X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Flinux%2Fsched.h;h=f118809c953ff137b2a97e0d9e674b2836ee331a;hb=cc106eb35ed4abea675bce0d8fe40a46ff0b4a72;hp=8f3e63cb33a629019edd5907a645efb71a7aa076;hpb=f8af4da3b4c14e7267c4ffb952079af3912c51c5;p=safe%2Fjmp%2Flinux-2.6

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8f3e63c..f118809 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -97,9 +97,8 @@ struct sched_param {
 struct exec_domain;
 struct futex_pi_state;
 struct robust_list_head;
-struct bio;
+struct bio_list;
 struct fs_struct;
-struct bts_context;
 struct perf_event_context;
 
 /*
@@ -140,8 +139,11 @@ extern int nr_processes(void);
 extern unsigned long nr_running(void);
 extern unsigned long nr_uninterruptible(void);
 extern unsigned long nr_iowait(void);
+extern unsigned long nr_iowait_cpu(void);
+extern unsigned long this_cpu_load(void);
+
+
 extern void calc_global_load(void);
-extern u64 cpu_nr_migrations(int cpu);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -167,8 +169,6 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 }
 #endif
 
-extern unsigned long long time_sync_thresh;
-
 /*
  * Task state bitmask. NOTE! These bits are also
  * encoded in fs/proc/array.c: get_task_state().
@@ -191,6 +191,12 @@ extern unsigned long long time_sync_thresh;
 #define TASK_DEAD		64
 #define TASK_WAKEKILL		128
 #define TASK_WAKING		256
+#define TASK_STATE_MAX		512
+
+#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW"
+
+extern char ___assert_task_state[1 - 2*!!(
+		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
 
 /* Convenience macros for the sake of set_task_state */
 #define TASK_KILLABLE		(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
@@ -251,6 +257,10 @@ extern spinlock_t mmlist_lock;
 
 struct task_struct;
 
+#ifdef CONFIG_PROVE_RCU
+extern int lockdep_tasklist_lock_is_held(void);
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
 extern void sched_init(void);
 extern void sched_init_smp(void);
 extern asmlinkage void schedule_tail(struct task_struct *prev);
@@ -258,17 +268,22 @@ extern void init_idle(struct task_struct *idle, int cpu);
 extern void init_idle_bootup_task(struct task_struct *idle);
 
 extern int runqueue_is_locked(int cpu);
-extern void task_rq_unlock_wait(struct task_struct *p);
 
 extern cpumask_var_t nohz_cpu_mask;
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
 extern int select_nohz_load_balancer(int cpu);
 extern int get_nohz_load_balancer(void);
+extern int nohz_ratelimit(int cpu);
 #else
 static inline int select_nohz_load_balancer(int cpu)
 {
 	return 0;
 }
+
+static inline int nohz_ratelimit(int cpu)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -303,9 +318,10 @@ extern void sched_show_task(struct task_struct *p);
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 extern void softlockup_tick(void);
 extern void touch_softlockup_watchdog(void);
+extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
 extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
-				    struct file *filp, void __user *buffer,
+				    void __user *buffer,
 				    size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
 extern int softlockup_thresh;
@@ -316,6 +332,9 @@ static inline void softlockup_tick(void)
 static inline void touch_softlockup_watchdog(void)
 {
 }
+static inline void touch_softlockup_watchdog_sync(void)
+{
+}
 static inline void touch_all_softlockup_watchdogs(void)
 {
 }
@@ -327,7 +346,7 @@ extern unsigned long sysctl_hung_task_check_count;
 extern unsigned long sysctl_hung_task_timeout_secs;
 extern unsigned long sysctl_hung_task_warnings;
 extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
-					 struct file *filp, void __user *buffer,
+					 void __user *buffer,
 					 size_t *lenp, loff_t *ppos);
 #endif
 
@@ -345,7 +364,6 @@ extern signed long schedule_timeout(signed long timeout);
 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);
 asmlinkage void schedule(void);
 extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
 
@@ -365,12 +383,14 @@ struct user_namespace;
  * 1-3 now and depends on arch. We use "5" as safe margin, here.
  */
 #define MAPCOUNT_ELF_CORE_MARGIN	(5)
-#define DEFAULT_MAX_MAP_COUNT	(USHORT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
+#define DEFAULT_MAX_MAP_COUNT	(USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
 
 extern int sysctl_max_map_count;
 
 #include <linux/aio.h>
 
+#ifdef CONFIG_MMU
+extern void arch_pick_mmap_layout(struct mm_struct *mm);
 extern unsigned long
 arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
 		       unsigned long, unsigned long);
@@ -380,52 +400,10 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 			  unsigned long flags);
 extern void arch_unmap_area(struct mm_struct *, unsigned long);
 extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
+#else
+static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
+#endif
 
-#if USE_SPLIT_PTLOCKS
-/*
- * The mm counters are not protected by its page_table_lock,
- * so must be incremented atomically.
- */
-#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value)
-#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member))
-#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member)
-#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member)
-#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member)
-
-#else  /* !USE_SPLIT_PTLOCKS */
-/*
- * The mm counters are protected by its page_table_lock,
- * so can be incremented directly.
- */
-#define set_mm_counter(mm, member, value) (mm)->_##member = (value)
-#define get_mm_counter(mm, member) ((mm)->_##member)
-#define add_mm_counter(mm, member, value) (mm)->_##member += (value)
-#define inc_mm_counter(mm, member) (mm)->_##member++
-#define dec_mm_counter(mm, member) (mm)->_##member--
-
-#endif /* !USE_SPLIT_PTLOCKS */
-
-#define get_mm_rss(mm)					\
-	(get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
-#define update_hiwater_rss(mm)	do {			\
-	unsigned long _rss = get_mm_rss(mm);		\
-	if ((mm)->hiwater_rss < _rss)			\
-		(mm)->hiwater_rss = _rss;		\
-} while (0)
-#define update_hiwater_vm(mm)	do {			\
-	if ((mm)->hiwater_vm < (mm)->total_vm)		\
-		(mm)->hiwater_vm = (mm)->total_vm;	\
-} while (0)
-
-static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)
-{
-	return max(mm->hiwater_rss, get_mm_rss(mm));
-}
-
-static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
-{
-	return max(mm->hiwater_vm, mm->total_vm);
-}
 
 extern void set_dumpable(struct mm_struct *mm, int value);
 extern int get_dumpable(struct mm_struct *mm);
@@ -480,6 +458,13 @@ struct pacct_struct {
 	unsigned long		ac_minflt, ac_majflt;
 };
 
+struct cpu_itimer {
+	cputime_t expires;
+	cputime_t incr;
+	u32 error;
+	u32 incr_error;
+};
+
 /**
  * struct task_cputime - collected CPU time counts
  * @utime:		time spent in user mode, in &cputime_t units
@@ -541,8 +526,9 @@ struct thread_group_cputimer {
  * the locking of signal_struct.
  */
 struct signal_struct {
-	atomic_t		count;
+	atomic_t		sigcnt;
 	atomic_t		live;
+	int			nr_threads;
 
 	wait_queue_head_t	wait_chldexit;	/* for wait4() */
 
@@ -574,9 +560,12 @@ struct signal_struct {
 	struct pid *leader_pid;
 	ktime_t it_real_incr;
 
-	/* ITIMER_PROF and ITIMER_VIRTUAL timers for the process */
-	cputime_t it_prof_expires, it_virt_expires;
-	cputime_t it_prof_incr, it_virt_incr;
+	/*
+	 * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use
+	 * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these
+	 * values are defined to 0 and 1 respectively
+	 */
+	struct cpu_itimer it[2];
 
 	/*
 	 * Thread group totals for process CPU timers.
@@ -605,9 +594,13 @@ struct signal_struct {
 	cputime_t utime, stime, cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+	cputime_t prev_utime, prev_stime;
+#endif
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
 	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
 	unsigned long inblock, oublock, cinblock, coublock;
+	unsigned long maxrss, cmaxrss;
 	struct task_io_accounting ioac;
 
 	/*
@@ -639,6 +632,8 @@ struct signal_struct {
 	unsigned audit_tty;
 	struct tty_audit_buf *tty_audit_buf;
 #endif
+
+	int oom_adj;	/* OOM kill score adjustment (bit shift) */
 };
 
 /* Context switch must be unlocked if interrupts are to be enabled */
@@ -700,14 +695,6 @@ struct user_struct {
 	uid_t uid;
 	struct user_namespace *user_ns;
 
-#ifdef CONFIG_USER_SCHED
-	struct task_group *tg;
-#ifdef CONFIG_SYSFS
-	struct kobject kobj;
-	struct delayed_work work;
-#endif
-#endif
-
 #ifdef CONFIG_PERF_EVENTS
 	atomic_long_t locked_vm;
 #endif
@@ -838,7 +825,10 @@ static inline int sd_balance_for_mc_power(void)
 	if (sched_smt_power_savings)
 		return SD_POWERSAVINGS_BALANCE;
 
-	return SD_PREFER_SIBLING;
+	if (!sched_mc_power_savings)
+		return SD_PREFER_SIBLING;
+
+	return 0;
 }
 
 static inline int sd_balance_for_package_power(void)
@@ -969,6 +959,7 @@ struct sched_domain {
 	char *name;
 #endif
 
+	unsigned int span_weight;
 	/*
 	 * Span of all CPUs in this domain.
 	 *
@@ -987,9 +978,13 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
 	return to_cpumask(sd->span);
 }
 
-extern void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 				    struct sched_domain_attr *dattr_new);
 
+/* Allocate an array of sched domains, for partition_sched_domains(). */
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
+
 /* Test a flag in parent sched domain */
 static inline int test_sd_parent(struct sched_domain *sd, int flag)
 {
@@ -1007,7 +1002,7 @@ unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
 struct sched_domain_attr;
 
 static inline void
-partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			struct sched_domain_attr *dattr_new)
 {
 }
@@ -1037,11 +1032,17 @@ struct sched_domain;
 #define WF_SYNC		0x01		/* waker goes to sleep after wakup */
 #define WF_FORK		0x02		/* child wakeup after fork */
 
+#define ENQUEUE_WAKEUP		1
+#define ENQUEUE_WAKING		2
+#define ENQUEUE_HEAD		4
+
+#define DEQUEUE_SLEEP		1
+
 struct sched_class {
 	const struct sched_class *next;
 
-	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
-	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
+	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);
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
@@ -1050,19 +1051,13 @@ struct sched_class {
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
-	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
+	int  (*select_task_rq)(struct rq *rq, struct task_struct *p,
+			       int sd_flag, int flags);
 
-	unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
-			struct rq *busiest, unsigned long max_load_move,
-			struct sched_domain *sd, enum cpu_idle_type idle,
-			int *all_pinned, int *this_best_prio);
-
-	int (*move_one_task) (struct rq *this_rq, int this_cpu,
-			      struct rq *busiest, struct sched_domain *sd,
-			      enum cpu_idle_type idle);
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);
-	void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
+	void (*task_waking) (struct rq *this_rq, struct task_struct *task);
+	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
 
 	void (*set_cpus_allowed)(struct task_struct *p,
 				 const struct cpumask *newmask);
@@ -1073,7 +1068,7 @@ struct sched_class {
 
 	void (*set_curr_task) (struct rq *rq);
 	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
-	void (*task_new) (struct rq *rq, struct task_struct *p);
+	void (*task_fork) (struct task_struct *p);
 
 	void (*switched_from) (struct rq *this_rq, struct task_struct *task,
 			       int running);
@@ -1082,10 +1077,11 @@ struct sched_class {
 	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
 			     int oldprio, int running);
 
-	unsigned int (*get_rr_interval) (struct task_struct *task);
+	unsigned int (*get_rr_interval) (struct rq *rq,
+					 struct task_struct *task);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	void (*moved_group) (struct task_struct *p);
+	void (*moved_group) (struct task_struct *p, int on_rq);
 #endif
 };
 
@@ -1093,38 +1089,8 @@ struct load_weight {
 	unsigned long weight, inv_weight;
 };
 
-/*
- * CFS stats for a schedulable entity (task, task-group etc)
- *
- * Current field usage histogram:
- *
- *     4 se->block_start
- *     4 se->run_node
- *     4 se->sleep_start
- *     6 se->load.weight
- */
-struct sched_entity {
-	struct load_weight	load;		/* for load-balancing */
-	struct rb_node		run_node;
-	struct list_head	group_node;
-	unsigned int		on_rq;
-
-	u64			exec_start;
-	u64			sum_exec_runtime;
-	u64			vruntime;
-	u64			prev_sum_exec_runtime;
-
-	u64			last_wakeup;
-	u64			avg_overlap;
-
-	u64			nr_migrations;
-
-	u64			start_runtime;
-	u64			avg_wakeup;
-
-	u64			avg_running;
-
 #ifdef CONFIG_SCHEDSTATS
+struct sched_statistics {
 	u64			wait_start;
 	u64			wait_max;
 	u64			wait_count;
@@ -1146,7 +1112,6 @@ struct sched_entity {
 	u64			nr_failed_migrations_running;
 	u64			nr_failed_migrations_hot;
 	u64			nr_forced_migrations;
-	u64			nr_forced2_migrations;
 
 	u64			nr_wakeups;
 	u64			nr_wakeups_sync;
@@ -1157,6 +1122,24 @@ struct sched_entity {
 	u64			nr_wakeups_affine_attempts;
 	u64			nr_wakeups_passive;
 	u64			nr_wakeups_idle;
+};
+#endif
+
+struct sched_entity {
+	struct load_weight	load;		/* for load-balancing */
+	struct rb_node		run_node;
+	struct list_head	group_node;
+	unsigned int		on_rq;
+
+	u64			exec_start;
+	u64			sum_exec_runtime;
+	u64			vruntime;
+	u64			prev_sum_exec_runtime;
+
+	u64			nr_migrations;
+
+#ifdef CONFIG_SCHEDSTATS
+	struct sched_statistics statistics;
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1221,7 +1204,6 @@ struct task_struct {
 	 * a short time
 	 */
 	unsigned char fpu_counter;
-	s8 oomkilladj; /* OOM kill score adjustment (bit shift). */
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	unsigned int btrace_seq;
 #endif
@@ -1244,9 +1226,10 @@ struct task_struct {
 	struct plist_node pushable_tasks;
 
 	struct mm_struct *mm, *active_mm;
-
+#if defined(SPLIT_RSS_COUNTING)
+	struct task_rss_stat	rss_stat;
+#endif
 /* task state */
-	struct linux_binfmt *binfmt;
 	int exit_state;
 	int exit_code, exit_signal;
 	int pdeath_signal;  /*  The signal sent when the parent dies  */
@@ -1291,12 +1274,6 @@ struct task_struct {
 	struct list_head ptraced;
 	struct list_head ptrace_entry;
 
-	/*
-	 * This is the tracer handle for the ptrace BTS extension.
-	 * This field actually belongs to the ptracer task.
-	 */
-	struct bts_context *bts;
-
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
 	struct list_head thread_group;
@@ -1307,7 +1284,9 @@ struct task_struct {
 
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	cputime_t prev_utime, prev_stime;
+#endif
 	unsigned long nvcsw, nivcsw; /* context switch counts */
 	struct timespec start_time; 		/* monotonic time */
 	struct timespec real_start_time;	/* boot based time */
@@ -1330,7 +1309,7 @@ struct task_struct {
 	char comm[TASK_COMM_LEN]; /* executable name excluding path
 				     - access with [gs]et_task_comm (which lock
 				       it with task_lock())
-				     - initialized normally by flush_old_exec */
+				     - initialized normally by setup_new_exec */
 /* file system info */
 	int link_count, total_link_count;
 #ifdef CONFIG_SYSVIPC
@@ -1382,7 +1361,7 @@ struct task_struct {
 #endif
 
 	/* Protection of the PI data structures: */
-	spinlock_t pi_lock;
+	raw_spinlock_t pi_lock;
 
 #ifdef CONFIG_RT_MUTEXES
 	/* PI waiters blocked on a rt_mutex held by this task */
@@ -1397,17 +1376,17 @@ struct task_struct {
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	unsigned int irq_events;
-	int hardirqs_enabled;
 	unsigned long hardirq_enable_ip;
-	unsigned int hardirq_enable_event;
 	unsigned long hardirq_disable_ip;
+	unsigned int hardirq_enable_event;
 	unsigned int hardirq_disable_event;
-	int softirqs_enabled;
+	int hardirqs_enabled;
+	int hardirq_context;
 	unsigned long softirq_disable_ip;
-	unsigned int softirq_disable_event;
 	unsigned long softirq_enable_ip;
+	unsigned int softirq_disable_event;
 	unsigned int softirq_enable_event;
-	int hardirq_context;
+	int softirqs_enabled;
 	int softirq_context;
 #endif
 #ifdef CONFIG_LOCKDEP
@@ -1423,7 +1402,7 @@ struct task_struct {
 	void *journal_info;
 
 /* stacked block device info */
-	struct bio *bio_list, **bio_tail;
+	struct bio_list *bio_list;
 
 /* VM state */
 	struct reclaim_state *reclaim_state;
@@ -1442,7 +1421,9 @@ struct task_struct {
 #endif
 #ifdef CONFIG_CPUSETS
 	nodemask_t mems_allowed;	/* Protected by alloc_lock */
+	int mems_allowed_change_disable;
 	int cpuset_mem_spread_rotor;
+	int cpuset_slab_spread_rotor;
 #endif
 #ifdef CONFIG_CGROUPS
 	/* Control Group info protected by css_set_lock */
@@ -1494,7 +1475,7 @@ struct task_struct {
 
 	struct list_head	*scm_work_list;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* Index of current stored adress in ret_stack */
+	/* Index of current stored address in ret_stack */
 	int curr_ret_stack;
 	/* Stack of return addresses for return function tracing */
 	struct ftrace_ret_stack	*ret_stack;
@@ -1514,10 +1495,18 @@ struct task_struct {
 	/* bitmask 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 */
+	} memcg_batch;
+#endif
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
-#define tsk_cpumask(tsk) (&(tsk)->cpus_allowed)
+#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
 /*
  * Priority of a process goes from 0..MAX_PRIO-1, valid RT
@@ -1695,9 +1684,8 @@ static inline void put_task_struct(struct task_struct *t)
 		__put_task_struct(t);
 }
 
-extern cputime_t task_utime(struct task_struct *p);
-extern cputime_t task_stime(struct task_struct *p);
-extern cputime_t task_gtime(struct task_struct *p);
+extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
 
 /*
  * Per process flags
@@ -1709,6 +1697,7 @@ extern cputime_t task_gtime(struct task_struct *p);
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
 #define PF_VCPU		0x00000010	/* I'm a virtual CPU */
 #define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
+#define PF_MCE_PROCESS  0x00000080      /* process policy on mce errors */
 #define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
 #define PF_DUMPCORE	0x00000200	/* dumped core */
 #define PF_SIGNALED	0x00000400	/* killed by a signal */
@@ -1720,7 +1709,7 @@ extern cputime_t task_gtime(struct task_struct *p);
 #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_SWAPOFF	0x00080000	/* I am in swapoff */
+#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 */
@@ -1728,6 +1717,7 @@ extern cputime_t task_gtime(struct task_struct *p);
 #define PF_SPREAD_PAGE	0x01000000	/* Spread page cache over cpuset */
 #define PF_SPREAD_SLAB	0x02000000	/* Spread some slab caches over cpuset */
 #define PF_THREAD_BOUND	0x04000000	/* Thread bound to specific cpu */
+#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 */
@@ -1791,10 +1781,13 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p,
 	return 0;
 }
 #endif
+
+#ifndef CONFIG_CPUMASK_OFFSTACK
 static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
 {
 	return set_cpus_allowed_ptr(p, &new_mask);
 }
+#endif
 
 /*
  * Architectures can set this to 1 if they have specified
@@ -1806,7 +1799,8 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
 extern int sched_clock_stable;
 #endif
 
-extern unsigned long long sched_clock(void);
+/* ftrace calls sched_clock() directly */
+extern unsigned long long notrace sched_clock(void);
 
 extern void sched_clock_init(void);
 extern u64 sched_clock_cpu(int cpu);
@@ -1850,6 +1844,7 @@ 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) {}
@@ -1869,15 +1864,23 @@ 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 {
+	SCHED_TUNABLESCALING_NONE,
+	SCHED_TUNABLESCALING_LOG,
+	SCHED_TUNABLESCALING_LINEAR,
+	SCHED_TUNABLESCALING_END,
+};
+extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
+
 #ifdef CONFIG_SCHED_DEBUG
-extern unsigned int sysctl_sched_features;
 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;
 
-int sched_nr_latency_handler(struct ctl_table *table, int write,
-		struct file *file, void __user *buffer, size_t *length,
+int sched_proc_update_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *length,
 		loff_t *ppos);
 #endif
 #ifdef CONFIG_SCHED_DEBUG
@@ -1895,7 +1898,7 @@ extern unsigned int sysctl_sched_rt_period;
 extern int sysctl_sched_rt_runtime;
 
 int sched_rt_handler(struct ctl_table *table, int write,
-		struct file *filp, void __user *buffer, size_t *lenp,
+		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
 
 extern unsigned int sysctl_sched_compat_yield;
@@ -2030,10 +2033,10 @@ extern int kill_pgrp(struct pid *pid, int sig, int priv);
 extern int kill_pid(struct pid *pid, int sig, int priv);
 extern int kill_proc_info(int, struct siginfo *, pid_t);
 extern int do_notify_parent(struct task_struct *, int);
+extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
 extern void force_sig(int, struct task_struct *);
-extern void force_sig_specific(int, struct task_struct *);
 extern int send_sig(int, struct task_struct *, int);
-extern void zap_other_threads(struct task_struct *p);
+extern int zap_other_threads(struct task_struct *p);
 extern struct sigqueue *sigqueue_alloc(void);
 extern void sigqueue_free(struct sigqueue *);
 extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
@@ -2050,16 +2053,18 @@ static inline int kill_cad_pid(int sig, int priv)
 #define SEND_SIG_PRIV	((struct siginfo *) 1)
 #define SEND_SIG_FORCED	((struct siginfo *) 2)
 
-static inline int is_si_special(const struct siginfo *info)
-{
-	return info <= SEND_SIG_FORCED;
-}
-
-/* True if we are on the alternate signal stack.  */
-
+/*
+ * True if we are on the alternate signal stack.
+ */
 static inline int on_sig_stack(unsigned long sp)
 {
-	return (sp - current->sas_ss_sp < current->sas_ss_size);
+#ifdef CONFIG_STACK_GROWSUP
+	return sp >= current->sas_ss_sp &&
+		sp - current->sas_ss_sp < current->sas_ss_size;
+#else
+	return sp > current->sas_ss_sp &&
+		sp - current->sas_ss_sp <= current->sas_ss_size;
+#endif
 }
 
 static inline int sas_ss_flags(unsigned long sp)
@@ -2096,7 +2101,6 @@ extern void flush_thread(void);
 extern void exit_thread(void);
 
 extern void exit_files(struct task_struct *);
-extern void __cleanup_signal(struct signal_struct *);
 extern void __cleanup_sighand(struct sighand_struct *);
 
 extern void exit_itimers(struct signal_struct *);
@@ -2116,10 +2120,8 @@ 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
-extern void wait_task_context_switch(struct task_struct *p);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
-static inline void wait_task_context_switch(struct task_struct *p) {}
 static inline unsigned long wait_task_inactive(struct task_struct *p,
 					       long match_state)
 {
@@ -2145,6 +2147,11 @@ extern bool current_is_single_threaded(void);
 #define while_each_thread(g, t) \
 	while ((t = next_thread(t)) != g)
 
+static inline int get_nr_threads(struct task_struct *tsk)
+{
+	return tsk->signal->nr_threads;
+}
+
 /* de_thread depends on thread_group_leader not being a pid based check */
 #define thread_group_leader(p)	(p == p->group_leader)
 
@@ -2307,7 +2314,10 @@ static inline int signal_pending(struct task_struct *p)
 	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
 }
 
-extern int __fatal_signal_pending(struct task_struct *p);
+static inline int __fatal_signal_pending(struct task_struct *p)
+{
+	return unlikely(sigismember(&p->pending.signal, SIGKILL));
+}
 
 static inline int fatal_signal_pending(struct task_struct *p)
 {
@@ -2385,13 +2395,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
 
 static inline void thread_group_cputime_init(struct signal_struct *sig)
 {
-	sig->cputimer.cputime = INIT_CPUTIME;
 	spin_lock_init(&sig->cputimer.lock);
-	sig->cputimer.running = 0;
-}
-
-static inline void thread_group_cputime_free(struct signal_struct *sig)
-{
 }
 
 /*
@@ -2430,8 +2434,6 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 #endif /* CONFIG_SMP */
 
-extern void arch_pick_mmap_layout(struct mm_struct *mm);
-
 #ifdef CONFIG_TRACING
 extern void
 __trace_special(void *__tr, void *__data,
@@ -2449,13 +2451,9 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
 extern void normalize_rt_tasks(void);
 
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
 
 extern struct task_group init_task_group;
-#ifdef CONFIG_USER_SCHED
-extern struct task_group root_task_group;
-extern void set_tg_uid(struct user_struct *user);
-#endif
 
 extern struct task_group *sched_create_group(struct task_group *parent);
 extern void sched_destroy_group(struct task_group *tg);
@@ -2540,7 +2538,27 @@ static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
 }
 #endif /* CONFIG_MM_OWNER */
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtZX"
+static inline unsigned long task_rlimit(const struct task_struct *tsk,
+		unsigned int limit)
+{
+	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur);
+}
+
+static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
+		unsigned int limit)
+{
+	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max);
+}
+
+static inline unsigned long rlimit(unsigned int limit)
+{
+	return task_rlimit(current, limit);
+}
+
+static inline unsigned long rlimit_max(unsigned int limit)
+{
+	return task_rlimit_max(current, limit);
+}
 
 #endif /* __KERNEL__ */