Merge branch 'rt/head' into rt/2.6.31

Documentation/trace/ftrace.txt

@@ -111,9 +111,14 @@ of ftrace. Here is a list of some of the key files:
 	For example, the time interrupts are disabled.
 	This time is saved in this file. The max trace
 	will also be stored, and displayed by "trace".
-	A new max trace will only be recorded if the
+	A new max trace will only be recorded, if the
 	latency is greater than the value in this
-	file. (in microseconds)
+	file (in microseconds). Note that the max latency
+	recorded by the wakeup and the wakeup_rt tracer
+	do not necessarily reflect the worst-case latency
+	of the system, but may be erroneously high in
+	case two or more processes share the maximum
+	priority of the system.
 
   buffer_size_kb:
 

Documentation/trace/histograms.txt

@@ -24,26 +24,43 @@ histograms of potential sources of latency, the kernel stores the time
 stamp at the start of a critical section, determines the time elapsed
 when the end of the section is reached, and increments the frequency
 counter of that latency value - irrespective of whether any concurrently
-running process is affected by latency or not.
+running process is affected by this latency or not.
 - Configuration items (in the Kernel hacking/Tracers submenu)
-  CONFIG_INTERRUPT_OFF_LATENCY
-  CONFIG_PREEMPT_OFF_LATENCY
+  CONFIG_INTERRUPT_OFF_HIST
+  CONFIG_PREEMPT_OFF_HIST
 
 
 * Effective latencies
-
-Effective latencies are actually occuring during wakeup of a process. To
-determine effective latencies, the kernel stores the time stamp when a
-process is scheduled to be woken up, and determines the duration of the
-wakeup time shortly before control is passed over to this process. Note
-that the apparent latency in user space may be considerably longer,
-since
-i) interrupts may be disabled preventing the scheduler from initiating
-the wakeup mechanism, and
+There are two types of effective latencies, wakeup latencies and missed
+timer latencies
+
+* Wakeup latencies
+Wakeup latencies may occur during wakeup of a process. To determine
+wakeup latencies, the kernel stores the time stamp when a process is
+scheduled to be woken up, and determines the duration of the wakeup time
+shortly before control is passed over to this process. Note that the
+apparent latency in user space may be considerably longer, since
+i) interrupts may be disabled preventing the timer from waking up a process
+in time
 ii) the process may be interrupted after control is passed over to it
 but before user space execution takes place.
+If a particular wakeup latency is highest so far, details of the task
+that is suffering from this latency are stored as well (see below).
+- Configuration item (in the Kernel hacking/Tracers submenu)
+  CONFIG_WAKEUP_LATENCY_HIST
+
+* Missed timer latencies
+
+Missed timer latencies occur when a timer interrupt is serviced later
+than it should. This is mainly due to disabled interrupts. To determine
+the missed timer latency, the expected and the real execution time of a
+timer are compared. If the former precedes the latter, the difference is
+entered into the missed timer offsets histogram. If the timer is
+responsible to wakeup a sleeping process and the latency is highest so
+far among previous wakeup timers, details of the related task are stored
+as well (see below).
 - Configuration item (in the Kernel hacking/Tracers submenu)
-  CONFIG_WAKEUP_LATENCY
+  CONFIG_MISSED_TIMER_OFFSETS_HIST
 
 
 * Usage
@@ -59,30 +76,36 @@ from shell command line level, or add
 nodev	/sys			sysfs	defaults	0 0
 nodev	/sys/kernel/debug	debugfs	defaults	0 0
 
-to the file /etc/fstab. All latency histogram related files are
+to the file /etc/fstab in order to implicitly mount the debug file
+system at every reboot. All latency histogram related files are
 available in the directory /sys/kernel/debug/tracing/latency_hist. A
 particular histogram type is enabled by writing non-zero to the related
 variable in the /sys/kernel/debug/tracing/latency_hist/enable directory.
-Select "preemptirqsoff" for the histograms of potential sources of
-latencies and "wakeup" for histograms of effective latencies. The
-histogram data - one per CPU - are available in the files
+Select "preemptirqsoff" for histograms of potential sources of
+latencies, "wakeup" for histograms of wakeup latencies and
+"missed_timer_offsets" for histograms of missed timer offsets,
+respectively.
 
+The histogram data - one per CPU - are available in the files
 /sys/kernel/debug/tracing/latency_hist/preemptoff/CPUx
 /sys/kernel/debug/tracing/latency_hist/irqsoff/CPUx
 /sys/kernel/debug/tracing/latency_hist/preemptirqsoff/CPUx
 /sys/kernel/debug/tracing/latency_hist/wakeup/CPUx.
+/sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio/CPUx.
+/sys/kernel/debug/tracing/latency_hist/missed_timer_offsets/CPUx.
 
 The histograms are reset by writing non-zero to the file "reset" in a
 particular latency directory. To reset all latency data, use
 
-#!/bin/sh
+#!/bin/bash
 
-HISTDIR=/sys/kernel/debug/tracing/latency_hist
+TRACINGDIR=/sys/kernel/debug/tracing
+HISTDIR=$TRACINGDIR/latency_hist
 
 if test -d $HISTDIR
 then
   cd $HISTDIR
-  for i in */reset
+  for i in `find . | grep /reset$`
   do
     echo 1 >$i
   done
@@ -92,19 +115,19 @@ fi
 * Data format
 
 Latency data are stored with a resolution of one microsecond. The
-maximum latency is 10,240 microseconds. The data are only valid, if the
-overflow register is empty. Every output line contains the latency in
-microseconds in the first row and the number of samples in the second
-row. To display only lines with a positive latency count, use, for
-example,
+maximum latency is 10,240 microseconds. Every output line contains the
+latency in microseconds in the first row and the number of samples in
+the second row. To display only lines with a positive latency count,
+use, for example,
 
 grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0
 
-#Minimum latency: 0 microseconds.
-#Average latency: 0 microseconds.
-#Maximum latency: 25 microseconds.
+#Minimum latency: 0 microseconds
+#Average latency: 0 microseconds
+#Maximum latency: 25 microseconds
 #Total samples: 3104770694
-#There are 0 samples greater or equal than 10240 microseconds
+#There are 0 samples lower than 0 microseconds.
+#There are 0 samples greater or equal than 10240 microseconds.
 #usecs	         samples
     0	      2984486876
     1	        49843506
@@ -133,6 +156,23 @@ grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0
    25	               1
 
 
+* Two types of wakeup latency histograms
+
+Two different algorithms are used to determine the wakeup latency of a
+process. One of them only considers processes that exclusively use the
+highest priority of the system, the other one records the wakeup latency
+of a process even if it shares the highest system latency with other
+processes. The former is used to determine the worst-case latency of a
+system; if higher than expected, the hardware and or system software
+(e.g. the Linux kernel) may need to be debugged and fixed. The latter
+reflects the priority design of a given system; if higher than expected,
+the system design may need to be re-evaluated - the hardware
+manufacturer or the kernel developers must not be blamed for such
+latencies. The exclusive-priority wakeup latency histograms are located
+in the "wakeup" subdirectory, the shared-priority histograms are located
+in the "wakeup/sharedprio" subdirectory.
+
+
 * Wakeup latency of a selected process
 
 To only collect wakeup latency data of a particular process, write the
@@ -143,14 +183,18 @@ PID of the requested process to
 PIDs are not considered, if this variable is set to 0.
 
 
-* Details of the process with the highest wakeup latency so far
+* Details of processes with the highest wakeup or missed timer
+latency so far
 
-Selected data of the process that suffered from the highest wakeup
-latency that occurred in a particular CPU are available in the file
+Selected data of processes that suffered from the highest wakeup or
+missed timer latency that occurred on a particular CPU are available in
+the files
 
-/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx.
+/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx
+/sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio/max_latency-CPUx
+/sys/kernel/debug/tracing/latency_hist/missed_timer_offsets/max_latency-CPUx
 
 The format of the data is
 <PID> <Priority> <Latency> <Command>
 
-These data are also reset when the wakeup histogram ist reset.
+These data are also reset when the related histograms are reset.

drivers/gpu/drm/r128/r128_cce.c

@@ -353,6 +353,11 @@ static int r128_do_init_cce(struct drm_device * dev, drm_r128_init_t * init)
 
 	DRM_DEBUG("\n");
 
+	if (dev->dev_private) {
+		DRM_DEBUG("called when already initialized\n");
+		return -EINVAL;
+	}
+
 	dev_priv = kzalloc(sizeof(drm_r128_private_t), GFP_KERNEL);
 	if (dev_priv == NULL)
 		return -ENOMEM;
@@ -649,6 +654,8 @@ int r128_cce_start(struct drm_device *dev, void *data, struct drm_file *file_pri
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
+
 	if (dev_priv->cce_running || dev_priv->cce_mode == R128_PM4_NONPM4) {
 		DRM_DEBUG("while CCE running\n");
 		return 0;
@@ -671,6 +678,8 @@ int r128_cce_stop(struct drm_device *dev, void *data, struct drm_file *file_priv
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
+
 	/* Flush any pending CCE commands.  This ensures any outstanding
 	 * commands are exectuted by the engine before we turn it off.
 	 */
@@ -708,10 +717,7 @@ int r128_cce_reset(struct drm_device *dev, void *data, struct drm_file *file_pri
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
-	if (!dev_priv) {
-		DRM_DEBUG("called before init done\n");
-		return -EINVAL;
-	}
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
 
 	r128_do_cce_reset(dev_priv);
 
@@ -728,6 +734,8 @@ int r128_cce_idle(struct drm_device *dev, void *data, struct drm_file *file_priv
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
+
 	if (dev_priv->cce_running) {
 		r128_do_cce_flush(dev_priv);
 	}
@@ -741,6 +749,8 @@ int r128_engine_reset(struct drm_device *dev, void *data, struct drm_file *file_
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
+	DEV_INIT_TEST_WITH_RETURN(dev->dev_private);
+
 	return r128_do_engine_reset(dev);
 }
 

drivers/gpu/drm/r128/r128_drv.h

@@ -422,6 +422,14 @@ static __inline__ void r128_update_ring_snapshot(drm_r128_private_t * dev_priv)
  * Misc helper macros
  */
 
+#define DEV_INIT_TEST_WITH_RETURN(_dev_priv)				\
+do {									\
+	if (!_dev_priv) {						\
+		DRM_ERROR("called with no initialization\n");		\
+		return -EINVAL;						\
+	}								\
+} while (0)
+
 #define RING_SPACE_TEST_WITH_RETURN( dev_priv )				\
 do {									\
 	drm_r128_ring_buffer_t *ring = &dev_priv->ring; int i;		\

drivers/gpu/drm/r128/r128_state.c

@@ -1244,14 +1244,18 @@ static void r128_cce_dispatch_stipple(struct drm_device * dev, u32 * stipple)
 static int r128_cce_clear(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
 	drm_r128_private_t *dev_priv = dev->dev_private;
-	drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv;
+	drm_r128_sarea_t *sarea_priv;
 	drm_r128_clear_t *clear = data;
 	DRM_DEBUG("\n");
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
+
 	RING_SPACE_TEST_WITH_RETURN(dev_priv);
 
+	sarea_priv = dev_priv->sarea_priv;
+
 	if (sarea_priv->nbox > R128_NR_SAREA_CLIPRECTS)
 		sarea_priv->nbox = R128_NR_SAREA_CLIPRECTS;
 
@@ -1312,6 +1316,8 @@ static int r128_cce_flip(struct drm_device *dev, void *data, struct drm_file *fi
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
+
 	RING_SPACE_TEST_WITH_RETURN(dev_priv);
 
 	if (!dev_priv->page_flipping)
@@ -1331,6 +1337,8 @@ static int r128_cce_swap(struct drm_device *dev, void *data, struct drm_file *fi
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
+
 	RING_SPACE_TEST_WITH_RETURN(dev_priv);
 
 	if (sarea_priv->nbox > R128_NR_SAREA_CLIPRECTS)
@@ -1354,10 +1362,7 @@ static int r128_cce_vertex(struct drm_device *dev, void *data, struct drm_file *
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
-	if (!dev_priv) {
-		DRM_ERROR("called with no initialization\n");
-		return -EINVAL;
-	}
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
 
 	DRM_DEBUG("pid=%d index=%d count=%d discard=%d\n",
 		  DRM_CURRENTPID, vertex->idx, vertex->count, vertex->discard);
@@ -1410,10 +1415,7 @@ static int r128_cce_indices(struct drm_device *dev, void *data, struct drm_file
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
-	if (!dev_priv) {
-		DRM_ERROR("called with no initialization\n");
-		return -EINVAL;
-	}
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
 
 	DRM_DEBUG("pid=%d buf=%d s=%d e=%d d=%d\n", DRM_CURRENTPID,
 		  elts->idx, elts->start, elts->end, elts->discard);
@@ -1476,6 +1478,8 @@ static int r128_cce_blit(struct drm_device *dev, void *data, struct drm_file *fi
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
+
 	DRM_DEBUG("pid=%d index=%d\n", DRM_CURRENTPID, blit->idx);
 
 	if (blit->idx < 0 || blit->idx >= dma->buf_count) {
@@ -1501,6 +1505,8 @@ static int r128_cce_depth(struct drm_device *dev, void *data, struct drm_file *f
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
+
 	RING_SPACE_TEST_WITH_RETURN(dev_priv);
 
 	ret = -EINVAL;
@@ -1531,6 +1537,8 @@ static int r128_cce_stipple(struct drm_device *dev, void *data, struct drm_file
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
+
 	if (DRM_COPY_FROM_USER(&mask, stipple->mask, 32 * sizeof(u32)))
 		return -EFAULT;
 
@@ -1555,10 +1563,7 @@ static int r128_cce_indirect(struct drm_device *dev, void *data, struct drm_file
 
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
-	if (!dev_priv) {
-		DRM_ERROR("called with no initialization\n");
-		return -EINVAL;
-	}
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
 
 	DRM_DEBUG("idx=%d s=%d e=%d d=%d\n",
 		  indirect->idx, indirect->start, indirect->end,
@@ -1620,10 +1625,7 @@ static int r128_getparam(struct drm_device *dev, void *data, struct drm_file *fi
 	drm_r128_getparam_t *param = data;
 	int value;
 
-	if (!dev_priv) {
-		DRM_ERROR("called with no initialization\n");
-		return -EINVAL;
-	}
+	DEV_INIT_TEST_WITH_RETURN(dev_priv);
 
 	DRM_DEBUG("pid=%d\n", DRM_CURRENTPID);
 

drivers/misc/Kconfig

@@ -79,7 +79,7 @@ config IBM_ASM
 config HWLAT_DETECTOR
 	tristate "Testing module to detect hardware-induced latencies"
 	depends on DEBUG_FS
-	select RING_BUFFER
+	depends on RING_BUFFER
 	default m
 	---help---
 	  A simple hardware latency detector. Use this module to detect

drivers/misc/hwlat_detector.c

@@ -607,7 +607,11 @@ static ssize_t  debug_enable_fwrite(struct file *filp,
 		if (!enabled)
 			goto unlock;
 		enabled = 0;
-		stop_kthread();
+		err = stop_kthread();
+		if (err) {
+			printk(KERN_ERR BANNER "cannot stop kthread\n");
+			return -EFAULT;
+		}
 		wake_up(&data.wq);		/* reader(s) should return */
 	}
 unlock:
@@ -1194,9 +1198,13 @@ out:
  */
 static void detector_exit(void)
 {
+	int err;
+
 	if (enabled) {
 		enabled = 0;
-		stop_kthread();
+		err = stop_kthread();
+		if (err)
+			printk(KERN_ERR BANNER "cannot stop kthread\n");
 	}
 
 	free_debugfs();

fs/pipe.c

@@ -789,36 +789,55 @@ pipe_rdwr_release(struct inode *inode, struct file *filp)
 static int
 pipe_read_open(struct inode *inode, struct file *filp)
 {
-	/* We could have perhaps used atomic_t, but this and friends
-	   below are the only places.  So it doesn't seem worthwhile.  */
+	int ret = -ENOENT;
+
 	mutex_lock(&inode->i_mutex);
+
+	if (inode->i_pipe) {
+		ret = 0;
 		inode->i_pipe->readers++;
+	}
+
 	mutex_unlock(&inode->i_mutex);
 
-	return 0;
+	return ret;
 }
 
 static int
 pipe_write_open(struct inode *inode, struct file *filp)
 {
+	int ret = -ENOENT;
+
 	mutex_lock(&inode->i_mutex);
+
+	if (inode->i_pipe) {
+		ret = 0;
 		inode->i_pipe->writers++;
+	}
+
 	mutex_unlock(&inode->i_mutex);
 
-	return 0;
+	return ret;
 }
 
 static int
 pipe_rdwr_open(struct inode *inode, struct file *filp)
 {
+	int ret = -ENOENT;
+
 	mutex_lock(&inode->i_mutex);
+
+	if (inode->i_pipe) {
+		ret = 0;
 		if (filp->f_mode & FMODE_READ)
 			inode->i_pipe->readers++;
 		if (filp->f_mode & FMODE_WRITE)
 			inode->i_pipe->writers++;
+	}
+
 	mutex_unlock(&inode->i_mutex);
 
-	return 0;
+	return ret;
 }
 
 /*

include/linux/sched.h

@@ -1548,6 +1548,9 @@ struct task_struct {
 	unsigned long trace;
 	/* bitmask of trace recursion */
 	unsigned long trace_recursion;
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+	u64 preempt_timestamp_hist;
+#endif
 #endif /* CONFIG_TRACING */
 #ifdef CONFIG_PREEMPT_RT
 	/*

include/trace/events/hist.h

@@ -17,8 +17,8 @@ TRACE_EVENT(preemptirqsoff_hist,
 	TP_ARGS(reason, starthist),
 
 	TP_STRUCT__entry(
-		__field(	int,	reason	)
-		__field(	int,	starthist	)
+		__field(int,	reason	)
+		__field(int,	starthist	)
 	),
 
 	TP_fast_assign(
@@ -31,6 +31,31 @@ TRACE_EVENT(preemptirqsoff_hist,
 );
 #endif
 
+#ifndef CONFIG_MISSED_TIMER_OFFSETS_HIST
+#define trace_hrtimer_interrupt(a,b,c)
+#else
+TRACE_EVENT(hrtimer_interrupt,
+
+	TP_PROTO(int cpu, long long offset, struct task_struct *task),
+
+	TP_ARGS(cpu, offset, task),
+
+	TP_STRUCT__entry(
+		__array(char,		comm,	TASK_COMM_LEN)
+		__field(int,		cpu	)
+		__field(long long,	offset	)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->comm, task != NULL ? task->comm : "", TASK_COMM_LEN);
+		__entry->cpu	= cpu;
+		__entry->offset	= offset;
+	),
+
+	TP_printk("cpu=%d offset=%lld thread=%s", __entry->cpu, __entry->offset, __entry->comm)
+);
+#endif
+
 #endif /* _TRACE_HIST_H */
 
 /* This part must be outside protection */

init/main.c

@@ -936,7 +936,15 @@ static int __init kernel_init(void * unused)
 	WARN_ON(irqs_disabled());
 #endif
 
-#define DEBUG_COUNT (defined(CONFIG_DEBUG_RT_MUTEXES) + defined(CONFIG_IRQSOFF_TRACER) + defined(CONFIG_PREEMPT_TRACER) + defined(CONFIG_STACK_TRACER) + defined(CONFIG_INTERRUPT_OFF_HIST) + defined(CONFIG_PREEMPT_OFF_HIST) + defined(CONFIG_WAKEUP_LATENCY_HIST) + defined(CONFIG_DEBUG_SLAB) + defined(CONFIG_DEBUG_PAGEALLOC) + defined(CONFIG_LOCKDEP) + (defined(CONFIG_FTRACE) - defined(CONFIG_FTRACE_MCOUNT_RECORD)))
+#define DEBUG_COUNT (defined(CONFIG_DEBUG_RT_MUTEXES) + \
+	defined(CONFIG_IRQSOFF_TRACER) + defined(CONFIG_PREEMPT_TRACER) + \
+	defined(CONFIG_STACK_TRACER) + defined(CONFIG_INTERRUPT_OFF_HIST) + \
+	defined(CONFIG_PREEMPT_OFF_HIST) + \
+	defined(CONFIG_WAKEUP_LATENCY_HIST) + \
+	defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + \
+	defined(CONFIG_DEBUG_SLAB) + defined(CONFIG_DEBUG_PAGEALLOC) + \
+	defined(CONFIG_LOCKDEP) + \
+	(defined(CONFIG_FTRACE) - defined(CONFIG_FTRACE_MCOUNT_RECORD)))
 
 #if DEBUG_COUNT > 0
 	printk(KERN_ERR "*****************************************************************************\n");
@@ -968,6 +976,9 @@ static int __init kernel_init(void * unused)
 #ifdef CONFIG_WAKEUP_LATENCY_HIST
 	printk(KERN_ERR "*        CONFIG_WAKEUP_LATENCY_HIST                                         *\n");
 #endif
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	printk(KERN_ERR "*        CONFIG_MISSED_TIMER_OFFSETS_HIST                                   *\n");
+#endif
 #ifdef CONFIG_DEBUG_SLAB
 	printk(KERN_ERR "*        CONFIG_DEBUG_SLAB                                                  *\n");
 #endif

kernel/hrtimer.c

@@ -48,6 +48,8 @@
 
 #include <asm/uaccess.h>
 
+#include <trace/events/hist.h>
+
 /*
  * The timer bases:
  *
@@ -1349,6 +1351,7 @@ static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; }
 #ifdef CONFIG_HIGH_RES_TIMERS
 
 static int force_clock_reprogram;
+static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer);
 
 /*
  * After 5 iteration's attempts, we consider that hrtimer_interrupt()
@@ -1419,6 +1422,13 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
 			timer = rb_entry(node, struct hrtimer, node);
 
+			trace_hrtimer_interrupt(raw_smp_processor_id(),
+			    ktime_to_ns(ktime_sub(
+				hrtimer_get_expires(timer), basenow)),
+			    timer->function == hrtimer_wakeup ?
+			    container_of(timer, struct hrtimer_sleeper,
+				timer)->task : NULL);
+
 			/*
 			 * The immediate goal for using the softexpires is
 			 * minimizing wakeups, not running timers at the

kernel/trace/Kconfig

@@ -143,7 +143,6 @@ config FUNCTION_GRAPH_TRACER
 	  the return value. This is done by setting the current return 
 	  address on the current task structure into a stack of calls.
 
-
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
 	default n
@@ -171,16 +170,19 @@ config INTERRUPT_OFF_HIST
 	bool "Interrupts-off Latency Histogram"
 	depends on IRQSOFF_TRACER
 	help
-	  This option generates a continuously updated histogram (one per cpu)
+	  This option generates continuously updated histograms (one per cpu)
 	  of the duration of time periods with interrupts disabled. The
-	  histogram is disabled by default. To enable it, write a non-zero
-	  number to the related file in
+	  histograms are disabled by default. To enable them, write a non-zero
+	  number to
 
 	      /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff
 
-	  If PREEMPT_OFF_HIST is also selected, an additional histogram (one
-	  per cpu) is generated that accumulates the duration of time periods
-	  when both interrupts and preemption are disabled.
+	  If PREEMPT_OFF_HIST is also selected, additional histograms (one
+	  per cpu) are generated that accumulate the duration of time periods
+	  when both interrupts and preemption are disabled. The histogram data
+	  will be located in the debug file system at
+
+	      /sys/kernel/debug/tracing/latency_hist/irqsoff
 
 config PREEMPT_TRACER
 	bool "Preemption-off Latency Tracer"
@@ -208,16 +210,19 @@ config PREEMPT_OFF_HIST
 	bool "Preemption-off Latency Histogram"
 	depends on PREEMPT_TRACER
 	help
-	  This option generates a continuously updated histogram (one per cpu)
+	  This option generates continuously updated histograms (one per cpu)
 	  of the duration of time periods with preemption disabled. The
-	  histogram is disabled by default. To enable it, write a non-zero
+	  histograms are disabled by default. To enable them, write a non-zero
 	  number to
 
 	      /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff
 
-	  If INTERRUPT_OFF_HIST is also selected, an additional histogram (one
-	  per cpu) is generated that accumulates the duration of time periods
-	  when both interrupts and preemption are disabled.
+	  If INTERRUPT_OFF_HIST is also selected, additional histograms (one
+	  per cpu) are generated that accumulate the duration of time periods
+	  when both interrupts and preemption are disabled. The histogram data
+	  will be located in the debug file system at
+
+	      /sys/kernel/debug/tracing/latency_hist/preemptoff
 
 config SCHED_TRACER
 	bool "Scheduling Latency Tracer"
@@ -232,12 +237,42 @@ config WAKEUP_LATENCY_HIST
 	bool "Scheduling Latency Histogram"
 	depends on SCHED_TRACER
 	help
-	  This option generates a continuously updated histogram (one per cpu)
-	  of the scheduling latency of the highest priority task. The histogram
-	  is disabled by default. To enable it, write a non-zero number to
+	  This option generates continuously updated histograms (one per cpu)
+	  of the scheduling latency of the highest priority task.
+	  The histograms are disabled by default. To enable them, write a
+	  non-zero number to
 
 	      /sys/kernel/debug/tracing/latency_hist/enable/wakeup
 
+	  Two different algorithms are used, one to determine the latency of
+	  processes that exclusively use the highest priority of the system and
+	  another one to determine the latency of processes that share the
+	  highest system priority with other processes. The former is used to
+	  improve hardware and system software, the latter to optimize the
+	  priority design of a given system. The histogram data will be
+	  located in the debug file system at
+
+	      /sys/kernel/debug/tracing/latency_hist/wakeup
+
+	  and
+
+	      /sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio
+
+config MISSED_TIMER_OFFSETS_HIST
+	depends on GENERIC_TIME
+	select GENERIC_TRACER
+	bool "Missed timer offsets histogram"
+	help
+	  Generate a histogram of missed timer offsets in microseconds. The
+	  histograms are disabled by default. To enable them, write a non-zero
+	  number to
+
+	      /sys/kernel/debug/tracing/latency_hist/enable/missed_timer_offsets
+
+ 	  The histogram data will be located in the debug file system at
+
+	      /sys/kernel/debug/tracing/latency_hist/missed_timer_offsets
+
 config SYSPROF_TRACER
 	bool "Sysprof Tracer"
 	depends on X86

kernel/trace/Makefile

@@ -38,6 +38,7 @@ obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
 obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o
 obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o
 obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o
+obj-$(CONFIG_MISSED_TIMER_OFFSETS_HIST) += latency_hist.o
 obj-$(CONFIG_NOP_TRACER) += trace_nop.o
 obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o

net/sched/cls_api.c

@@ -348,7 +348,7 @@ static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp,
 	tcm = NLMSG_DATA(nlh);
 	tcm->tcm_family = AF_UNSPEC;
 	tcm->tcm__pad1 = 0;
-	tcm->tcm__pad1 = 0;
+	tcm->tcm__pad2 = 0;
 	tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex;
 	tcm->tcm_parent = tp->classid;
 	tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol);

net/unix/af_unix.c

@@ -1074,6 +1074,8 @@ restart:
 	err = -ECONNREFUSED;
 	if (other->sk_state != TCP_LISTEN)
 		goto out_unlock;
+	if (other->sk_shutdown & RCV_SHUTDOWN)
+		goto out_unlock;
 
 	if (unix_recvq_full(other)) {
 		err = -EAGAIN;

security/keys/keyctl.c

@@ -860,7 +860,7 @@ static long get_instantiation_keyring(key_serial_t ringid,
 	/* otherwise specify the destination keyring recorded in the
 	 * authorisation key (any KEY_SPEC_*_KEYRING) */
 	if (ringid >= KEY_SPEC_REQUESTOR_KEYRING) {
-		*_dest_keyring = rka->dest_keyring;
+		*_dest_keyring = key_get(rka->dest_keyring);
 		return 0;
 	}