1 files changed, 110 insertions, 123 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 724814191fe9..225347d97d47 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -100,7 +100,7 @@ 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;
@@ -148,7 +148,6 @@ 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);
 
@@ -174,8 +173,6 @@ 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().
@@ -198,6 +195,12 @@ 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)
@@ -258,6 +261,10 @@ 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);
@@ -310,6 +317,7 @@ 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,
                                     void __user *buffer,
@@ -323,6 +331,9 @@ 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)
 {
 }
@@ -352,7 +363,6 @@ 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);
 
@@ -378,6 +388,8 @@ 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);
@@ -387,61 +399,10 @@ 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 void setmax_mm_hiwater_rss(unsigned long *maxrss,
-                                         struct mm_struct *mm)
-{
-        unsigned long hiwater_rss = get_mm_hiwater_rss(mm);
-
-        if (*maxrss < hiwater_rss)
-                *maxrss = hiwater_rss;
-}
-
-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);
@@ -631,6 +592,9 @@ 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;
@@ -729,14 +693,6 @@ 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
@@ -867,7 +823,10 @@ 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)
@@ -1016,9 +975,13 @@ 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)
 {
@@ -1036,7 +999,7 @@ 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)
 {
 }
@@ -1069,7 +1032,8 @@ struct sched_domain;
 struct sched_class {
         const struct sched_class *next;
 
-        void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
+        void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup,
+                              bool head);
         void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
         void (*yield_task) (struct rq *rq);
 
@@ -1081,17 +1045,10 @@ struct sched_class {
 #ifdef CONFIG_SMP
         int  (*select_task_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);
@@ -1102,7 +1059,7 @@ 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);
@@ -1111,10 +1068,11 @@ 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
 };
 
@@ -1151,8 +1109,6 @@ struct sched_entity {
         u64                     start_runtime;
         u64                     avg_wakeup;
 
-        u64                     avg_running;
-
 #ifdef CONFIG_SCHEDSTATS
         u64                     wait_start;
         u64                     wait_max;
@@ -1175,7 +1131,6 @@ 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;
@@ -1273,7 +1228,9 @@ 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 */
         int exit_state;
         int exit_code, exit_signal;
@@ -1335,7 +1292,9 @@ 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 */
@@ -1358,7 +1317,7 @@ 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
@@ -1410,7 +1369,7 @@ 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 */
@@ -1425,17 +1384,17 @@ 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
@@ -1451,7 +1410,7 @@ 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;
@@ -1529,7 +1488,7 @@ 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;
@@ -1549,11 +1508,18 @@ struct task_struct {
         /* bitmask of trace recursion */
         unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
-        unsigned long stack_start;
+#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
@@ -1731,9 +1697,8 @@ 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
@@ -1847,7 +1812,8 @@ 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);
@@ -1910,14 +1876,22 @@ 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,
+int sched_proc_update_handler(struct ctl_table *table, int write,
                 void __user *buffer, size_t *length,
                 loff_t *ppos);
 #endif
@@ -2073,7 +2047,6 @@ 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 struct sigqueue *sigqueue_alloc(void);
@@ -2092,16 +2065,18 @@ 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)
@@ -2430,9 +2405,7 @@ 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)
@@ -2475,8 +2448,6 @@ 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,
@@ -2494,13 +2465,9 @@ 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);
@@ -2585,7 +2552,27 @@ 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__ */