Merge branch 'perfcounters-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perfcounters-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (58 commits)
  perf_counter: Fix perf_copy_attr() pointer arithmetic
  perf utils: Use a define for the maximum length of a trace event
  perf: Add timechart help text and add timechart to "perf help"
  tracing, x86, cpuidle: Move the end point of a C state in the power tracer
  perf utils: Be consistent about minimum text size in the svghelper
  perf timechart: Add "perf timechart record"
  perf: Add the timechart tool
  perf: Add a SVG helper library file
  tracing, perf: Convert the power tracer into an event tracer
  perf: Add a sample_event type to the event_union
  perf: Allow perf utilities to have "callback" options without arguments
  perf: Store trace event name/id pairs in perf.data
  perf: Add a timestamp to fork events
  sched_clock: Make it NMI safe
  perf_counter: Fix up swcounter throttling
  x86, perf_counter, bts: Optimize BTS overflow handling
  perf sched: Add --input=file option to builtin-sched.c
  perf trace: Sample timestamp and cpu when using record flag
  perf tools: Increase MAX_EVENT_LENGTH
  perf tools: Fix memory leak in read_ftrace_printk()
  ...

3 files changed, 188 insertions, 6 deletions

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 972f90d7a32f..bd341007c4fc 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -199,10 +199,14 @@ struct perf_counter_attr {
                                 inherit_stat   :  1, /* per task counts       */
                                 enable_on_exec :  1, /* next exec enables     */
                                 task           :  1, /* trace fork/exit       */
+                                watermark      :  1, /* wakeup_watermark      */
 
-                                __reserved_1   : 50;
+                                __reserved_1   : 49;
 
-        __u32                   wakeup_events;  /* wakeup every n events */
+        union {
+                __u32           wakeup_events;    /* wakeup every n events */
+                __u32           wakeup_watermark; /* bytes before wakeup   */
+        };
         __u32                   __reserved_2;
 
         __u64                   __reserved_3;
@@ -332,6 +336,7 @@ enum perf_event_type {
          *      struct perf_event_header        header;
          *      u32                             pid, ppid;
          *      u32                             tid, ptid;
+         *      u64                             time;
          * };
          */
         PERF_EVENT_EXIT                 = 4,
@@ -352,6 +357,7 @@ enum perf_event_type {
          *      struct perf_event_header        header;
          *      u32                             pid, ppid;
          *      u32                             tid, ptid;
+         *      { u64                           time;     } && PERF_SAMPLE_TIME
          * };
          */
         PERF_EVENT_FORK                 = 7,
@@ -521,6 +527,8 @@ struct perf_mmap_data {
         atomic_t                        wakeup;         /* needs a wakeup    */
         atomic_t                        lost;           /* nr records lost   */
 
+        long                            watermark;      /* wakeup watermark  */
+
         struct perf_counter_mmap_page   *user_page;
         void                            *data_pages[0];
 };
@@ -685,6 +693,17 @@ struct perf_cpu_context {
         int                             recursion[4];
 };
 
+struct perf_output_handle {
+        struct perf_counter     *counter;
+        struct perf_mmap_data   *data;
+        unsigned long           head;
+        unsigned long           offset;
+        int                     nmi;
+        int                     sample;
+        int                     locked;
+        unsigned long           flags;
+};
+
 #ifdef CONFIG_PERF_COUNTERS
 
 /*
@@ -716,16 +735,38 @@ extern int hw_perf_group_sched_in(struct perf_counter *group_leader,
 extern void perf_counter_update_userpage(struct perf_counter *counter);
 
 struct perf_sample_data {
-        struct pt_regs                  *regs;
+        u64                             type;
+
+        u64                             ip;
+        struct {
+                u32     pid;
+                u32     tid;
+        }                               tid_entry;
+        u64                             time;
         u64                             addr;
+        u64                             id;
+        u64                             stream_id;
+        struct {
+                u32     cpu;
+                u32     reserved;
+        }                               cpu_entry;
         u64                             period;
+        struct perf_callchain_entry     *callchain;
         struct perf_raw_record          *raw;
 };
 
+extern void perf_output_sample(struct perf_output_handle *handle,
+                               struct perf_event_header *header,
+                               struct perf_sample_data *data,
+                               struct perf_counter *counter);
+extern void perf_prepare_sample(struct perf_event_header *header,
+                                struct perf_sample_data *data,
+                                struct perf_counter *counter,
+                                struct pt_regs *regs);
+
 extern int perf_counter_overflow(struct perf_counter *counter, int nmi,
-                                 struct perf_sample_data *data);
-extern void perf_counter_output(struct perf_counter *counter, int nmi,
-                                struct perf_sample_data *data);
+                                 struct perf_sample_data *data,
+                                 struct pt_regs *regs);
 
 /*
  * Return 1 for a software counter, 0 for a hardware counter
@@ -775,6 +816,12 @@ extern void perf_tpcounter_event(int event_id, u64 addr, u64 count,
 #define perf_instruction_pointer(regs)  instruction_pointer(regs)
 #endif
 
+extern int perf_output_begin(struct perf_output_handle *handle,
+                             struct perf_counter *counter, unsigned int size,
+                             int nmi, int sample);
+extern void perf_output_end(struct perf_output_handle *handle);
+extern void perf_output_copy(struct perf_output_handle *handle,
+                             const void *buf, unsigned int len);
 #else
 static inline void
 perf_counter_task_sched_in(struct task_struct *task, int cpu)           { }
@@ -801,7 +848,28 @@ static inline void perf_counter_mmap(struct vm_area_struct *vma)	{ }
 static inline void perf_counter_comm(struct task_struct *tsk)           { }
 static inline void perf_counter_fork(struct task_struct *tsk)           { }
 static inline void perf_counter_init(void)                              { }
+
+static inline int
+perf_output_begin(struct perf_output_handle *handle, struct perf_counter *c,
+                  unsigned int size, int nmi, int sample)               { }
+static inline void perf_output_end(struct perf_output_handle *handle)   { }
+static inline void
+perf_output_copy(struct perf_output_handle *handle,
+                 const void *buf, unsigned int len)                     { }
+static inline void
+perf_output_sample(struct perf_output_handle *handle,
+                   struct perf_event_header *header,
+                   struct perf_sample_data *data,
+                   struct perf_counter *counter)                        { }
+static inline void
+perf_prepare_sample(struct perf_event_header *header,
+                    struct perf_sample_data *data,
+                    struct perf_counter *counter,
+                    struct pt_regs *regs)                               { }
 #endif
 
+#define perf_output_put(handle, x) \
+        perf_output_copy((handle), &(x), sizeof(x))
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_PERF_COUNTER_H */
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
new file mode 100644
index 000000000000..ea6d579261ad
--- /dev/null
+++ b/include/trace/events/power.h
@@ -0,0 +1,81 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM power
+
+#if !defined(_TRACE_POWER_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_POWER_H
+
+#include <linux/ktime.h>
+#include <linux/tracepoint.h>
+
+#ifndef _TRACE_POWER_ENUM_
+#define _TRACE_POWER_ENUM_
+enum {
+        POWER_NONE = 0,
+        POWER_CSTATE = 1,
+        POWER_PSTATE = 2,
+};
+#endif
+
+
+
+TRACE_EVENT(power_start,
+
+        TP_PROTO(unsigned int type, unsigned int state),
+
+        TP_ARGS(type, state),
+
+        TP_STRUCT__entry(
+                __field(        u64,            type            )
+                __field(        u64,            state           )
+        ),
+
+        TP_fast_assign(
+                __entry->type = type;
+                __entry->state = state;
+        ),
+
+        TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long)__entry->state)
+);
+
+TRACE_EVENT(power_end,
+
+        TP_PROTO(int dummy),
+
+        TP_ARGS(dummy),
+
+        TP_STRUCT__entry(
+                __field(        u64,            dummy           )
+        ),
+
+        TP_fast_assign(
+                __entry->dummy = 0xffff;
+        ),
+
+        TP_printk("dummy=%lu", (unsigned long)__entry->dummy)
+
+);
+
+
+TRACE_EVENT(power_frequency,
+
+        TP_PROTO(unsigned int type, unsigned int state),
+
+        TP_ARGS(type, state),
+
+        TP_STRUCT__entry(
+                __field(        u64,            type            )
+                __field(        u64,            state           )
+        ),
+
+        TP_fast_assign(
+                __entry->type = type;
+                __entry->state = state;
+        ),
+
+        TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long) __entry->state)
+);
+
+#endif /* _TRACE_POWER_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index b48f1ad7c946..4069c43f4187 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -380,6 +380,39 @@ TRACE_EVENT(sched_stat_wait,
 );
 
 /*
+ * Tracepoint for accounting runtime (time the task is executing
+ * on a CPU).
+ */
+TRACE_EVENT(sched_stat_runtime,
+
+        TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
+
+        TP_ARGS(tsk, runtime, vruntime),
+
+        TP_STRUCT__entry(
+                __array( char,  comm,   TASK_COMM_LEN   )
+                __field( pid_t, pid                     )
+                __field( u64,   runtime                 )
+                __field( u64,   vruntime                        )
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+                __entry->pid            = tsk->pid;
+                __entry->runtime        = runtime;
+                __entry->vruntime       = vruntime;
+        )
+        TP_perf_assign(
+                __perf_count(runtime);
+        ),
+
+        TP_printk("task: %s:%d runtime: %Lu [ns], vruntime: %Lu [ns]",
+                        __entry->comm, __entry->pid,
+                        (unsigned long long)__entry->runtime,
+                        (unsigned long long)__entry->vruntime)
+);
+
+/*
  * Tracepoint for accounting sleep time (time the task is not runnable,
  * including iowait, see below).
  */