1 files changed, 109 insertions, 35 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b4c38bc8049c..3ab08e4bb6b8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -77,6 +77,7 @@ struct sched_param {
 #include <linux/proportions.h>
 #include <linux/seccomp.h>
 #include <linux/rcupdate.h>
+#include <linux/rculist.h>
 #include <linux/rtmutex.h>
 
 #include <linux/time.h>
@@ -91,13 +92,13 @@ struct sched_param {
 
 #include <asm/processor.h>
 
-struct mem_cgroup;
 struct exec_domain;
 struct futex_pi_state;
 struct robust_list_head;
 struct bio;
-struct bts_tracer;
 struct fs_struct;
+struct bts_context;
+struct perf_counter_context;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -116,6 +117,7 @@ struct fs_struct;
  *    11 bit fractions.
  */
 extern unsigned long avenrun[];         /* Load averages */
+extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
 
 #define FSHIFT          11              /* nr of bits of precision */
 #define FIXED_1         (1<<FSHIFT)     /* 1.0 as fixed-point */
@@ -135,8 +137,9 @@ 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_active(void);
 extern unsigned long nr_iowait(void);
+extern void calc_global_load(void);
+extern u64 cpu_nr_migrations(int cpu);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -206,7 +209,7 @@ extern unsigned long long time_sync_thresh;
                         ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task)  \
                                 ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-                                 (task->flags & PF_FROZEN) == 0)
+                                 (task->flags & PF_FREEZING) == 0)
 
 #define __set_task_state(tsk, state_value)              \
         do { (tsk)->state = (state_value); } while (0)
@@ -257,6 +260,7 @@ 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);
 #else
 static inline int select_nohz_load_balancer(int cpu)
 {
@@ -345,8 +349,20 @@ extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
 struct nsproxy;
 struct user_namespace;
 
-/* Maximum number of active map areas.. This is a random (large) number */
-#define DEFAULT_MAX_MAP_COUNT   65536
+/*
+ * 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   (USHORT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
 
 extern int sysctl_max_map_count;
 
@@ -482,6 +498,15 @@ struct task_cputime {
                 .sum_exec_runtime = 0,                          \
         }
 
+/*
+ * Disable preemption until the scheduler is running.
+ * Reset by start_kernel()->sched_init()->init_idle().
+ *
+ * We include PREEMPT_ACTIVE to avoid cond_resched() from working
+ * before the scheduler is active -- see should_resched().
+ */
+#define INIT_PREEMPT_COUNT      (1 + PREEMPT_ACTIVE)
+
 /**
  * struct thread_group_cputimer - thread group interval timer counts
  * @cputime:            thread group interval timers.
@@ -669,8 +694,12 @@ struct user_struct {
         struct task_group *tg;
 #ifdef CONFIG_SYSFS
         struct kobject kobj;
-        struct work_struct work;
+        struct delayed_work work;
+#endif
 #endif
+
+#ifdef CONFIG_PERF_COUNTERS
+        atomic_long_t locked_vm;
 #endif
 };
 
@@ -838,7 +867,17 @@ struct sched_group {
          */
         u32 reciprocal_cpu_power;
 
-        unsigned long cpumask[];
+        /*
+         * The CPUs this group covers.
+         *
+         * NOTE: this field is variable length. (Allocated dynamically
+         * by attaching extra space to the end of the structure,
+         * depending on how many CPUs the kernel has booted up with)
+         *
+         * It is also be embedded into static data structures at build
+         * time. (See 'struct static_sched_group' in kernel/sched.c)
+         */
+        unsigned long cpumask[0];
 };
 
 static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
@@ -924,8 +963,17 @@ struct sched_domain {
         char *name;
 #endif
 
-        /* span of all CPUs in this domain */
-        unsigned long span[];
+        /*
+         * Span of all CPUs in this domain.
+         *
+         * NOTE: this field is variable length. (Allocated dynamically
+         * by attaching extra space to the end of the structure,
+         * depending on how many CPUs the kernel has booted up with)
+         *
+         * It is also be embedded into static data structures at build
+         * time. (See 'struct static_sched_domain' in kernel/sched.c)
+         */
+        unsigned long span[0];
 };
 
 static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
@@ -1052,9 +1100,10 @@ struct sched_entity {
         u64                     last_wakeup;
         u64                     avg_overlap;
 
+        u64                     nr_migrations;
+
         u64                     start_runtime;
         u64                     avg_wakeup;
-        u64                     nr_migrations;
 
 #ifdef CONFIG_SCHEDSTATS
         u64                     wait_start;
@@ -1149,7 +1198,6 @@ 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
@@ -1209,18 +1257,11 @@ struct task_struct {
         struct list_head ptraced;
         struct list_head ptrace_entry;
 
-#ifdef CONFIG_X86_PTRACE_BTS
         /*
          * This is the tracer handle for the ptrace BTS extension.
          * This field actually belongs to the ptracer task.
          */
-        struct bts_tracer *bts;
-        /*
-         * The buffer to hold the BTS data.
-         */
-        void *bts_buffer;
-        size_t bts_size;
-#endif /* CONFIG_X86_PTRACE_BTS */
+        struct bts_context *bts;
 
         /* PID/PID hash table linkage. */
         struct pid_link pids[PIDTYPE_MAX];
@@ -1247,7 +1288,9 @@ struct task_struct {
                                          * credentials (COW) */
         const struct cred *cred;        /* effective (overridable) subjective task
                                          * credentials (COW) */
-        struct mutex cred_exec_mutex;   /* execve vs ptrace cred calculation mutex */
+        struct mutex cred_guard_mutex;  /* guard against foreign influences on
+                                         * credential calculations
+                                         * (notably. ptrace) */
 
         char comm[TASK_COMM_LEN]; /* executable name excluding path
                                      - access with [gs]et_task_comm (which lock
@@ -1294,7 +1337,8 @@ struct task_struct {
 /* Thread group tracking */
         u32 parent_exec_id;
         u32 self_exec_id;
-/* Protection of (de-)allocation: mm, files, fs, tty, keyrings */
+/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
+ * mempolicy */
         spinlock_t alloc_lock;
 
 #ifdef CONFIG_GENERIC_HARDIRQS
@@ -1362,8 +1406,7 @@ struct task_struct {
         cputime_t acct_timexpd; /* stime + utime since last update */
 #endif
 #ifdef CONFIG_CPUSETS
-        nodemask_t mems_allowed;
-        int cpuset_mems_generation;
+        nodemask_t mems_allowed;        /* Protected by alloc_lock */
         int cpuset_mem_spread_rotor;
 #endif
 #ifdef CONFIG_CGROUPS
@@ -1380,8 +1423,13 @@ struct task_struct {
         struct list_head pi_state_list;
         struct futex_pi_state *pi_state_cache;
 #endif
+#ifdef CONFIG_PERF_COUNTERS
+        struct perf_counter_context *perf_counter_ctxp;
+        struct mutex perf_counter_mutex;
+        struct list_head perf_counter_list;
+#endif
 #ifdef CONFIG_NUMA
-        struct mempolicy *mempolicy;
+        struct mempolicy *mempolicy;    /* Protected by alloc_lock */
         short il_next;
 #endif
         atomic_t fs_excl;       /* holding fs exclusive resources */
@@ -1428,7 +1476,9 @@ struct task_struct {
 #ifdef CONFIG_TRACING
         /* state flags for use by tracers */
         unsigned long trace;
-#endif
+        /* bitmask of trace recursion */
+        unsigned long trace_recursion;
+#endif /* CONFIG_TRACING */
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
@@ -1630,6 +1680,7 @@ extern cputime_t task_gtime(struct task_struct *p);
 #define PF_MEMALLOC     0x00000800      /* Allocating memory */
 #define PF_FLUSHER      0x00001000      /* responsible for disk writeback */
 #define PF_USED_MATH    0x00002000      /* if unset the fpu must be initialized before use */
+#define PF_FREEZING     0x00004000      /* freeze in progress. do not account to load */
 #define PF_NOFREEZE     0x00008000      /* this thread should not be frozen */
 #define PF_FROZEN       0x00010000      /* frozen for system suspend */
 #define PF_FSTRANS      0x00020000      /* inside a filesystem transaction */
@@ -1766,11 +1817,23 @@ extern unsigned int sysctl_sched_child_runs_first;
 extern unsigned int sysctl_sched_features;
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
+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,
                 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;
 
@@ -1837,9 +1900,6 @@ extern struct pid_namespace init_pid_ns;
 /*
  * find a task by one of its numerical ids
  *
- * find_task_by_pid_type_ns():
- *      it is the most generic call - it finds a task by all id,
- *      type and namespace specified
  * find_task_by_pid_ns():
  *      finds a task by its pid in the specified namespace
  * find_task_by_vpid():
@@ -1848,9 +1908,6 @@ extern struct pid_namespace init_pid_ns;
  * see also find_vpid() etc in include/linux/pid.h
  */
 
-extern struct task_struct *find_task_by_pid_type_ns(int type, int pid,
-                struct pid_namespace *ns);
-
 extern struct task_struct *find_task_by_vpid(pid_t nr);
 extern struct task_struct *find_task_by_pid_ns(pid_t nr,
                 struct pid_namespace *ns);
@@ -1885,6 +1942,7 @@ extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);
 extern void flush_signals(struct task_struct *);
+extern void __flush_signals(struct task_struct *);
 extern void ignore_signals(struct task_struct *);
 extern void flush_signal_handlers(struct task_struct *, int force_default);
 extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
@@ -2001,8 +2059,10 @@ 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)
 {
@@ -2010,7 +2070,8 @@ static inline unsigned long wait_task_inactive(struct task_struct *p,
 }
 #endif
 
-#define next_task(p)    list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
+#define next_task(p) \
+        list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
 
 #define for_each_process(p) \
         for (p = &init_task ; (p = next_task(p)) != &init_task ; )
@@ -2049,8 +2110,8 @@ int same_thread_group(struct task_struct *p1, struct task_struct *p2)
 
 static inline struct task_struct *next_thread(const struct task_struct *p)
 {
-        return list_entry(rcu_dereference(p->thread_group.next),
-                          struct task_struct, thread_group);
+        return list_entry_rcu(p->thread_group.next,
+                              struct task_struct, thread_group);
 }
 
 static inline int thread_group_empty(struct task_struct *p)
@@ -2178,6 +2239,12 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
         return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
 }
 
+static inline int restart_syscall(void)
+{
+        set_tsk_thread_flag(current, TIF_SIGPENDING);
+        return -ERESTARTNOINTR;
+}
+
 static inline int signal_pending(struct task_struct *p)
 {
         return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
@@ -2388,6 +2455,13 @@ static inline void inc_syscw(struct task_struct *tsk)
 #define TASK_SIZE_OF(tsk)       TASK_SIZE
 #endif
 
+/*
+ * Call the function if the target task is executing on a CPU right now:
+ */
+extern void task_oncpu_function_call(struct task_struct *p,
+                                     void (*func) (void *info), void *info);
+
+
 #ifdef CONFIG_MM_OWNER
 extern void mm_update_next_owner(struct mm_struct *mm);
 extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);