[PATCH 3/6] move_task_off_dead_cpu: remove retry logic

[PATCH 3/6] move_task_off_dead_cpu: remove retry logic

[Oleg Nesterov]

The previous patch preserved the retry logic, but it looks unneeded.

__migrate_task() can only fail if we raced with migration after we dropped
the lock, but in this case the caller of set_cpus_allowed/etc must initiate
migration itself if ->on_rq == T.

We already fixed p->cpus_allowed, the changes in active/online masks must
be visible to racer, it should migrate the task to online cpu correctly.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---

 kernel/sched.c |   13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

--- 34-rc1/kernel/sched.c~2_XXX_MTODC_DONT_RETRY	2010-03-15 09:40:31.000000000 +0100
+++ 34-rc1/kernel/sched.c	2010-03-15 09:40:44.000000000 +0100
@@ -5517,7 +5517,7 @@ static void move_task_off_dead_cpu(int d
 	struct rq *rq = cpu_rq(dead_cpu);
 	int needs_cpu, dest_cpu;
 	unsigned long flags;
-again:
+
 	local_irq_save(flags);
 
 	raw_spin_lock(&rq->lock);
@@ -5525,14 +5525,13 @@ again:
 	if (needs_cpu)
 		dest_cpu = select_fallback_rq(dead_cpu, p);
 	raw_spin_unlock(&rq->lock);
-
-	/* It can have affinity changed while we were choosing. */
+	/*
+	 * It can only fail if we race with set_cpus_allowed(),
+	 * in the racer should migrate the task anyway.
+	 */
 	if (needs_cpu)
-		needs_cpu = !__migrate_task(p, dead_cpu, dest_cpu);
+		__migrate_task(p, dead_cpu, dest_cpu);
 	local_irq_restore(flags);
-
-	if (unlikely(needs_cpu))
-		goto again;
 }
 
 /*

[tip:sched/core] sched: move_task_off_dead_cpu(): Remove retry logic

[tip-bot for Oleg Nesterov]

Commit-ID:  c1804d547dc098363443667609c272d1e4d15ee8
Gitweb:     http://git.kernel.org/tip/c1804d547dc098363443667609c272d1e4d15ee8
Author:     Oleg Nesterov <oleg@redhat.com>
AuthorDate: Mon, 15 Mar 2010 10:10:14 +0100
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 2 Apr 2010 20:12:02 +0200

sched: move_task_off_dead_cpu(): Remove retry logic

The previous patch preserved the retry logic, but it looks unneeded.

__migrate_task() can only fail if we raced with migration after we dropped
the lock, but in this case the caller of set_cpus_allowed/etc must initiate
migration itself if ->on_rq == T.

We already fixed p->cpus_allowed, the changes in active/online masks must
be visible to racer, it should migrate the task to online cpu correctly.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100315091014.GA9138@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c |   13 ++++++-------
 1 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 27774b5..f475c60 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5456,7 +5456,7 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 	struct rq *rq = cpu_rq(dead_cpu);
 	int needs_cpu, uninitialized_var(dest_cpu);
 	unsigned long flags;
-again:
+
 	local_irq_save(flags);
 
 	raw_spin_lock(&rq->lock);
@@ -5464,14 +5464,13 @@ again:
 	if (needs_cpu)
 		dest_cpu = select_fallback_rq(dead_cpu, p);
 	raw_spin_unlock(&rq->lock);
-
-	/* It can have affinity changed while we were choosing. */
+	/*
+	 * It can only fail if we race with set_cpus_allowed(),
+	 * in the racer should migrate the task anyway.
+	 */
 	if (needs_cpu)
-		needs_cpu = !__migrate_task(p, dead_cpu, dest_cpu);
+		__migrate_task(p, dead_cpu, dest_cpu);
 	local_irq_restore(flags);
-
-	if (unlikely(needs_cpu))
-		goto again;
 }
 
 /*