[PATCH RT 0/8] [ANNOUNCE] 3.2.22-rt35-rc1 stable review

[PATCH RT 0/8] [ANNOUNCE] 3.2.22-rt35-rc1 stable review

[Steven Rostedt]

Dear RT Folks,

This is the RT stable review cycle of patch 3.2.22-rt35-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 7/16/2012.

Enjoy,

-- Steve


To build 3.2.22-rt35-rc1 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.2.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.2.22.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.2/patch-3.2.22-rt35-rc1.patch.xz

You can also build from 3.2.22-rt34 by applying the incremental patch:

http://www.kernel.org/pub/linux/kernel/projects/rt/3.2/incr/patch-3.2.22-rt34-rt35-rc1.patch.xz


Changes from 3.2.22-rt34:

---


Carsten Emde (4):
      Latency histogramms: Cope with backwards running local trace clock
      Latency histograms: Adjust timer, if already elapsed when programmed
      Disable RT_GROUP_SCHED in PREEMPT_RT_FULL
      Latency histograms: Detect another yet overlooked sharedprio condition

Mike Galbraith (1):
      fs, jbd: pull your plug when waiting for space

Steven Rostedt (1):
      Linux 3.2.22-rt35-rc1

Thomas Gleixner (1):
      slab: Prevent local lock deadlock

Yong Zhang (1):
      perf: Make swevent hrtimer run in irq instead of softirq

----
 fs/jbd/checkpoint.c         |    2 ++
 include/linux/hrtimer.h     |    3 ++
 include/linux/sched.h       |    2 +-
 init/Kconfig                |    1 +
 kernel/events/core.c        |    1 +
 kernel/hrtimer.c            |   16 ++++++++--
 kernel/trace/latency_hist.c |   74 +++++++++++++++++++++++--------------------
 localversion-rt             |    2 +-
 mm/slab.c                   |   26 ++++++++++++---
 9 files changed, 85 insertions(+), 42 deletions(-)

[PATCH RT 1/8] Latency histogramms: Cope with backwards running local trace clock

[Steven Rostedt]

[-- Attachment #1: 0001-Latency-histogramms-Cope-with-backwards-running-loca.patch --]
[-- Type: text/plain, Size: 9414 bytes --]

From: Carsten Emde <C.Emde@osadl.org>

Thanks to the wonders of modern technology, the local trace clock can
now run backwards. Since this never happened before, the time difference
between now and somewhat earlier was expected to never become negative
and, thus, stored in an unsigned integer variable. Nowadays, we need a
signed integer to ensure that the value is stored as underflow in the
related histogram. (In cases where this is not a misfunction, bipolar
histograms can be used.)

This patch takes care that all latency variables are represented as
signed integers and negative numbers are considered as histogram
underflows.

In one of the misbehaving processors switching to global clock solved
the problem:
  echo global >/sys/kernel/debug/tracing/trace_clock

Signed-off-by: Carsten Emde <C.Emde@osadl.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/sched.h       |    2 +-
 kernel/trace/latency_hist.c |   71 ++++++++++++++++++++++---------------------
 2 files changed, 38 insertions(+), 35 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1f6b11a..0174e3a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1585,7 +1585,7 @@ struct task_struct {
 #ifdef CONFIG_WAKEUP_LATENCY_HIST
 	u64 preempt_timestamp_hist;
 #ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
-	unsigned long timer_offset;
+	long timer_offset;
 #endif
 #endif
 #endif /* CONFIG_TRACING */
diff --git a/kernel/trace/latency_hist.c b/kernel/trace/latency_hist.c
index 9d49fcb..d514eef 100644
--- a/kernel/trace/latency_hist.c
+++ b/kernel/trace/latency_hist.c
@@ -27,6 +27,8 @@
 #include "trace.h"
 #include <trace/events/sched.h>
 
+#define NSECS_PER_USECS 1000L
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/hist.h>
 
@@ -46,11 +48,11 @@ enum {
 struct hist_data {
 	atomic_t hist_mode; /* 0 log, 1 don't log */
 	long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */
-	unsigned long min_lat;
-	unsigned long max_lat;
+	long min_lat;
+	long max_lat;
 	unsigned long long below_hist_bound_samples;
 	unsigned long long above_hist_bound_samples;
-	unsigned long long accumulate_lat;
+	long long accumulate_lat;
 	unsigned long long total_samples;
 	unsigned long long hist_array[MAX_ENTRY_NUM];
 };
@@ -152,8 +154,8 @@ static struct enable_data timerandwakeup_enabled_data = {
 static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc);
 #endif
 
-void notrace latency_hist(int latency_type, int cpu, unsigned long latency,
-			  unsigned long timeroffset, cycle_t stop,
+void notrace latency_hist(int latency_type, int cpu, long latency,
+			  long timeroffset, cycle_t stop,
 			  struct task_struct *p)
 {
 	struct hist_data *my_hist;
@@ -224,7 +226,7 @@ void notrace latency_hist(int latency_type, int cpu, unsigned long latency,
 		my_hist->hist_array[latency]++;
 
 	if (unlikely(latency > my_hist->max_lat ||
-	    my_hist->min_lat == ULONG_MAX)) {
+	    my_hist->min_lat == LONG_MAX)) {
 #if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
     defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
 		if (latency_type == WAKEUP_LATENCY ||
@@ -263,15 +265,14 @@ static void *l_start(struct seq_file *m, loff_t *pos)
 		atomic_dec(&my_hist->hist_mode);
 
 		if (likely(my_hist->total_samples)) {
-			unsigned long avg = (unsigned long)
-			    div64_u64(my_hist->accumulate_lat,
+			long avg = (long) div64_s64(my_hist->accumulate_lat,
 			    my_hist->total_samples);
 			snprintf(minstr, sizeof(minstr), "%ld",
-			    (long) my_hist->min_lat - my_hist->offset);
+			    my_hist->min_lat - my_hist->offset);
 			snprintf(avgstr, sizeof(avgstr), "%ld",
-			    (long) avg - my_hist->offset);
+			    avg - my_hist->offset);
 			snprintf(maxstr, sizeof(maxstr), "%ld",
-			    (long) my_hist->max_lat - my_hist->offset);
+			    my_hist->max_lat - my_hist->offset);
 		} else {
 			strcpy(minstr, "<undef>");
 			strcpy(avgstr, minstr);
@@ -376,10 +377,10 @@ static void hist_reset(struct hist_data *hist)
 	memset(hist->hist_array, 0, sizeof(hist->hist_array));
 	hist->below_hist_bound_samples = 0ULL;
 	hist->above_hist_bound_samples = 0ULL;
-	hist->min_lat = ULONG_MAX;
-	hist->max_lat = 0UL;
+	hist->min_lat = LONG_MAX;
+	hist->max_lat = LONG_MIN;
 	hist->total_samples = 0ULL;
-	hist->accumulate_lat = 0ULL;
+	hist->accumulate_lat = 0LL;
 
 	atomic_inc(&hist->hist_mode);
 }
@@ -790,9 +791,9 @@ static notrace void probe_preemptirqsoff_hist(void *v, int reason,
 
 			stop = ftrace_now(cpu);
 			time_set++;
-			if (start && stop >= start) {
-				unsigned long latency =
-				    nsecs_to_usecs(stop - start);
+			if (start) {
+				long latency = ((long) (stop - start)) /
+				    NSECS_PER_USECS;
 
 				latency_hist(IRQSOFF_LATENCY, cpu, latency, 0,
 				    stop, NULL);
@@ -808,9 +809,9 @@ static notrace void probe_preemptirqsoff_hist(void *v, int reason,
 
 			if (!(time_set++))
 				stop = ftrace_now(cpu);
-			if (start && stop >= start) {
-				unsigned long latency =
-				    nsecs_to_usecs(stop - start);
+			if (start) {
+				long latency = ((long) (stop - start)) /
+				    NSECS_PER_USECS;
 
 				latency_hist(PREEMPTOFF_LATENCY, cpu, latency,
 				    0, stop, NULL);
@@ -827,9 +828,10 @@ static notrace void probe_preemptirqsoff_hist(void *v, int reason,
 
 			if (!time_set)
 				stop = ftrace_now(cpu);
-			if (start && stop >= start) {
-				unsigned long latency =
-				    nsecs_to_usecs(stop - start);
+			if (start) {
+				long latency = ((long) (stop - start)) /
+				    NSECS_PER_USECS;
+
 				latency_hist(PREEMPTIRQSOFF_LATENCY, cpu,
 				    latency, 0, stop, NULL);
 			}
@@ -908,7 +910,7 @@ static notrace void probe_wakeup_latency_hist_stop(void *v,
 {
 	unsigned long flags;
 	int cpu = task_cpu(next);
-	unsigned long latency;
+	long latency;
 	cycle_t stop;
 	struct task_struct *cpu_wakeup_task;
 
@@ -939,7 +941,8 @@ static notrace void probe_wakeup_latency_hist_stop(void *v,
 	 */
 	stop = ftrace_now(raw_smp_processor_id());
 
-	latency = nsecs_to_usecs(stop - next->preempt_timestamp_hist);
+	latency = ((long) (stop - next->preempt_timestamp_hist)) /
+	    NSECS_PER_USECS;
 
 	if (per_cpu(wakeup_sharedprio, cpu)) {
 		latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop,
@@ -975,7 +978,7 @@ static notrace void probe_hrtimer_interrupt(void *v, int cpu,
 	    (task->prio < curr->prio ||
 	    (task->prio == curr->prio &&
 	    !cpumask_test_cpu(cpu, &task->cpus_allowed)))) {
-		unsigned long latency;
+		long latency;
 		cycle_t now;
 
 		if (missed_timer_offsets_pid) {
@@ -985,7 +988,7 @@ static notrace void probe_hrtimer_interrupt(void *v, int cpu,
 		}
 
 		now = ftrace_now(cpu);
-		latency = (unsigned long) div_s64(-latency_ns, 1000);
+		latency = (long) div_s64(-latency_ns, NSECS_PER_USECS);
 		latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now,
 		    task);
 #ifdef CONFIG_WAKEUP_LATENCY_HIST
@@ -1026,7 +1029,7 @@ static __init int latency_hist_init(void)
 		    &per_cpu(irqsoff_hist, i), &latency_hist_fops);
 		my_hist = &per_cpu(irqsoff_hist, i);
 		atomic_set(&my_hist->hist_mode, 1);
-		my_hist->min_lat = 0xFFFFFFFFUL;
+		my_hist->min_lat = LONG_MAX;
 	}
 	entry = debugfs_create_file("reset", 0644, dentry,
 	    (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops);
@@ -1041,7 +1044,7 @@ static __init int latency_hist_init(void)
 		    &per_cpu(preemptoff_hist, i), &latency_hist_fops);
 		my_hist = &per_cpu(preemptoff_hist, i);
 		atomic_set(&my_hist->hist_mode, 1);
-		my_hist->min_lat = 0xFFFFFFFFUL;
+		my_hist->min_lat = LONG_MAX;
 	}
 	entry = debugfs_create_file("reset", 0644, dentry,
 	    (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops);
@@ -1056,7 +1059,7 @@ static __init int latency_hist_init(void)
 		    &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops);
 		my_hist = &per_cpu(preemptirqsoff_hist, i);
 		atomic_set(&my_hist->hist_mode, 1);
-		my_hist->min_lat = 0xFFFFFFFFUL;
+		my_hist->min_lat = LONG_MAX;
 	}
 	entry = debugfs_create_file("reset", 0644, dentry,
 	    (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops);
@@ -1081,14 +1084,14 @@ static __init int latency_hist_init(void)
 		    &latency_hist_fops);
 		my_hist = &per_cpu(wakeup_latency_hist, i);
 		atomic_set(&my_hist->hist_mode, 1);
-		my_hist->min_lat = 0xFFFFFFFFUL;
+		my_hist->min_lat = LONG_MAX;
 
 		entry = debugfs_create_file(name, 0444, dentry_sharedprio,
 		    &per_cpu(wakeup_latency_hist_sharedprio, i),
 		    &latency_hist_fops);
 		my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i);
 		atomic_set(&my_hist->hist_mode, 1);
-		my_hist->min_lat = 0xFFFFFFFFUL;
+		my_hist->min_lat = LONG_MAX;
 
 		sprintf(name, cpufmt_maxlatproc, i);
 
@@ -1122,7 +1125,7 @@ static __init int latency_hist_init(void)
 		    &per_cpu(missed_timer_offsets, i), &latency_hist_fops);
 		my_hist = &per_cpu(missed_timer_offsets, i);
 		atomic_set(&my_hist->hist_mode, 1);
-		my_hist->min_lat = 0xFFFFFFFFUL;
+		my_hist->min_lat = LONG_MAX;
 
 		sprintf(name, cpufmt_maxlatproc, i);
 		mp = &per_cpu(missed_timer_offsets_maxlatproc, i);
@@ -1150,7 +1153,7 @@ static __init int latency_hist_init(void)
 		    &latency_hist_fops);
 		my_hist = &per_cpu(timerandwakeup_latency_hist, i);
 		atomic_set(&my_hist->hist_mode, 1);
-		my_hist->min_lat = 0xFFFFFFFFUL;
+		my_hist->min_lat = LONG_MAX;
 
 		sprintf(name, cpufmt_maxlatproc, i);
 		mp = &per_cpu(timerandwakeup_maxlatproc, i);
-- 
1.7.10.4

[PATCH RT 2/8] Latency histograms: Adjust timer, if already elapsed when programmed

[Steven Rostedt]

[-- Attachment #1: 0002-Latency-histograms-Adjust-timer-if-already-elapsed-w.patch --]
[-- Type: text/plain, Size: 2131 bytes --]

From: Carsten Emde <C.Emde@osadl.org>

Nothing prevents a programmer from calling clock_nanosleep() with an
already elapsed wakeup time in absolute time mode or with a too small
delay in relative time mode. Such timers cannot wake up in time and,
thus, should be corrected when entered into the missed timers latency
histogram (CONFIG_MISSED_TIMERS_HIST).

This patch marks such timers and uses a corrected expiration time.

Signed-off-by: Carsten Emde <C.Emde@osadl.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/hrtimer.h |    3 +++
 kernel/hrtimer.c        |   16 ++++++++++++++--
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 0e37086..7408760 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -113,6 +113,9 @@ struct hrtimer {
 	unsigned long			state;
 	struct list_head		cb_entry;
 	int				irqsafe;
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	ktime_t 			praecox;
+#endif
 #ifdef CONFIG_TIMER_STATS
 	int				start_pid;
 	void				*start_site;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 3991464..a080e62 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1021,6 +1021,17 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 #endif
 	}
 
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	{
+		ktime_t now = new_base->get_time();
+
+		if (ktime_to_ns(tim) < ktime_to_ns(now))
+			timer->praecox = now;
+		else
+			timer->praecox = ktime_set(0, 0);
+	}
+#endif
+
 	hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
 	timer_stats_hrtimer_set_start_info(timer);
@@ -1458,8 +1469,9 @@ retry:
 			timer = container_of(node, struct hrtimer, node);
 
 			trace_hrtimer_interrupt(raw_smp_processor_id(),
-			    ktime_to_ns(ktime_sub(
-				hrtimer_get_expires(timer), basenow)),
+			    ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ?
+				timer->praecox : hrtimer_get_expires(timer),
+				basenow)),
 			    current,
 			    timer->function == hrtimer_wakeup ?
 			    container_of(timer, struct hrtimer_sleeper,
-- 
1.7.10.4

[PATCH RT 3/8] Disable RT_GROUP_SCHED in PREEMPT_RT_FULL

[Steven Rostedt]

[-- Attachment #1: 0003-Disable-RT_GROUP_SCHED-in-PREEMPT_RT_FULL.patch --]
[-- Type: text/plain, Size: 728 bytes --]

From: Carsten Emde <C.Emde@osadl.org>

Strange CPU stalls have been observed in RT when RT_GROUP_SCHED
was configured.

Disable it for now.

Signed-off-by: Carsten Emde <C.Emde@osadl.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 init/Kconfig |    1 +
 1 file changed, 1 insertion(+)

diff --git a/init/Kconfig b/init/Kconfig
index dbc82d0..720c182 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -731,6 +731,7 @@ config RT_GROUP_SCHED
 	bool "Group scheduling for SCHED_RR/FIFO"
 	depends on EXPERIMENTAL
 	depends on CGROUP_SCHED
+	depends on !PREEMPT_RT_FULL
 	default n
 	help
 	  This feature lets you explicitly allocate real CPU bandwidth
-- 
1.7.10.4

[PATCH RT 4/8] Latency histograms: Detect another yet overlooked sharedprio condition

[Steven Rostedt]

[-- Attachment #1: 0004-Latency-histograms-Detect-another-yet-overlooked-sha.patch --]
[-- Type: text/plain, Size: 1161 bytes --]

From: Carsten Emde <C.Emde@osadl.org>

While waiting for an RT process to be woken up, the previous process may
go to wait and switch to another one with the same priority which then
becomes current. This condition was not correctly recognized and led to
erroneously high latency recordings during periods of low CPU load.

This patch correctly marks such latencies as sharedprio and prevents
them from being recorded as actual system latency.

Signed-off-by: Carsten Emde <C.Emde@osadl.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/latency_hist.c |    3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/trace/latency_hist.c b/kernel/trace/latency_hist.c
index d514eef..6a4c869 100644
--- a/kernel/trace/latency_hist.c
+++ b/kernel/trace/latency_hist.c
@@ -935,6 +935,9 @@ static notrace void probe_wakeup_latency_hist_stop(void *v,
 		goto out;
 	}
 
+	if (current->prio == cpu_wakeup_task->prio)
+		per_cpu(wakeup_sharedprio, cpu) = 1;
+
 	/*
 	 * The task we are waiting for is about to be switched to.
 	 * Calculate latency and store it in histogram.
-- 
1.7.10.4

[PATCH RT 5/8] slab: Prevent local lock deadlock

[Steven Rostedt]

[-- Attachment #1: 0005-slab-Prevent-local-lock-deadlock.patch --]
[-- Type: text/plain, Size: 2000 bytes --]

From: Thomas Gleixner <tglx@linutronix.de>

On RT we avoid the cross cpu function calls and take the per cpu local
locks instead. Now the code missed that taking the local lock on the
cpu which runs the code must use the proper local lock functions and
not a simple spin_lock(). Otherwise it deadlocks later when trying to
acquire the local lock with the proper function.

Reported-and-tested-by: Chris Pringle <chris.pringle@miranda.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 mm/slab.c |   26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/mm/slab.c b/mm/slab.c
index 5f0c5ef..3bef5e5 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -739,8 +739,26 @@ slab_on_each_cpu(void (*func)(void *arg, int this_cpu), void *arg)
 {
 	unsigned int i;
 
+	get_cpu_light();
 	for_each_online_cpu(i)
 		func(arg, i);
+	put_cpu_light();
+}
+
+static void lock_slab_on(unsigned int cpu)
+{
+	if (cpu == smp_processor_id())
+		local_lock_irq(slab_lock);
+	else
+		local_spin_lock_irq(slab_lock, &per_cpu(slab_lock, cpu).lock);
+}
+
+static void unlock_slab_on(unsigned int cpu)
+{
+	if (cpu == smp_processor_id())
+		local_unlock_irq(slab_lock);
+	else
+		local_spin_unlock_irq(slab_lock, &per_cpu(slab_lock, cpu).lock);
 }
 #endif
 
@@ -2627,10 +2645,10 @@ static void do_drain(void *arg, int cpu)
 {
 	LIST_HEAD(tmp);
 
-	spin_lock_irq(&per_cpu(slab_lock, cpu).lock);
+	lock_slab_on(cpu);
 	__do_drain(arg, cpu);
 	list_splice_init(&per_cpu(slab_free_list, cpu), &tmp);
-	spin_unlock_irq(&per_cpu(slab_lock, cpu).lock);
+	unlock_slab_on(cpu);
 	free_delayed(&tmp);
 }
 #endif
@@ -4095,9 +4113,9 @@ static void do_ccupdate_local(void *info)
 #else
 static void do_ccupdate_local(void *info, int cpu)
 {
-	spin_lock_irq(&per_cpu(slab_lock, cpu).lock);
+	lock_slab_on(cpu);
 	__do_ccupdate_local(info, cpu);
-	spin_unlock_irq(&per_cpu(slab_lock, cpu).lock);
+	unlock_slab_on(cpu);
 }
 #endif
 
-- 
1.7.10.4

[PATCH RT 6/8] fs, jbd: pull your plug when waiting for space

[Steven Rostedt]

[-- Attachment #1: 0006-fs-jbd-pull-your-plug-when-waiting-for-space.patch --]
[-- Type: text/plain, Size: 1004 bytes --]

From: Mike Galbraith <mgalbraith@suse.de>

With an -rt kernel, and a heavy sync IO load, tasks can jam
up on journal locks without unplugging, which can lead to
terminal IO starvation.  Unplug and schedule when waiting for space.

Signed-off-by: Mike Galbraith <mgalbraith@suse.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Theodore Tso <tytso@mit.edu>
Link: http://lkml.kernel.org/r/1341812414.7370.73.camel@marge.simpson.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 fs/jbd/checkpoint.c |    2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index 5c93ffc..ddbd223 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -129,6 +129,8 @@ void __log_wait_for_space(journal_t *journal)
 		if (journal->j_flags & JFS_ABORT)
 			return;
 		spin_unlock(&journal->j_state_lock);
+		if (current->plug)
+			io_schedule();
 		mutex_lock(&journal->j_checkpoint_mutex);
 
 		/*
-- 
1.7.10.4

[PATCH RT 7/8] perf: Make swevent hrtimer run in irq instead of softirq

[Steven Rostedt]

[-- Attachment #1: 0007-perf-Make-swevent-hrtimer-run-in-irq-instead-of-soft.patch --]
[-- Type: text/plain, Size: 3603 bytes --]

From: Yong Zhang <yong.zhang@windriver.com>

Otherwise we get a deadlock like below:

[ 1044.042749] BUG: scheduling while atomic: ksoftirqd/21/141/0x00010003
[ 1044.042752] INFO: lockdep is turned off.
[ 1044.042754] Modules linked in:
[ 1044.042757] Pid: 141, comm: ksoftirqd/21 Tainted: G        W    3.4.0-rc2-rt3-23676-ga723175-dirty #29
[ 1044.042759] Call Trace:
[ 1044.042761]  <IRQ>  [<ffffffff8107d8e5>] __schedule_bug+0x65/0x80
[ 1044.042770]  [<ffffffff8168978c>] __schedule+0x83c/0xa70
[ 1044.042775]  [<ffffffff8106bdd2>] ? prepare_to_wait+0x32/0xb0
[ 1044.042779]  [<ffffffff81689a5e>] schedule+0x2e/0xa0
[ 1044.042782]  [<ffffffff81071ebd>] hrtimer_wait_for_timer+0x6d/0xb0
[ 1044.042786]  [<ffffffff8106bb30>] ? wake_up_bit+0x40/0x40
[ 1044.042790]  [<ffffffff81071f20>] hrtimer_cancel+0x20/0x40
[ 1044.042794]  [<ffffffff8111da0c>] perf_swevent_cancel_hrtimer+0x3c/0x50
[ 1044.042798]  [<ffffffff8111da31>] task_clock_event_stop+0x11/0x40
[ 1044.042802]  [<ffffffff8111da6e>] task_clock_event_del+0xe/0x10
[ 1044.042805]  [<ffffffff8111c568>] event_sched_out+0x118/0x1d0
[ 1044.042809]  [<ffffffff8111c649>] group_sched_out+0x29/0x90
[ 1044.042813]  [<ffffffff8111ed7e>] __perf_event_disable+0x18e/0x200
[ 1044.042817]  [<ffffffff8111c343>] remote_function+0x63/0x70
[ 1044.042821]  [<ffffffff810b0aae>] generic_smp_call_function_single_interrupt+0xce/0x120
[ 1044.042826]  [<ffffffff81022bc7>] smp_call_function_single_interrupt+0x27/0x40
[ 1044.042831]  [<ffffffff8168d50c>] call_function_single_interrupt+0x6c/0x80
[ 1044.042833]  <EOI>  [<ffffffff811275b0>] ? perf_event_overflow+0x20/0x20
[ 1044.042840]  [<ffffffff8168b970>] ? _raw_spin_unlock_irq+0x30/0x70
[ 1044.042844]  [<ffffffff8168b976>] ? _raw_spin_unlock_irq+0x36/0x70
[ 1044.042848]  [<ffffffff810702e2>] run_hrtimer_softirq+0xc2/0x200
[ 1044.042853]  [<ffffffff811275b0>] ? perf_event_overflow+0x20/0x20
[ 1044.042857]  [<ffffffff81045265>] __do_softirq_common+0xf5/0x3a0
[ 1044.042862]  [<ffffffff81045c3d>] __thread_do_softirq+0x15d/0x200
[ 1044.042865]  [<ffffffff81045dda>] run_ksoftirqd+0xfa/0x210
[ 1044.042869]  [<ffffffff81045ce0>] ? __thread_do_softirq+0x200/0x200
[ 1044.042873]  [<ffffffff81045ce0>] ? __thread_do_softirq+0x200/0x200
[ 1044.042877]  [<ffffffff8106b596>] kthread+0xb6/0xc0
[ 1044.042881]  [<ffffffff8168b97b>] ? _raw_spin_unlock_irq+0x3b/0x70
[ 1044.042886]  [<ffffffff8168d994>] kernel_thread_helper+0x4/0x10
[ 1044.042889]  [<ffffffff8107d98c>] ? finish_task_switch+0x8c/0x110
[ 1044.042894]  [<ffffffff8168b97b>] ? _raw_spin_unlock_irq+0x3b/0x70
[ 1044.042897]  [<ffffffff8168bd5d>] ? retint_restore_args+0xe/0xe
[ 1044.042900]  [<ffffffff8106b4e0>] ? kthreadd+0x1e0/0x1e0
[ 1044.042902]  [<ffffffff8168d990>] ? gs_change+0xb/0xb

Signed-off-by: Yong Zhang <yong.zhang0@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1341476476-5666-1-git-send-email-yong.zhang0@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/events/core.c |    1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 58690af..4d9159a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5420,6 +5420,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event)
 
 	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hwc->hrtimer.function = perf_swevent_hrtimer;
+	hwc->hrtimer.irqsafe = 1;
 
 	/*
 	 * Since hrtimers have a fixed rate, we can do a static freq->period
-- 
1.7.10.4

[PATCH RT 8/8] Linux 3.2.22-rt35-rc1

[Steven Rostedt]

[-- Attachment #1: 0008-Linux-3.2.22-rt35-rc1.patch --]
[-- Type: text/plain, Size: 289 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

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

diff --git a/localversion-rt b/localversion-rt
index 21988f9..87569d2 100644
--- a/localversion-rt
+++ b/localversion-rt
@@ -1 +1 @@
--rt34
+-rt35-rc1
-- 
1.7.10.4