[PATCH 0/2] [GIT PULL][v3.0] sched: various fixes

[PATCH 0/2] [GIT PULL][v3.0] sched: various fixes

[Steven Rostedt]

Ingo,

Please pull the latest tip/sched/urgent tree, which can be found at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-rt.git
tip/sched/urgent

Head SHA1: 349d467dc2c8d22df6a891562843bb7d8409f93f


Hillf Danton (1):
      sched: Fix need_resched() when checking peempt

Steven Rostedt (1):
      sched: Check if lowest_mask is initialized in find_lowest_rq

----
 kernel/sched_rt.c |    6 +++++-
 1 files changed, 5 insertions(+), 1 deletions(-)

[PATCH 1/2] sched: Fix need_resched() when checking peempt

[Steven Rostedt]

[-- Attachment #1: 0001-sched-Fix-need_resched-when-checking-peempt.patch --]
[-- Type: text/plain, Size: 1065 bytes --]

From: Hillf Danton <dhillf@gmail.com>

The RT preempt check tests the wrong task if NEED_RESCHED is set. It currently
checks the local CPU task. It is suppose to check the task that is running on
the run queue we are about to wake another task on.

Signed-off-by: Hillf Danton <dhillf@gmail.com>
Link: http://lkml.kernel.org/r/BANLkTi=e=69xvJZ1+56xzuFyhmdN0hZHRQ@mail.gmail.com
Reviewed-by: Yong Zhang <yong.zhang0@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/sched_rt.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 88725c9..9b8d5dc 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1096,7 +1096,7 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
 	 * to move current somewhere else, making room for our non-migratable
 	 * task.
 	 */
-	if (p->prio == rq->curr->prio && !need_resched())
+	if (p->prio == rq->curr->prio && !test_tsk_need_resched(rq->curr))
 		check_preempt_equal_prio(rq, p);
 #endif
 }
-- 
1.7.4.4

[tip:sched/urgent] sched: Fix need_resched() when checking peempt

[tip-bot for Hillf Danton]

Commit-ID:  8dd0de8be31b4b966d17750a0b10df2f575c91ac
Gitweb:     http://git.kernel.org/tip/8dd0de8be31b4b966d17750a0b10df2f575c91ac
Author:     Hillf Danton <dhillf@gmail.com>
AuthorDate: Tue, 14 Jun 2011 18:36:24 -0400
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Wed, 15 Jun 2011 09:50:32 +0200

sched: Fix need_resched() when checking peempt

The RT preempt check tests the wrong task if NEED_RESCHED is
set. It currently checks the local CPU task. It is supposed to
check the task that is running on the runqueue we are about to
wake another task on.

Signed-off-by: Hillf Danton <dhillf@gmail.com>
Reviewed-by: Yong Zhang <yong.zhang0@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20110614223657.450239027@goodmis.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_rt.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 88725c9..9b8d5dc 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1096,7 +1096,7 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
 	 * to move current somewhere else, making room for our non-migratable
 	 * task.
 	 */
-	if (p->prio == rq->curr->prio && !need_resched())
+	if (p->prio == rq->curr->prio && !test_tsk_need_resched(rq->curr))
 		check_preempt_equal_prio(rq, p);
 #endif
 }

[PATCH 2/2] sched: Check if lowest_mask is initialized in find_lowest_rq

[Steven Rostedt]

[-- Attachment #1: 0002-sched-Check-if-lowest_mask-is-initialized-in-find_lo.patch --]
[-- Type: text/plain, Size: 1269 bytes --]

From: Steven Rostedt <rostedt@goodmis.org>

On system boot up, the lowest_mask is initialized with early_initcall.
But RT tasks may wake up on other early_initcall callers before the
lowest_mask is initialized, causing a system crash.

The commit d72bce0e67 rcu: Cure load woes
was the first commit to wake up RT tasks in early init. Before this
commit this bug should not happen.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Reported-by: Andrew Theurer <habanero@linux.vnet.ibm.com>
Tested-by: Andrew Theurer <habanero@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1308014683.9218.107.camel@gandalf.stny.rr.com
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/sched_rt.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 9b8d5dc..10d0182 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1239,6 +1239,10 @@ static int find_lowest_rq(struct task_struct *task)
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
 
+	/* Make sure the mask is initialized first */
+	if (unlikely(!lowest_mask))
+		return -1;
+
 	if (task->rt.nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
 
-- 
1.7.4.4

Re: [PATCH 2/2] sched: Check if lowest_mask is initialized in find_lowest_rq

[Paul E. McKenney]

On Tue, Jun 14, 2011 at 06:36:25PM -0400, Steven Rostedt wrote:
> From: Steven Rostedt <rostedt@goodmis.org>
> 
> On system boot up, the lowest_mask is initialized with early_initcall.
> But RT tasks may wake up on other early_initcall callers before the
> lowest_mask is initialized, causing a system crash.
> 
> The commit d72bce0e67 rcu: Cure load woes
> was the first commit to wake up RT tasks in early init. Before this
> commit this bug should not happen.

I never was able to reproduce this, but after adding Shaohua's patch, I
need this one too on some systems.  So:

Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
> Reported-by: Andrew Theurer <habanero@linux.vnet.ibm.com>
> Tested-by: Andrew Theurer <habanero@linux.vnet.ibm.com>
> Link: http://lkml.kernel.org/r/1308014683.9218.107.camel@gandalf.stny.rr.com
> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
> ---
>  kernel/sched_rt.c |    4 ++++
>  1 files changed, 4 insertions(+), 0 deletions(-)
> 
> diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
> index 9b8d5dc..10d0182 100644
> --- a/kernel/sched_rt.c
> +++ b/kernel/sched_rt.c
> @@ -1239,6 +1239,10 @@ static int find_lowest_rq(struct task_struct *task)
>  	int this_cpu = smp_processor_id();
>  	int cpu      = task_cpu(task);
> 
> +	/* Make sure the mask is initialized first */
> +	if (unlikely(!lowest_mask))
> +		return -1;
> +
>  	if (task->rt.nr_cpus_allowed == 1)
>  		return -1; /* No other targets possible */
> 
> -- 
> 1.7.4.4
> 
> 

Re: [PATCH 2/2] sched: Check if lowest_mask is initialized in find_lowest_rq

[Peter Zijlstra]

On Tue, 2011-06-14 at 18:36 -0400, Steven Rostedt wrote:
> plain text document attachment
> (0002-sched-Check-if-lowest_mask-is-initialized-in-find_lo.patch)
> From: Steven Rostedt <rostedt@goodmis.org>
> 
> On system boot up, the lowest_mask is initialized with early_initcall.
> But RT tasks may wake up on other early_initcall callers before the
> lowest_mask is initialized, causing a system crash.
> 
> The commit d72bce0e67 rcu: Cure load woes
> was the first commit to wake up RT tasks in early init. Before this
> commit this bug should not happen.
> 

Acked-by: Peter Zijlstra <peterz@infradead.org>

> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
> Reported-by: Andrew Theurer <habanero@linux.vnet.ibm.com>
> Tested-by: Andrew Theurer <habanero@linux.vnet.ibm.com>
> Link: http://lkml.kernel.org/r/1308014683.9218.107.camel@gandalf.stny.rr.com
> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
> ---
>  kernel/sched_rt.c |    4 ++++
>  1 files changed, 4 insertions(+), 0 deletions(-)
> 
> diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
> index 9b8d5dc..10d0182 100644
> --- a/kernel/sched_rt.c
> +++ b/kernel/sched_rt.c
> @@ -1239,6 +1239,10 @@ static int find_lowest_rq(struct task_struct *task)
>  	int this_cpu = smp_processor_id();
>  	int cpu      = task_cpu(task);
>  
> +	/* Make sure the mask is initialized first */
> +	if (unlikely(!lowest_mask))
> +		return -1;
> +
>  	if (task->rt.nr_cpus_allowed == 1)
>  		return -1; /* No other targets possible */
>  

[tip:sched/urgent] sched: Check if lowest_mask is initialized in find_lowest_rq()

[tip-bot for Steven Rostedt]

Commit-ID:  0da938c44921cfb690283d3b0c9c48a10375db2c
Gitweb:     http://git.kernel.org/tip/0da938c44921cfb690283d3b0c9c48a10375db2c
Author:     Steven Rostedt <rostedt@goodmis.org>
AuthorDate: Tue, 14 Jun 2011 18:36:25 -0400
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Wed, 15 Jun 2011 11:44:48 +0200

sched: Check if lowest_mask is initialized in find_lowest_rq()

On system boot up, the lowest_mask is initialized with an
early_initcall(). But RT tasks may wake up on other
early_initcall() callers before the lowest_mask is initialized,
causing a system crash.

Commit "d72bce0e67 rcu: Cure load woes" was the first commit
to wake up RT tasks in early init. Before this commit this bug
should not happen.

Reported-by: Andrew Theurer <habanero@linux.vnet.ibm.com>
Tested-by: Andrew Theurer <habanero@linux.vnet.ibm.com>
Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20110614223657.824872966@goodmis.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_rt.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 9b8d5dc..10d0182 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1239,6 +1239,10 @@ static int find_lowest_rq(struct task_struct *task)
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
 
+	/* Make sure the mask is initialized first */
+	if (unlikely(!lowest_mask))
+		return -1;
+
 	if (task->rt.nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */