[tip:sched/core] sched: Make finish_task_switch() return ' struct rq *'
From: tip-bot for Oleg Nesterov
Date: Tue Oct 28 2014 - 07:07:29 EST
Commit-ID: dfa50b605c2a933b7bb1c1d575a0da4e897e3c7d
Gitweb: http://git.kernel.org/tip/dfa50b605c2a933b7bb1c1d575a0da4e897e3c7d
Author: Oleg Nesterov <oleg@xxxxxxxxxx>
AuthorDate: Thu, 9 Oct 2014 21:32:32 +0200
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Tue, 28 Oct 2014 10:47:55 +0100
sched: Make finish_task_switch() return 'struct rq *'
Both callers of finish_task_switch() need to recalculate this_rq()
and pass it as an argument, plus __schedule() does this again after
context_switch().
It would be simpler to call this_rq() once in finish_task_switch()
and return the this rq to the callers.
Note: probably "int cpu" in __schedule() should die; it is not used
and both rcu_note_context_switch() and wq_worker_sleeping() do not
really need this argument.
Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Kirill Tkhai <tkhai@xxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/20141009193232.GB5408@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
kernel/sched/core.c | 38 +++++++++++++++-----------------------
1 file changed, 15 insertions(+), 23 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b493560..1b69603 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2220,7 +2220,6 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
/**
* finish_task_switch - clean up after a task-switch
- * @rq: runqueue associated with task-switch
* @prev: the thread we just switched away from.
*
* finish_task_switch must be called after the context switch, paired
@@ -2232,10 +2231,16 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
* so, we finish that here outside of the runqueue lock. (Doing it
* with the lock held can cause deadlocks; see schedule() for
* details.)
+ *
+ * The context switch have flipped the stack from under us and restored the
+ * local variables which were saved when this task called schedule() in the
+ * past. prev == current is still correct but we need to recalculate this_rq
+ * because prev may have moved to another CPU.
*/
-static void finish_task_switch(struct rq *rq, struct task_struct *prev)
+static struct rq *finish_task_switch(struct task_struct *prev)
__releases(rq->lock)
{
+ struct rq *rq = this_rq();
struct mm_struct *mm = rq->prev_mm;
long prev_state;
@@ -2275,6 +2280,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
}
tick_nohz_task_switch(current);
+ return rq;
}
#ifdef CONFIG_SMP
@@ -2313,8 +2319,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
/* finish_task_switch() drops rq->lock and enables preemtion */
preempt_disable();
- rq = this_rq();
- finish_task_switch(rq, prev);
+ rq = finish_task_switch(prev);
post_schedule(rq);
preempt_enable();
@@ -2323,10 +2328,9 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
}
/*
- * context_switch - switch to the new MM and the new
- * thread's register state.
+ * context_switch - switch to the new MM and the new thread's register state.
*/
-static inline void
+static inline struct rq *
context_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
@@ -2365,14 +2369,9 @@ context_switch(struct rq *rq, struct task_struct *prev,
context_tracking_task_switch(prev, next);
/* Here we just switch the register state and the stack. */
switch_to(prev, next, prev);
-
barrier();
- /*
- * this_rq must be evaluated again because prev may have moved
- * CPUs since it called schedule(), thus the 'rq' on its stack
- * frame will be invalid.
- */
- finish_task_switch(this_rq(), prev);
+
+ return finish_task_switch(prev);
}
/*
@@ -2854,15 +2853,8 @@ need_resched:
rq->curr = next;
++*switch_count;
- context_switch(rq, prev, next); /* unlocks the rq */
- /*
- * The context switch have flipped the stack from under us
- * and restored the local variables which were saved when
- * this task called schedule() in the past. prev == current
- * is still correct, but it can be moved to another cpu/rq.
- */
- cpu = smp_processor_id();
- rq = cpu_rq(cpu);
+ rq = context_switch(rq, prev, next); /* unlocks the rq */
+ cpu = cpu_of(rq);
} else
raw_spin_unlock_irq(&rq->lock);
--
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/