1 files changed, 78 insertions, 150 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d2112477ff5e..d35d2b6ddbfb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -51,6 +51,7 @@ struct sched_param {
 #include <linux/cred.h>
 #include <linux/llist.h>
 #include <linux/uidgid.h>
+#include <linux/gfp.h>
 
 #include <asm/processor.h>
 
@@ -98,7 +99,6 @@ extern int nr_threads;
 DECLARE_PER_CPU(unsigned long, process_counts);
 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(int cpu);
 extern unsigned long this_cpu_load(void);
@@ -304,19 +304,6 @@ static inline void lockup_detector_init(void)
 }
 #endif
 
-#ifdef CONFIG_DETECT_HUNG_TASK
-extern unsigned int  sysctl_hung_task_panic;
-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,
-					 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. */
 #define __sched		__attribute__((__section__(".sched.text")))
 
@@ -338,23 +325,6 @@ extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
 struct nsproxy;
 struct user_namespace;
 
-/*
- * Default maximum number of active map areas, this limits the number of vmas
- * per mm struct. Users can overwrite this number by sysctl but there is a
- * problem.
- *
- * When a program's coredump is generated as ELF format, a section is created
- * per a vma. In ELF, the number of sections is represented in unsigned short.
- * This means the number of sections should be smaller than 65535 at coredump.
- * Because the kernel adds some informative sections to a image of program at
- * generating coredump, we need some margin. The number of extra sections is
- * 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	(USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
-
-extern int sysctl_max_map_count;
-
 #include <linux/aio.h>
 
 #ifdef CONFIG_MMU
@@ -376,11 +346,6 @@ static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
 extern void set_dumpable(struct mm_struct *mm, int value);
 extern int get_dumpable(struct mm_struct *mm);
 
-/* get/set_dumpable() values */
-#define SUID_DUMPABLE_DISABLED	0
-#define SUID_DUMPABLE_ENABLED	1
-#define SUID_DUMPABLE_SAFE	2
-
 /* mm flags */
 /* dumpable bits */
 #define MMF_DUMPABLE      0  /* core dump is permitted */
@@ -1194,6 +1159,7 @@ struct sched_entity {
 	/* rq "owned" by this entity/group: */
 	struct cfs_rq		*my_q;
 #endif
+
 /*
  * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
  * removed when useful for applications beyond shares distribution (e.g.
@@ -1208,6 +1174,7 @@ struct sched_entity {
 struct sched_rt_entity {
 	struct list_head run_list;
 	unsigned long timeout;
+	unsigned long watchdog_stamp;
 	unsigned int time_slice;
 
 	struct sched_rt_entity *back;
@@ -1220,11 +1187,6 @@ struct sched_rt_entity {
 #endif
 };
 
-/*
- * default timeslice is 100 msecs (used only for SCHED_RR tasks).
- * Timeslices get refilled after they expire.
- */
-#define RR_TIMESLICE		(100 * HZ / 1000)
 
 struct rcu_node;
 
@@ -1368,6 +1330,15 @@ struct task_struct {
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	struct cputime prev_cputime;
 #endif
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+	seqlock_t vtime_seqlock;
+	unsigned long long vtime_snap;
+	enum {
+		VTIME_SLEEPING = 0,
+		VTIME_USER,
+		VTIME_SYS,
+	} vtime_snap_whence;
+#endif
 	unsigned long nvcsw, nivcsw; /* context switch counts */
 	struct timespec start_time; 		/* monotonic time */
 	struct timespec real_start_time;	/* boot based time */
@@ -1622,37 +1593,6 @@ static inline void set_numabalancing_state(bool enabled)
 }
 #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 struct pid *task_pid(struct task_struct *task)
 {
 	return task->pids[PIDTYPE_PID].pid;
@@ -1792,6 +1732,37 @@ static inline void put_task_struct(struct task_struct *t)
 		__put_task_struct(t);
 }
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+extern void task_cputime(struct task_struct *t,
+			 cputime_t *utime, cputime_t *stime);
+extern void task_cputime_scaled(struct task_struct *t,
+				cputime_t *utimescaled, cputime_t *stimescaled);
+extern cputime_t task_gtime(struct task_struct *t);
+#else
+static inline void task_cputime(struct task_struct *t,
+				cputime_t *utime, cputime_t *stime)
+{
+	if (utime)
+		*utime = t->utime;
+	if (stime)
+		*stime = t->stime;
+}
+
+static inline void task_cputime_scaled(struct task_struct *t,
+				       cputime_t *utimescaled,
+				       cputime_t *stimescaled)
+{
+	if (utimescaled)
+		*utimescaled = t->utimescaled;
+	if (stimescaled)
+		*stimescaled = t->stimescaled;
+}
+
+static inline cputime_t task_gtime(struct task_struct *t)
+{
+	return t->gtime;
+}
+#endif
 extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
 extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
 
@@ -1815,6 +1786,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #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_MEMALLOC_NOIO 0x00080000	/* Allocating memory without IO involved */
 #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 */
@@ -1852,6 +1824,26 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */
+static inline gfp_t memalloc_noio_flags(gfp_t flags)
+{
+	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
+		flags &= ~__GFP_IO;
+	return flags;
+}
+
+static inline unsigned int memalloc_noio_save(void)
+{
+	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
+	current->flags |= PF_MEMALLOC_NOIO;
+	return flags;
+}
+
+static inline void memalloc_noio_restore(unsigned int flags)
+{
+	current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
+}
+
 /*
  * task->jobctl flags
  */
@@ -2033,58 +2025,7 @@ extern void wake_up_idle_cpu(int cpu);
 static inline void wake_up_idle_cpu(int cpu) { }
 #endif
 
-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_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;
-
-extern unsigned int sysctl_numa_balancing_scan_delay;
-extern unsigned int sysctl_numa_balancing_scan_period_min;
-extern unsigned int sysctl_numa_balancing_scan_period_max;
-extern unsigned int sysctl_numa_balancing_scan_period_reset;
-extern unsigned int sysctl_numa_balancing_scan_size;
-extern unsigned int sysctl_numa_balancing_settle_count;
-
-#ifdef CONFIG_SCHED_DEBUG
-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,
-		loff_t *ppos);
-#endif
-#ifdef CONFIG_SCHED_DEBUG
-static inline unsigned int get_sysctl_timer_migration(void)
-{
-	return sysctl_timer_migration;
-}
-#else
-static inline unsigned int get_sysctl_timer_migration(void)
-{
-	return 1;
-}
-#endif
-extern unsigned int sysctl_sched_rt_period;
-extern int sysctl_sched_rt_runtime;
-
-int sched_rt_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos);
-
 #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);
@@ -2100,30 +2041,6 @@ static inline void sched_autogroup_fork(struct signal_struct *sig) { }
 static inline void sched_autogroup_exit(struct signal_struct *sig) { }
 #endif
 
-#ifdef CONFIG_CFS_BANDWIDTH
-extern unsigned int sysctl_sched_cfs_bandwidth_slice;
-#endif
-
-#ifdef CONFIG_RT_MUTEXES
-extern int rt_mutex_getprio(struct task_struct *p);
-extern void rt_mutex_setprio(struct task_struct *p, int prio);
-extern void rt_mutex_adjust_pi(struct task_struct *p);
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
-	return tsk->pi_blocked_on != NULL;
-}
-#else
-static inline int rt_mutex_getprio(struct task_struct *p)
-{
-	return p->normal_prio;
-}
-# define rt_mutex_adjust_pi(p)		do { } while (0)
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
-	return false;
-}
-#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);
@@ -2259,7 +2176,6 @@ extern struct sigqueue *sigqueue_alloc(void);
 extern void sigqueue_free(struct sigqueue *);
 extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
 extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
-extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);
 
 static inline void restore_saved_sigmask(void)
 {
@@ -2305,6 +2221,17 @@ static inline int sas_ss_flags(unsigned long sp)
 		: on_sig_stack(sp) ? SS_ONSTACK : 0);
 }
 
+static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig)
+{
+	if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp))
+#ifdef CONFIG_STACK_GROWSUP
+		return current->sas_ss_sp;
+#else
+		return current->sas_ss_sp + current->sas_ss_size;
+#endif
+	return sp;
+}
+
 /*
  * Routines for handling mm_structs
  */
@@ -2753,14 +2680,15 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
 extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
-extern void normalize_rt_tasks(void);
-
 #ifdef CONFIG_CGROUP_SCHED
 
 extern struct task_group root_task_group;
 
 extern struct task_group *sched_create_group(struct task_group *parent);
+extern void sched_online_group(struct task_group *tg,
+			       struct task_group *parent);
 extern void sched_destroy_group(struct task_group *tg);
+extern void sched_offline_group(struct task_group *tg);
 extern void sched_move_task(struct task_struct *tsk);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);