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

Pull perf changes from Ingo Molnar:
 "Lots of changes:

   - (much) improved assembly annotation support in perf report, with
     jump visualization, searching, navigation, visual output
     improvements and more.

    - kernel support for AMD IBS PMU hardware features.  Notably 'perf
      record -e cycles:p' and 'perf top -e cycles:p' should work without
      skid now, like PEBS does on the Intel side, because it takes
      advantage of IBS transparently.

    - the libtracevents library: it is the first step towards unifying
      tracing tooling and perf, and it also gives a tracing library for
      external tools like powertop to rely on.

    - infrastructure: various improvements and refactoring of the UI
      modules and related code

    - infrastructure: cleanup and simplification of the profiling
      targets code (--uid, --pid, --tid, --cpu, --all-cpus, etc.)

    - tons of robustness fixes all around

    - various ftrace updates: speedups, cleanups, robustness
      improvements.

    - typing 'make' in tools/ will now give you a menu of projects to
      build and a short help text to explain what each does.

    - ... and lots of other changes I forgot to list.

  The perf record make bzImage + perf report regression you reported
  should be fixed."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (166 commits)
  tracing: Remove kernel_lock annotations
  tracing: Fix initial buffer_size_kb state
  ring-buffer: Merge separate resize loops
  perf evsel: Create events initially disabled -- again
  perf tools: Split term type into value type and term type
  perf hists: Fix callchain ip printf format
  perf target: Add uses_mmap field
  ftrace: Remove selecting FRAME_POINTER with FUNCTION_TRACER
  ftrace/x86: Have x86 ftrace use the ftrace_modify_all_code()
  ftrace: Make ftrace_modify_all_code() global for archs to use
  ftrace: Return record ip addr for ftrace_location()
  ftrace: Consolidate ftrace_location() and ftrace_text_reserved()
  ftrace: Speed up search by skipping pages by address
  ftrace: Remove extra helper functions
  ftrace: Sort all function addresses, not just per page
  tracing: change CPU ring buffer state from tracing_cpumask
  tracing: Check return value of tracing_dentry_percpu()
  ring-buffer: Reset head page before running self test
  ring-buffer: Add integrity check at end of iter read
  ring-buffer: Make addition of pages in ring buffer atomic
  ...

5 files changed, 38 insertions, 31 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 8aeadf6..4e2e1cc 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -486,8 +486,8 @@
 	CPU_DISCARD(init.data)						\
 	MEM_DISCARD(init.data)						\
 	KERNEL_CTORS()							\
-	*(.init.rodata)							\
 	MCOUNT_REC()							\
+	*(.init.rodata)							\
 	FTRACE_EVENTS()							\
 	TRACE_SYSCALLS()						\
 	DEV_DISCARD(init.rodata)					\
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 72a6cab..55e6d63 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -286,10 +286,16 @@ struct ftrace_rec_iter *ftrace_rec_iter_start(void);
 struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter);
 struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter);
 
+#define for_ftrace_rec_iter(iter)		\
+	for (iter = ftrace_rec_iter_start();	\
+	     iter;				\
+	     iter = ftrace_rec_iter_next(iter))
+
+
 int ftrace_update_record(struct dyn_ftrace *rec, int enable);
 int ftrace_test_record(struct dyn_ftrace *rec, int enable);
 void ftrace_run_stop_machine(int command);
-int ftrace_location(unsigned long ip);
+unsigned long ftrace_location(unsigned long ip);
 
 extern ftrace_func_t ftrace_trace_function;
 
@@ -308,11 +314,14 @@ ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable);
 /* defined in arch */
 extern int ftrace_ip_converted(unsigned long ip);
 extern int ftrace_dyn_arch_init(void *data);
+extern void ftrace_replace_code(int enable);
 extern int ftrace_update_ftrace_func(ftrace_func_t func);
 extern void ftrace_caller(void);
 extern void ftrace_call(void);
 extern void mcount_call(void);
 
+void ftrace_modify_all_code(int command);
+
 #ifndef FTRACE_ADDR
 #define FTRACE_ADDR ((unsigned long)ftrace_caller)
 #endif
@@ -485,8 +494,12 @@ static inline void __ftrace_enabled_restore(int enabled)
   extern void trace_preempt_on(unsigned long a0, unsigned long a1);
   extern void trace_preempt_off(unsigned long a0, unsigned long a1);
 #else
-  static inline void trace_preempt_on(unsigned long a0, unsigned long a1) { }
-  static inline void trace_preempt_off(unsigned long a0, unsigned long a1) { }
+/*
+ * Use defines instead of static inlines because some arches will make code out
+ * of the CALLER_ADDR, when we really want these to be a real nop.
+ */
+# define trace_preempt_on(a0, a1) do { } while (0)
+# define trace_preempt_off(a0, a1) do { } while (0)
 #endif
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 645231c..c0d3442 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -480,15 +480,16 @@ do {									\
 
 #define trace_printk(fmt, args...)					\
 do {									\
+	static const char *trace_printk_fmt				\
+		__attribute__((section("__trace_printk_fmt"))) =	\
+		__builtin_constant_p(fmt) ? fmt : NULL;			\
+									\
 	__trace_printk_check_format(fmt, ##args);			\
-	if (__builtin_constant_p(fmt)) {				\
-		static const char *trace_printk_fmt			\
-		  __attribute__((section("__trace_printk_fmt"))) =	\
-			__builtin_constant_p(fmt) ? fmt : NULL;		\
 									\
+	if (__builtin_constant_p(fmt))					\
 		__trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args);	\
-	} else								\
-		__trace_printk(_THIS_IP_, fmt, ##args);		\
+	else								\
+		__trace_printk(_THIS_IP_, fmt, ##args);			\
 } while (0)
 
 extern __printf(2, 3)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index ddbb6a9..8adf70e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1084,10 +1084,8 @@ extern void perf_pmu_unregister(struct pmu *pmu);
 
 extern int perf_num_counters(void);
 extern const char *perf_pmu_name(void);
-extern void __perf_event_task_sched_in(struct task_struct *prev,
-				       struct task_struct *task);
-extern void __perf_event_task_sched_out(struct task_struct *prev,
-					struct task_struct *next);
+extern void __perf_event_task_sched(struct task_struct *prev,
+				    struct task_struct *next);
 extern int perf_event_init_task(struct task_struct *child);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
@@ -1132,11 +1130,14 @@ struct perf_sample_data {
 	struct perf_branch_stack	*br_stack;
 };
 
-static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
+static inline void perf_sample_data_init(struct perf_sample_data *data,
+					 u64 addr, u64 period)
 {
+	/* remaining struct members initialized in perf_prepare_sample() */
 	data->addr = addr;
 	data->raw  = NULL;
 	data->br_stack = NULL;
+	data->period	= period;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
@@ -1204,20 +1205,13 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 
 extern struct static_key_deferred perf_sched_events;
 
-static inline void perf_event_task_sched_in(struct task_struct *prev,
+static inline void perf_event_task_sched(struct task_struct *prev,
 					    struct task_struct *task)
 {
-	if (static_key_false(&perf_sched_events.key))
-		__perf_event_task_sched_in(prev, task);
-}
-
-static inline void perf_event_task_sched_out(struct task_struct *prev,
-					     struct task_struct *next)
-{
 	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
 
 	if (static_key_false(&perf_sched_events.key))
-		__perf_event_task_sched_out(prev, next);
+		__perf_event_task_sched(prev, task);
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);
@@ -1292,11 +1286,8 @@ extern void perf_event_disable(struct perf_event *event);
 extern void perf_event_task_tick(void);
 #else
 static inline void
-perf_event_task_sched_in(struct task_struct *prev,
-			 struct task_struct *task)			{ }
-static inline void
-perf_event_task_sched_out(struct task_struct *prev,
-			  struct task_struct *next)			{ }
+perf_event_task_sched(struct task_struct *prev,
+		      struct task_struct *task)				{ }
 static inline int perf_event_init_task(struct task_struct *child)	{ return 0; }
 static inline void perf_event_exit_task(struct task_struct *child)	{ }
 static inline void perf_event_free_task(struct task_struct *task)	{ }
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 7be2e88..6c8835f 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -96,9 +96,11 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k
 	__ring_buffer_alloc((size), (flags), &__key);	\
 })
 
+#define RING_BUFFER_ALL_CPUS -1
+
 void ring_buffer_free(struct ring_buffer *buffer);
 
-int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
+int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, int cpu);
 
 void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val);
 
@@ -129,7 +131,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts);
 void ring_buffer_iter_reset(struct ring_buffer_iter *iter);
 int ring_buffer_iter_empty(struct ring_buffer_iter *iter);
 
-unsigned long ring_buffer_size(struct ring_buffer *buffer);
+unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu);
 
 void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu);
 void ring_buffer_reset(struct ring_buffer *buffer);