#include <linux/completion.h>
#include <linux/pid.h>
#include <linux/percpu.h>
+#include <linux/topology.h>
struct exec_domain;
+extern int exec_shield;
+extern int exec_shield_randomize;
+extern int print_fatal_signals;
/*
* cloning flags:
extern int nr_threads;
extern int last_pid;
DECLARE_PER_CPU(unsigned long, process_counts);
+// DECLARE_PER_CPU(struct runqueue, runqueues); -- removed after ckrm cpu v7 merge
extern int nr_processes(void);
extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
#define TASK_UNINTERRUPTIBLE 2
#define TASK_STOPPED 4
#define TASK_TRACED 8
-#define TASK_ZOMBIE 16
-#define TASK_DEAD 32
+#define EXIT_ZOMBIE 16
+#define EXIT_DEAD 32
+#define TASK_ONHOLD 64
#define __set_task_state(tsk, state_value) \
do { (tsk)->state = (state_value); } while (0)
#ifdef __KERNEL__
+#include <linux/taskdelays.h>
#include <linux/spinlock.h>
/*
extern unsigned long
arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
unsigned long, unsigned long);
+
+extern unsigned long
+arch_get_unmapped_exec_area(struct file *, unsigned long, unsigned long,
+ unsigned long, unsigned long);
extern unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long (*get_unmapped_area) (struct file *filp,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags);
+ unsigned long (*get_unmapped_exec_area) (struct file *filp,
+ unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags);
void (*unmap_area) (struct vm_area_struct *area);
unsigned long mmap_base; /* base of mmap area */
unsigned long free_area_cache; /* first hole */
atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */
int map_count; /* number of VMAs */
struct rw_semaphore mmap_sem;
- spinlock_t page_table_lock; /* Protects task page tables and mm->rss */
+ spinlock_t page_table_lock; /* Protects page tables, mm->rss, mm->anon_rss */
- struct list_head mmlist; /* List of all active mm's. These are globally strung
+ struct list_head mmlist; /* List of maybe swapped mm's. These are globally strung
* together off init_mm.mmlist, and are protected
* by mmlist_lock
*/
unsigned long start_code, end_code, start_data, end_data;
unsigned long start_brk, brk, start_stack;
unsigned long arg_start, arg_end, env_start, env_end;
- unsigned long rss, total_vm, locked_vm, shared_vm;
- unsigned long exec_vm, stack_vm, reserved_vm, def_flags;
+ unsigned long rss, anon_rss, total_vm, locked_vm, shared_vm;
+ unsigned long exec_vm, stack_vm, reserved_vm, def_flags, nr_ptes;
unsigned long saved_auxv[42]; /* for /proc/PID/auxv */
- unsigned dumpable:1;
+ unsigned dumpable:2;
cpumask_t cpu_vm_mask;
/* Architecture-specific MM context */
mm_context_t context;
+ struct vx_info *mm_vx_info;
/* Token based thrashing protection. */
unsigned long swap_token_time;
struct kioctx *ioctx_list;
struct kioctx default_kioctx;
+#ifdef CONFIG_CKRM_RES_MEM
+ struct ckrm_mem_res *memclass;
+ struct list_head tasklist; /* list of all tasks sharing this address space */
+ spinlock_t peertask_lock; /* protect above tasklist */
+#endif
};
-extern int mmlist_nr;
-
struct sighand_struct {
atomic_t count;
struct k_sigaction action[_NSIG];
*/
struct signal_struct {
atomic_t count;
+ atomic_t live;
/* current thread group signal load-balancing target: */
task_t *curr_target;
unsigned long utime, stime, cutime, cstime;
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
+
+ /*
+ * We don't bother to synchronize most readers of this at all,
+ * because there is no reader checking a limit that actually needs
+ * to get both rlim_cur and rlim_max atomically, and either one
+ * alone is a single word that can safely be read normally.
+ * getrlimit/setrlimit use task_lock(current->group_leader) to
+ * protect this instead of the siglock, because they really
+ * have no need to disable irqs.
+ */
+ struct rlimit rlim[RLIM_NLIMITS];
};
/*
unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */
unsigned long locked_shm; /* How many pages of mlocked shm ? */
+#ifdef CONFIG_KEYS
+ struct key *uid_keyring; /* UID specific keyring */
+ struct key *session_keyring; /* UID's default session keyring */
+#endif
+
/* Hash table maintenance information */
struct list_head uidhash_list;
uid_t uid;
+ xid_t xid;
};
-extern struct user_struct *find_user(uid_t);
+extern struct user_struct *find_user(xid_t, uid_t);
extern struct user_struct root_user;
#define INIT_USER (&root_user)
struct backing_dev_info;
struct reclaim_state;
-/* POSIX.1b interval timer structure. */
-struct k_itimer {
- struct list_head list; /* free/ allocate list */
- spinlock_t it_lock;
- clockid_t it_clock; /* which timer type */
- timer_t it_id; /* timer id */
- int it_overrun; /* overrun on pending signal */
- int it_overrun_last; /* overrun on last delivered signal */
- int it_requeue_pending; /* waiting to requeue this timer */
- int it_sigev_notify; /* notify word of sigevent struct */
- int it_sigev_signo; /* signo word of sigevent struct */
- sigval_t it_sigev_value; /* value word of sigevent struct */
- unsigned long it_incr; /* interval specified in jiffies */
- struct task_struct *it_process; /* process to send signal to */
- struct timer_list it_timer;
- struct sigqueue *sigq; /* signal queue entry. */
- struct list_head abs_timer_entry; /* clock abs_timer_list */
- struct timespec wall_to_prev; /* wall_to_monotonic used when set */
-};
-
#ifdef CONFIG_SCHEDSTATS
struct sched_info {
/* cumulative counters */
extern struct file_operations proc_schedstat_operations;
#endif
+enum idle_type
+{
+ SCHED_IDLE,
+ NOT_IDLE,
+ NEWLY_IDLE,
+ MAX_IDLE_TYPES
+};
+
+/*
+ * sched-domains (multiprocessor balancing) declarations:
+ */
+#ifdef CONFIG_SMP
+#define SCHED_LOAD_SCALE 128UL /* increase resolution of load */
+
+#define SD_LOAD_BALANCE 1 /* Do load balancing on this domain. */
+#define SD_BALANCE_NEWIDLE 2 /* Balance when about to become idle */
+#define SD_BALANCE_EXEC 4 /* Balance on exec */
+#define SD_WAKE_IDLE 8 /* Wake to idle CPU on task wakeup */
+#define SD_WAKE_AFFINE 16 /* Wake task to waking CPU */
+#define SD_WAKE_BALANCE 32 /* Perform balancing at task wakeup */
+#define SD_SHARE_CPUPOWER 64 /* Domain members share cpu power */
+
+struct sched_group {
+ struct sched_group *next; /* Must be a circular list */
+ cpumask_t cpumask;
+
+ /*
+ * CPU power of this group, SCHED_LOAD_SCALE being max power for a
+ * single CPU. This is read only (except for setup, hotplug CPU).
+ */
+ unsigned long cpu_power;
+};
+
+struct sched_domain {
+ /* These fields must be setup */
+ struct sched_domain *parent; /* top domain must be null terminated */
+ struct sched_group *groups; /* the balancing groups of the domain */
+ cpumask_t span; /* span of all CPUs in this domain */
+ unsigned long min_interval; /* Minimum balance interval ms */
+ 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 per_cpu_gain; /* CPU % gained by adding domain cpus */
+ int flags; /* See SD_* */
+
+ /* Runtime fields. */
+ unsigned long last_balance; /* init to jiffies. units in jiffies */
+ unsigned int balance_interval; /* initialise to 1. units in ms. */
+ unsigned int nr_balance_failed; /* initialise to 0 */
+
+#ifdef CONFIG_SCHEDSTATS
+ /* load_balance() stats */
+ unsigned long lb_cnt[MAX_IDLE_TYPES];
+ unsigned long lb_failed[MAX_IDLE_TYPES];
+ unsigned long lb_imbalance[MAX_IDLE_TYPES];
+ unsigned long lb_nobusyg[MAX_IDLE_TYPES];
+ unsigned long lb_nobusyq[MAX_IDLE_TYPES];
+
+ /* sched_balance_exec() stats */
+ unsigned long sbe_attempts;
+ unsigned long sbe_pushed;
+
+ /* try_to_wake_up() stats */
+ unsigned long ttwu_wake_affine;
+ unsigned long ttwu_wake_balance;
+#endif
+};
+
+#ifdef ARCH_HAS_SCHED_DOMAIN
+/* Useful helpers that arch setup code may use. Defined in kernel/sched.c */
+extern cpumask_t cpu_isolated_map;
+extern void init_sched_build_groups(struct sched_group groups[],
+ cpumask_t span, int (*group_fn)(int cpu));
+extern void cpu_attach_domain(struct sched_domain *sd, int cpu);
+#endif /* ARCH_HAS_SCHED_DOMAIN */
+#endif /* CONFIG_SMP */
+
+
struct io_context; /* See blkdev.h */
void exit_io_context(void);
struct audit_context; /* See audit.c */
struct mempolicy;
+#ifdef CONFIG_CKRM_CPU_SCHEDULE
+/**
+ * ckrm_cpu_demand_stat - used to track the cpu demand of a task/class
+ * @run: how much time it has been running since the counter started
+ * @total: total time since the counter started
+ * @last_sleep: the last time it sleeps, last_sleep = 0 when not sleeping
+ * @recalc_interval: how often do we recalculate the cpu_demand
+ * @cpu_demand: moving average of run/total
+ */
+struct ckrm_cpu_demand_stat {
+ unsigned long long run;
+ unsigned long long total;
+ unsigned long long last_sleep;
+ unsigned long long recalc_interval;
+ unsigned long cpu_demand; /*estimated cpu demand */
+};
+#endif
+
+
struct task_struct {
volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
struct thread_info *thread_info;
/* task state */
struct linux_binfmt *binfmt;
+ long exit_state;
int exit_code, exit_signal;
int pdeath_signal; /* The signal sent when the parent dies */
/* ??? */
kernel_cap_t cap_effective, cap_inheritable, cap_permitted;
unsigned keep_capabilities:1;
struct user_struct *user;
-/* limits */
- struct rlimit rlim[RLIM_NLIMITS];
+#ifdef CONFIG_KEYS
+ struct key *session_keyring; /* keyring inherited over fork */
+ struct key *process_keyring; /* keyring private to this process (CLONE_THREAD) */
+ struct key *thread_keyring; /* keyring private to this thread */
+#endif
unsigned short used_math;
char comm[16];
/* file system info */
/* signal handlers */
struct signal_struct *signal;
struct sighand_struct *sighand;
-
sigset_t blocked, real_blocked;
struct sigpending pending;
int (*notifier)(void *priv);
void *notifier_data;
sigset_t *notifier_mask;
+
+ /* TUX state */
+ void *tux_info;
+ void (*tux_exit)(void);
+
void *security;
struct audit_context *audit_context;
+/* vserver context data */
+ xid_t xid;
+ struct vx_info *vx_info;
+
+/* vserver network data */
+ nid_t nid;
+ struct nx_info *nx_info;
+
/* Thread group tracking */
u32 parent_exec_id;
u32 self_exec_id;
-/* Protection of (de-)allocation: mm, files, fs, tty */
+/* Protection of (de-)allocation: mm, files, fs, tty, keyrings */
spinlock_t alloc_lock;
/* Protection of proc_dentry: nesting proc_lock, dcache_lock, write_lock_irq(&tasklist_lock); */
spinlock_t proc_lock;
struct io_context *io_context;
+ int ioprio;
+
unsigned long ptrace_message;
siginfo_t *last_siginfo; /* For ptrace use. */
/*
struct mempolicy *mempolicy;
short il_next; /* could be shared with used_math */
#endif
+
+#ifdef CONFIG_CKRM
+ spinlock_t ckrm_tsklock;
+ void *ce_data;
+#ifdef CONFIG_CKRM_TYPE_TASKCLASS
+ // .. Hubertus should change to CONFIG_CKRM_TYPE_TASKCLASS
+ struct ckrm_task_class *taskclass;
+ struct list_head taskclass_link;
+#ifdef CONFIG_CKRM_CPU_SCHEDULE
+ struct ckrm_cpu_class *cpu_class;
+ //track cpu demand of this task
+ struct ckrm_cpu_demand_stat demand_stat;
+#endif //CONFIG_CKRM_CPU_SCHEDULE
+#endif // CONFIG_CKRM_TYPE_TASKCLASS
+#ifdef CONFIG_CKRM_RES_MEM
+ struct list_head mm_peers; // list of tasks using same mm_struct
+#endif // CONFIG_CKRM_RES_MEM
+#endif // CONFIG_CKRM
+ struct task_delay_info delays;
};
static inline pid_t process_group(struct task_struct *tsk)
return tsk->signal->pgrp;
}
+/**
+ * pid_alive - check that a task structure is not stale
+ * @p: Task structure to be checked.
+ *
+ * Test if a process is not yet dead (at most zombie state)
+ * If pid_alive fails, then pointers within the task structure
+ * can be stale and must not be dereferenced.
+ */
+static inline int pid_alive(struct task_struct *p)
+{
+ return p->pids[PIDTYPE_PID].nr != 0;
+}
+
extern void free_task(struct task_struct *tsk);
extern void __put_task_struct(struct task_struct *tsk);
#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
#define PF_SWAPOFF 0x00080000 /* I am in swapoff */
#define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */
#define PF_SYNCWRITE 0x00200000 /* I am doing a sync write */
+#define PF_BORROWED_MM 0x00400000 /* I am a kthread doing use_mm */
+#define PF_RELOCEXEC 0x00800000 /* relocate shared libraries */
+#define PF_MEMIO 0x01000000 /* I am potentially doing I/O for mem */
+#define PF_IOWAIT 0x02000000 /* I am waiting on disk I/O */
#ifdef CONFIG_SMP
extern int set_cpus_allowed(task_t *p, cpumask_t new_mask);
extern struct mm_struct init_mm;
-#define find_task_by_pid(nr) find_task_by_pid_type(PIDTYPE_PID, nr)
+
+#define find_task_by_real_pid(nr) \
+ find_task_by_pid_type(PIDTYPE_PID, nr)
+#define find_task_by_pid(nr) \
+ find_task_by_pid_type(PIDTYPE_PID, \
+ vx_rmap_pid(nr))
+
extern struct task_struct *find_task_by_pid_type(int type, int pid);
extern void set_special_pids(pid_t session, pid_t pgrp);
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(xid_t, uid_t);
static inline struct user_struct *get_uid(struct user_struct *u)
{
atomic_inc(&u->__count);
return u;
}
+
extern void free_uid(struct user_struct *);
extern void switch_uid(struct user_struct *);
#include <asm/current.h>
-extern unsigned long itimer_ticks;
-extern unsigned long itimer_next;
extern void do_timer(struct pt_regs *);
extern int FASTCALL(wake_up_state(struct task_struct * tsk, unsigned int state));
extern int force_sig_info(int, struct siginfo *, struct task_struct *);
extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp);
extern int kill_pg_info(int, struct siginfo *, pid_t);
-extern int kill_sl_info(int, struct siginfo *, pid_t);
extern int kill_proc_info(int, struct siginfo *, pid_t);
extern void do_notify_parent(struct task_struct *, int);
extern void force_sig(int, struct task_struct *);
}
#endif
+
/*
* Routines for handling mm_structs
*/
extern void unhash_process(struct task_struct *p);
/*
- * Protects ->fs, ->files, ->mm, ->ptrace, ->group_info, ->comm and
- * synchronises with wait4().
+ * Protects ->fs, ->files, ->mm, ->ptrace, ->group_info, ->comm, keyring
+ * subscriptions and synchronises with wait4(). Also used in procfs.
*
* Nests both inside and outside of read_lock(&tasklist_lock).
* It must not be nested with write_lock_irq(&tasklist_lock),
#endif /* CONFIG_SMP */
+/* API for registering delay info */
+#ifdef CONFIG_DELAY_ACCT
+
+#define test_delay_flag(tsk,flg) ((tsk)->flags & (flg))
+#define set_delay_flag(tsk,flg) ((tsk)->flags |= (flg))
+#define clear_delay_flag(tsk,flg) ((tsk)->flags &= ~(flg))
+
+#define def_delay_var(var) unsigned long long var
+#define get_delay(tsk,field) ((tsk)->delays.field)
+
+#define start_delay(var) ((var) = sched_clock())
+#define start_delay_set(var,flg) (set_delay_flag(current,flg),(var) = sched_clock())
+
+#define inc_delay(tsk,field) (((tsk)->delays.field)++)
+
+/* because of hardware timer drifts in SMPs and task continue on different cpu
+ * then where the start_ts was taken there is a possibility that
+ * end_ts < start_ts by some usecs. In this case we ignore the diff
+ * and add nothing to the total.
+ */
+#ifdef CONFIG_SMP
+#define test_ts_integrity(start_ts,end_ts) (likely((end_ts) > (start_ts)))
+#else
+#define test_ts_integrity(start_ts,end_ts) (1)
+#endif
+
+#define add_delay_ts(tsk,field,start_ts,end_ts) \
+ do { if (test_ts_integrity(start_ts,end_ts)) (tsk)->delays.field += ((end_ts)-(start_ts)); } while (0)
+
+#define add_delay_clear(tsk,field,start_ts,flg) \
+ do { \
+ unsigned long long now = sched_clock();\
+ add_delay_ts(tsk,field,start_ts,now); \
+ clear_delay_flag(tsk,flg); \
+ } while (0)
+
+static inline void add_io_delay(unsigned long long dstart)
+{
+ struct task_struct * tsk = current;
+ unsigned long long now = sched_clock();
+ unsigned long long val;
+
+ if (test_ts_integrity(dstart,now))
+ val = now - dstart;
+ else
+ val = 0;
+ if (test_delay_flag(tsk,PF_MEMIO)) {
+ tsk->delays.mem_iowait_total += val;
+ tsk->delays.num_memwaits++;
+ } else {
+ tsk->delays.iowait_total += val;
+ tsk->delays.num_iowaits++;
+ }
+ clear_delay_flag(tsk,PF_IOWAIT);
+}
+
+inline static void init_delays(struct task_struct *tsk)
+{
+ memset((void*)&tsk->delays,0,sizeof(tsk->delays));
+}
+
+#else
+
+#define test_delay_flag(tsk,flg) (0)
+#define set_delay_flag(tsk,flg) do { } while (0)
+#define clear_delay_flag(tsk,flg) do { } while (0)
+
+#define def_delay_var(var)
+#define get_delay(tsk,field) (0)
+
+#define start_delay(var) do { } while (0)
+#define start_delay_set(var,flg) do { } while (0)
+
+#define inc_delay(tsk,field) do { } while (0)
+#define add_delay_ts(tsk,field,start_ts,now) do { } while (0)
+#define add_delay_clear(tsk,field,start_ts,flg) do { } while (0)
+#define add_io_delay(dstart) do { } while (0)
+#define init_delays(tsk) do { } while (0)
+#endif
+
+
+
#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
extern void arch_pick_mmap_layout(struct mm_struct *mm);
#else
extern long sched_setaffinity(pid_t pid, cpumask_t new_mask);
extern long sched_getaffinity(pid_t pid, cpumask_t *mask);
+#ifdef CONFIG_MAGIC_SYSRQ
+
+extern void normalize_rt_tasks(void);
+
+#endif
+
#endif /* __KERNEL__ */
#endif