10 files changed, 421 insertions, 44 deletions

diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 01e9e00..6bcb006 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -242,18 +242,20 @@ TRACE_EVENT(ext4_da_writepages,
 		__entry->pages_skipped	= wbc->pages_skipped;
 		__entry->range_start	= wbc->range_start;
 		__entry->range_end	= wbc->range_end;
-		__entry->nonblocking	= wbc->nonblocking;
 		__entry->for_kupdate	= wbc->for_kupdate;
 		__entry->for_reclaim	= wbc->for_reclaim;
 		__entry->range_cyclic	= wbc->range_cyclic;
 		__entry->writeback_index = inode->i_mapping->writeback_index;
 	),
 
-	TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d writeback_index %lu",
+	TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld "
+		  "range_start %llu range_end %llu "
+		  "for_kupdate %d for_reclaim %d "
+		  "range_cyclic %d writeback_index %lu",
 		  jbd2_dev_to_name(__entry->dev),
 		  (unsigned long) __entry->ino, __entry->nr_to_write,
 		  __entry->pages_skipped, __entry->range_start,
-		  __entry->range_end, __entry->nonblocking,
+		  __entry->range_end,
 		  __entry->for_kupdate, __entry->for_reclaim,
 		  __entry->range_cyclic,
 		  (unsigned long) __entry->writeback_index)
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
index 0e4cfb6..1c09820 100644
--- a/include/trace/events/irq.h
+++ b/include/trace/events/irq.h
@@ -5,7 +5,9 @@
 #define _TRACE_IRQ_H
 
 #include <linux/tracepoint.h>
-#include <linux/interrupt.h>
+
+struct irqaction;
+struct softirq_action;
 
 #define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq }
 #define show_softirq_name(val)				\
@@ -84,56 +86,62 @@ TRACE_EVENT(irq_handler_exit,
 
 DECLARE_EVENT_CLASS(softirq,
 
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+	TP_PROTO(unsigned int vec_nr),
 
-	TP_ARGS(h, vec),
+	TP_ARGS(vec_nr),
 
 	TP_STRUCT__entry(
-		__field(	int,	vec			)
+		__field(	unsigned int,	vec	)
 	),
 
 	TP_fast_assign(
-		__entry->vec = (int)(h - vec);
+		__entry->vec = vec_nr;
 	),
 
-	TP_printk("vec=%d [action=%s]", __entry->vec,
+	TP_printk("vec=%u [action=%s]", __entry->vec,
 		  show_softirq_name(__entry->vec))
 );
 
 /**
  * softirq_entry - called immediately before the softirq handler
- * @h: pointer to struct softirq_action
- * @vec: pointer to first struct softirq_action in softirq_vec array
+ * @vec_nr:  softirq vector number
  *
- * The @h parameter, contains a pointer to the struct softirq_action
- * which has a pointer to the action handler that is called. By subtracting
- * the @vec pointer from the @h pointer, we can determine the softirq
- * number. Also, when used in combination with the softirq_exit tracepoint
- * we can determine the softirq latency.
+ * When used in combination with the softirq_exit tracepoint
+ * we can determine the softirq handler runtine.
  */
 DEFINE_EVENT(softirq, softirq_entry,
 
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+	TP_PROTO(unsigned int vec_nr),
 
-	TP_ARGS(h, vec)
+	TP_ARGS(vec_nr)
 );
 
 /**
  * softirq_exit - called immediately after the softirq handler returns
- * @h: pointer to struct softirq_action
- * @vec: pointer to first struct softirq_action in softirq_vec array
+ * @vec_nr:  softirq vector number
  *
- * The @h parameter contains a pointer to the struct softirq_action
- * that has handled the softirq. By subtracting the @vec pointer from
- * the @h pointer, we can determine the softirq number. Also, when used in
- * combination with the softirq_entry tracepoint we can determine the softirq
- * latency.
+ * When used in combination with the softirq_entry tracepoint
+ * we can determine the softirq handler runtine.
  */
 DEFINE_EVENT(softirq, softirq_exit,
 
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+	TP_PROTO(unsigned int vec_nr),
+
+	TP_ARGS(vec_nr)
+);
+
+/**
+ * softirq_raise - called immediately when a softirq is raised
+ * @vec_nr:  softirq vector number
+ *
+ * When used in combination with the softirq_entry tracepoint
+ * we can determine the softirq raise to run latency.
+ */
+DEFINE_EVENT(softirq, softirq_raise,
+
+	TP_PROTO(unsigned int vec_nr),
 
-	TP_ARGS(h, vec)
+	TP_ARGS(vec_nr)
 );
 
 #endif /*  _TRACE_IRQ_H */
diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h
index 188deca..8fe1e93 100644
--- a/include/trace/events/napi.h
+++ b/include/trace/events/napi.h
@@ -6,10 +6,31 @@
 
 #include <linux/netdevice.h>
 #include <linux/tracepoint.h>
+#include <linux/ftrace.h>
+
+#define NO_DEV "(no_device)"
+
+TRACE_EVENT(napi_poll,
 
-DECLARE_TRACE(napi_poll,
 	TP_PROTO(struct napi_struct *napi),
-	TP_ARGS(napi));
+
+	TP_ARGS(napi),
+
+	TP_STRUCT__entry(
+		__field(	struct napi_struct *,	napi)
+		__string(	dev_name, napi->dev ? napi->dev->name : NO_DEV)
+	),
+
+	TP_fast_assign(
+		__entry->napi = napi;
+		__assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV);
+	),
+
+	TP_printk("napi poll on napi struct %p for device %s",
+		__entry->napi, __get_str(dev_name))
+);
+
+#undef NO_DEV
 
 #endif /* _TRACE_NAPI_H_ */
 
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
new file mode 100644
index 0000000..5f247f5
--- /dev/null
+++ b/include/trace/events/net.h
@@ -0,0 +1,82 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM net
+
+#if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NET_H
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/ip.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(net_dev_xmit,
+
+	TP_PROTO(struct sk_buff *skb,
+		 int rc),
+
+	TP_ARGS(skb, rc),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__field(	int,		rc		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__entry->rc = rc;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u rc=%d",
+		__get_str(name), __entry->skbaddr, __entry->len, __entry->rc)
+);
+
+DECLARE_EVENT_CLASS(net_dev_template,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u",
+		__get_str(name), __entry->skbaddr, __entry->len)
+)
+
+DEFINE_EVENT(net_dev_template, net_dev_queue,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_receive_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_rx,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+#endif /* _TRACE_NET_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 35a2a6e..286784d 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -10,12 +10,17 @@
 #ifndef _TRACE_POWER_ENUM_
 #define _TRACE_POWER_ENUM_
 enum {
-	POWER_NONE = 0,
-	POWER_CSTATE = 1,
-	POWER_PSTATE = 2,
+	POWER_NONE	= 0,
+	POWER_CSTATE	= 1,	/* C-State */
+	POWER_PSTATE	= 2,	/* Fequency change or DVFS */
+	POWER_SSTATE	= 3,	/* Suspend */
 };
 #endif
 
+/*
+ * The power events are used for cpuidle & suspend (power_start, power_end)
+ *  and for cpufreq (power_frequency)
+ */
 DECLARE_EVENT_CLASS(power,
 
 	TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id),
@@ -70,6 +75,85 @@ TRACE_EVENT(power_end,
 
 );
 
+/*
+ * The clock events are used for clock enable/disable and for
+ *  clock rate change
+ */
+DECLARE_EVENT_CLASS(clock,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+	),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_enable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_disable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_set_rate,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+/*
+ * The power domain events are used for power domains transitions
+ */
+DECLARE_EVENT_CLASS(power_domain,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(power_domain, power_domain_target,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
 #endif /* _TRACE_POWER_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 9208c92..f633478 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -362,6 +362,35 @@ TRACE_EVENT(sched_stat_runtime,
 			(unsigned long long)__entry->vruntime)
 );
 
+/*
+ * Tracepoint for showing priority inheritance modifying a tasks
+ * priority.
+ */
+TRACE_EVENT(sched_pi_setprio,
+
+	TP_PROTO(struct task_struct *tsk, int newprio),
+
+	TP_ARGS(tsk, newprio),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__field( int,	oldprio			)
+		__field( int,	newprio			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid		= tsk->pid;
+		__entry->oldprio	= tsk->prio;
+		__entry->newprio	= newprio;
+	),
+
+	TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
+			__entry->comm, __entry->pid,
+			__entry->oldprio, __entry->newprio)
+);
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 4b2be6d..75ce9d5 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -35,6 +35,23 @@ TRACE_EVENT(kfree_skb,
 		__entry->skbaddr, __entry->protocol, __entry->location)
 );
 
+TRACE_EVENT(consume_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,	skbaddr	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+	),
+
+	TP_printk("skbaddr=%p", __entry->skbaddr)
+);
+
 TRACE_EVENT(skb_copy_datagram_iovec,
 
 	TP_PROTO(const struct sk_buff *skb, int len),
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 370aa5a..c255fcc 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -10,6 +10,7 @@
 
 #define RECLAIM_WB_ANON		0x0001u
 #define RECLAIM_WB_FILE		0x0002u
+#define RECLAIM_WB_MIXED	0x0010u
 #define RECLAIM_WB_SYNC		0x0004u
 #define RECLAIM_WB_ASYNC	0x0008u
 
@@ -17,13 +18,20 @@
 	(flags) ? __print_flags(flags, "|",			\
 		{RECLAIM_WB_ANON,	"RECLAIM_WB_ANON"},	\
 		{RECLAIM_WB_FILE,	"RECLAIM_WB_FILE"},	\
+		{RECLAIM_WB_MIXED,	"RECLAIM_WB_MIXED"},	\
 		{RECLAIM_WB_SYNC,	"RECLAIM_WB_SYNC"},	\
 		{RECLAIM_WB_ASYNC,	"RECLAIM_WB_ASYNC"}	\
 		) : "RECLAIM_WB_NONE"
 
 #define trace_reclaim_flags(page, sync) ( \
 	(page_is_file_cache(page) ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \
-	(sync == PAGEOUT_IO_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC)   \
+	(sync == LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC)   \
+	)
+
+#define trace_shrink_flags(file, sync) ( \
+	(sync == LUMPY_MODE_SYNC ? RECLAIM_WB_MIXED : \
+			(file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON)) |  \
+	(sync == LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \
 	)
 
 TRACE_EVENT(mm_vmscan_kswapd_sleep,
@@ -269,6 +277,40 @@ TRACE_EVENT(mm_vmscan_writepage,
 		show_reclaim_flags(__entry->reclaim_flags))
 );
 
+TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
+
+	TP_PROTO(int nid, int zid,
+			unsigned long nr_scanned, unsigned long nr_reclaimed,
+			int priority, int reclaim_flags),
+
+	TP_ARGS(nid, zid, nr_scanned, nr_reclaimed, priority, reclaim_flags),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(int, zid)
+		__field(unsigned long, nr_scanned)
+		__field(unsigned long, nr_reclaimed)
+		__field(int, priority)
+		__field(int, reclaim_flags)
+	),
+
+	TP_fast_assign(
+		__entry->nid = nid;
+		__entry->zid = zid;
+		__entry->nr_scanned = nr_scanned;
+		__entry->nr_reclaimed = nr_reclaimed;
+		__entry->priority = priority;
+		__entry->reclaim_flags = reclaim_flags;
+	),
+
+	TP_printk("nid=%d zid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s",
+		__entry->nid, __entry->zid,
+		__entry->nr_scanned, __entry->nr_reclaimed,
+		__entry->priority,
+		show_reclaim_flags(__entry->reclaim_flags))
+);
+
+
 #endif /* _TRACE_VMSCAN_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
index 49682d7..7d49729 100644
--- a/include/trace/events/workqueue.h
+++ b/include/trace/events/workqueue.h
@@ -7,38 +7,83 @@
 #include <linux/tracepoint.h>
 #include <linux/workqueue.h>
 
+DECLARE_EVENT_CLASS(workqueue_work,
+
+	TP_PROTO(struct work_struct *work),
+
+	TP_ARGS(work),
+
+	TP_STRUCT__entry(
+		__field( void *,	work	)
+	),
+
+	TP_fast_assign(
+		__entry->work		= work;
+	),
+
+	TP_printk("work struct %p", __entry->work)
+);
+
 /**
- * workqueue_execute_start - called immediately before the workqueue callback
+ * workqueue_queue_work - called when a work gets queued
+ * @req_cpu:	the requested cpu
+ * @cwq:	pointer to struct cpu_workqueue_struct
  * @work:	pointer to struct work_struct
  *
- * Allows to track workqueue execution.
+ * This event occurs when a work is queued immediately or once a
+ * delayed work is actually queued on a workqueue (ie: once the delay
+ * has been reached).
  */
-TRACE_EVENT(workqueue_execute_start,
+TRACE_EVENT(workqueue_queue_work,
 
-	TP_PROTO(struct work_struct *work),
+	TP_PROTO(unsigned int req_cpu, struct cpu_workqueue_struct *cwq,
+		 struct work_struct *work),
 
-	TP_ARGS(work),
+	TP_ARGS(req_cpu, cwq, work),
 
 	TP_STRUCT__entry(
 		__field( void *,	work	)
 		__field( void *,	function)
+		__field( void *,	workqueue)
+		__field( unsigned int,	req_cpu	)
+		__field( unsigned int,	cpu	)
 	),
 
 	TP_fast_assign(
 		__entry->work		= work;
 		__entry->function	= work->func;
+		__entry->workqueue	= cwq->wq;
+		__entry->req_cpu	= req_cpu;
+		__entry->cpu		= cwq->gcwq->cpu;
 	),
 
-	TP_printk("work struct %p: function %pf", __entry->work, __entry->function)
+	TP_printk("work struct=%p function=%pf workqueue=%p req_cpu=%u cpu=%u",
+		  __entry->work, __entry->function, __entry->workqueue,
+		  __entry->req_cpu, __entry->cpu)
 );
 
 /**
- * workqueue_execute_end - called immediately before the workqueue callback
+ * workqueue_activate_work - called when a work gets activated
+ * @work:	pointer to struct work_struct
+ *
+ * This event occurs when a queued work is put on the active queue,
+ * which happens immediately after queueing unless @max_active limit
+ * is reached.
+ */
+DEFINE_EVENT(workqueue_work, workqueue_activate_work,
+
+	TP_PROTO(struct work_struct *work),
+
+	TP_ARGS(work)
+);
+
+/**
+ * workqueue_execute_start - called immediately before the workqueue callback
  * @work:	pointer to struct work_struct
  *
  * Allows to track workqueue execution.
  */
-TRACE_EVENT(workqueue_execute_end,
+TRACE_EVENT(workqueue_execute_start,
 
 	TP_PROTO(struct work_struct *work),
 
@@ -46,15 +91,29 @@ TRACE_EVENT(workqueue_execute_end,
 
 	TP_STRUCT__entry(
 		__field( void *,	work	)
+		__field( void *,	function)
 	),
 
 	TP_fast_assign(
 		__entry->work		= work;
+		__entry->function	= work->func;
 	),
 
-	TP_printk("work struct %p", __entry->work)
+	TP_printk("work struct %p: function %pf", __entry->work, __entry->function)
 );
 
+/**
+ * workqueue_execute_end - called immediately before the workqueue callback
+ * @work:	pointer to struct work_struct
+ *
+ * Allows to track workqueue execution.
+ */
+DEFINE_EVENT(workqueue_work, workqueue_execute_end,
+
+	TP_PROTO(struct work_struct *work),
+
+	TP_ARGS(work)
+);
 
 #endif /*  _TRACE_WORKQUEUE_H */
 
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index f345f66..89a2b2d 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -96,8 +96,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__field(long, nr_to_write)
 		__field(long, pages_skipped)
 		__field(int, sync_mode)
-		__field(int, nonblocking)
-		__field(int, encountered_congestion)
 		__field(int, for_kupdate)
 		__field(int, for_background)
 		__field(int, for_reclaim)
@@ -153,6 +151,41 @@ DEFINE_WBC_EVENT(wbc_balance_dirty_written);
 DEFINE_WBC_EVENT(wbc_balance_dirty_wait);
 DEFINE_WBC_EVENT(wbc_writepage);
 
+DECLARE_EVENT_CLASS(writeback_congest_waited_template,
+
+	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),
+
+	TP_ARGS(usec_timeout, usec_delayed),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	usec_timeout	)
+		__field(	unsigned int,	usec_delayed	)
+	),
+
+	TP_fast_assign(
+		__entry->usec_timeout	= usec_timeout;
+		__entry->usec_delayed	= usec_delayed;
+	),
+
+	TP_printk("usec_timeout=%u usec_delayed=%u",
+			__entry->usec_timeout,
+			__entry->usec_delayed)
+);
+
+DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait,
+
+	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),
+
+	TP_ARGS(usec_timeout, usec_delayed)
+);
+
+DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested,
+
+	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),
+
+	TP_ARGS(usec_timeout, usec_delayed)
+);
+
 #endif /* _TRACE_WRITEBACK_H */
 
 /* This part must be outside protection */