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

kernel/trace/latency_hist.c

@@ -34,6 +34,8 @@ enum {
 	PREEMPTOFF_LATENCY,
 	PREEMPTIRQSOFF_LATENCY,
 	WAKEUP_LATENCY,
+	WAKEUP_LATENCY_SHAREDPRIO,
+	MISSED_TIMER_OFFSETS,
 	MAX_LATENCY_TYPE,
 };
 
@@ -41,9 +43,11 @@ 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;
-	unsigned long long beyond_hist_bound_samples;
+	unsigned long long below_hist_bound_samples;
+	unsigned long long above_hist_bound_samples;
 	unsigned long long accumulate_lat;
 	unsigned long long total_samples;
 	unsigned long long hist_array[MAX_ENTRY_NUM];
@@ -59,16 +63,22 @@ static char *latency_hist_dir_root = "latency_hist";
 #ifdef CONFIG_INTERRUPT_OFF_HIST
 static DEFINE_PER_CPU(struct hist_data, irqsoff_hist);
 static char *irqsoff_hist_dir = "irqsoff";
+static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start);
+static DEFINE_PER_CPU(int, hist_irqsoff_counting);
 #endif
 
 #ifdef CONFIG_PREEMPT_OFF_HIST
 static DEFINE_PER_CPU(struct hist_data, preemptoff_hist);
 static char *preemptoff_hist_dir = "preemptoff";
+static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start);
+static DEFINE_PER_CPU(int, hist_preemptoff_counting);
 #endif
 
 #if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST)
 static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist);
 static char *preemptirqsoff_hist_dir = "preemptirqsoff";
+static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start);
+static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting);
 #endif
 
 #if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST)
@@ -79,9 +89,21 @@ static struct enable_data preemptirqsoff_enabled_data = {
 };
 #endif
 
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+struct maxlatproc_data {
+	char comm[FIELD_SIZEOF(struct task_struct, comm)];
+	unsigned int pid;
+	unsigned int prio;
+	unsigned long latency;
+};
+#endif
+
 #ifdef CONFIG_WAKEUP_LATENCY_HIST
 static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist);
+static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio);
 static char *wakeup_latency_hist_dir = "wakeup";
+static char *wakeup_latency_hist_dir_sharedprio = "sharedprio";
 static notrace void probe_wakeup_latency_hist_start(struct rq *rq,
     struct task_struct *p, int success);
 static notrace void probe_wakeup_latency_hist_stop(struct rq *rq,
@@ -90,23 +112,34 @@ static struct enable_data wakeup_latency_enabled_data = {
 	.latency_type = WAKEUP_LATENCY,
 	.enabled = 0,
 };
-static struct task_struct *ts;
-struct maxlatproc_data {
-	char comm[sizeof(ts->comm)];
-	unsigned int pid;
-	unsigned int prio;
-	unsigned long latency;
-};
 static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc);
-static unsigned wakeup_prio = (unsigned)-1;
+static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio);
 static struct task_struct *wakeup_task;
+static int wakeup_sharedprio;
 static int wakeup_pid;
 #endif
 
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets);
+static char *missed_timer_offsets_dir = "missed_timer_offsets";
+static notrace void probe_hrtimer_interrupt(int cpu,
+    long long offset, struct task_struct *task);
+static struct enable_data missed_timer_offsets_enabled_data = {
+	.latency_type = MISSED_TIMER_OFFSETS,
+	.enabled = 0,
+};
+static DEFINE_PER_CPU(struct maxlatproc_data,
+    missed_timer_offsets_maxlatproc);
+#endif
+
 void notrace latency_hist(int latency_type, int cpu, unsigned long latency,
 			  struct task_struct *p)
 {
 	struct hist_data *my_hist;
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+	struct maxlatproc_data *mp = NULL;
+#endif
 
 	if (cpu < 0 || cpu >= NR_CPUS || latency_type < 0 ||
 	    latency_type >= MAX_LATENCY_TYPE)
@@ -118,22 +151,30 @@ void notrace latency_hist(int latency_type, int cpu, unsigned long latency,
 		my_hist = &per_cpu(irqsoff_hist, cpu);
 		break;
 #endif
-
 #ifdef CONFIG_PREEMPT_OFF_HIST
 	case PREEMPTOFF_LATENCY:
 		my_hist = &per_cpu(preemptoff_hist, cpu);
 		break;
 #endif
-
 #if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST)
 	case PREEMPTIRQSOFF_LATENCY:
 		my_hist = &per_cpu(preemptirqsoff_hist, cpu);
 		break;
 #endif
-
 #ifdef CONFIG_WAKEUP_LATENCY_HIST
 	case WAKEUP_LATENCY:
 		my_hist = &per_cpu(wakeup_latency_hist, cpu);
+		mp = &per_cpu(wakeup_maxlatproc, cpu);
+		break;
+	case WAKEUP_LATENCY_SHAREDPRIO:
+		my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu);
+		mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu);
+		break;
+#endif
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	case MISSED_TIMER_OFFSETS:
+		my_hist = &per_cpu(missed_timer_offsets, cpu);
+		mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu);
 		break;
 #endif
 	default:
@@ -143,18 +184,23 @@ void notrace latency_hist(int latency_type, int cpu, unsigned long latency,
 	if (atomic_read(&my_hist->hist_mode) == 0)
 		return;
 
-	if (latency >= MAX_ENTRY_NUM)
-		my_hist->beyond_hist_bound_samples++;
+	latency += my_hist->offset;
+
+	if (latency < 0 || latency >= MAX_ENTRY_NUM) {
+		if (latency < 0)
+			my_hist->below_hist_bound_samples++;
 		else
+			my_hist->above_hist_bound_samples++;
+	} else
 		my_hist->hist_array[latency]++;
 
 	if (latency < my_hist->min_lat)
 		my_hist->min_lat = latency;
 	else if (latency > my_hist->max_lat) {
-#ifdef CONFIG_WAKEUP_LATENCY_HIST
-		if (latency_type == WAKEUP_LATENCY) {
-			struct maxlatproc_data *mp =
-			    &per_cpu(wakeup_maxlatproc, cpu);
+#if defined (CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+		if (latency_type == WAKEUP_LATENCY ||
+		    latency_type == WAKEUP_LATENCY_SHAREDPRIO) {
 			strncpy(mp->comm, p->comm, sizeof(mp->comm));
 			mp->pid = task_pid_nr(p);
 			mp->prio = p->prio;
@@ -163,7 +209,15 @@ void notrace latency_hist(int latency_type, int cpu, unsigned long latency,
 #endif
 		my_hist->max_lat = latency;
 	}
-
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	if (latency_type == MISSED_TIMER_OFFSETS && p != NULL &&
+	    latency > mp->latency) {
+		strncpy(mp->comm, p->comm, sizeof(mp->comm));
+		mp->pid = task_pid_nr(p);
+		mp->prio = p->prio;
+		mp->latency = latency;
+	}
+#endif
 	my_hist->total_samples++;
 	my_hist->accumulate_lat += latency;
 	return;
@@ -179,30 +233,42 @@ static void *l_start(struct seq_file *m, loff_t *pos)
 		return NULL;
 
 	if (index == 0) {
-		char avgstr[32];
+		char minstr[32], avgstr[32], maxstr[32];
 
 		atomic_dec(&my_hist->hist_mode);
+
 		if (likely(my_hist->total_samples)) {
 			unsigned long avg = (unsigned long)
 			    div64_u64(my_hist->accumulate_lat,
 			    my_hist->total_samples);
-			sprintf(avgstr, "%lu", avg);
-		} else
-			strcpy(avgstr, "<undef>");
+			snprintf(minstr, sizeof(minstr), "%ld",
+			    (long) my_hist->min_lat - my_hist->offset);
+			snprintf(avgstr, sizeof(avgstr), "%ld",
+			    (long) avg - my_hist->offset);
+			snprintf(maxstr, sizeof(minstr), "%ld",
+			    (long) my_hist->max_lat - my_hist->offset);
+		} else {
+			strcpy(minstr, "<undef>");
+			strcpy(avgstr, minstr);
+			strcpy(maxstr, minstr);
+		}
 
-		seq_printf(m, "#Minimum latency: %lu microseconds.\n"
-			   "#Average latency: %s microseconds.\n"
-			   "#Maximum latency: %lu microseconds.\n"
+		seq_printf(m, "#Minimum latency: %s microseconds\n"
+			   "#Average latency: %s microseconds\n"
+			   "#Maximum latency: %s microseconds\n"
 			   "#Total samples: %llu\n"
+			   "#There are %llu samples lower than %ld"
+			   " microseconds.\n"
 			   "#There are %llu samples greater or equal"
-			   " than %d microseconds\n"
-			   "#usecs\t%16s\n"
-			   , my_hist->min_lat
-			   , avgstr
-			   , my_hist->max_lat
-			   , my_hist->total_samples
-			   , my_hist->beyond_hist_bound_samples
-			   , MAX_ENTRY_NUM, "samples");
+			   " than %ld microseconds.\n"
+			   "#usecs\t%16s\n",
+			   minstr, avgstr, maxstr,
+			   my_hist->total_samples,
+			   my_hist->below_hist_bound_samples,
+			   -my_hist->offset,
+			   my_hist->above_hist_bound_samples,
+			   MAX_ENTRY_NUM - my_hist->offset,
+			   "samples");
 	}
 	if (index >= MAX_ENTRY_NUM)
 		return NULL;
@@ -233,8 +299,15 @@ static int l_show(struct seq_file *m, void *p)
 {
 	int index = *(loff_t *) p;
 	struct hist_data *my_hist = m->private;
+	char *fmt;
 
-	seq_printf(m, "%5d\t%16llu\n", index, my_hist->hist_array[index]);
+	if (my_hist->offset)
+		fmt = "%6d\t%16llu\n";
+	else
+		fmt = "%5d\t%16llu\n";
+
+	seq_printf(m, fmt, index - my_hist->offset,
+	    my_hist->hist_array[index]);
 	return 0;
 }
 
@@ -269,7 +342,8 @@ static void hist_reset(struct hist_data *hist)
 	atomic_dec(&hist->hist_mode);
 
 	memset(hist->hist_array, 0, sizeof(hist->hist_array));
-	hist->beyond_hist_bound_samples = 0ULL;
+	hist->below_hist_bound_samples = 0ULL;
+	hist->above_hist_bound_samples = 0ULL;
 	hist->min_lat = 0xFFFFFFFFUL;
 	hist->max_lat = 0UL;
 	hist->total_samples = 0ULL;
@@ -284,10 +358,13 @@ latency_hist_reset(struct file *file, const char __user *a,
 {
 	int cpu;
 	struct hist_data *hist;
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+	struct maxlatproc_data *mp = NULL;
+#endif
 	int latency_type = (int) file->private_data;
 
 	switch (latency_type) {
-
 #ifdef CONFIG_PREEMPT_OFF_HIST
 	case PREEMPTOFF_LATENCY:
 		for_each_online_cpu(cpu) {
@@ -296,7 +373,6 @@ latency_hist_reset(struct file *file, const char __user *a,
 		}
 		break;
 #endif
-
 #ifdef CONFIG_INTERRUPT_OFF_HIST
 	case IRQSOFF_LATENCY:
 		for_each_online_cpu(cpu) {
@@ -305,7 +381,6 @@ latency_hist_reset(struct file *file, const char __user *a,
 		}
 		break;
 #endif
-
 #if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
 	case PREEMPTIRQSOFF_LATENCY:
 		for_each_online_cpu(cpu) {
@@ -314,16 +389,34 @@ latency_hist_reset(struct file *file, const char __user *a,
 		}
 		break;
 #endif
-
 #ifdef CONFIG_WAKEUP_LATENCY_HIST
 	case WAKEUP_LATENCY:
 		for_each_online_cpu(cpu) {
-			struct maxlatproc_data *mp =
-			    &per_cpu(wakeup_maxlatproc, cpu);
+			hist = &per_cpu(wakeup_latency_hist, cpu);
+			hist_reset(hist);
+			mp = &per_cpu(wakeup_maxlatproc, cpu);
 			mp->comm[0] = '\0';
 			mp->prio = mp->pid = mp->latency = 0;
-			hist = &per_cpu(wakeup_latency_hist, cpu);
+		}
+		break;
+	case WAKEUP_LATENCY_SHAREDPRIO:
+		for_each_online_cpu(cpu) {
+			hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu);
 			hist_reset(hist);
+			mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu);
+			mp->comm[0] = '\0';
+			mp->prio = mp->pid = mp->latency = 0;
+		}
+		break;
+#endif
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	case MISSED_TIMER_OFFSETS:
+		for_each_online_cpu(cpu) {
+			hist = &per_cpu(missed_timer_offsets, cpu);
+			hist_reset(hist);
+			mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu);
+			mp->comm[0] = '\0';
+			mp->prio = mp->pid = mp->latency = 0;
 		}
 		break;
 #endif
@@ -341,8 +434,6 @@ latency_hist_show_pid(struct file *filp, char __user *ubuf,
 	int r;
 
 	r = snprintf(buf, sizeof(buf), "%u\n", wakeup_pid);
-	if (r > sizeof(buf))
-		r = sizeof(buf);
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
@@ -367,7 +458,10 @@ latency_hist_pid(struct file *filp, const char __user *ubuf,
 	wakeup_pid = pid;
 	return cnt;
 }
+#endif
 
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
 static ssize_t
 latency_hist_show_maxlatproc(struct file *filp, char __user *ubuf,
 		      size_t cnt, loff_t *ppos)
@@ -379,27 +473,11 @@ latency_hist_show_maxlatproc(struct file *filp, char __user *ubuf,
 
 	r = snprintf(buf, sizeof(buf), "%5d %3d %ld %s\n",
 	    mp->pid, mp->prio, mp->latency, mp->comm);
-	if (r > sizeof(buf))
-		r = sizeof(buf);
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
 #endif
 
-#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
-#ifdef CONFIG_INTERRUPT_OFF_HIST
-static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start);
-static DEFINE_PER_CPU(int, hist_irqsoff_counting);
-#endif
-#ifdef CONFIG_PREEMPT_OFF_HIST
-static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start);
-static DEFINE_PER_CPU(int, hist_preemptoff_counting);
-#endif
-#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
-static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start);
-static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting);
-#endif
-
 static ssize_t
 latency_hist_show_enable(struct file *filp, char __user *ubuf,
 			 size_t cnt, loff_t *ppos)
@@ -409,8 +487,6 @@ latency_hist_show_enable(struct file *filp, char __user *ubuf,
 	int r;
 
 	r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled);
-	if (r > sizeof(buf))
-		r = sizeof(buf);
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
@@ -440,6 +516,19 @@ latency_hist_enable(struct file *filp, const char __user *ubuf,
 		int ret;
 
 		switch (ed->latency_type) {
+#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
+		case PREEMPTIRQSOFF_LATENCY:
+			ret = register_trace_preemptirqsoff_hist(
+			    probe_preemptirqsoff_hist);
+			if (ret) {
+				pr_info("wakeup trace: Couldn't assign "
+				    "probe_preemptirqsoff_hist "
+				    "to trace_preemptirqsoff_hist\n");
+				return ret;
+			}
+			break;
+#endif
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
 		case WAKEUP_LATENCY:
 			ret = register_trace_sched_wakeup(
 			    probe_wakeup_latency_hist_start);
@@ -472,48 +561,66 @@ latency_hist_enable(struct file *filp, const char __user *ubuf,
 				return ret;
 			}
 			break;
-		case PREEMPTIRQSOFF_LATENCY:
-			ret = register_trace_preemptirqsoff_hist(
-			    probe_preemptirqsoff_hist);
+#endif
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+		case MISSED_TIMER_OFFSETS:
+			ret = register_trace_hrtimer_interrupt(
+			    probe_hrtimer_interrupt);
 			if (ret) {
 				pr_info("wakeup trace: Couldn't assign "
-				    "probe_preemptirqsoff_hist "
-				    "to trace_preemptirqsoff_hist\n");
+				    "probe_hrtimer_interrupt "
+				    "to trace_hrtimer_interrupt\n");
 				return ret;
 			}
 			break;
+#endif
 		default:
 			break;
 		}
 	} else {
-		int cpu;
-
 		switch (ed->latency_type) {
-		case WAKEUP_LATENCY:
-			unregister_trace_sched_wakeup(
-			    probe_wakeup_latency_hist_start);
-			unregister_trace_sched_wakeup_new(
-			    probe_wakeup_latency_hist_start);
-			unregister_trace_sched_switch(
-			    probe_wakeup_latency_hist_stop);
-			wakeup_task = NULL;
-			wakeup_prio = (unsigned)-1;
-			break;
+#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
 		case PREEMPTIRQSOFF_LATENCY:
+			{
+				int cpu;
+
 				unregister_trace_preemptirqsoff_hist(
 				    probe_preemptirqsoff_hist);
 				for_each_online_cpu(cpu) {
 #ifdef CONFIG_INTERRUPT_OFF_HIST
-				per_cpu(hist_irqsoff_counting, cpu) = 0;
+					per_cpu(hist_irqsoff_counting,
+					    cpu) = 0;
 #endif
 #ifdef CONFIG_PREEMPT_OFF_HIST
-				per_cpu(hist_preemptoff_counting, cpu) = 0;
+					per_cpu(hist_preemptoff_counting,
+					    cpu) = 0;
 #endif
 #if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
-				per_cpu(hist_preemptirqsoff_counting, cpu) = 0;
+					per_cpu(hist_preemptirqsoff_counting,
+					    cpu) = 0;
 #endif
 				}
+			}
 			break;
+#endif
+#ifdef CONFIG_WAKEUP_LATEHCY_HIST
+		case WAKEUP_LATENCY:
+			unregister_trace_sched_wakeup(
+			    probe_wakeup_latency_hist_start);
+			unregister_trace_sched_wakeup_new(
+			    probe_wakeup_latency_hist_start);
+			unregister_trace_sched_switch(
+			    probe_wakeup_latency_hist_stop);
+			wakeup_task = NULL;
+			wakeup_sharedprio = 0;
+			break;
+#endif
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+		case MISSED_TIMER_OFFSETS:
+			unregister_trace_hrtimer_interrupt(
+			    probe_hrtimer_interrupt);
+			break;
+#endif
 		default:
 			break;
 		}
@@ -522,28 +629,34 @@ latency_hist_enable(struct file *filp, const char __user *ubuf,
 	return cnt;
 }
 
-static struct file_operations latency_hist_reset_fops = {
+static const struct file_operations latency_hist_reset_fops = {
 	.open = tracing_open_generic,
 	.write = latency_hist_reset,
 };
 
-static struct file_operations latency_hist_pid_fops = {
+static const struct file_operations latency_hist_enable_fops = {
 	.open = tracing_open_generic,
-	.read = latency_hist_show_pid,
-	.write = latency_hist_pid,
+	.read = latency_hist_show_enable,
+	.write = latency_hist_enable,
 };
 
-static struct file_operations latency_hist_maxlatproc_fops = {
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+static const struct file_operations latency_hist_pid_fops = {
 	.open = tracing_open_generic,
-	.read = latency_hist_show_maxlatproc,
+	.read = latency_hist_show_pid,
+	.write = latency_hist_pid,
 };
+#endif
 
-static struct file_operations latency_hist_enable_fops = {
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+static const struct file_operations latency_hist_maxlatproc_fops = {
 	.open = tracing_open_generic,
-	.read = latency_hist_show_enable,
-	.write = latency_hist_enable,
+	.read = latency_hist_show_maxlatproc,
 };
+#endif
 
+#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
 notrace void probe_preemptirqsoff_hist(int reason, int starthist)
 {
 	int cpu = raw_smp_processor_id();
@@ -643,11 +756,9 @@ notrace void probe_preemptirqsoff_hist(int reason, int starthist)
 #endif
 	}
 }
-
 #endif
 
 #ifdef CONFIG_WAKEUP_LATENCY_HIST
-static cycle_t wakeup_start;
 static DEFINE_ATOMIC_SPINLOCK(wakeup_lock);
 
 notrace void probe_wakeup_latency_hist_start(struct rq *rq,
@@ -657,23 +768,28 @@ notrace void probe_wakeup_latency_hist_start(struct rq *rq,
 	struct task_struct *curr = rq_curr(rq);
 
 	if (wakeup_pid) {
+		if ((wakeup_task && p->prio == wakeup_task->prio) ||
+		    p->prio == curr->prio)
+			wakeup_sharedprio = 1;
 		if (likely(wakeup_pid != task_pid_nr(p)))
 			return;
 	} else {
 		if (likely(!rt_task(p)) ||
-		    p->prio >= wakeup_prio ||
-		    p->prio >= curr->prio)
+		    (wakeup_task && p->prio > wakeup_task->prio) ||
+		    p->prio > curr->prio)
 			return;
+		if ((wakeup_task && p->prio == wakeup_task->prio) ||
+		    p->prio == curr->prio)
+			wakeup_sharedprio = 1;
 	}
 
 	atomic_spin_lock_irqsave(&wakeup_lock, flags);
 	if (wakeup_task)
 		put_task_struct(wakeup_task);
-
 	get_task_struct(p);
 	wakeup_task = p;
-	wakeup_prio = p->prio;
-	wakeup_start = ftrace_now(raw_smp_processor_id());
+	wakeup_task->preempt_timestamp_hist =
+	    ftrace_now(raw_smp_processor_id());
 	atomic_spin_unlock_irqrestore(&wakeup_lock, flags);
 }
 
@@ -692,31 +808,59 @@ notrace void probe_wakeup_latency_hist_stop(struct rq *rq,
 	stop = ftrace_now(cpu);
 
 	atomic_spin_lock_irqsave(&wakeup_lock, flags);
-	if (next != wakeup_task)
+
+	latency = nsecs_to_usecs(stop - next->preempt_timestamp_hist);
+	if (next != wakeup_task) {
+		if (wakeup_task && next->prio == wakeup_task->prio)
+			latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency,
+			    next);
 		goto out;
+	}
 
-	latency = nsecs_to_usecs(stop - wakeup_start);
+	if (wakeup_sharedprio) {
+		latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, next);
+		wakeup_sharedprio = 0;
+	} else
 		latency_hist(WAKEUP_LATENCY, cpu, latency, next);
 
 	put_task_struct(wakeup_task);
 	wakeup_task = NULL;
-	wakeup_prio = (unsigned)-1;
 out:
 	atomic_spin_unlock_irqrestore(&wakeup_lock, flags);
 }
+#endif
+
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+notrace void probe_hrtimer_interrupt(int cpu, long long latency_ns,
+    struct task_struct *task)
+{
+	if (latency_ns <= 0) {
+		unsigned long latency;
+
+		latency = (unsigned long) div_s64(-latency_ns, 1000);
 
+		latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, task);
+	}
+}
 #endif
 
 static __init int latency_hist_init(void)
 {
 	struct dentry *latency_hist_root = NULL;
 	struct dentry *dentry;
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+	struct dentry *dentry_sharedprio;
+#endif
 	struct dentry *entry;
 	struct dentry *latency_hist_enable_root;
-	int i = 0, len = 0;
+	int i = 0;
 	struct hist_data *my_hist;
 	char name[64];
 	char *cpufmt = "CPU%d";
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+	char *cpufmt_maxlatproc = "max_latency-CPU%d";
+#endif
 
 	dentry = tracing_init_dentry();
 
@@ -729,69 +873,60 @@ static __init int latency_hist_init(void)
 #ifdef CONFIG_INTERRUPT_OFF_HIST
 	dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root);
 	for_each_possible_cpu(i) {
-		len = sprintf(name, cpufmt, i);
-		name[len] = '\0';
+		sprintf(name, cpufmt, i);
 		entry = debugfs_create_file(name, 0444, dentry,
-					    &per_cpu(irqsoff_hist, i),
-					    &latency_hist_fops);
+		    &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;
 	}
 	entry = debugfs_create_file("reset", 0644, dentry,
-				    (void *)IRQSOFF_LATENCY,
-				    &latency_hist_reset_fops);
+	    (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops);
 #endif
 
 #ifdef CONFIG_PREEMPT_OFF_HIST
 	dentry = debugfs_create_dir(preemptoff_hist_dir,
 	    latency_hist_root);
 	for_each_possible_cpu(i) {
-		len = sprintf(name, cpufmt, i);
-		name[len] = '\0';
+		sprintf(name, cpufmt, i);
 		entry = debugfs_create_file(name, 0444, dentry,
-					    &per_cpu(preemptoff_hist, i),
-					    &latency_hist_fops);
+		    &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;
 	}
 	entry = debugfs_create_file("reset", 0644, dentry,
-				    (void *)PREEMPTOFF_LATENCY,
-				    &latency_hist_reset_fops);
+	    (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops);
 #endif
 
 #if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
 	dentry = debugfs_create_dir(preemptirqsoff_hist_dir,
 	    latency_hist_root);
 	for_each_possible_cpu(i) {
-		len = sprintf(name, cpufmt, i);
-		name[len] = '\0';
+		sprintf(name, cpufmt, i);
 		entry = debugfs_create_file(name, 0444, dentry,
-					    &per_cpu(preemptirqsoff_hist, i),
-					    &latency_hist_fops);
+		    &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;
 	}
 	entry = debugfs_create_file("reset", 0644, dentry,
-				    (void *)PREEMPTIRQSOFF_LATENCY,
-				    &latency_hist_reset_fops);
+	    (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops);
 #endif
 
 #if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
 	entry = debugfs_create_file("preemptirqsoff", 0644,
-				    latency_hist_enable_root,
-				    (void *)&preemptirqsoff_enabled_data,
+	    latency_hist_enable_root, (void *)&preemptirqsoff_enabled_data,
 	    &latency_hist_enable_fops);
 #endif
 
 #ifdef CONFIG_WAKEUP_LATENCY_HIST
 	dentry = debugfs_create_dir(wakeup_latency_hist_dir,
 	    latency_hist_root);
+	dentry_sharedprio = debugfs_create_dir(
+	    wakeup_latency_hist_dir_sharedprio, dentry);
 	for_each_possible_cpu(i) {
-		len = sprintf(name, cpufmt, i);
-		name[len] = '\0';
+		sprintf(name, cpufmt, i);
 		entry = debugfs_create_file(name, 0444, dentry,
 		    &per_cpu(wakeup_latency_hist, i),
 		    &latency_hist_fops);
@@ -799,21 +934,56 @@ static __init int latency_hist_init(void)
 		atomic_set(&my_hist->hist_mode, 1);
 		my_hist->min_lat = 0xFFFFFFFFUL;
 
-		len = sprintf(name, "max_latency-CPU%d", i);
-		name[len] = '\0';
+		sprintf(name, cpufmt, i);
+		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;
+
+		sprintf(name, cpufmt_maxlatproc, i);
 		entry = debugfs_create_file(name, 0444, dentry,
 		    &per_cpu(wakeup_maxlatproc, i),
 		    &latency_hist_maxlatproc_fops);
+
+		sprintf(name, cpufmt_maxlatproc, i);
+		entry = debugfs_create_file(name, 0444, dentry_sharedprio,
+		    &per_cpu(wakeup_maxlatproc_sharedprio, i),
+		    &latency_hist_maxlatproc_fops);
 	}
 	entry = debugfs_create_file("pid", 0644, dentry,
-				    (void *)&wakeup_pid,
-				    &latency_hist_pid_fops);
+	    (void *)&wakeup_pid, &latency_hist_pid_fops);
 	entry = debugfs_create_file("reset", 0644, dentry,
-				    (void *)WAKEUP_LATENCY,
-				    &latency_hist_reset_fops);
+	    (void *)WAKEUP_LATENCY, &latency_hist_reset_fops);
+	entry = debugfs_create_file("reset", 0644, dentry_sharedprio,
+	    (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops);
 	entry = debugfs_create_file("wakeup", 0644,
+	    latency_hist_enable_root, (void *)&wakeup_latency_enabled_data,
+	    &latency_hist_enable_fops);
+#endif
+
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	dentry = debugfs_create_dir(missed_timer_offsets_dir,
+	    latency_hist_root);
+	for_each_possible_cpu(i) {
+		sprintf(name, cpufmt, i);
+		entry = debugfs_create_file(name, 0444, dentry,
+		    &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;
+
+		sprintf(name, cpufmt_maxlatproc, i);
+		entry = debugfs_create_file(name, 0444, dentry,
+		    &per_cpu(missed_timer_offsets_maxlatproc, i),
+		    &latency_hist_maxlatproc_fops);
+	}
+	entry = debugfs_create_file("reset", 0644, dentry,
+	    (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops);
+	entry = debugfs_create_file("missed_timer_offsets", 0644,
 	    latency_hist_enable_root,
-				    (void *)&wakeup_latency_enabled_data,
+	    (void *)&missed_timer_offsets_enabled_data,
 	    &latency_hist_enable_fops);
 #endif
 	return 0;

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;
 	}