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

Pull perf updates from Ingo Molnar:
 "Lots of activity:

   211 files changed, 8328 insertions(+), 4116 deletions(-)

  most of it on the tooling side.

  Main changes:

   * ftrace enhancements and fixes from Steve Rostedt.

   * uprobes fixes, cleanups and preparation for the ARM port from Oleg
     Nesterov.

   * UAPI fixes, from David Howels - prepares the arch/x86 UAPI
     transition

   * Separate perf tests into multiple objects, one per test, from Jiri
     Olsa.

   * Make hardware event translations available in sysfs, from Jiri
     Olsa.

   * Fixes to /proc/pid/maps parsing, preparatory to supporting data
     maps, from Namhyung Kim

   * Implement ui_progress for GTK, from Namhyung Kim

   * Add framework for automated perf_event_attr tests, where tools with
     different command line options will be run from a 'perf test', via
     python glue, and the perf syscall will be intercepted to verify
     that the perf_event_attr fields set by the tool are those expected,
     from Jiri Olsa

   * Add a 'link' method for hists, so that we can have the leader with
     buckets for all the entries in all the hists.  This new method is
     now used in the default 'diff' output, making the sum of the
     'baseline' column be 100%, eliminating blind spots.

   * libtraceevent fixes for compiler warnings trying to make perf it
     build on some distros, like fedora 14, 32-bit, some of the warnings
     really pointed to real bugs.

   * Add a browser for 'perf script' and make it available from the
     report and annotate browsers.  It does filtering to find the
     scripts that handle events found in the perf.data file used.  From
     Feng Tang

   * perf inject changes to allow showing where a task sleeps, from
     Andrew Vagin.

   * Makefile improvements from Namhyung Kim.

   * Add --pre and --post command hooks in 'stat', from Peter Zijlstra.

   * Don't stop synthesizing threads when one vanishes, this is for the
     existing threads when we start a tool like trace.

   * Use sched:sched_stat_runtime to provide a thread summary, this
     produces the same output as the 'trace summary' subcommand of
     tglx's original "trace" tool.

   * Support interrupted syscalls in 'trace'

   * Add an event duration column and filter in 'trace'.

   * There are references to the man pages in some tools, so try to
     build Documentation when installing, warning the user if that is
     not possible, from Borislav Petkov.

   * Give user better message if precise is not supported, from David
     Ahern.

   * Try to find cross-built objdump path by using the session
     environment information in the perf.data file header, from Irina
     Tirdea, original patch and idea by Namhyung Kim.

   * Diplays more output on features check for make V=1, so that one can
     figure out what is happening by looking at gcc output, etc.  From
     Jiri Olsa.

   * Add on_exit implementation for systems without one, e.g.  Android,
     from Bernhard Rosenkraenzer.

   * Only process events for vcpus of interest, helps handling large
     number of events, from David Ahern.

   * Cross compilation fixes for Android, from Irina Tirdea.

   * Add documentation on compiling for Android, from Irina Tirdea.

   * perf diff improvements from Jiri Olsa.

   * Target (task/user/cpu/syswide) handling improvements, from Namhyung
     Kim.

   * Add support in 'trace' for tracing workload given by command line,
     from Namhyung Kim.

   * ... and much more."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (194 commits)
  uprobes: Use percpu_rw_semaphore to fix register/unregister vs dup_mmap() race
  perf evsel: Introduce is_group_member method
  perf powerpc: Use uapi/unistd.h to fix build error
  tools: Pass the target in descend
  tools: Honour the O= flag when tool build called from a higher Makefile
  tools: Define a Makefile function to do subdir processing
  perf ui: Always compile browser setup code
  perf ui: Add ui_progress__finish()
  perf ui gtk: Implement ui_progress functions
  perf ui: Introduce generic ui_progress helper
  perf ui tui: Move progress.c under ui/tui directory
  perf tools: Add basic event modifier sanity check
  perf tools: Omit group members from perf_evlist__disable/enable
  perf tools: Ensure single disable call per event in record comand
  perf tools: Fix 'disabled' attribute config for record command
  perf tools: Fix attributes for '{}' defined event groups
  perf tools: Use sscanf for parsing /proc/pid/maps
  perf tools: Add gtk.<command> config option for launching GTK browser
  perf tools: Fix compile error on NO_NEWT=1 build
  perf hists: Initialize all of he->stat with zeroes
  ...

8 files changed, 44 insertions, 113 deletions

diff --git a/include/asm-generic/trace_clock.h b/include/asm-generic/trace_clock.h
new file mode 100644
index 0000000..6726f1b
--- /dev/null
+++ b/include/asm-generic/trace_clock.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_GENERIC_TRACE_CLOCK_H
+#define _ASM_GENERIC_TRACE_CLOCK_H
+/*
+ * Arch-specific trace clocks.
+ */
+
+/*
+ * Additional trace clocks added to the trace_clocks
+ * array in kernel/trace/trace.c
+ * None if the architecture has not defined it.
+ */
+#ifndef ARCH_TRACE_CLOCKS
+# define ARCH_TRACE_CLOCKS
+#endif
+
+#endif  /* _ASM_GENERIC_TRACE_CLOCK_H */
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 642928c..a3d4895 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -86,6 +86,12 @@ struct trace_iterator {
 	cpumask_var_t		started;
 };
 
+enum trace_iter_flags {
+	TRACE_FILE_LAT_FMT	= 1,
+	TRACE_FILE_ANNOTATE	= 2,
+	TRACE_FILE_TIME_IN_NS	= 4,
+};
+
 
 struct trace_event;
 
@@ -127,13 +133,13 @@ trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer,
 void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
 					struct ring_buffer_event *event,
 					unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
-				       struct ring_buffer_event *event,
-					unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer,
-					    struct ring_buffer_event *event,
-					    unsigned long flags, int pc,
-					    struct pt_regs *regs);
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
+				struct ring_buffer_event *event,
+				unsigned long flags, int pc);
+void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer,
+				     struct ring_buffer_event *event,
+				     unsigned long flags, int pc,
+				     struct pt_regs *regs);
 void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
 					 struct ring_buffer_event *event);
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index dd9900c..d97ed58 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -527,9 +527,6 @@ __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
 
 extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode);
 #else
-static inline __printf(1, 2)
-int trace_printk(const char *fmt, ...);
-
 static inline void tracing_start(void) { }
 static inline void tracing_stop(void) { }
 static inline void ftrace_off_permanent(void) { }
@@ -539,8 +536,8 @@ static inline void tracing_on(void) { }
 static inline void tracing_off(void) { }
 static inline int tracing_is_on(void) { return 0; }
 
-static inline int
-trace_printk(const char *fmt, ...)
+static inline __printf(1, 2)
+int trace_printk(const char *fmt, ...)
 {
 	return 0;
 }
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 6c8835f..519777e 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -159,13 +159,14 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer);
 void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
 void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
 
-unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu);
+u64 ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_bytes_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_entries(struct ring_buffer *buffer);
 unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
diff --git a/include/linux/trace_clock.h b/include/linux/trace_clock.h
index 4eb4902..d563f37 100644
--- a/include/linux/trace_clock.h
+++ b/include/linux/trace_clock.h
@@ -12,6 +12,8 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 
+#include <asm/trace_clock.h>
+
 extern u64 notrace trace_clock_local(void);
 extern u64 notrace trace_clock(void);
 extern u64 notrace trace_clock_global(void);
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 2459457..4f628a6 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -97,12 +97,12 @@ extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_con
 extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_mmap(struct vm_area_struct *vma);
 extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+extern void uprobe_start_dup_mmap(void);
+extern void uprobe_end_dup_mmap(void);
 extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm);
 extern void uprobe_free_utask(struct task_struct *t);
 extern void uprobe_copy_process(struct task_struct *t);
 extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
-extern void __weak arch_uprobe_enable_step(struct arch_uprobe *arch);
-extern void __weak arch_uprobe_disable_step(struct arch_uprobe *arch);
 extern int uprobe_post_sstep_notifier(struct pt_regs *regs);
 extern int uprobe_pre_sstep_notifier(struct pt_regs *regs);
 extern void uprobe_notify_resume(struct pt_regs *regs);
@@ -129,6 +129,12 @@ static inline void
 uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
 }
+static inline void uprobe_start_dup_mmap(void)
+{
+}
+static inline void uprobe_end_dup_mmap(void)
+{
+}
 static inline void
 uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
 {
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index a763888..40dc5e8 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -545,8 +545,7 @@ ftrace_raw_event_##call(void *__data, proto)				\
 	{ assign; }							\
 									\
 	if (!filter_current_check_discard(buffer, event_call, entry, event)) \
-		trace_nowake_buffer_unlock_commit(buffer,		\
-						  event, irq_flags, pc); \
+		trace_buffer_unlock_commit(buffer, event, irq_flags, pc); \
 }
 /*
  * The ftrace_test_probe is compiled out, it is only here as a build time check
@@ -620,79 +619,6 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-/*
- * Define the insertion callback to perf events
- *
- * The job is very similar to ftrace_raw_event_<call> except that we don't
- * insert in the ring buffer but in a perf counter.
- *
- * static void ftrace_perf_<call>(proto)
- * {
- *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
- *	struct ftrace_event_call *event_call = &event_<call>;
- *	extern void perf_tp_event(int, u64, u64, void *, int);
- *	struct ftrace_raw_##call *entry;
- *	struct perf_trace_buf *trace_buf;
- *	u64 __addr = 0, __count = 1;
- *	unsigned long irq_flags;
- *	struct trace_entry *ent;
- *	int __entry_size;
- *	int __data_size;
- *	int __cpu
- *	int pc;
- *
- *	pc = preempt_count();
- *
- *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
- *
- *	// Below we want to get the aligned size by taking into account
- *	// the u32 field that will later store the buffer size
- *	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),
- *			     sizeof(u64));
- *	__entry_size -= sizeof(u32);
- *
- *	// Protect the non nmi buffer
- *	// This also protects the rcu read side
- *	local_irq_save(irq_flags);
- *	__cpu = smp_processor_id();
- *
- *	if (in_nmi())
- *		trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
- *	else
- *		trace_buf = rcu_dereference_sched(perf_trace_buf);
- *
- *	if (!trace_buf)
- *		goto end;
- *
- *	trace_buf = per_cpu_ptr(trace_buf, __cpu);
- *
- * 	// Avoid recursion from perf that could mess up the buffer
- * 	if (trace_buf->recursion++)
- *		goto end_recursion;
- *
- * 	raw_data = trace_buf->buf;
- *
- *	// Make recursion update visible before entering perf_tp_event
- *	// so that we protect from perf recursions.
- *
- *	barrier();
- *
- *	//zero dead bytes from alignment to avoid stack leak to userspace:
- *	*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;
- *	entry = (struct ftrace_raw_<call> *)raw_data;
- *	ent = &entry->ent;
- *	tracing_generic_entry_update(ent, irq_flags, pc);
- *	ent->type = event_call->id;
- *
- *	<tstruct> <- do some jobs with dynamic arrays
- *
- *	<assign>  <- affect our values
- *
- *	perf_tp_event(event_call->id, __addr, __count, entry,
- *		     __entry_size);  <- submit them to perf counter
- *
- * }
- */
 
 #ifdef CONFIG_PERF_EVENTS
 
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 31966a4..84bc419 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -31,27 +31,4 @@ struct syscall_metadata {
 	struct ftrace_event_call *exit_event;
 };
 
-#ifdef CONFIG_FTRACE_SYSCALLS
-extern unsigned long arch_syscall_addr(int nr);
-extern int init_syscall_trace(struct ftrace_event_call *call);
-
-extern int reg_event_syscall_enter(struct ftrace_event_call *call);
-extern void unreg_event_syscall_enter(struct ftrace_event_call *call);
-extern int reg_event_syscall_exit(struct ftrace_event_call *call);
-extern void unreg_event_syscall_exit(struct ftrace_event_call *call);
-extern int
-ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s);
-enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags,
-				      struct trace_event *event);
-enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags,
-				     struct trace_event *event);
-#endif
-
-#ifdef CONFIG_PERF_EVENTS
-int perf_sysenter_enable(struct ftrace_event_call *call);
-void perf_sysenter_disable(struct ftrace_event_call *call);
-int perf_sysexit_enable(struct ftrace_event_call *call);
-void perf_sysexit_disable(struct ftrace_event_call *call);
-#endif
-
 #endif /* _TRACE_SYSCALL_H */