[PATCH] posixtimers: Fix posix clock monotonicity

[Hidetoshi Seto]

This patch rehires task_sched_runtime() and thread_group_sched_runtime()
which were removed at the time of 2.6.28-rc1.

These functions protect the sampling of clock with rq lock.
This rq lock is required not to update rq->clock during the sampling.
i.e. You may get ((banked runtime before update)+(delta after update)).

Signed-off-by: Hidetoshi Seto <seto.hidetoshi@xxxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxx	[2.6.28.x]

---
 kernel/posix-cpu-timers.c |    7 +++--
 kernel/sched.c            |   58 +++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 55 insertions(+), 10 deletions(-)

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 4e5288a..a65641a 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -294,7 +294,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 		cpu->cpu = virt_ticks(p);
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = p->se.sum_exec_runtime + task_delta_exec(p);
+		cpu->sched = task_sched_runtime(p);
 		break;
 	}
 	return 0;
@@ -310,18 +310,19 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 {
 	struct task_cputime cputime;
 
-	thread_group_cputime(p, &cputime);
 	switch (CPUCLOCK_WHICH(which_clock)) {
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
+		thread_group_cputime(p, &cputime);
 		cpu->cpu = cputime_add(cputime.utime, cputime.stime);
 		break;
 	case CPUCLOCK_VIRT:
+		thread_group_cputime(p, &cputime);
 		cpu->cpu = cputime.utime;
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
+		cpu->sched = thread_group_sched_runtime(p);
 		break;
 	}
 	return 0;
diff --git a/kernel/sched.c b/kernel/sched.c
index db66874..617d1b8 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4066,7 +4066,23 @@ EXPORT_PER_CPU_SYMBOL(kstat);
 /*
  * Return any ns on the sched_clock that have not yet been banked in
  * @p in case that task is currently running.
+ *
+ * Called with task_rq_lock() held on @rq.
  */
+static u64 __task_delta_exec(struct task_struct *p, struct rq *rq)
+{
+	u64 ns = 0;
+
+	if (task_current(rq, p)) {
+		update_rq_clock(rq);
+		ns = rq->clock - p->se.exec_start;
+		if ((s64)ns < 0)
+			ns = 0;
+	}
+
+	return ns;
+}
+
 unsigned long long task_delta_exec(struct task_struct *p)
 {
 	unsigned long flags;
@@ -4074,16 +4090,44 @@ unsigned long long task_delta_exec(struct task_struct *p)
 	u64 ns = 0;
 
 	rq = task_rq_lock(p, &flags);
+	ns = __task_delta_exec(p, rq);
+	task_rq_unlock(rq, &flags);
 
-	if (task_current(rq, p)) {
-		u64 delta_exec;
+	return ns;
+}
 
-		update_rq_clock(rq);
-		delta_exec = rq->clock - p->se.exec_start;
-		if ((s64)delta_exec > 0)
-			ns = delta_exec;
-	}
+/*
+ * Return p->sum_exec_runtime plus any more ns on the sched_clock
+ * that have not yet been banked in case the task is currently running.
+ */
+unsigned long long task_sched_runtime(struct task_struct *p)
+{
+	unsigned long flags;
+	struct rq *rq;
+	u64 ns = 0;
+
+	rq = task_rq_lock(p, &flags);
+	ns = p->se.sum_exec_runtime + __task_delta_exec(p, rq);
+	task_rq_unlock(rq, &flags);
+
+	return ns;
+}
 
+/*
+ * Return sum_exec_runtime for the thread group plus any more ns on the
+ * sched_clock that have not yet been banked in case the task is currently
+ * running.
+ */
+unsigned long long thread_group_sched_runtime(struct task_struct *p)
+{
+	struct task_cputime totals;
+	unsigned long flags;
+	struct rq *rq;
+	u64 ns;
+
+	rq = task_rq_lock(p, &flags);
+	thread_group_cputime(p, &totals);
+	ns = totals.sum_exec_runtime + __task_delta_exec(p, rq);
 	task_rq_unlock(rq, &flags);
 
 	return ns;
-- 
1.6.2.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/