1 files changed, 247 insertions, 79 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 693f0e6c54d4..313c6b6e774f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -26,6 +26,7 @@
 #define CLONE_STOPPED		0x02000000	/* Start in stopped state */
 #define CLONE_NEWUTS		0x04000000	/* New utsname group? */
 #define CLONE_NEWIPC		0x08000000	/* New ipcs */
+#define CLONE_NEWUSER		0x10000000	/* New user namespace */
 
 /*
  * Scheduling policies
@@ -34,6 +35,8 @@
 #define SCHED_FIFO		1
 #define SCHED_RR		2
 #define SCHED_BATCH		3
+/* SCHED_ISO: reserved but not implemented yet */
+#define SCHED_IDLE		5
 
 #ifdef __KERNEL__
 
@@ -110,7 +113,7 @@ extern unsigned long avenrun[];		/* Load averages */
 
 #define FSHIFT		11		/* nr of bits of precision */
 #define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
-#define LOAD_FREQ	(5*HZ)		/* 5 sec intervals */
+#define LOAD_FREQ	(5*HZ+1)	/* 5 sec intervals */
 #define EXP_1		1884		/* 1/exp(5sec/1min) as fixed-point */
 #define EXP_5		2014		/* 1/exp(5sec/5min) */
 #define EXP_15		2037		/* 1/exp(5sec/15min) */
@@ -130,6 +133,26 @@ extern unsigned long nr_active(void);
 extern unsigned long nr_iowait(void);
 extern unsigned long weighted_cpuload(const int cpu);
 
+struct seq_file;
+struct cfs_rq;
+#ifdef CONFIG_SCHED_DEBUG
+extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
+extern void proc_sched_set_task(struct task_struct *p);
+extern void
+print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+#else
+static inline void
+proc_sched_show_task(struct task_struct *p, struct seq_file *m)
+{
+}
+static inline void proc_sched_set_task(struct task_struct *p)
+{
+}
+static inline void
+print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
+{
+}
+#endif
 
 /*
  * Task state bitmask. NOTE! These bits are also
@@ -193,6 +216,7 @@ struct task_struct;
 extern void sched_init(void);
 extern void sched_init_smp(void);
 extern void init_idle(struct task_struct *idle, int cpu);
+extern void init_idle_bootup_task(struct task_struct *idle);
 
 extern cpumask_t nohz_cpu_mask;
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
@@ -264,6 +288,7 @@ extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void schedule(void);
 
 struct nsproxy;
+struct user_namespace;
 
 /* Maximum number of active map areas.. This is a random (large) number */
 #define DEFAULT_MAX_MAP_COUNT	65536
@@ -320,6 +345,27 @@ typedef unsigned long mm_counter_t;
 		(mm)->hiwater_vm = (mm)->total_vm;	\
 } while (0)
 
+extern void set_dumpable(struct mm_struct *mm, int value);
+extern int get_dumpable(struct mm_struct *mm);
+
+/* mm flags */
+/* dumpable bits */
+#define MMF_DUMPABLE      0  /* core dump is permitted */
+#define MMF_DUMP_SECURELY 1  /* core file is readable only by root */
+#define MMF_DUMPABLE_BITS 2
+
+/* coredump filter bits */
+#define MMF_DUMP_ANON_PRIVATE	2
+#define MMF_DUMP_ANON_SHARED	3
+#define MMF_DUMP_MAPPED_PRIVATE	4
+#define MMF_DUMP_MAPPED_SHARED	5
+#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
+#define MMF_DUMP_FILTER_BITS	4
+#define MMF_DUMP_FILTER_MASK \
+	(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
+#define MMF_DUMP_FILTER_DEFAULT \
+	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED))
+
 struct mm_struct {
 	struct vm_area_struct * mmap;		/* list of VMAs */
 	struct rb_root mm_rb;
@@ -377,7 +423,7 @@ struct mm_struct {
 	unsigned int token_priority;
 	unsigned int last_interval;
 
-	unsigned char dumpable:2;
+	unsigned long flags; /* Must use atomic bitops to access the bits */
 
 	/* coredumping support */
 	int core_waiters;
@@ -392,7 +438,7 @@ struct sighand_struct {
 	atomic_t		count;
 	struct k_sigaction	action[_NSIG];
 	spinlock_t		siglock;
-	struct list_head        signalfd_list;
+	wait_queue_head_t	signalfd_wqh;
 };
 
 struct pacct_struct {
@@ -479,7 +525,7 @@ struct signal_struct {
 	 * from jiffies_to_ns(utime + stime) if sched_clock uses something
 	 * other than jiffies.)
 	 */
-	unsigned long long sched_time;
+	unsigned long long sum_sched_runtime;
 
 	/*
 	 * We don't bother to synchronize most readers of this at all,
@@ -506,6 +552,10 @@ struct signal_struct {
 #ifdef CONFIG_TASKSTATS
 	struct taskstats *stats;
 #endif
+#ifdef CONFIG_AUDIT
+	unsigned audit_tty;
+	struct tty_audit_buf *tty_audit_buf;
+#endif
 };
 
 /* Context switch must be unlocked if interrupts are to be enabled */
@@ -521,31 +571,6 @@ struct signal_struct {
 #define SIGNAL_STOP_CONTINUED	0x00000004 /* SIGCONT since WCONTINUED reap */
 #define SIGNAL_GROUP_EXIT	0x00000008 /* group exit in progress */
 
-
-/*
- * Priority of a process goes from 0..MAX_PRIO-1, valid RT
- * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
- * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
- * values are inverted: lower p->prio value means higher priority.
- *
- * The MAX_USER_RT_PRIO value allows the actual maximum
- * RT priority to be separate from the value exported to
- * user-space.  This allows kernel threads to set their
- * priority to a value higher than any user task. Note:
- * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
- */
-
-#define MAX_USER_RT_PRIO	100
-#define MAX_RT_PRIO		MAX_USER_RT_PRIO
-
-#define MAX_PRIO		(MAX_RT_PRIO + 40)
-
-#define rt_prio(prio)		unlikely((prio) < MAX_RT_PRIO)
-#define rt_task(p)		rt_prio((p)->prio)
-#define batch_task(p)		(unlikely((p)->policy == SCHED_BATCH))
-#define is_rt_policy(p)		((p) != SCHED_NORMAL && (p) != SCHED_BATCH)
-#define has_rt_policy(p)	unlikely(is_rt_policy((p)->policy))
-
 /*
  * Some day this will be a full-fledged user tracking system..
  */
@@ -568,7 +593,7 @@ struct user_struct {
 #endif
 
 	/* Hash table maintenance information */
-	struct list_head uidhash_list;
+	struct hlist_node uidhash_node;
 	uid_t uid;
 };
 
@@ -583,13 +608,13 @@ struct reclaim_state;
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 struct sched_info {
 	/* cumulative counters */
-	unsigned long	cpu_time,	/* time spent on the cpu */
-			run_delay,	/* time spent waiting on a runqueue */
-			pcnt;		/* # of timeslices run on this cpu */
+	unsigned long pcnt;	      /* # of times run on this cpu */
+	unsigned long long cpu_time,  /* time spent on the cpu */
+			   run_delay; /* time spent waiting on a runqueue */
 
 	/* timestamps */
-	unsigned long	last_arrival,	/* when we last ran on a cpu */
-			last_queued;	/* when we were last queued to run */
+	unsigned long long last_arrival,/* when we last ran on a cpu */
+			   last_queued;	/* when we were last queued to run */
 };
 #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
 
@@ -639,18 +664,24 @@ static inline int sched_info_on(void)
 #endif
 }
 
-enum idle_type
-{
-	SCHED_IDLE,
-	NOT_IDLE,
-	NEWLY_IDLE,
-	MAX_IDLE_TYPES
+enum cpu_idle_type {
+	CPU_IDLE,
+	CPU_NOT_IDLE,
+	CPU_NEWLY_IDLE,
+	CPU_MAX_IDLE_TYPES
 };
 
 /*
  * sched-domains (multiprocessor balancing) declarations:
  */
-#define SCHED_LOAD_SCALE	128UL	/* increase resolution of load */
+
+/*
+ * Increase resolution of nice-level calculations:
+ */
+#define SCHED_LOAD_SHIFT	10
+#define SCHED_LOAD_SCALE	(1L << SCHED_LOAD_SHIFT)
+
+#define SCHED_LOAD_SCALE_FUZZ	SCHED_LOAD_SCALE
 
 #ifdef CONFIG_SMP
 #define SD_LOAD_BALANCE		1	/* Do load balancing on this domain. */
@@ -703,7 +734,6 @@ struct sched_domain {
 	unsigned long max_interval;	/* Maximum balance interval ms */
 	unsigned int busy_factor;	/* less balancing by factor if busy */
 	unsigned int imbalance_pct;	/* No balance until over watermark */
-	unsigned long long cache_hot_time; /* Task considered cache hot (ns) */
 	unsigned int cache_nice_tries;	/* Leave cache hot tasks for # tries */
 	unsigned int busy_idx;
 	unsigned int idle_idx;
@@ -719,14 +749,14 @@ struct sched_domain {
 
 #ifdef CONFIG_SCHEDSTATS
 	/* load_balance() stats */
-	unsigned long lb_cnt[MAX_IDLE_TYPES];
-	unsigned long lb_failed[MAX_IDLE_TYPES];
-	unsigned long lb_balanced[MAX_IDLE_TYPES];
-	unsigned long lb_imbalance[MAX_IDLE_TYPES];
-	unsigned long lb_gained[MAX_IDLE_TYPES];
-	unsigned long lb_hot_gained[MAX_IDLE_TYPES];
-	unsigned long lb_nobusyg[MAX_IDLE_TYPES];
-	unsigned long lb_nobusyq[MAX_IDLE_TYPES];
+	unsigned long lb_cnt[CPU_MAX_IDLE_TYPES];
+	unsigned long lb_failed[CPU_MAX_IDLE_TYPES];
+	unsigned long lb_balanced[CPU_MAX_IDLE_TYPES];
+	unsigned long lb_imbalance[CPU_MAX_IDLE_TYPES];
+	unsigned long lb_gained[CPU_MAX_IDLE_TYPES];
+	unsigned long lb_hot_gained[CPU_MAX_IDLE_TYPES];
+	unsigned long lb_nobusyg[CPU_MAX_IDLE_TYPES];
+	unsigned long lb_nobusyq[CPU_MAX_IDLE_TYPES];
 
 	/* Active load balancing */
 	unsigned long alb_cnt;
@@ -753,14 +783,24 @@ struct sched_domain {
 extern int partition_sched_domains(cpumask_t *partition1,
 				    cpumask_t *partition2);
 
+#endif	/* CONFIG_SMP */
+
 /*
- * Maximum cache size the migration-costs auto-tuning code will
- * search from:
+ * A runqueue laden with a single nice 0 task scores a weighted_cpuload of
+ * SCHED_LOAD_SCALE. This function returns 1 if any cpu is laden with a
+ * task of nice 0 or enough lower priority tasks to bring up the
+ * weighted_cpuload
  */
-extern unsigned int max_cache_size;
-
-#endif	/* CONFIG_SMP */
+static inline int above_background_load(void)
+{
+	unsigned long cpu;
 
+	for_each_online_cpu(cpu) {
+		if (weighted_cpuload(cpu) >= SCHED_LOAD_SCALE)
+			return 1;
+	}
+	return 0;
+}
 
 struct io_context;			/* See blkdev.h */
 struct cpuset;
@@ -809,14 +849,90 @@ struct mempolicy;
 struct pipe_inode_info;
 struct uts_namespace;
 
-enum sleep_type {
-	SLEEP_NORMAL,
-	SLEEP_NONINTERACTIVE,
-	SLEEP_INTERACTIVE,
-	SLEEP_INTERRUPTED,
+struct rq;
+struct sched_domain;
+
+struct sched_class {
+	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 (*yield_task) (struct rq *rq, struct task_struct *p);
+
+	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p);
+
+	struct task_struct * (*pick_next_task) (struct rq *rq);
+	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
+
+	unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
+			struct rq *busiest,
+			unsigned long max_nr_move, unsigned long max_load_move,
+			struct sched_domain *sd, enum cpu_idle_type idle,
+			int *all_pinned, int *this_best_prio);
+
+	void (*set_curr_task) (struct rq *rq);
+	void (*task_tick) (struct rq *rq, struct task_struct *p);
+	void (*task_new) (struct rq *rq, struct task_struct *p);
 };
 
-struct prio_array;
+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
+ *     4 se->sleep_start_fair
+ *     6 se->load.weight
+ *     7 se->delta_fair
+ *    15 se->wait_runtime
+ */
+struct sched_entity {
+	long			wait_runtime;
+	unsigned long		delta_fair_run;
+	unsigned long		delta_fair_sleep;
+	unsigned long		delta_exec;
+	s64			fair_key;
+	struct load_weight	load;		/* for load-balancing */
+	struct rb_node		run_node;
+	unsigned int		on_rq;
+
+	u64			exec_start;
+	u64			sum_exec_runtime;
+	u64			prev_sum_exec_runtime;
+	u64			wait_start_fair;
+	u64			sleep_start_fair;
+
+#ifdef CONFIG_SCHEDSTATS
+	u64			wait_start;
+	u64			wait_max;
+	s64			sum_wait_runtime;
+
+	u64			sleep_start;
+	u64			sleep_max;
+	s64			sum_sleep_runtime;
+
+	u64			block_start;
+	u64			block_max;
+	u64			exec_max;
+
+	unsigned long		wait_runtime_overruns;
+	unsigned long		wait_runtime_underruns;
+#endif
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	struct sched_entity	*parent;
+	/* rq on which this entity is (to be) queued: */
+	struct cfs_rq		*cfs_rq;
+	/* rq "owned" by this entity/group: */
+	struct cfs_rq		*my_q;
+#endif
+};
 
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
@@ -832,23 +948,25 @@ struct task_struct {
 	int oncpu;
 #endif
 #endif
-	int load_weight;	/* for niceness load balancing purposes */
+
 	int prio, static_prio, normal_prio;
 	struct list_head run_list;
-	struct prio_array *array;
+	struct sched_class *sched_class;
+	struct sched_entity se;
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+	/* list of struct preempt_notifier: */
+	struct hlist_head preempt_notifiers;
+#endif
 
 	unsigned short ioprio;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	unsigned int btrace_seq;
 #endif
-	unsigned long sleep_avg;
-	unsigned long long timestamp, last_ran;
-	unsigned long long sched_time; /* sched_clock time spent running */
-	enum sleep_type sleep_type;
 
 	unsigned int policy;
 	cpumask_t cpus_allowed;
-	unsigned int time_slice, first_time_slice;
+	unsigned int time_slice;
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	struct sched_info sched_info;
@@ -905,7 +1023,8 @@ struct task_struct {
 	unsigned int rt_priority;
 	cputime_t utime, stime;
 	unsigned long nvcsw, nivcsw; /* context switch counts */
-	struct timespec start_time;
+	struct timespec start_time; 		/* monotonic time */
+	struct timespec real_start_time;	/* boot based time */
 /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
 	unsigned long min_flt, maj_flt;
 
@@ -1078,6 +1197,37 @@ struct task_struct {
 #endif
 };
 
+/*
+ * Priority of a process goes from 0..MAX_PRIO-1, valid RT
+ * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
+ * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
+ * values are inverted: lower p->prio value means higher priority.
+ *
+ * The MAX_USER_RT_PRIO value allows the actual maximum
+ * RT priority to be separate from the value exported to
+ * user-space.  This allows kernel threads to set their
+ * priority to a value higher than any user task. Note:
+ * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
+ */
+
+#define MAX_USER_RT_PRIO	100
+#define MAX_RT_PRIO		MAX_USER_RT_PRIO
+
+#define MAX_PRIO		(MAX_RT_PRIO + 40)
+#define DEFAULT_PRIO		(MAX_RT_PRIO + 20)
+
+static inline int rt_prio(int prio)
+{
+	if (unlikely(prio < MAX_RT_PRIO))
+		return 1;
+	return 0;
+}
+
+static inline int rt_task(struct task_struct *p)
+{
+	return rt_prio(p->prio);
+}
+
 static inline pid_t process_group(struct task_struct *tsk)
 {
 	return tsk->signal->pgrp;
@@ -1222,8 +1372,15 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
 #endif
 
 extern unsigned long long sched_clock(void);
+
+/*
+ * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
+ * clock constructed from sched_clock():
+ */
+extern unsigned long long cpu_clock(int cpu);
+
 extern unsigned long long
-current_sched_time(const struct task_struct *current_task);
+task_sched_runtime(struct task_struct *task);
 
 /* sched_exec is called by processes performing an exec */
 #ifdef CONFIG_SMP
@@ -1232,6 +1389,9 @@ extern void sched_exec(void);
 #define sched_exec()   {}
 #endif
 
+extern void sched_clock_idle_sleep_event(void);
+extern void sched_clock_idle_wakeup_event(u64 delta_ns);
+
 #ifdef CONFIG_HOTPLUG_CPU
 extern void idle_task_exit(void);
 #else
@@ -1240,6 +1400,16 @@ static inline void idle_task_exit(void) {}
 
 extern void sched_idle_next(void);
 
+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_batch_wakeup_granularity;
+extern unsigned int sysctl_sched_stat_granularity;
+extern unsigned int sysctl_sched_runtime_limit;
+extern unsigned int sysctl_sched_compat_yield;
+extern unsigned int sysctl_sched_child_runs_first;
+extern unsigned int sysctl_sched_features;
+
 #ifdef CONFIG_RT_MUTEXES
 extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);
@@ -1295,7 +1465,7 @@ extern struct task_struct *find_task_by_pid_type(int type, int pid);
 extern void __set_special_pids(pid_t session, pid_t pgrp);
 
 /* per-UID process charging. */
-extern struct user_struct * alloc_uid(uid_t);
+extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
 static inline struct user_struct *get_uid(struct user_struct *u)
 {
 	atomic_inc(&u->__count);
@@ -1303,6 +1473,7 @@ static inline struct user_struct *get_uid(struct user_struct *u)
 }
 extern void free_uid(struct user_struct *);
 extern void switch_uid(struct user_struct *);
+extern void release_uids(struct user_namespace *ns);
 
 #include <asm/current.h>
 
@@ -1317,8 +1488,8 @@ extern void FASTCALL(wake_up_new_task(struct task_struct * tsk,
 #else
  static inline void kick_process(struct task_struct *tsk) { }
 #endif
-extern void FASTCALL(sched_fork(struct task_struct * p, int clone_flags));
-extern void FASTCALL(sched_exit(struct task_struct * p));
+extern void sched_fork(struct task_struct *p, int clone_flags);
+extern void sched_dead(struct task_struct *p);
 
 extern int in_group_p(gid_t);
 extern int in_egroup_p(gid_t);
@@ -1406,7 +1577,7 @@ extern struct mm_struct * mm_alloc(void);
 extern void FASTCALL(__mmdrop(struct mm_struct *));
 static inline void mmdrop(struct mm_struct * mm)
 {
-	if (atomic_dec_and_test(&mm->mm_count))
+	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
 		__mmdrop(mm);
 }
 
@@ -1638,10 +1809,7 @@ static inline unsigned int task_cpu(const struct task_struct *p)
 	return task_thread_info(p)->cpu;
 }
 
-static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
-{
-	task_thread_info(p)->cpu = cpu;
-}
+extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
 
 #else