From: tip-bot for Oleg Nesterov <tipbot@zytor.com>
To: linux-tip-commits@vger.kernel.org
Cc: torvalds@linux-foundation.org, mingo@kernel.org, tkhai@yandex.ru,
linux-kernel@vger.kernel.org, tglx@linutronix.de,
rostedt@goodmis.org, oleg@redhat.com, hpa@zytor.com,
peterz@infradead.org
Subject: [tip:sched/core] sched: Make finish_task_switch() return ' struct rq *'
Date: Tue, 28 Oct 2014 04:06:19 -0700 [thread overview]
Message-ID: <tip-dfa50b605c2a933b7bb1c1d575a0da4e897e3c7d@git.kernel.org> (raw)
In-Reply-To: <20141009193232.GB5408@redhat.com>
Commit-ID: dfa50b605c2a933b7bb1c1d575a0da4e897e3c7d
Gitweb: http://git.kernel.org/tip/dfa50b605c2a933b7bb1c1d575a0da4e897e3c7d
Author: Oleg Nesterov <oleg@redhat.com>
AuthorDate: Thu, 9 Oct 2014 21:32:32 +0200
Committer: Ingo Molnar <mingo@kernel.org>
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@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141009193232.GB5408@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
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);
prev parent reply other threads:[~2014-10-28 11:07 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-10-07 19:50 [PATCH 0/1] sched: fix the PREEMPT_ACTIVE check in __trace_sched_switch_state() Oleg Nesterov
2014-10-07 19:51 ` [PATCH 1/1] " Oleg Nesterov
2014-10-10 9:54 ` Peter Zijlstra
2014-10-10 9:56 ` Peter Zijlstra
2014-10-28 11:05 ` [tip:sched/core] sched: Fix " tip-bot for Oleg Nesterov
2014-10-08 8:00 ` [PATCH 0/1] sched: fix " Peter Zijlstra
2014-10-08 18:33 ` [PATCH 0/2] (Was: sched: fix the PREEMPT_ACTIVE check in __trace_sched_switch_state()) Oleg Nesterov
2014-10-08 18:33 ` [PATCH 1/2] sched: schedule_tail() should disable preemption Oleg Nesterov
2014-10-08 19:36 ` [PATCH v2 " Oleg Nesterov
2014-10-08 21:37 ` Kirill Tkhai
2014-10-09 14:57 ` Oleg Nesterov
2014-10-09 15:17 ` Peter Zijlstra
2014-10-09 16:57 ` Oleg Nesterov
2014-10-09 17:28 ` Peter Zijlstra
2014-10-09 17:32 ` Peter Zijlstra
2014-10-09 17:55 ` Oleg Nesterov
2014-10-28 11:06 ` [tip:sched/core] sched: Fix schedule_tail() to " tip-bot for Oleg Nesterov
2014-10-08 18:33 ` [PATCH 2/2] sched: kill task_preempt_count() Oleg Nesterov
2014-10-28 11:06 ` [tip:sched/core] sched: Kill task_preempt_count() tip-bot for Oleg Nesterov
2014-10-09 19:32 ` [PATCH 0/1] sched: make finish_task_switch() return struct rq * Oleg Nesterov
2014-10-09 19:32 ` [PATCH 1/1] " Oleg Nesterov
2014-10-10 10:06 ` Peter Zijlstra
2014-10-10 17:06 ` Oleg Nesterov
2014-10-10 20:32 ` Peter Zijlstra
2014-10-14 17:57 ` Oleg Nesterov
2014-10-28 11:06 ` tip-bot for Oleg Nesterov [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=tip-dfa50b605c2a933b7bb1c1d575a0da4e897e3c7d@git.kernel.org \
--to=tipbot@zytor.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=tkhai@yandex.ru \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.