timers: split process wide cpu clocks/timers

Change the process wide cpu timers/clocks so that we:

 1) don't mess up the kernel with too many threads,
 2) don't have a per-cpu allocation for each process,
 3) have no impact when not used.

In order to accomplish this we're going to split it into two parts:

 - clocks; which can take all the time they want since they run
           from user context -- ie. sys_clock_gettime(CLOCK_PROCESS_CPUTIME_ID)

 - timers; which need constant time sampling but since they're
           explicity used, the user can pay the overhead.

The clock readout will go back to a full sum of the thread group, while the
timers will run of a global 'clock' that only runs when needed, so only
programs that make use of the facility pay the price.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 31 insertions, 23 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2e0646a30314..082d7619b3a1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -443,7 +443,6 @@ struct pacct_struct {
  * @utime:              time spent in user mode, in &cputime_t units
  * @stime:              time spent in kernel mode, in &cputime_t units
  * @sum_exec_runtime:   total time spent on the CPU, in nanoseconds
- * @lock:               lock for fields in this struct
  *
  * This structure groups together three kinds of CPU time that are
  * tracked for threads and thread groups.  Most things considering
@@ -454,23 +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;
 };
 
 /*
@@ -519,10 +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;
@@ -2191,27 +2200,26 @@ 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);
+        WARN_ON(!cputimer->running);
+
+        spin_lock_irqsave(&cputimer->lock, flags);
+        *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)