Merge branch 'tracing-v28-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'tracing-v28-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (131 commits)
  tracing/fastboot: improve help text
  tracing/stacktrace: improve help text
  tracing/fastboot: fix initcalls disposition in bootgraph.pl
  tracing/fastboot: fix bootgraph.pl initcall name regexp
  tracing/fastboot: fix issues and improve output of bootgraph.pl
  tracepoints: synchronize unregister static inline
  tracepoints: tracepoint_synchronize_unregister()
  ftrace: make ftrace_test_p6nop disassembler-friendly
  markers: fix synchronize marker unregister static inline
  tracing/fastboot: add better resolution to initcall debug/tracing
  trace: add build-time check to avoid overrunning hex buffer
  ftrace: fix hex output mode of ftrace
  tracing/fastboot: fix initcalls disposition in bootgraph.pl
  tracing/fastboot: fix printk format typo in boot tracer
  ftrace: return an error when setting a nonexistent tracer
  ftrace: make some tracers reentrant
  ring-buffer: make reentrant
  ring-buffer: move page indexes into page headers
  tracing/fastboot: only trace non-module initcalls
  ftrace: move pc counter in irqtrace
  ...

Manually fix conflicts:
 - init/main.c: initcall tracing
 - kernel/module.c: verbose level vs tracepoints
 - scripts/bootgraph.pl: fallout from cherry-picking commits.

include/linux/compiler.h

@@ -44,6 +44,8 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # error Sorry, your compiler is too old/not recognized.
 #endif
 
+#define notrace __attribute__((no_instrument_function))
+
 /* Intel compiler defines __GNUC__. So we will overwrite implementations
  * coming from above header files here
  */

include/linux/ftrace.h

@@ -1,10 +1,14 @@
 #ifndef _LINUX_FTRACE_H
 #define _LINUX_FTRACE_H
 
-#ifdef CONFIG_FTRACE
-
 #include <linux/linkage.h>
 #include <linux/fs.h>
+#include <linux/ktime.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kallsyms.h>
+
+#ifdef CONFIG_FTRACE
 
 extern int ftrace_enabled;
 extern int
@@ -36,6 +40,7 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1);
 # define register_ftrace_function(ops) do { } while (0)
 # define unregister_ftrace_function(ops) do { } while (0)
 # define clear_ftrace_function(ops) do { } while (0)
+static inline void ftrace_kill_atomic(void) { }
 #endif /* CONFIG_FTRACE */
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -76,8 +81,10 @@ extern void mcount_call(void);
 
 extern int skip_trace(unsigned long ip);
 
-void ftrace_disable_daemon(void);
-void ftrace_enable_daemon(void);
+extern void ftrace_release(void *start, unsigned long size);
+
+extern void ftrace_disable_daemon(void);
+extern void ftrace_enable_daemon(void);
 
 #else
 # define skip_trace(ip)				({ 0; })
@@ -85,6 +92,7 @@ void ftrace_enable_daemon(void);
 # define ftrace_set_filter(buf, len, reset)	do { } while (0)
 # define ftrace_disable_daemon()		do { } while (0)
 # define ftrace_enable_daemon()			do { } while (0)
+static inline void ftrace_release(void *start, unsigned long size) { }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /* totally disable ftrace - can not re-enable after this */
@@ -98,9 +106,11 @@ static inline void tracer_disable(void)
 #endif
 }
 
-/* Ftrace disable/restore without lock. Some synchronization mechanism
+/*
+ * Ftrace disable/restore without lock. Some synchronization mechanism
  * must be used to prevent ftrace_enabled to be changed between
- * disable/restore. */
+ * disable/restore.
+ */
 static inline int __ftrace_enabled_save(void)
 {
 #ifdef CONFIG_FTRACE
@@ -157,9 +167,71 @@ static inline void __ftrace_enabled_restore(int enabled)
 #ifdef CONFIG_TRACING
 extern void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
+
+/**
+ * ftrace_printk - printf formatting in the ftrace buffer
+ * @fmt: the printf format for printing
+ *
+ * Note: __ftrace_printk is an internal function for ftrace_printk and
+ *       the @ip is passed in via the ftrace_printk macro.
+ *
+ * This function allows a kernel developer to debug fast path sections
+ * that printk is not appropriate for. By scattering in various
+ * printk like tracing in the code, a developer can quickly see
+ * where problems are occurring.
+ *
+ * This is intended as a debugging tool for the developer only.
+ * Please refrain from leaving ftrace_printks scattered around in
+ * your code.
+ */
+# define ftrace_printk(fmt...) __ftrace_printk(_THIS_IP_, fmt)
+extern int
+__ftrace_printk(unsigned long ip, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+extern void ftrace_dump(void);
 #else
 static inline void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
+static inline int
+ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)));
+
+static inline int
+ftrace_printk(const char *fmt, ...)
+{
+	return 0;
+}
+static inline void ftrace_dump(void) { }
 #endif
 
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+extern void ftrace_init(void);
+extern void ftrace_init_module(unsigned long *start, unsigned long *end);
+#else
+static inline void ftrace_init(void) { }
+static inline void
+ftrace_init_module(unsigned long *start, unsigned long *end) { }
+#endif
+
+
+struct boot_trace {
+	pid_t			caller;
+	char			func[KSYM_NAME_LEN];
+	int			result;
+	unsigned long long	duration;		/* usecs */
+	ktime_t			calltime;
+	ktime_t			rettime;
+};
+
+#ifdef CONFIG_BOOT_TRACER
+extern void trace_boot(struct boot_trace *it, initcall_t fn);
+extern void start_boot_trace(void);
+extern void stop_boot_trace(void);
+#else
+static inline void trace_boot(struct boot_trace *it, initcall_t fn) { }
+static inline void start_boot_trace(void) { }
+static inline void stop_boot_trace(void) { }
+#endif
+
+
+
 #endif /* _LINUX_FTRACE_H */

include/linux/init.h

@@ -40,7 +40,7 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text) __cold
+#define __init		__section(.init.text) __cold notrace
 #define __initdata	__section(.init.data)
 #define __initconst	__section(.init.rodata)
 #define __exitdata	__section(.exit.data)

include/linux/kernel.h

@@ -496,4 +496,9 @@ struct sysinfo {
 #define NUMA_BUILD 0
 #endif
 
+/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
+#endif
+
 #endif

include/linux/kprobes.h

@@ -29,6 +29,7 @@
  *		<jkenisto@us.ibm.com>  and Prasanna S Panchamukhi
  *		<prasanna@in.ibm.com> added function-return probes.
  */
+#include <linux/linkage.h>
 #include <linux/list.h>
 #include <linux/notifier.h>
 #include <linux/smp.h>
@@ -47,7 +48,7 @@
 #define KPROBE_HIT_SSDONE	0x00000008
 
 /* Attach to insert probes on any functions which should be ignored*/
-#define __kprobes	__attribute__((__section__(".kprobes.text")))
+#define __kprobes	__attribute__((__section__(".kprobes.text"))) notrace
 
 struct kprobe;
 struct pt_regs;
@@ -256,7 +257,7 @@ void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
 
 #else /* CONFIG_KPROBES */
 
-#define __kprobes	/**/
+#define __kprobes	notrace
 struct jprobe;
 struct kretprobe;
 

include/linux/linkage.h

@@ -4,8 +4,6 @@
 #include <linux/compiler.h>
 #include <asm/linkage.h>
 
-#define notrace __attribute__((no_instrument_function))
-
 #ifdef __cplusplus
 #define CPP_ASMLINKAGE extern "C"
 #else

include/linux/marker.h

@@ -160,4 +160,11 @@ extern int marker_probe_unregister_private_data(marker_probe_func *probe,
 extern void *marker_get_private_data(const char *name, marker_probe_func *probe,
 	int num);
 
+/*
+ * marker_synchronize_unregister must be called between the last marker probe
+ * unregistration and the end of module exit to make sure there is no caller
+ * executing a probe when it is freed.
+ */
+#define marker_synchronize_unregister() synchronize_sched()
+
 #endif

include/linux/mmiotrace.h

@@ -34,11 +34,15 @@ extern void unregister_kmmio_probe(struct kmmio_probe *p);
 /* Called from page fault handler. */
 extern int kmmio_handler(struct pt_regs *regs, unsigned long addr);
 
-/* Called from ioremap.c */
 #ifdef CONFIG_MMIOTRACE
+/* Called from ioremap.c */
 extern void mmiotrace_ioremap(resource_size_t offset, unsigned long size,
 							void __iomem *addr);
 extern void mmiotrace_iounmap(volatile void __iomem *addr);
+
+/* For anyone to insert markers. Remember trailing newline. */
+extern int mmiotrace_printk(const char *fmt, ...)
+				__attribute__ ((format (printf, 1, 2)));
 #else
 static inline void mmiotrace_ioremap(resource_size_t offset,
 					unsigned long size, void __iomem *addr)
@@ -48,15 +52,22 @@ static inline void mmiotrace_ioremap(resource_size_t offset,
 static inline void mmiotrace_iounmap(volatile void __iomem *addr)
 {
 }
-#endif /* CONFIG_MMIOTRACE_HOOKS */
+
+static inline int mmiotrace_printk(const char *fmt, ...)
+				__attribute__ ((format (printf, 1, 0)));
+
+static inline int mmiotrace_printk(const char *fmt, ...)
+{
+	return 0;
+}
+#endif /* CONFIG_MMIOTRACE */
 
 enum mm_io_opcode {
 	MMIO_READ = 0x1,     /* struct mmiotrace_rw */
 	MMIO_WRITE = 0x2,    /* struct mmiotrace_rw */
 	MMIO_PROBE = 0x3,    /* struct mmiotrace_map */
 	MMIO_UNPROBE = 0x4,  /* struct mmiotrace_map */
-	MMIO_MARKER = 0x5,   /* raw char data */
-	MMIO_UNKNOWN_OP = 0x6, /* struct mmiotrace_rw */
+	MMIO_UNKNOWN_OP = 0x5, /* struct mmiotrace_rw */
 };
 
 struct mmiotrace_rw {
@@ -81,5 +92,6 @@ extern void enable_mmiotrace(void);
 extern void disable_mmiotrace(void);
 extern void mmio_trace_rw(struct mmiotrace_rw *rw);
 extern void mmio_trace_mapping(struct mmiotrace_map *map);
+extern int mmio_trace_printk(const char *fmt, va_list args);
 
 #endif /* MMIOTRACE_H */

include/linux/module.h

@@ -16,6 +16,7 @@
 #include <linux/kobject.h>
 #include <linux/moduleparam.h>
 #include <linux/marker.h>
+#include <linux/tracepoint.h>
 #include <asm/local.h>
 
 #include <asm/module.h>
@@ -331,6 +332,10 @@ struct module
 	struct marker *markers;
 	unsigned int num_markers;
 #endif
+#ifdef CONFIG_TRACEPOINTS
+	struct tracepoint *tracepoints;
+	unsigned int num_tracepoints;
+#endif
 
 #ifdef CONFIG_MODULE_UNLOAD
 	/* What modules depend on me? */
@@ -453,6 +458,9 @@ extern void print_modules(void);
 
 extern void module_update_markers(void);
 
+extern void module_update_tracepoints(void);
+extern int module_get_iter_tracepoints(struct tracepoint_iter *iter);
+
 #else /* !CONFIG_MODULES... */
 #define EXPORT_SYMBOL(sym)
 #define EXPORT_SYMBOL_GPL(sym)
@@ -557,6 +565,15 @@ static inline void module_update_markers(void)
 {
 }
 
+static inline void module_update_tracepoints(void)
+{
+}
+
+static inline int module_get_iter_tracepoints(struct tracepoint_iter *iter)
+{
+	return 0;
+}
+
 #endif /* CONFIG_MODULES */
 
 struct device_driver;

include/linux/ring_buffer.h

@@ -0,0 +1,127 @@
+#ifndef _LINUX_RING_BUFFER_H
+#define _LINUX_RING_BUFFER_H
+
+#include <linux/mm.h>
+#include <linux/seq_file.h>
+
+struct ring_buffer;
+struct ring_buffer_iter;
+
+/*
+ * Don't reference this struct directly, use functions below.
+ */
+struct ring_buffer_event {
+	u32		type:2, len:3, time_delta:27;
+	u32		array[];
+};
+
+/**
+ * enum ring_buffer_type - internal ring buffer types
+ *
+ * @RINGBUF_TYPE_PADDING:	Left over page padding
+ *				 array is ignored
+ *				 size is variable depending on how much
+ *				  padding is needed
+ *
+ * @RINGBUF_TYPE_TIME_EXTEND:	Extend the time delta
+ *				 array[0] = time delta (28 .. 59)
+ *				 size = 8 bytes
+ *
+ * @RINGBUF_TYPE_TIME_STAMP:	Sync time stamp with external clock
+ *				 array[0] = tv_nsec
+ *				 array[1] = tv_sec
+ *				 size = 16 bytes
+ *
+ * @RINGBUF_TYPE_DATA:		Data record
+ *				 If len is zero:
+ *				  array[0] holds the actual length
+ *				  array[1..(length+3)/4-1] holds data
+ *				 else
+ *				  length = len << 2
+ *				  array[0..(length+3)/4] holds data
+ */
+enum ring_buffer_type {
+	RINGBUF_TYPE_PADDING,
+	RINGBUF_TYPE_TIME_EXTEND,
+	/* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
+	RINGBUF_TYPE_TIME_STAMP,
+	RINGBUF_TYPE_DATA,
+};
+
+unsigned ring_buffer_event_length(struct ring_buffer_event *event);
+void *ring_buffer_event_data(struct ring_buffer_event *event);
+
+/**
+ * ring_buffer_event_time_delta - return the delta timestamp of the event
+ * @event: the event to get the delta timestamp of
+ *
+ * The delta timestamp is the 27 bit timestamp since the last event.
+ */
+static inline unsigned
+ring_buffer_event_time_delta(struct ring_buffer_event *event)
+{
+	return event->time_delta;
+}
+
+/*
+ * size is in bytes for each per CPU buffer.
+ */
+struct ring_buffer *
+ring_buffer_alloc(unsigned long size, unsigned flags);
+void ring_buffer_free(struct ring_buffer *buffer);
+
+int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
+
+struct ring_buffer_event *
+ring_buffer_lock_reserve(struct ring_buffer *buffer,
+			 unsigned long length,
+			 unsigned long *flags);
+int ring_buffer_unlock_commit(struct ring_buffer *buffer,
+			      struct ring_buffer_event *event,
+			      unsigned long flags);
+int ring_buffer_write(struct ring_buffer *buffer,
+		      unsigned long length, void *data);
+
+struct ring_buffer_event *
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts);
+struct ring_buffer_event *
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts);
+
+struct ring_buffer_iter *
+ring_buffer_read_start(struct ring_buffer *buffer, int cpu);
+void ring_buffer_read_finish(struct ring_buffer_iter *iter);
+
+struct ring_buffer_event *
+ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts);
+struct ring_buffer_event *
+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);
+
+void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu);
+void ring_buffer_reset(struct ring_buffer *buffer);
+
+int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
+			 struct ring_buffer *buffer_b, int cpu);
+
+int ring_buffer_empty(struct ring_buffer *buffer);
+int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
+
+void ring_buffer_record_disable(struct ring_buffer *buffer);
+void ring_buffer_record_enable(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_entries(struct ring_buffer *buffer);
+unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
+
+u64 ring_buffer_time_stamp(int cpu);
+void ring_buffer_normalize_time_stamp(int cpu, u64 *ts);
+
+enum ring_buffer_flags {
+	RB_FL_OVERWRITE		= 1 << 0,
+};
+
+#endif /* _LINUX_RING_BUFFER_H */

include/linux/tracepoint.h

@@ -0,0 +1,137 @@
+#ifndef _LINUX_TRACEPOINT_H
+#define _LINUX_TRACEPOINT_H
+
+/*
+ * Kernel Tracepoint API.
+ *
+ * See Documentation/tracepoint.txt.
+ *
+ * (C) Copyright 2008 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
+ *
+ * Heavily inspired from the Linux Kernel Markers.
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+
+struct module;
+struct tracepoint;
+
+struct tracepoint {
+	const char *name;		/* Tracepoint name */
+	int state;			/* State. */
+	void **funcs;
+} __attribute__((aligned(8)));
+
+
+#define TPPROTO(args...)	args
+#define TPARGS(args...)		args
+
+#ifdef CONFIG_TRACEPOINTS
+
+/*
+ * it_func[0] is never NULL because there is at least one element in the array
+ * when the array itself is non NULL.
+ */
+#define __DO_TRACE(tp, proto, args)					\
+	do {								\
+		void **it_func;						\
+									\
+		rcu_read_lock_sched();					\
+		it_func = rcu_dereference((tp)->funcs);			\
+		if (it_func) {						\
+			do {						\
+				((void(*)(proto))(*it_func))(args);	\
+			} while (*(++it_func));				\
+		}							\
+		rcu_read_unlock_sched();				\
+	} while (0)
+
+/*
+ * Make sure the alignment of the structure in the __tracepoints section will
+ * not add unwanted padding between the beginning of the section and the
+ * structure. Force alignment to the same alignment as the section start.
+ */
+#define DEFINE_TRACE(name, proto, args)					\
+	static inline void trace_##name(proto)				\
+	{								\
+		static const char __tpstrtab_##name[]			\
+		__attribute__((section("__tracepoints_strings")))	\
+		= #name ":" #proto;					\
+		static struct tracepoint __tracepoint_##name		\
+		__attribute__((section("__tracepoints"), aligned(8))) =	\
+		{ __tpstrtab_##name, 0, NULL };				\
+		if (unlikely(__tracepoint_##name.state))		\
+			__DO_TRACE(&__tracepoint_##name,		\
+				TPPROTO(proto), TPARGS(args));		\
+	}								\
+	static inline int register_trace_##name(void (*probe)(proto))	\
+	{								\
+		return tracepoint_probe_register(#name ":" #proto,	\
+			(void *)probe);					\
+	}								\
+	static inline void unregister_trace_##name(void (*probe)(proto))\
+	{								\
+		tracepoint_probe_unregister(#name ":" #proto,		\
+			(void *)probe);					\
+	}
+
+extern void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end);
+
+#else /* !CONFIG_TRACEPOINTS */
+#define DEFINE_TRACE(name, proto, args)			\
+	static inline void _do_trace_##name(struct tracepoint *tp, proto) \
+	{ }								\
+	static inline void trace_##name(proto)				\
+	{ }								\
+	static inline int register_trace_##name(void (*probe)(proto))	\
+	{								\
+		return -ENOSYS;						\
+	}								\
+	static inline void unregister_trace_##name(void (*probe)(proto))\
+	{ }
+
+static inline void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end)
+{ }
+#endif /* CONFIG_TRACEPOINTS */
+
+/*
+ * Connect a probe to a tracepoint.
+ * Internal API, should not be used directly.
+ */
+extern int tracepoint_probe_register(const char *name, void *probe);
+
+/*
+ * Disconnect a probe from a tracepoint.
+ * Internal API, should not be used directly.
+ */
+extern int tracepoint_probe_unregister(const char *name, void *probe);
+
+struct tracepoint_iter {
+	struct module *module;
+	struct tracepoint *tracepoint;
+};
+
+extern void tracepoint_iter_start(struct tracepoint_iter *iter);
+extern void tracepoint_iter_next(struct tracepoint_iter *iter);
+extern void tracepoint_iter_stop(struct tracepoint_iter *iter);
+extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
+extern int tracepoint_get_iter_range(struct tracepoint **tracepoint,
+	struct tracepoint *begin, struct tracepoint *end);
+
+/*
+ * tracepoint_synchronize_unregister must be called between the last tracepoint
+ * probe unregistration and the end of module exit to make sure there is no
+ * caller executing a probe when it is freed.
+ */
+static inline void tracepoint_synchronize_unregister(void)
+{
+	synchronize_sched();
+}
+
+#endif