[PATCH RT 4/5] rtmutex: use a trylock for waiter lock in trylock

[PATCH RT 4/5] rtmutex: use a trylock for waiter lock in trylock

[Steven Rostedt]

[-- Attachment #1: 0004-rtmutex-use-a-trylock-for-waiter-lock-in-trylock.patch --]
[-- Type: text/plain, Size: 5030 bytes --]

3.10.22-rt20-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Mike Galbraith captered the following:
| >#11 [ffff88017b243e90] _raw_spin_lock at ffffffff815d2596
| >#12 [ffff88017b243e90] rt_mutex_trylock at ffffffff815d15be
| >#13 [ffff88017b243eb0] get_next_timer_interrupt at ffffffff81063b42
| >#14 [ffff88017b243f00] tick_nohz_stop_sched_tick at ffffffff810bd1fd
| >#15 [ffff88017b243f70] tick_nohz_irq_exit at ffffffff810bd7d2
| >#16 [ffff88017b243f90] irq_exit at ffffffff8105b02d
| >#17 [ffff88017b243fb0] reschedule_interrupt at ffffffff815db3dd
| >--- <IRQ stack> ---
| >#18 [ffff88017a2a9bc8] reschedule_interrupt at ffffffff815db3dd
| >    [exception RIP: task_blocks_on_rt_mutex+51]
| >#19 [ffff88017a2a9ce0] rt_spin_lock_slowlock at ffffffff815d183c
| >#20 [ffff88017a2a9da0] lock_timer_base.isra.35 at ffffffff81061cbf
| >#21 [ffff88017a2a9dd0] schedule_timeout at ffffffff815cf1ce
| >#22 [ffff88017a2a9e50] rcu_gp_kthread at ffffffff810f9bbb
| >#23 [ffff88017a2a9ed0] kthread at ffffffff810796d5
| >#24 [ffff88017a2a9f50] ret_from_fork at ffffffff815da04c

lock_timer_base() does a try_lock() which deadlocks on the waiter lock
not the lock itself.
This patch takes the waiter_lock with trylock so it should work from interrupt
context as well. If the fastpath doesn't work and the waiter_lock itself is
taken then it seems that the lock itself taken.
This patch also adds a "rt_spin_try_unlock" to keep lockdep happy. If we
managed to take the wait_lock in the first place we should also be able
to take it in the unlock path.

Cc: stable-rt@vger.kernel.org
Reported-by: Mike Galbraith <bitbucket@online.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/spinlock_rt.h |  1 +
 kernel/rtmutex.c            | 31 +++++++++++++++++++++++++++----
 kernel/timer.c              |  2 +-
 3 files changed, 29 insertions(+), 5 deletions(-)

diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h
index 0618387..b3c504b 100644
--- a/include/linux/spinlock_rt.h
+++ b/include/linux/spinlock_rt.h
@@ -22,6 +22,7 @@ extern void __lockfunc rt_spin_lock(spinlock_t *lock);
 extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock);
 extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass);
 extern void __lockfunc rt_spin_unlock(spinlock_t *lock);
+extern void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock);
 extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock);
 extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags);
 extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock);
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 5d76634..0a64a90 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -802,10 +802,8 @@ static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
 /*
  * Slow path to release a rt_mutex spin_lock style
  */
-static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
+static void __sched __rt_spin_lock_slowunlock(struct rt_mutex *lock)
 {
-	raw_spin_lock(&lock->wait_lock);
-
 	debug_rt_mutex_unlock(lock);
 
 	rt_mutex_deadlock_account_unlock(current);
@@ -824,6 +822,23 @@ static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
 	rt_mutex_adjust_prio(current);
 }
 
+static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
+{
+	raw_spin_lock(&lock->wait_lock);
+	__rt_spin_lock_slowunlock(lock);
+}
+
+static void  noinline __sched rt_spin_lock_slowunlock_hirq(struct rt_mutex *lock)
+{
+	int ret;
+
+	do {
+		ret = raw_spin_trylock(&lock->wait_lock);
+	} while (!ret);
+
+	__rt_spin_lock_slowunlock(lock);
+}
+
 void __lockfunc rt_spin_lock(spinlock_t *lock)
 {
 	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
@@ -854,6 +869,13 @@ void __lockfunc rt_spin_unlock(spinlock_t *lock)
 }
 EXPORT_SYMBOL(rt_spin_unlock);
 
+void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock)
+{
+	/* NOTE: we always pass in '1' for nested, for simplicity */
+	spin_release(&lock->dep_map, 1, _RET_IP_);
+	rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_hirq);
+}
+
 void __lockfunc __rt_spin_unlock(struct rt_mutex *lock)
 {
 	rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock);
@@ -1057,7 +1079,8 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
 {
 	int ret = 0;
 
-	raw_spin_lock(&lock->wait_lock);
+	if (!raw_spin_trylock(&lock->wait_lock))
+		return ret;
 	init_lists(lock);
 
 	if (likely(rt_mutex_owner(lock) != current)) {
diff --git a/kernel/timer.c b/kernel/timer.c
index f53f592..48652cc 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1400,7 +1400,7 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 		expires = base->next_timer;
 	}
 #ifdef CONFIG_PREEMPT_RT_FULL
-	rt_spin_unlock(&base->lock);
+	rt_spin_unlock_after_trylock_in_irq(&base->lock);
 #else
 	spin_unlock(&base->lock);
 #endif
-- 
1.8.4.3

[PATCH RT 0/5] Linux 3.8.13.13-rt26-rc1

[Steven Rostedt]

Dear RT Folks,

This is the RT stable review cycle of patch 3.8.13.13-rt26-rc1.

Please scream at me if I messed something up. Please test the patches too.

The -rc release will be uploaded to kernel.org and will be deleted when
the final release is out. This is just a review release (or release candidate).

The pre-releases will not be pushed to the git repository, only the
final release is.

If all goes well, this patch will be converted to the next main release
on 12/13/2013.

Enjoy,

-- Steve


To build 3.8.13.13-rt26-rc1 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.8.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.8.13.13.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.8/patch-3.8.13.13-rt26-rc1.patch.xz

You can also build from 3.8.13.13-rt25 by applying the incremental patch:

http://www.kernel.org/pub/linux/kernel/projects/rt/3.8/incr/patch-3.8.13.13-rt25-rt26-rc1.patch.xz


Changes from 3.8.13.13-rt25:

---


Peter Zijlstra (1):
      lockdep: Correctly annotate hardirq context in irq_exit()

Sebastian Andrzej Siewior (2):
      a few open coded completions
      rtmutex: use a trylock for waiter lock in trylock

Steven Rostedt (Red Hat) (1):
      Linux 3.8.13.13-rt26-rc1

Tiejun Chen (1):
      cpu_down: move migrate_enable() back

----
 drivers/net/wireless/orinoco/orinoco_usb.c |  2 +-
 drivers/usb/gadget/f_fs.c                  |  2 +-
 drivers/usb/gadget/inode.c                 |  4 +--
 include/linux/netdevice.h                  |  2 +-
 include/linux/spinlock_rt.h                |  1 +
 kernel/cpu.c                               |  2 +-
 kernel/rtmutex.c                           | 31 +++++++++++++++++---
 kernel/softirq.c                           | 45 ++++++++++++++++++++++++++++--
 kernel/timer.c                             |  2 +-
 localversion-rt                            |  2 +-
 10 files changed, 78 insertions(+), 15 deletions(-)

[PATCH RT 1/5] cpu_down: move migrate_enable() back

[Steven Rostedt]

[-- Attachment #1: 0001-cpu_down-move-migrate_enable-back.patch --]
[-- Type: text/plain, Size: 1634 bytes --]

3.8.13.13-rt26-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Tiejun Chen <tiejun.chen@windriver.com>

Commit 08c1ab68, "hotplug-use-migrate-disable.patch", intends to
use migrate_enable()/migrate_disable() to replace that combination
of preempt_enable() and preempt_disable(), but actually in
!CONFIG_PREEMPT_RT_FULL case, migrate_enable()/migrate_disable()
are still equal to preempt_enable()/preempt_disable(). So that
followed cpu_hotplug_begin()/cpu_unplug_begin(cpu) would go schedule()
to trigger schedule_debug() like this:

_cpu_down()
	|
	+ migrate_disable() = preempt_disable()
	|
	+ cpu_hotplug_begin() or cpu_unplug_begin()
		|
		+ schedule()
			|
			+ __schedule()
				|
				+ preempt_disable();
				|
				+ __schedule_bug() is true!

So we should move migrate_enable() as the original scheme.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Tiejun Chen <tiejun.chen@windriver.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/cpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 98f2ea3..da6e128 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -594,6 +594,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 		err = -EBUSY;
 		goto restore_cpus;
 	}
+	migrate_enable();
 
 	cpu_hotplug_begin();
 	err = cpu_unplug_begin(cpu);
@@ -647,7 +648,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 out_release:
 	cpu_unplug_done(cpu);
 out_cancel:
-	migrate_enable();
 	cpu_hotplug_done();
 	if (!err)
 		cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);
-- 
1.8.4.3

[PATCH RT 2/5] a few open coded completions

[Steven Rostedt]

[-- Attachment #1: 0002-a-few-open-coded-completions.patch --]
[-- Type: text/plain, Size: 3027 bytes --]

3.8.13.13-rt26-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Cc: stable-rt@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 drivers/net/wireless/orinoco/orinoco_usb.c | 2 +-
 drivers/usb/gadget/f_fs.c                  | 2 +-
 drivers/usb/gadget/inode.c                 | 4 ++--
 include/linux/netdevice.h                  | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/orinoco/orinoco_usb.c b/drivers/net/wireless/orinoco/orinoco_usb.c
index 01624dc..b0f9d2c 100644
--- a/drivers/net/wireless/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/orinoco/orinoco_usb.c
@@ -714,7 +714,7 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv,
 			while (!ctx->done.done && msecs--)
 				udelay(1000);
 		} else {
-			wait_event_interruptible(ctx->done.wait,
+			swait_event_interruptible(ctx->done.wait,
 						 ctx->done.done);
 		}
 		break;
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index de3e266..5b2a068 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -1284,7 +1284,7 @@ static void ffs_data_put(struct ffs_data *ffs)
 		pr_info("%s(): freeing\n", __func__);
 		ffs_data_clear(ffs);
 		BUG_ON(waitqueue_active(&ffs->ev.waitq) ||
-		       waitqueue_active(&ffs->ep0req_completion.wait));
+		       swaitqueue_active(&ffs->ep0req_completion.wait));
 		kfree(ffs->dev_name);
 		kfree(ffs);
 	}
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index 8ac840f..fe85df7 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -338,7 +338,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
 	spin_unlock_irq (&epdata->dev->lock);
 
 	if (likely (value == 0)) {
-		value = wait_event_interruptible (done.wait, done.done);
+		value = swait_event_interruptible (done.wait, done.done);
 		if (value != 0) {
 			spin_lock_irq (&epdata->dev->lock);
 			if (likely (epdata->ep != NULL)) {
@@ -347,7 +347,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
 				usb_ep_dequeue (epdata->ep, epdata->req);
 				spin_unlock_irq (&epdata->dev->lock);
 
-				wait_event (done.wait, done.done);
+				swait_event (done.wait, done.done);
 				if (epdata->status == -ECONNRESET)
 					epdata->status = -EINTR;
 			} else {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0b58fd6..bc45789 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1123,7 +1123,7 @@ struct net_device {
 	unsigned char		perm_addr[MAX_ADDR_LEN]; /* permanent hw address */
 	unsigned char		addr_assign_type; /* hw address assignment type */
 	unsigned char		addr_len;	/* hardware address length	*/
-	unsigned char		neigh_priv_len;
+	unsigned short		neigh_priv_len;
 	unsigned short          dev_id;		/* for shared network cards */
 
 	spinlock_t		addr_list_lock;
-- 
1.8.4.3

[PATCH RT 3/5] lockdep: Correctly annotate hardirq context in irq_exit()

[Steven Rostedt]

[-- Attachment #1: 0003-lockdep-Correctly-annotate-hardirq-context-in-irq_ex.patch --]
[-- Type: text/plain, Size: 4208 bytes --]

3.8.13.13-rt26-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Peter Zijlstra <peterz@infradead.org>

There was a reported deadlock on -rt which lockdep didn't report.

It turns out that in irq_exit() we tell lockdep that the hardirq
context ends and then do all kinds of locking afterwards.

To fix it, move trace_hardirq_exit() to the very end of irq_exit(), this
ensures all locking in tick_irq_exit() and rcu_irq_exit() are properly
recorded as happening from hardirq context.

This however leads to the 'fun' little problem of running softirqs
while in hardirq context. To cure this make the softirq code a little
more complex (in the CONFIG_TRACE_IRQFLAGS case).

Due to stack swizzling arch dependent trickery we cannot pass an
argument to __do_softirq() to tell it if it was done from hardirq
context or not; so use a side-band argument.

When we do __do_softirq() from hardirq context, 'atomically' flip to
softirq context and back, so that no locking goes without being in
either hard- or soft-irq context.

I didn't find any new problems in mainline using this patch, but it
did show the -rt problem.

Cc: stable-rt@vger.kernel.org
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-dgwc5cdksbn0jk09vbmcc9sa@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 kernel/softirq.c | 45 ++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 42 insertions(+), 3 deletions(-)

diff --git a/kernel/softirq.c b/kernel/softirq.c
index 8447c8d..42b121f 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -350,6 +350,44 @@ EXPORT_SYMBOL(local_bh_enable_ip);
  */
 #define MAX_SOFTIRQ_RESTART 10
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * Convoluted means of passing __do_softirq() a message through the various
+ * architecture execute_on_stack() bits.
+ *
+ * When we run softirqs from irq_exit() and thus on the hardirq stack we need
+ * to keep the lockdep irq context tracking as tight as possible in order to
+ * not miss-qualify lock contexts and miss possible deadlocks.
+ */
+static DEFINE_PER_CPU(int, softirq_from_hardirq);
+
+static inline void lockdep_softirq_from_hardirq(void)
+{
+	this_cpu_write(softirq_from_hardirq, 1);
+}
+
+static inline void lockdep_softirq_start(void)
+{
+	if (this_cpu_read(softirq_from_hardirq))
+		trace_hardirq_exit();
+	lockdep_softirq_enter();
+}
+
+static inline void lockdep_softirq_end(void)
+{
+	lockdep_softirq_exit();
+	if (this_cpu_read(softirq_from_hardirq)) {
+		this_cpu_write(softirq_from_hardirq, 0);
+		trace_hardirq_enter();
+	}
+}
+
+#else
+static inline void lockdep_softirq_from_hardirq(void) { }
+static inline void lockdep_softirq_start(void) { }
+static inline void lockdep_softirq_end(void) { }
+#endif
+
 asmlinkage void __do_softirq(void)
 {
 	__u32 pending;
@@ -369,7 +407,7 @@ asmlinkage void __do_softirq(void)
 
 	__local_bh_disable((unsigned long)__builtin_return_address(0),
 			   SOFTIRQ_OFFSET);
-	lockdep_softirq_enter();
+	lockdep_softirq_start();
 
 	cpu = smp_processor_id();
 restart:
@@ -385,7 +423,7 @@ restart:
 	if (pending)
 		wakeup_softirqd();
 
-	lockdep_softirq_exit();
+	lockdep_softirq_end();
 
 	vtime_account_irq_exit(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
@@ -692,6 +730,7 @@ static inline void invoke_softirq(void)
 {
 #ifndef CONFIG_PREEMPT_RT_FULL
 	if (!force_irqthreads) {
+		lockdep_softirq_from_hardirq();
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
 		__do_softirq();
 #else
@@ -720,7 +759,6 @@ static inline void invoke_softirq(void)
 void irq_exit(void)
 {
 	vtime_account_irq_exit(current);
-	trace_hardirq_exit();
 	sub_preempt_count(IRQ_EXIT_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
@@ -731,6 +769,7 @@ void irq_exit(void)
 		tick_nohz_irq_exit();
 #endif
 	rcu_irq_exit();
+	trace_hardirq_exit(); /* must be last! */
 	sched_preempt_enable_no_resched();
 }
 
-- 
1.8.4.3

[PATCH RT 4/5] rtmutex: use a trylock for waiter lock in trylock

[Steven Rostedt]

[-- Attachment #1: 0004-rtmutex-use-a-trylock-for-waiter-lock-in-trylock.patch --]
[-- Type: text/plain, Size: 5034 bytes --]

3.8.13.13-rt26-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Mike Galbraith captered the following:
| >#11 [ffff88017b243e90] _raw_spin_lock at ffffffff815d2596
| >#12 [ffff88017b243e90] rt_mutex_trylock at ffffffff815d15be
| >#13 [ffff88017b243eb0] get_next_timer_interrupt at ffffffff81063b42
| >#14 [ffff88017b243f00] tick_nohz_stop_sched_tick at ffffffff810bd1fd
| >#15 [ffff88017b243f70] tick_nohz_irq_exit at ffffffff810bd7d2
| >#16 [ffff88017b243f90] irq_exit at ffffffff8105b02d
| >#17 [ffff88017b243fb0] reschedule_interrupt at ffffffff815db3dd
| >--- <IRQ stack> ---
| >#18 [ffff88017a2a9bc8] reschedule_interrupt at ffffffff815db3dd
| >    [exception RIP: task_blocks_on_rt_mutex+51]
| >#19 [ffff88017a2a9ce0] rt_spin_lock_slowlock at ffffffff815d183c
| >#20 [ffff88017a2a9da0] lock_timer_base.isra.35 at ffffffff81061cbf
| >#21 [ffff88017a2a9dd0] schedule_timeout at ffffffff815cf1ce
| >#22 [ffff88017a2a9e50] rcu_gp_kthread at ffffffff810f9bbb
| >#23 [ffff88017a2a9ed0] kthread at ffffffff810796d5
| >#24 [ffff88017a2a9f50] ret_from_fork at ffffffff815da04c

lock_timer_base() does a try_lock() which deadlocks on the waiter lock
not the lock itself.
This patch takes the waiter_lock with trylock so it should work from interrupt
context as well. If the fastpath doesn't work and the waiter_lock itself is
taken then it seems that the lock itself taken.
This patch also adds a "rt_spin_try_unlock" to keep lockdep happy. If we
managed to take the wait_lock in the first place we should also be able
to take it in the unlock path.

Cc: stable-rt@vger.kernel.org
Reported-by: Mike Galbraith <bitbucket@online.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/spinlock_rt.h |  1 +
 kernel/rtmutex.c            | 31 +++++++++++++++++++++++++++----
 kernel/timer.c              |  2 +-
 3 files changed, 29 insertions(+), 5 deletions(-)

diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h
index 0618387..b3c504b 100644
--- a/include/linux/spinlock_rt.h
+++ b/include/linux/spinlock_rt.h
@@ -22,6 +22,7 @@ extern void __lockfunc rt_spin_lock(spinlock_t *lock);
 extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock);
 extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass);
 extern void __lockfunc rt_spin_unlock(spinlock_t *lock);
+extern void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock);
 extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock);
 extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags);
 extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock);
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 20742e7..3825e1c 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -801,10 +801,8 @@ static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
 /*
  * Slow path to release a rt_mutex spin_lock style
  */
-static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
+static void __sched __rt_spin_lock_slowunlock(struct rt_mutex *lock)
 {
-	raw_spin_lock(&lock->wait_lock);
-
 	debug_rt_mutex_unlock(lock);
 
 	rt_mutex_deadlock_account_unlock(current);
@@ -823,6 +821,23 @@ static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
 	rt_mutex_adjust_prio(current);
 }
 
+static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
+{
+	raw_spin_lock(&lock->wait_lock);
+	__rt_spin_lock_slowunlock(lock);
+}
+
+static void  noinline __sched rt_spin_lock_slowunlock_hirq(struct rt_mutex *lock)
+{
+	int ret;
+
+	do {
+		ret = raw_spin_trylock(&lock->wait_lock);
+	} while (!ret);
+
+	__rt_spin_lock_slowunlock(lock);
+}
+
 void __lockfunc rt_spin_lock(spinlock_t *lock)
 {
 	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
@@ -853,6 +868,13 @@ void __lockfunc rt_spin_unlock(spinlock_t *lock)
 }
 EXPORT_SYMBOL(rt_spin_unlock);
 
+void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock)
+{
+	/* NOTE: we always pass in '1' for nested, for simplicity */
+	spin_release(&lock->dep_map, 1, _RET_IP_);
+	rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_hirq);
+}
+
 void __lockfunc __rt_spin_unlock(struct rt_mutex *lock)
 {
 	rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock);
@@ -1056,7 +1078,8 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
 {
 	int ret = 0;
 
-	raw_spin_lock(&lock->wait_lock);
+	if (!raw_spin_trylock(&lock->wait_lock))
+		return ret;
 	init_lists(lock);
 
 	if (likely(rt_mutex_owner(lock) != current)) {
diff --git a/kernel/timer.c b/kernel/timer.c
index 3bb957e..330221b 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1398,7 +1398,7 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 		expires = base->next_timer;
 	}
 #ifdef CONFIG_PREEMPT_RT_FULL
-	rt_spin_unlock(&base->lock);
+	rt_spin_unlock_after_trylock_in_irq(&base->lock);
 #else
 	spin_unlock(&base->lock);
 #endif
-- 
1.8.4.3

[PATCH RT 5/5] Linux 3.8.13.13-rt26-rc1

[Steven Rostedt]

[-- Attachment #1: 0005-Linux-3.8.13.13-rt26-rc1.patch --]
[-- Type: text/plain, Size: 406 bytes --]

3.8.13.13-rt26-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

---
 localversion-rt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/localversion-rt b/localversion-rt
index c5b71f9..02556f4 100644
--- a/localversion-rt
+++ b/localversion-rt
@@ -1 +1 @@
--rt25
+-rt26-rc1
-- 
1.8.4.3

[PATCH RT 4/5] rtmutex: use a trylock for waiter lock in trylock

[Steven Rostedt]

[-- Attachment #1: 0004-rtmutex-use-a-trylock-for-waiter-lock-in-trylock.patch --]
[-- Type: text/plain, Size: 5105 bytes --]

3.4.72-rt90-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Mike Galbraith captered the following:
| >#11 [ffff88017b243e90] _raw_spin_lock at ffffffff815d2596
| >#12 [ffff88017b243e90] rt_mutex_trylock at ffffffff815d15be
| >#13 [ffff88017b243eb0] get_next_timer_interrupt at ffffffff81063b42
| >#14 [ffff88017b243f00] tick_nohz_stop_sched_tick at ffffffff810bd1fd
| >#15 [ffff88017b243f70] tick_nohz_irq_exit at ffffffff810bd7d2
| >#16 [ffff88017b243f90] irq_exit at ffffffff8105b02d
| >#17 [ffff88017b243fb0] reschedule_interrupt at ffffffff815db3dd
| >--- <IRQ stack> ---
| >#18 [ffff88017a2a9bc8] reschedule_interrupt at ffffffff815db3dd
| >    [exception RIP: task_blocks_on_rt_mutex+51]
| >#19 [ffff88017a2a9ce0] rt_spin_lock_slowlock at ffffffff815d183c
| >#20 [ffff88017a2a9da0] lock_timer_base.isra.35 at ffffffff81061cbf
| >#21 [ffff88017a2a9dd0] schedule_timeout at ffffffff815cf1ce
| >#22 [ffff88017a2a9e50] rcu_gp_kthread at ffffffff810f9bbb
| >#23 [ffff88017a2a9ed0] kthread at ffffffff810796d5
| >#24 [ffff88017a2a9f50] ret_from_fork at ffffffff815da04c

lock_timer_base() does a try_lock() which deadlocks on the waiter lock
not the lock itself.
This patch takes the waiter_lock with trylock so it should work from interrupt
context as well. If the fastpath doesn't work and the waiter_lock itself is
taken then it seems that the lock itself taken.
This patch also adds a "rt_spin_try_unlock" to keep lockdep happy. If we
managed to take the wait_lock in the first place we should also be able
to take it in the unlock path.

Cc: stable-rt@vger.kernel.org
Reported-by: Mike Galbraith <bitbucket@online.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/spinlock_rt.h |  1 +
 kernel/rtmutex.c            | 31 +++++++++++++++++++++++++++----
 kernel/timer.c              |  2 +-
 3 files changed, 29 insertions(+), 5 deletions(-)

diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h
index 0618387..b3c504b 100644
--- a/include/linux/spinlock_rt.h
+++ b/include/linux/spinlock_rt.h
@@ -22,6 +22,7 @@ extern void __lockfunc rt_spin_lock(spinlock_t *lock);
 extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock);
 extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass);
 extern void __lockfunc rt_spin_unlock(spinlock_t *lock);
+extern void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock);
 extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock);
 extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags);
 extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock);
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 20742e7..3825e1c 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -801,10 +801,8 @@ static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
 /*
  * Slow path to release a rt_mutex spin_lock style
  */
-static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
+static void __sched __rt_spin_lock_slowunlock(struct rt_mutex *lock)
 {
-	raw_spin_lock(&lock->wait_lock);
-
 	debug_rt_mutex_unlock(lock);
 
 	rt_mutex_deadlock_account_unlock(current);
@@ -823,6 +821,23 @@ static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
 	rt_mutex_adjust_prio(current);
 }
 
+static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
+{
+	raw_spin_lock(&lock->wait_lock);
+	__rt_spin_lock_slowunlock(lock);
+}
+
+static void  noinline __sched rt_spin_lock_slowunlock_hirq(struct rt_mutex *lock)
+{
+	int ret;
+
+	do {
+		ret = raw_spin_trylock(&lock->wait_lock);
+	} while (!ret);
+
+	__rt_spin_lock_slowunlock(lock);
+}
+
 void __lockfunc rt_spin_lock(spinlock_t *lock)
 {
 	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
@@ -853,6 +868,13 @@ void __lockfunc rt_spin_unlock(spinlock_t *lock)
 }
 EXPORT_SYMBOL(rt_spin_unlock);
 
+void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock)
+{
+	/* NOTE: we always pass in '1' for nested, for simplicity */
+	spin_release(&lock->dep_map, 1, _RET_IP_);
+	rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_hirq);
+}
+
 void __lockfunc __rt_spin_unlock(struct rt_mutex *lock)
 {
 	rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock);
@@ -1056,7 +1078,8 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
 {
 	int ret = 0;
 
-	raw_spin_lock(&lock->wait_lock);
+	if (!raw_spin_trylock(&lock->wait_lock))
+		return ret;
 	init_lists(lock);
 
 	if (likely(rt_mutex_owner(lock) != current)) {
diff --git a/kernel/timer.c b/kernel/timer.c
index 78f07e5..fb1c00d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1386,7 +1386,7 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 		if (time_before_eq(base->next_timer, base->timer_jiffies))
 			base->next_timer = __next_timer_interrupt(base);
 		expires = base->next_timer;
-		rt_spin_unlock(&base->lock);
+		rt_spin_unlock_after_trylock_in_irq(&base->lock);
 	} else {
 		expires = now + 1;
 	}
-- 
1.8.4.3

Re: [PATCH RT 2/5] a few open coded completions

[Steven Rostedt]

Here's the new patch for 3.8-rt.

-- Steve

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 28 Oct 2013 11:50:06 +0100
Subject: [PATCH] swait: Add a few more users

The wait-simple queue is lighter weight and more efficient than the full
wait queue, and may be used in atomic context on PREEMPT_RT.

Fix up some places that needed to call the swait_*() functions instead
of the wait_*() functions.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 drivers/net/wireless/orinoco/orinoco_usb.c | 2 +-
 drivers/usb/gadget/f_fs.c                  | 2 +-
 drivers/usb/gadget/inode.c                 | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/orinoco/orinoco_usb.c b/drivers/net/wireless/orinoco/orinoco_usb.c
index 01624dc..b0f9d2c 100644
--- a/drivers/net/wireless/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/orinoco/orinoco_usb.c
@@ -714,7 +714,7 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv,
 			while (!ctx->done.done && msecs--)
 				udelay(1000);
 		} else {
-			wait_event_interruptible(ctx->done.wait,
+			swait_event_interruptible(ctx->done.wait,
 						 ctx->done.done);
 		}
 		break;
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index de3e266..5b2a068 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -1284,7 +1284,7 @@ static void ffs_data_put(struct ffs_data *ffs)
 		pr_info("%s(): freeing\n", __func__);
 		ffs_data_clear(ffs);
 		BUG_ON(waitqueue_active(&ffs->ev.waitq) ||
-		       waitqueue_active(&ffs->ep0req_completion.wait));
+		       swaitqueue_active(&ffs->ep0req_completion.wait));
 		kfree(ffs->dev_name);
 		kfree(ffs);
 	}
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index 8ac840f..fe85df7 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -338,7 +338,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
 	spin_unlock_irq (&epdata->dev->lock);
 
 	if (likely (value == 0)) {
-		value = wait_event_interruptible (done.wait, done.done);
+		value = swait_event_interruptible (done.wait, done.done);
 		if (value != 0) {
 			spin_lock_irq (&epdata->dev->lock);
 			if (likely (epdata->ep != NULL)) {
@@ -347,7 +347,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
 				usb_ep_dequeue (epdata->ep, epdata->req);
 				spin_unlock_irq (&epdata->dev->lock);
 
-				wait_event (done.wait, done.done);
+				swait_event (done.wait, done.done);
 				if (epdata->status == -ECONNRESET)
 					epdata->status = -EINTR;
 			} else {
-- 
1.8.4.3