timers: split process wide cpu clocks/timers, fix

[safe/jmp/linux-2.6] / include / linux / sched.h

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c20943e..5d10fa0 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -293,6 +293,9 @@ extern void sched_show_task(struct task_struct *p);
 extern void softlockup_tick(void);
 extern void touch_softlockup_watchdog(void);
 extern void touch_all_softlockup_watchdogs(void);
+extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
+                                   struct file *filp, void __user *buffer,
+                                   size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
 extern unsigned long sysctl_hung_task_check_count;
 extern unsigned long sysctl_hung_task_timeout_secs;
@@ -450,23 +453,33 @@ struct task_cputime {
        cputime_t utime;
        cputime_t stime;
        unsigned long long sum_exec_runtime;
-       spinlock_t lock;
 };
 /* Alternate field names when used to cache expirations. */
 #define prof_exp       stime
 #define virt_exp       utime
 #define sched_exp      sum_exec_runtime
 
+#define INIT_CPUTIME   \
+       (struct task_cputime) {                                 \
+               .utime = cputime_zero,                          \
+               .stime = cputime_zero,                          \
+               .sum_exec_runtime = 0,                          \
+       }
+
 /**
- * struct thread_group_cputime - thread group interval timer counts
- * @totals:            thread group interval timers; substructure for
- *                     uniprocessor kernel, per-cpu for SMP kernel.
+ * struct thread_group_cputimer - thread group interval timer counts
+ * @cputime:           thread group interval timers.
+ * @running:           non-zero when there are timers running and
+ *                     @cputime receives updates.
+ * @lock:              lock for fields in this struct.
  *
  * This structure contains the version of task_cputime, above, that is
- * used for thread group CPU clock calculations.
+ * used for thread group CPU timer calculations.
  */
-struct thread_group_cputime {
-       struct task_cputime totals;
+struct thread_group_cputimer {
+       struct task_cputime cputime;
+       int running;
+       spinlock_t lock;
 };
 
 /*
@@ -515,10 +528,10 @@ struct signal_struct {
        cputime_t it_prof_incr, it_virt_incr;
 
        /*
-        * Thread group totals for process CPU clocks.
-        * See thread_group_cputime(), et al, for details.
+        * Thread group totals for process CPU timers.
+        * See thread_group_cputimer(), et al, for details.
         */
-       struct thread_group_cputime cputime;
+       struct thread_group_cputimer cputimer;
 
        /* Earliest-expiration cache. */
        struct task_cputime cputime_expires;
@@ -555,7 +568,7 @@ struct signal_struct {
         * Live threads maintain their own counters and add to these
         * in __exit_signal, except for the group leader.
         */
-       cputime_t cutime, cstime;
+       cputime_t utime, stime, cutime, cstime;
        cputime_t gtime;
        cputime_t cgtime;
        unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
@@ -564,6 +577,14 @@ struct signal_struct {
        struct task_io_accounting ioac;
 
        /*
+        * Cumulative ns of schedule CPU time fo dead threads in the
+        * group, not including a zombie group leader, (This only differs
+        * from jiffies_to_ns(utime + stime) if sched_clock uses something
+        * other than jiffies.)
+        */
+       unsigned long long sum_sched_runtime;
+
+       /*
         * 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
@@ -627,7 +648,6 @@ struct user_struct {
        atomic_t inotify_devs;  /* How many inotify devs does this user have opened? */
 #endif
 #ifdef CONFIG_EPOLL
-       atomic_t epoll_devs;    /* The number of epoll descriptors currently open */
        atomic_t epoll_watches; /* The number of file descriptors currently watched */
 #endif
 #ifdef CONFIG_POSIX_MQUEUE
@@ -2180,27 +2200,25 @@ static inline int spin_needbreak(spinlock_t *lock)
 /*
  * Thread group CPU time accounting.
  */
+void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
 
 static inline
-void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
+void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
 {
-       struct task_cputime *totals = &tsk->signal->cputime.totals;
+       struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
        unsigned long flags;
 
-       spin_lock_irqsave(&totals->lock, flags);
-       *times = *totals;
-       spin_unlock_irqrestore(&totals->lock, flags);
+       spin_lock_irqsave(&cputimer->lock, flags);
+       cputimer->running = 1;
+       *times = cputimer->cputime;
+       spin_unlock_irqrestore(&cputimer->lock, flags);
 }
 
 static inline void thread_group_cputime_init(struct signal_struct *sig)
 {
-       sig->cputime.totals = (struct task_cputime){
-               .utime = cputime_zero,
-               .stime = cputime_zero,
-               .sum_exec_runtime = 0,
-       };
-
-       spin_lock_init(&sig->cputime.totals.lock);
+       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)