlockup_thresh;
+void lockup_detector_init(void);
 #else
 static inline void touch_softlockup_watchdog(void)
 {
@@ -330,6 +330,9 @@ static inline void touch_softlockup_watchdog_sync(void)
 static inline void touch_all_softlockup_watchdogs(void)
 {
 }
+static inline void lockup_detector_init(void)
+{
+}
 #endif
 
 #ifdef CONFIG_DETECT_HUNG_TASK
@@ -340,6 +343,9 @@ extern unsigned long sysctl_hung_task_warnings;
 extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
                                          void __user *buffer,
                                          size_t *lenp, loff_t *ppos);
+#else
+/* Avoid need for ifdefs elsewhere in the code */
+enum { sysctl_hung_task_timeout_secs = 0 };
 #endif
 
 /* Attach to any functions which should be ignored in wchan output. */
@@ -357,7 +363,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout);
 extern signed long schedule_timeout_killable(signed long timeout);
 extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void schedule(void);
-extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
+extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
 
 struct nsproxy;
 struct user_namespace;
@@ -432,6 +438,7 @@ extern int get_dumpable(struct mm_struct *mm);
 #endif
                                         /* leave room for more dump flags */
 #define MMF_VM_MERGEABLE        16      /* KSM may merge identical pages */
+#define MMF_VM_HUGEPAGE         17      /* set when VM_HUGEPAGE is set on vma */
 
 #define MMF_INIT_MASK           (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
 
@@ -510,8 +517,11 @@ struct thread_group_cputimer {
         spinlock_t lock;
 };
 
+#include <linux/rwsem.h>
+struct autogroup;
+
 /*
- * NOTE! "signal_struct" does not have it's own
+ * NOTE! "signal_struct" does not have its own
  * locking, because a shared signal_struct always
  * implies a shared sighand_struct, so locking
  * sighand_struct is always a proper superset of
@@ -577,6 +587,9 @@ struct signal_struct {
 
         struct tty_struct *tty; /* NULL if no tty */
 
+#ifdef CONFIG_SCHED_AUTOGROUP
+        struct autogroup *autogroup;
+#endif
         /*
          * Cumulative resource counters for dead threads in the group,
          * and for reaped dead child processes forked by this group.
@@ -624,9 +637,25 @@ struct signal_struct {
         unsigned audit_tty;
         struct tty_audit_buf *tty_audit_buf;
 #endif
+#ifdef CONFIG_CGROUPS
+        /*
+         * The threadgroup_fork_lock prevents threads from forking with
+         * CLONE_THREAD while held for writing. Use this for fork-sensitive
+         * threadgroup-wide operations. It's taken for reading in fork.c in
+         * copy_process().
+         * Currently only needed write-side by cgroups.
+         */
+        struct rw_semaphore threadgroup_fork_lock;
+#endif
 
         int oom_adj;            /* OOM kill score adjustment (bit shift) */
         int oom_score_adj;      /* OOM kill score adjustment */
+        int oom_score_adj_min;  /* OOM kill score adjustment minimum value.
+                                 * Only settable by CAP_SYS_RESOURCE. */
+
+        struct mutex cred_guard_mutex;  /* guard against foreign influences on
+                                         * credential calculations
+                                         * (notably. ptrace) */
 };
 
 /* Context switch must be unlocked if interrupts are to be enabled */
@@ -638,9 +667,8 @@ struct signal_struct {
  * Bits in flags field of signal_struct.
  */
 #define SIGNAL_STOP_STOPPED     0x00000001 /* job control stop in effect */
-#define SIGNAL_STOP_DEQUEUED    0x00000002 /* stop signal dequeued */
-#define SIGNAL_STOP_CONTINUED   0x00000004 /* SIGCONT since WCONTINUED reap */
-#define SIGNAL_GROUP_EXIT       0x00000008 /* group exit in progress */
+#define SIGNAL_STOP_CONTINUED   0x00000002 /* SIGCONT since WCONTINUED reap */
+#define SIGNAL_GROUP_EXIT       0x00000004 /* group exit in progress */
 /*
  * Pending notifications to parent.
  */
@@ -669,8 +697,11 @@ struct user_struct {
         atomic_t inotify_watches; /* How many inotify watches does this user have? */
         atomic_t inotify_devs;  /* How many inotify devs does this user have opened? */
 #endif
+#ifdef CONFIG_FANOTIFY
+        atomic_t fanotify_listeners;
+#endif
 #ifdef CONFIG_EPOLL
-        atomic_t epoll_watches; /* The number of file descriptors currently watched */
+        atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
 #endif
 #ifdef CONFIG_POSIX_MQUEUE
         /* protected by mq_lock */
@@ -713,10 +744,6 @@ struct sched_info {
         /* timestamps */
         unsigned long long last_arrival,/* when we last ran on a cpu */
                            last_queued; /* when we were last queued to run */
-#ifdef CONFIG_SCHEDSTATS
-        /* BKL stats */
-        unsigned int bkl_count;
-#endif
 };
 #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
 
@@ -774,17 +801,39 @@ enum cpu_idle_type {
 };
 
 /*
- * sched-domains (multiprocessor balancing) declarations:
+ * Increase resolution of nice-level calculations for 64-bit architectures.
+ * The extra resolution improves shares distribution and load balancing of
+ * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
+ * hierarchies, especially on larger systems. This is not a user-visible change
+ * and does not change the user-interface for setting shares/weights.
+ *
+ * We increase resolution only if we have enough bits to allow this increased
+ * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution
+ * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the
+ * increased costs.
  */
+#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load  */
+# define SCHED_LOAD_RESOLUTION  10
+# define scale_load(w)          ((w) << SCHED_LOAD_RESOLUTION)
+# define scale_load_down(w)     ((w) >> SCHED_LOAD_RESOLUTION)
+#else
+# define SCHED_LOAD_RESOLUTION  0
+# define scale_load(w)          (w)
+# define scale_load_down(w)     (w)
+#endif
 
-/*
- * Increase resolution of nice-level calculations:
- */
-#define SCHED_LOAD_SHIFT        10
+#define SCHED_LOAD_SHIFT        (10 + SCHED_LOAD_RESOLUTION)
 #define SCHED_LOAD_SCALE        (1L << SCHED_LOAD_SHIFT)
 
-#define SCHED_LOAD_SCALE_FUZZ   SCHED_LOAD_SCALE
+/*
+ * Increase resolution of cpu_power calculations
+ */
+#define SCHED_POWER_SHIFT       10
+#define SCHED_POWER_SCALE       (1L << SCHED_POWER_SHIFT)
 
+/*
+ * sched-domains (multiprocessor balancing) declarations:
+ */
 #ifdef CONFIG_SMP
 #define SD_LOAD_BALANCE         0x0001  /* Do load balancing on this domain. */
 #define SD_BALANCE_NEWIDLE      0x0002  /* Balance when about to become idle */
@@ -799,6 +848,7 @@ enum cpu_idle_type {
 #define SD_SERIALIZE            0x0400  /* Only a single load balancing instance */
 #define SD_ASYM_PACKING         0x0800  /* Place busy groups earlier in the domain */
 #define SD_PREFER_SIBLING       0x1000  /* Prefer to place tasks in a sibling domain */
+#define SD_OVERLAP              0x2000  /* sched_domains of this level overlap */
 
 enum powersavings_balance_level {
         POWERSAVINGS_BALANCE_NONE = 0,  /* No power saving load balance */
@@ -836,7 +886,7 @@ extern int __weak arch_sd_sibiling_asym_packing(void);
 
 /*
  * Optimise SD flags for power savings:
- * SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings.
+ * SD_BALANCE_NEWIDLE helps aggressive task consolidation and power savings.
  * Keep default SD flags if sched_{smt,mc}_power_saving=0
  */
 
@@ -848,14 +898,21 @@ static inline int sd_power_saving_flags(void)
         return 0;
 }
 
-struct sched_group {
-        struct sched_group *next;       /* Must be a circular list */
-
+struct sched_group_power {
+        atomic_t ref;
         /*
          * CPU power of this group, SCHED_LOAD_SCALE being max power for a
          * single CPU.
          */
-        unsigned int cpu_power, cpu_power_orig;
+        unsigned int power, power_orig;
+};
+
+struct sched_group {
+        struct sched_group *next;       /* Must be a circular list */
+        atomic_t ref;
+
+        unsigned int group_weight;
+        struct sched_group_power *sgp;
 
         /*
          * The CPUs this group covers.
@@ -863,9 +920,6 @@ struct sched_group {
          * NOTE: this field is variable length. (Allocated dynamically
          * by attaching extra space to the end of the structure,
          * depending on how many CPUs the kernel has booted up with)
-         *
-         * It is also be embedded into static data structures at build
-         * time. (See 'struct static_sched_group' in kernel/sched.c)
          */
         unsigned long cpumask[0];
 };
@@ -875,16 +929,6 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
         return to_cpumask(sg->cpumask);
 }
 
-enum sched_domain_level {
-        SD_LV_NONE = 0,
-        SD_LV_SIBLING,
-        SD_LV_MC,
-        SD_LV_CPU,
-        SD_LV_NODE,
-        SD_LV_ALLNODES,
-        SD_LV_MAX
-};
-
 struct sched_domain_attr {
         int relax_domain_level;
 };
@@ -893,6 +937,8 @@ struct sched_domain_attr {
         .relax_domain_level = -1,                       \
 }
 
+extern int sched_domain_level_max;
+
 struct sched_domain {
         /* These fields must be setup */
         struct sched_domain *parent;    /* top domain must be null terminated */
@@ -910,7 +956,7 @@ struct sched_domain {
         unsigned int forkexec_idx;
         unsigned int smt_gain;
         int flags;                      /* See SD_* */
-        enum sched_domain_level level;
+        int level;
 
         /* Runtime fields. */
         unsigned long last_balance;     /* init to jiffies. units in jiffies */
@@ -953,6 +999,10 @@ struct sched_domain {
 #ifdef CONFIG_SCHED_DEBUG
         char *name;
 #endif
+        union {
+                void *private;          /* used during construction */
+                struct rcu_head rcu;    /* used during destruction */
+        };
 
         unsigned int span_weight;
         /*
@@ -961,9 +1011,6 @@ struct sched_domain {
          * NOTE: this field is variable length. (Allocated dynamically
          * by attaching extra space to the end of the structure,
          * depending on how many CPUs the kernel has booted up with)
-         *
-         * It is also be embedded into static data structures at build
-         * time. (See 'struct static_sched_domain' in kernel/sched.c)
          */
         unsigned long span[0];
 };
@@ -1026,10 +1073,15 @@ struct sched_domain;
  */
 #define WF_SYNC         0x01            /* waker goes to sleep after wakup */
 #define WF_FORK         0x02            /* child wakeup after fork */
+#define WF_MIGRATED     0x04            /* internal use, task got migrated */
 
 #define ENQUEUE_WAKEUP          1
-#define ENQUEUE_WAKING          2
-#define ENQUEUE_HEAD            4
+#define ENQUEUE_HEAD            2
+#ifdef CONFIG_SMP
+#define ENQUEUE_WAKING          4       /* sched_class::task_waking was called */
+#else
+#define ENQUEUE_WAKING          0
+#endif
 
 #define DEQUEUE_SLEEP           1
 
@@ -1039,6 +1091,7 @@ struct sched_class {
         void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
         void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
         void (*yield_task) (struct rq *rq);
+        bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
 
         void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
 
@@ -1046,12 +1099,11 @@ struct sched_class {
         void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
-        int  (*select_task_rq)(struct rq *rq, struct task_struct *p,
-                               int sd_flag, int flags);
+        int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
 
         void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
         void (*post_schedule) (struct rq *this_rq);
-        void (*task_waking) (struct rq *this_rq, struct task_struct *task);
+        void (*task_waking) (struct task_struct *task);
         void (*task_woken) (struct rq *this_rq, struct task_struct *task);
 
         void (*set_cpus_allowed)(struct task_struct *p,
@@ -1065,18 +1117,16 @@ struct sched_class {
         void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
         void (*task_fork) (struct task_struct *p);
 
-        void (*switched_from) (struct rq *this_rq, struct task_struct *task,
-                               int running);
-        void (*switched_to) (struct rq *this_rq, struct task_struct *task,
-                             int running);
+        void (*switched_from) (struct rq *this_rq, struct task_struct *task);
+        void (*switched_to) (struct rq *this_rq, struct task_struct *task);
         void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
-                             int oldprio, int running);
+                             int oldprio);
 
         unsigned int (*get_rr_interval) (struct rq *rq,
                                          struct task_struct *task);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-        void (*moved_group) (struct task_struct *p, int on_rq);
+        void (*task_move_group) (struct task_struct *p, int on_rq);
 #endif
 };
 
@@ -1165,6 +1215,13 @@ struct sched_rt_entity {
 struct rcu_node;
 struct od_table_entry;
 
+enum perf_event_task_context {
+        perf_invalid_context = -1,
+        perf_hw_context = 0,
+        perf_sw_context,
+        perf_nr_task_contexts,
+};
+
 struct task_struct {
         volatile long state;    /* -1 unrunnable, 0 runnable, >0 stopped */
         void *stack;
@@ -1172,13 +1229,11 @@ struct task_struct {
         unsigned int flags;     /* per process flags, defined below */
         unsigned int ptrace;
 
-        int lock_depth;         /* BKL lock depth */
-
 #ifdef CONFIG_SMP
-#ifdef __ARCH_WANT_UNLOCKED_CTXSW
-        int oncpu;
-#endif
+        struct task_struct *wake_entry;
+        int on_cpu;
 #endif
+        int on_rq;
 
         int prio, static_prio, normal_prio;
         unsigned int rt_priority;
@@ -1207,21 +1262,34 @@ struct task_struct {
         unsigned int policy;
         cpumask_t cpus_allowed;
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
         int rcu_read_lock_nesting;
         char rcu_read_unlock_special;
-        struct rcu_node *rcu_blocked_node;
+#if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU)
+        int rcu_boosted;
+#endif /* #if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) */
         struct list_head rcu_node_entry;
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+#ifdef CONFIG_TREE_PREEMPT_RCU
+        struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#ifdef CONFIG_RCU_BOOST
+        struct rt_mutex *rcu_boost_mutex;
+#endif /* #ifdef CONFIG_RCU_BOOST */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
         struct sched_info sched_info;
 #endif
 
         struct list_head tasks;
+#ifdef CONFIG_SMP
         struct plist_node pushable_tasks;
+#endif
 
         struct mm_struct *mm, *active_mm;
+#ifdef CONFIG_COMPAT_BRK
+        unsigned brk_randomized:1;
+#endif
 #if defined(SPLIT_RSS_COUNTING)
         struct task_rss_stat    rss_stat;
 #endif
@@ -1229,6 +1297,7 @@ struct task_struct {
         int exit_state;
         int exit_code, exit_signal;
         int pdeath_signal;  /*  The signal sent when the parent dies  */
+        unsigned int group_stop;        /* GROUP_STOP_*, siglock protected */
         /* ??? */
         unsigned int personality;
         unsigned did_exec:1;
@@ -1239,6 +1308,7 @@ struct task_struct {
 
         /* Revert to default priority/policy when forking */
         unsigned sched_reset_on_fork:1;
+        unsigned sched_contributes_to_load:1;
 
         pid_t pid;
         pid_t tgid;
@@ -1293,13 +1363,10 @@ struct task_struct {
         struct list_head cpu_timers[3];
 
 /* process credentials */
-        const struct cred *real_cred;   /* objective and real subjective task
+        const struct cred __rcu *real_cred; /* objective and real subjective task
                                          * credentials (COW) */
-        const struct cred *cred;        /* effective (overridable) subjective task
+        const struct cred __rcu *cred;  /* effective (overridable) subjective task
                                          * credentials (COW) */
-        struct mutex cred_guard_mutex;  /* guard against foreign influences on
-                                         * credential calculations
-                                         * (notably. ptrace) */
         struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */
 
         char comm[TASK_COMM_LEN]; /* executable name excluding path
@@ -1400,6 +1467,11 @@ struct task_struct {
 /* stacked block device info */
         struct bio_list *bio_list;
 
+#ifdef CONFIG_BLOCK
+/* stack plugging */
+        struct blk_plug *plug;
+#endif
+
 /* VM state */
         struct reclaim_state *reclaim_state;
 
@@ -1423,7 +1495,7 @@ struct task_struct {
 #endif
 #ifdef CONFIG_CGROUPS
         /* Control Group info protected by css_set_lock */
-        struct css_set *cgroups;
+        struct css_set __rcu *cgroups;
         /* cg_list protected by css_set_lock and tsk->alloc_lock */
         struct list_head cg_list;
 #endif
@@ -1436,13 +1508,14 @@ struct task_struct {
         struct futex_pi_state *pi_state_cache;
 #endif
 #ifdef CONFIG_PERF_EVENTS
-        struct perf_event_context *perf_event_ctxp;
+        struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
         struct mutex perf_event_mutex;
         struct list_head perf_event_list;
 #endif
 #ifdef CONFIG_NUMA
         struct mempolicy *mempolicy;    /* Protected by alloc_lock */
         short il_next;
+        short pref_node_fork;
 #endif
         atomic_t fs_excl;       /* holding fs exclusive resources */
         struct rcu_head rcu;
@@ -1495,17 +1568,20 @@ struct task_struct {
 #ifdef CONFIG_TRACING
         /* state flags for use by tracers */
         unsigned long trace;
-        /* bitmask of trace recursion */
+        /* bitmask and counter of trace recursion */
         unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
         struct memcg_batch_info {
                 int do_batch;   /* incremented when batch uncharge started */
                 struct mem_cgroup *memcg; /* target memcg of uncharge */
-                unsigned long bytes;            /* uncharged usage */
-                unsigned long memsw_bytes; /* uncharged mem+swap usage */
+                unsigned long nr_pages; /* uncharged usage */
+                unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
         } memcg_batch;
 #endif
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+        atomic_t ptrace_bp_refcnt;
+#endif
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
@@ -1693,8 +1769,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 /*
  * Per process flags
  */
-#define PF_ALIGNWARN    0x00000001      /* Print alignment warning msgs */
-                                        /* Not implemented yet, only for 486*/
 #define PF_STARTING     0x00000002      /* being created */
 #define PF_EXITING      0x00000004      /* getting shut down */
 #define PF_EXITPIDONE   0x00000008      /* pi exit done on shut down */
@@ -1706,14 +1780,12 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_DUMPCORE     0x00000200      /* dumped core */
 #define PF_SIGNALED     0x00000400      /* killed by a signal */
 #define PF_MEMALLOC     0x00000800      /* Allocating memory */
-#define PF_FLUSHER      0x00001000      /* responsible for disk writeback */
 #define PF_USED_MATH    0x00002000      /* if unset the fpu must be initialized before use */
 #define PF_FREEZING     0x00004000      /* freeze in progress. do not account to load */
 #define PF_NOFREEZE     0x00008000      /* this thread should not be frozen */
 #define PF_FROZEN       0x00010000      /* frozen for system suspend */
 #define PF_FSTRANS      0x00020000      /* inside a filesystem transaction */
 #define PF_KSWAPD       0x00040000      /* I am kswapd */
-#define PF_OOM_ORIGIN   0x00080000      /* Allocating much memory to others */
 #define PF_LESS_THROTTLE 0x00100000     /* Throttle me less: I clean memory */
 #define PF_KTHREAD      0x00200000      /* I am a kernel thread */
 #define PF_RANDOMIZE    0x00400000      /* randomize virtual address space */
@@ -1724,7 +1796,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
 #define PF_MEMPOLICY    0x10000000      /* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER 0x20000000      /* Thread belongs to the rt mutex tester */
-#define PF_FREEZER_SKIP 0x40000000      /* Freezer should not count it as freezeable */
+#define PF_FREEZER_SKIP 0x40000000      /* Freezer should not count it as freezable */
 #define PF_FREEZER_NOSIG 0x80000000     /* Freezer won't send signals to it */
 
 /*
@@ -1752,16 +1824,33 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+/*
+ * task->group_stop flags
+ */
+#define GROUP_STOP_SIGMASK      0xffff    /* signr of the last group stop */
+#define GROUP_STOP_PENDING      (1 << 16) /* task should stop for group stop */
+#define GROUP_STOP_CONSUME      (1 << 17) /* consume group stop count */
+#define GROUP_STOP_TRAPPING     (1 << 18) /* switching from STOPPED to TRACED */
+#define GROUP_STOP_DEQUEUED     (1 << 19) /* stop signal dequeued */
+
+extern void task_clear_group_stop_pending(struct task_struct *task);
+
+#ifdef CONFIG_PREEMPT_RCU
 
 #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
-#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
+#define RCU_READ_UNLOCK_BOOSTED (1 << 1) /* boosted while in RCU read-side. */
+#define RCU_READ_UNLOCK_NEED_QS (1 << 2) /* RCU core needs CPU response. */
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
         p->rcu_read_lock_nesting = 0;
         p->rcu_read_unlock_special = 0;
+#ifdef CONFIG_TREE_PREEMPT_RCU
         p->rcu_blocked_node = NULL;
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#ifdef CONFIG_RCU_BOOST
+        p->rcu_boost_mutex = NULL;
+#endif /* #ifdef CONFIG_RCU_BOOST */
         INIT_LIST_HEAD(&p->rcu_node_entry);
 }
 
@@ -1774,9 +1863,16 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif
 
 #ifdef CONFIG_SMP
+extern void do_set_cpus_allowed(struct task_struct *p,
+                               const struct cpumask *new_mask);
+
 extern int set_cpus_allowed_ptr(struct task_struct *p,
                                 const struct cpumask *new_mask);
 #else
+static inline void do_set_cpus_allowed(struct task_struct *p,
+                                      const struct cpumask *new_mask)
+{
+}
 static inline int set_cpus_allowed_ptr(struct task_struct *p,
                                        const struct cpumask *new_mask)
 {
@@ -1838,6 +1934,19 @@ extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
 #endif
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * An i/f to runtime opt-in for irq time accounting based off of sched_clock.
+ * The reason for this explicit opt-in is not to have perf penalty with
+ * slow sched_clocks.
+ */
+extern void enable_sched_clock_irqtime(void);
+extern void disable_sched_clock_irqtime(void);
+#else
+static inline void enable_sched_clock_irqtime(void) {}
+static inline void disable_sched_clock_irqtime(void) {}
+#endif
+
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
 extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
@@ -1853,14 +1962,11 @@ extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
 
 #ifdef CONFIG_HOTPLUG_CPU
-extern void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p);
 extern void idle_task_exit(void);
 #else
 static inline void idle_task_exit(void) {}
 #endif
 
-extern void sched_idle_next(void);
-
 #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
 extern void wake_up_idle_cpu(int cpu);
 #else
@@ -1870,8 +1976,6 @@ static inline void wake_up_idle_cpu(int cpu) { }
 extern unsigned int sysctl_sched_latency;
 extern unsigned int sysctl_sched_min_granularity;
 extern unsigned int sysctl_sched_wakeup_granularity;
-extern unsigned int sysctl_sched_shares_ratelimit;
-extern unsigned int sysctl_sched_shares_thresh;
 extern unsigned int sysctl_sched_child_runs_first;
 
 enum sched_tunable_scaling {
@@ -1887,6 +1991,7 @@ extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
 extern unsigned int sysctl_sched_time_avg;
 extern unsigned int sysctl_timer_migration;
+extern unsigned int sysctl_sched_shares_window;
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
                 void __user *buffer, size_t *length,
@@ -1910,7 +2015,23 @@ int sched_rt_handler(struct ctl_table *table, int write,
                 void __user *buffer, size_t *lenp,
                 loff_t *ppos);
 
-extern unsigned int sysctl_sched_compat_yield;
+#ifdef CONFIG_SCHED_AUTOGROUP
+extern unsigned int sysctl_sched_autogroup_enabled;
+
+extern void sched_autogroup_create_attach(struct task_struct *p);
+extern void sched_autogroup_detach(struct task_struct *p);
+extern void sched_autogroup_fork(struct signal_struct *sig);
+extern void sched_autogroup_exit(struct signal_struct *sig);
+#ifdef CONFIG_PROC_FS
+extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
+extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice);
+#endif
+#else
+static inline void sched_autogroup_create_attach(struct task_struct *p) { }
+static inline void sched_autogroup_detach(struct task_struct *p) { }
+static inline void sched_autogroup_fork(struct signal_struct *sig) { }
+static inline void sched_autogroup_exit(struct signal_struct *sig) { }
+#endif
 
 #ifdef CONFIG_RT_MUTEXES
 extern int rt_mutex_getprio(struct task_struct *p);
@@ -1924,15 +2045,17 @@ static inline int rt_mutex_getprio(struct task_struct *p)
 # define rt_mutex_adjust_pi(p)          do { } while (0)
 #endif
 
+extern bool yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
 extern int task_nice(const struct task_struct *p);
 extern int can_nice(const struct task_struct *p, const int nice);
 extern int task_curr(const struct task_struct *p);
 extern int idle_cpu(int cpu);
-extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);
+extern int sched_setscheduler(struct task_struct *, int,
+                              const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int,
-                                      struct sched_param *);
+                                      const struct sched_param *);
 extern struct task_struct *idle_task(int cpu);
 extern struct task_struct *curr_task(int cpu);
 extern void set_curr_task(int cpu, struct task_struct *p);
@@ -1995,18 +2118,17 @@ extern void release_uids(struct user_namespace *ns);
 
 #include <asm/current.h>
 
-extern void do_timer(unsigned long ticks);
+extern void xtime_update(unsigned long ticks);
 
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
-extern void wake_up_new_task(struct task_struct *tsk,
-                                unsigned long clone_flags);
+extern void wake_up_new_task(struct task_struct *tsk);
 #ifdef CONFIG_SMP
  extern void kick_process(struct task_struct *tsk);
 #else
  static inline void kick_process(struct task_struct *tsk) { }
 #endif
-extern void sched_fork(struct task_struct *p, int clone_flags);
+extern void sched_fork(struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);
@@ -2131,8 +2253,10 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
+void scheduler_ipi(void);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
+static inline void scheduler_ipi(void) { }
 static inline unsigned long wait_task_inactive(struct task_struct *p,
                                                long match_state)
 {
@@ -2222,15 +2346,47 @@ static inline void task_unlock(struct task_struct *p)
         spin_unlock(&p->alloc_lock);
 }
 
-extern struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
+extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
                                                         unsigned long *flags);
 
+#define lock_task_sighand(tsk, flags)                                   \
+({      struct sighand_struct *__ss;                                    \
+        __cond_lock(&(tsk)->sighand->siglock,                           \
+                    (__ss = __lock_task_sighand(tsk, flags)));          \
+        __ss;                                                           \
+})                                                                      \
+
 static inline void unlock_task_sighand(struct task_struct *tsk,
                                                 unsigned long *flags)
 {
         spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
 }
 
+/* See the declaration of threadgroup_fork_lock in signal_struct. */
+#ifdef CONFIG_CGROUPS
+static inline void threadgroup_fork_read_lock(struct task_struct *tsk)
+{
+        down_read(&tsk->signal->threadgroup_fork_lock);
+}
+static inline void threadgroup_fork_read_unlock(struct task_struct *tsk)
+{
+        up_read(&tsk->signal->threadgroup_fork_lock);
+}
+static inline void threadgroup_fork_write_lock(struct task_struct *tsk)
+{
+        down_write(&tsk->signal->threadgroup_fork_lock);
+}
+static inline void threadgroup_fork_write_unlock(struct task_struct *tsk)
+{
+        up_write(&tsk->signal->threadgroup_fork_lock);
+}
+#else
+static inline void threadgroup_fork_read_lock(struct task_struct *tsk) {}
+static inline void threadgroup_fork_read_unlock(struct task_struct *tsk) {}
+static inline void threadgroup_fork_write_lock(struct task_struct *tsk) {}
+static inline void threadgroup_fork_write_unlock(struct task_struct *tsk) {}
+#endif
+
 #ifndef __HAVE_THREAD_FUNCTIONS
 
 #define task_thread_info(task)  ((struct thread_info *)(task)->stack)
@@ -2380,9 +2536,9 @@ extern int __cond_resched_lock(spinlock_t *lock);
 
 extern int __cond_resched_softirq(void);
 
-#define cond_resched_softirq() ({                               \
-        __might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET);      \
-        __cond_resched_softirq();                               \
+#define cond_resched_softirq() ({                                       \
+        __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);      \
+        __cond_resched_softirq();                                       \
 })
 
 /*
@@ -2453,7 +2609,7 @@ extern void normalize_rt_tasks(void);
 
 #ifdef CONFIG_CGROUP_SCHED
 
-extern struct task_group init_task_group;
+extern struct task_group root_task_group;
 
 extern struct task_group *sched_create_group(struct task_group *parent);
 extern void sched_destroy_group(struct task_group *tg);
@@ -2518,13 +2674,6 @@ static inline void inc_syscw(struct task_struct *tsk)
 #define TASK_SIZE_OF(tsk)       TASK_SIZE
 #endif
 
-/*
- * Call the function if the target task is executing on a CPU right now:
- */
-extern void task_oncpu_function_call(struct task_struct *p,
-                                     void (*func) (void *info), void *info);
-
-
 #ifdef CONFIG_MM_OWNER
 extern void mm_update_next_owner(struct mm_struct *mm);
 extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);