1 files changed, 67 insertions, 133 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index abdfacc5865..f118809c953 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;
 
 /*
@@ -258,6 +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);
@@ -265,17 +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
 
 /*
@@ -310,6 +318,7 @@ 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 +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)
 {
 }
@@ -371,7 +383,7 @@ 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;
 
@@ -392,60 +404,6 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 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);
@@ -568,8 +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() */
 
@@ -736,14 +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
@@ -874,7 +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)
@@ -1005,6 +959,7 @@ struct sched_domain {
 	char *name;
 #endif
 
+	unsigned int span_weight;
 	/*
 	 * Span of all CPUs in this domain.
 	 *
@@ -1077,11 +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);
@@ -1090,16 +1051,9 @@ 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);
-
-	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  (*select_task_rq)(struct rq *rq, struct task_struct *p,
+			       int sd_flag, int flags);
 
-	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_waking) (struct rq *this_rq, struct task_struct *task);
@@ -1135,36 +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;
-
 #ifdef CONFIG_SCHEDSTATS
+struct sched_statistics {
 	u64			wait_start;
 	u64			wait_max;
 	u64			wait_count;
@@ -1196,6 +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
@@ -1282,7 +1226,9 @@ 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;
@@ -1328,12 +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;
@@ -1462,7 +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;
@@ -1481,7 +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 */
@@ -1533,7 +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;
@@ -1553,7 +1495,6 @@ 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 */
@@ -1903,6 +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) {}
@@ -2094,7 +2036,7 @@ 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 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);
@@ -2159,7 +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 *);
@@ -2179,10 +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)
 {
@@ -2208,6 +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)
 
@@ -2451,13 +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)
-{
 }
 
 /*
@@ -2513,13 +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);