[V3 0/3] Fixed dump_backtrace() when task running on another cpu

[V3 0/3] Fixed dump_backtrace() when task running on another cpu

[Wang Qing]

We cannot get FP and PC when the task is running on another CPU,
task->thread.cpu_context is the last time the task was switched out,
it's better to give a reminder than to provide wrong information
for example when Task blocked in spinlock/interrupt/busy loop.

The task_running() should be renamed to task_running_on_rq()
like the naming of task_running_on_cpu(), this is what it
originally mean.

Add task_running() no rq required.

V2:
- Add task_running_oncpu()
v3:
- Renamed task_running() to task_running_on_rq()
- Renamed task_running_oncpu() to task_running()

Wang Qing (3):
  ARM64:fixed dump_backtrace() when task running on another cpu
  sched:add task_running()
  sched:rename task_running() and to task_running_on_rq

 arch/arm64/kernel/traps.c |  7 +++++++
 include/linux/sched.h     | 10 ++++++++++
 kernel/sched/core.c       | 14 +++++++-------
 kernel/sched/deadline.c   |  6 +++---
 kernel/sched/fair.c       |  2 +-
 kernel/sched/rt.c         |  6 +++---
 kernel/sched/sched.h      |  2 +-
 7 files changed, 32 insertions(+), 15 deletions(-)

-- 
2.7.4

[V3 1/3] ARM64:fixed dump_backtrace() when task running on another cpu

[Wang Qing]

We cannot get FP and PC when the task is running on another CPU,
task->thread.cpu_context is the last time the task was switched out,
it's better to give a reminder than to provide wrong information
for example when Task blocked in spinlock/interrupt/busy loop.

Signed-off-by: Wang Qing <wangqing@vivo.com>
---
 arch/arm64/kernel/traps.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index cf402be..c74090b 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -106,6 +106,13 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 		start_backtrace(&frame,
 				(unsigned long)__builtin_frame_address(0),
 				(unsigned long)dump_backtrace);
+	} else if (task_running(tsk)) {
+		/*
+		 * The task is running in another cpu, we cannot get it.
+		 */
+		pr_warn("tsk: %s is running in CPU%d, Don't call trace!\n",
+			tsk->comm, task_cpu(tsk));
+		return;
 	} else {
 		/*
 		 * task blocked in __switch_to
-- 
2.7.4

[V3 2/3] sched:add task_running()

[Wang Qing]

The task_running() should be renamed to task_running_on_rq()
like the naming of task_running_on_cpu(), this is what it
originally mean.

Add task_running() no rq required.

Signed-off-by: Wang Qing <wangqing@vivo.com>
---
 include/linux/sched.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4418f5c..0a7b150 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1843,6 +1843,11 @@ static inline unsigned int task_cpu(const struct task_struct *p)
 
 extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
 
+static inline int task_running(const struct task_struct *p)
+{
+	return READ_ONCE(p->on_cpu);
+}
+
 #else
 
 static inline unsigned int task_cpu(const struct task_struct *p)
@@ -1854,6 +1859,11 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 {
 }
 
+static inline int task_running(const struct task_struct *p)
+{
+	return p == current;
+}
+
 #endif /* CONFIG_SMP */
 
 /*
-- 
2.7.4

[V3 3/3] sched:rename task_running() and to task_running_on_rq

[Wang Qing]

The task_running() should be renamed to task_running_on_rq()
like the naming of task_running_on_cpu(), this is what it
originally mean.

This solves the confusing naming problem.

Signed-off-by: Wang Qing <wangqing@vivo.com>
---
 kernel/sched/core.c     | 14 +++++++-------
 kernel/sched/deadline.c |  6 +++---
 kernel/sched/fair.c     |  2 +-
 kernel/sched/rt.c       |  6 +++---
 kernel/sched/sched.h    |  2 +-
 5 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a2694ba..7ba1840 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1672,7 +1672,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	if (cpumask_test_cpu(task_cpu(p), new_mask))
 		goto out;
 
-	if (task_running(rq, p) || p->state == TASK_WAKING) {
+	if (task_running_on_rq(rq, p) || p->state == TASK_WAKING) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
 		task_rq_unlock(rq, p, &rf);
@@ -1905,11 +1905,11 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 *
 		 * NOTE! Since we don't hold any locks, it's not
 		 * even sure that "rq" stays as the right runqueue!
-		 * But we don't care, since "task_running()" will
-		 * return false if the runqueue has changed and p
-		 * is actually now running somewhere else!
+		 * But we don't care, since "task_running_on_rq()"
+		 * will return false if the runqueue has changed
+		 * and p is actually now running somewhere else!
 		 */
-		while (task_running(rq, p)) {
+		while (task_running_on_rq(rq, p)) {
 			if (match_state && unlikely(p->state != match_state))
 				return 0;
 			cpu_relax();
@@ -1922,7 +1922,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 */
 		rq = task_rq_lock(p, &rf);
 		trace_sched_wait_task(p);
-		running = task_running(rq, p);
+		running = task_running_on_rq(rq, p);
 		queued = task_on_rq_queued(p);
 		ncsw = 0;
 		if (!match_state || p->state == match_state)
@@ -5745,7 +5745,7 @@ int __sched yield_to(struct task_struct *p, bool preempt)
 	if (curr->sched_class != p->sched_class)
 		goto out_unlock;
 
-	if (task_running(p_rq, p) || p->state)
+	if (task_running_on_rq(p_rq, p) || p->state)
 		goto out_unlock;
 
 	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 504d2f5..c04cecd 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1838,7 +1838,7 @@ static void task_fork_dl(struct task_struct *p)
 
 static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
 {
-	if (!task_running(rq, p) &&
+	if (!task_running_on_rq(rq, p) &&
 	    cpumask_test_cpu(cpu, p->cpus_ptr))
 		return 1;
 	return 0;
@@ -1990,7 +1990,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 		if (double_lock_balance(rq, later_rq)) {
 			if (unlikely(task_rq(task) != rq ||
 				     !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) ||
-				     task_running(rq, task) ||
+				     task_running_on_rq(rq, task) ||
 				     !dl_task(task) ||
 				     !task_on_rq_queued(task))) {
 				double_unlock_balance(rq, later_rq);
@@ -2217,7 +2217,7 @@ static void pull_dl_task(struct rq *this_rq)
  */
 static void task_woken_dl(struct rq *rq, struct task_struct *p)
 {
-	if (!task_running(rq, p) &&
+	if (!task_running_on_rq(rq, p) &&
 	    !test_tsk_need_resched(rq->curr) &&
 	    p->nr_cpus_allowed > 1 &&
 	    dl_task(rq->curr) &&
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1ea3ddd..6cc0b5b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7503,7 +7503,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	/* Record that we found atleast one task that could run on dst_cpu */
 	env->flags &= ~LBF_ALL_PINNED;
 
-	if (task_running(env->src_rq, p)) {
+	if (task_running_on_rq(env->src_rq, p)) {
 		schedstat_inc(p->se.statistics.nr_failed_migrations_running);
 		return 0;
 	}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index df11d88..ea647d9 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1655,7 +1655,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
-	if (!task_running(rq, p) &&
+	if (!task_running_on_rq(rq, p) &&
 	    cpumask_test_cpu(cpu, p->cpus_ptr))
 		return 1;
 
@@ -1810,7 +1810,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 */
 			if (unlikely(task_rq(task) != rq ||
 				     !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) ||
-				     task_running(rq, task) ||
+				     task_running_on_rq(rq, task) ||
 				     !rt_task(task) ||
 				     !task_on_rq_queued(task))) {
 
@@ -2218,7 +2218,7 @@ static void pull_rt_task(struct rq *this_rq)
  */
 static void task_woken_rt(struct rq *rq, struct task_struct *p)
 {
-	bool need_to_push = !task_running(rq, p) &&
+	bool need_to_push = !task_running_on_rq(rq, p) &&
 			    !test_tsk_need_resched(rq->curr) &&
 			    p->nr_cpus_allowed > 1 &&
 			    (dl_task(rq->curr) || rt_task(rq->curr)) &&
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0f616bf..e5b6538 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1659,7 +1659,7 @@ static inline int task_current(struct rq *rq, struct task_struct *p)
 	return rq->curr == p;
 }
 
-static inline int task_running(struct rq *rq, struct task_struct *p)
+static inline int task_running_on_rq(struct rq *rq, struct task_struct *p)
 {
 #ifdef CONFIG_SMP
 	return p->on_cpu;
-- 
2.7.4