[PATCH 3.0-rt1] ipc/mqueue: add a critical section to avoid a deadlock

[PATCH 3.0-rt1] ipc/mqueue: add a critical section to avoid a deadlock

[KOBAYASHI Yoshitake]

(Repost for v3.0-rt1 and changed the distination addreses)
I have tested the following patch on v3.0-rt1 with PREEMPT_RT_FULL.
In POSIX message queue, if a sender process uses SCHED_FIFO and
has a higher priority than a receiver process, the sender will
be stuck at ipc/mqueue.c:452

  452                 while (ewp->state == STATE_PENDING)
  453                         cpu_relax();

Description of the problem
 (receiver process)
   1. receiver changes sender's state to STATE_PENDING (mqueue.c:846)
   2. wake up sender process and "switch to sender" (mqueue.c:847)
      Note: This context switch only happens in PREEMPT_RT_FULL kernel.
 (sender process)
   3. sender check the own state in above loop (mqueue.c:452-453)
   *. receiver will never wake up and cannot change sender's state to
      STATE_READY because sender has higher priority


Signed-off-by: Yoshitake Kobayashi <yoshitake.kobayashi@toshiba.co.jp>
---
 ipc/mqueue.c |    5 +++++
 1 files changed, 5 insertions(+), 0 deletions(-)

diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 22a06a4..1cf6e53 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -841,12 +841,17 @@ static inline void pipelined_receive(struct
mqueue_inode_info *info)
 		wake_up_interruptible(&info->wait_q);
 		return;
 	}
+	/*
+	 * Keep them in one critical section for PREEMPT_RT:
+	 */
+	preempt_disable_rt();
 	msg_insert(sender->msg, info);
 	list_del(&sender->list);
 	sender->state = STATE_PENDING;
 	wake_up_process(sender->task);
 	smp_wmb();
 	sender->state = STATE_READY;
+	preempt_enable_rt();
 }

 SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
-- 
1.7.2.5

Re: [PATCH 3.0-rt1] ipc/mqueue: add a critical section to avoid a deadlock

[Thomas Gleixner]

On Sat, 23 Jul 2011, KOBAYASHI Yoshitake wrote:

> (Repost for v3.0-rt1 and changed the distination addreses)
> I have tested the following patch on v3.0-rt1 with PREEMPT_RT_FULL.
> In POSIX message queue, if a sender process uses SCHED_FIFO and
> has a higher priority than a receiver process, the sender will
> be stuck at ipc/mqueue.c:452
> 
>   452                 while (ewp->state == STATE_PENDING)
>   453                         cpu_relax();
> 
> Description of the problem
>  (receiver process)
>    1. receiver changes sender's state to STATE_PENDING (mqueue.c:846)
>    2. wake up sender process and "switch to sender" (mqueue.c:847)
>       Note: This context switch only happens in PREEMPT_RT_FULL kernel.
>  (sender process)
>    3. sender check the own state in above loop (mqueue.c:452-453)
>    *. receiver will never wake up and cannot change sender's state to
>       STATE_READY because sender has higher priority

Good catch! Queued for -rt2.

Thanks,

	tglx