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

* 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (413 commits)
  tracing, net: fix net tree and tracing tree merge interaction
  tracing, powerpc: fix powerpc tree and tracing tree interaction
  ring-buffer: do not remove reader page from list on ring buffer free
  function-graph: allow unregistering twice
  trace: make argument 'mem' of trace_seq_putmem() const
  tracing: add missing 'extern' keywords to trace_output.h
  tracing: provide trace_seq_reserve()
  blktrace: print out BLK_TN_MESSAGE properly
  blktrace: extract duplidate code
  blktrace: fix memory leak when freeing struct blk_io_trace
  blktrace: fix blk_probes_ref chaos
  blktrace: make classic output more classic
  blktrace: fix off-by-one bug
  blktrace: fix the original blktrace
  blktrace: fix a race when creating blk_tree_root in debugfs
  blktrace: fix timestamp in binary output
  tracing, Text Edit Lock: cleanup
  tracing: filter fix for TRACE_EVENT_FORMAT events
  ftrace: Using FTRACE_WARN_ON() to check "freed record" in ftrace_release()
  x86: kretprobe-booster interrupt emulation code fix
  ...

Fix up trivial conflicts in
 arch/parisc/include/asm/ftrace.h
 include/linux/memory.h
 kernel/extable.c
 kernel/module.c

include/linux/blktrace_api.h

@@ -144,6 +144,9 @@ struct blk_user_trace_setup {
 
 #ifdef __KERNEL__
 #if defined(CONFIG_BLK_DEV_IO_TRACE)
+
+#include <linux/sysfs.h>
+
 struct blk_trace {
 	int trace_state;
 	struct rchan *rchan;
@@ -194,6 +197,8 @@ extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 extern int blk_trace_startstop(struct request_queue *q, int start);
 extern int blk_trace_remove(struct request_queue *q);
 
+extern struct attribute_group blk_trace_attr_group;
+
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
 #define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
 #define blk_trace_shutdown(q)			do { } while (0)

include/linux/compiler.h

@@ -68,6 +68,7 @@ struct ftrace_branch_data {
 			unsigned long miss;
 			unsigned long hit;
 		};
+		unsigned long miss_hit[2];
 	};
 };
 
@@ -125,10 +126,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 				.line = __LINE__,			\
 			};						\
 		______r = !!(cond);					\
-		if (______r)						\
-			______f.hit++;					\
-		else							\
-			______f.miss++;					\
+		______f.miss_hit[______r]++;					\
 		______r;						\
 	}))
 #endif /* CONFIG_PROFILE_ALL_BRANCHES */

include/linux/debugfs.h

@@ -71,6 +71,9 @@ struct dentry *debugfs_create_bool(const char *name, mode_t mode,
 struct dentry *debugfs_create_blob(const char *name, mode_t mode,
 				  struct dentry *parent,
 				  struct debugfs_blob_wrapper *blob);
+
+bool debugfs_initialized(void);
+
 #else
 
 #include <linux/err.h>
@@ -183,6 +186,11 @@ static inline struct dentry *debugfs_create_blob(const char *name, mode_t mode,
 	return ERR_PTR(-ENODEV);
 }
 
+static inline bool debugfs_initialized(void)
+{
+	return false;
+}
+
 #endif
 
 #endif

include/linux/ftrace.h

@@ -1,15 +1,18 @@
 #ifndef _LINUX_FTRACE_H
 #define _LINUX_FTRACE_H
 
-#include <linux/linkage.h>
-#include <linux/fs.h>
-#include <linux/ktime.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/module.h>
+#include <linux/trace_clock.h>
 #include <linux/kallsyms.h>
+#include <linux/linkage.h>
 #include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/ktime.h>
 #include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+
+#include <asm/ftrace.h>
 
 #ifdef CONFIG_FUNCTION_TRACER
 
@@ -95,9 +98,41 @@ stack_trace_sysctl(struct ctl_table *table, int write,
 		   loff_t *ppos);
 #endif
 
+struct ftrace_func_command {
+	struct list_head	list;
+	char			*name;
+	int			(*func)(char *func, char *cmd,
+					char *params, int enable);
+};
+
 #ifdef CONFIG_DYNAMIC_FTRACE
-/* asm/ftrace.h must be defined for archs supporting dynamic ftrace */
-#include <asm/ftrace.h>
+
+int ftrace_arch_code_modify_prepare(void);
+int ftrace_arch_code_modify_post_process(void);
+
+struct seq_file;
+
+struct ftrace_probe_ops {
+	void			(*func)(unsigned long ip,
+					unsigned long parent_ip,
+					void **data);
+	int			(*callback)(unsigned long ip, void **data);
+	void			(*free)(void **data);
+	int			(*print)(struct seq_file *m,
+					 unsigned long ip,
+					 struct ftrace_probe_ops *ops,
+					 void *data);
+};
+
+extern int
+register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
+			      void *data);
+extern void
+unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
+				void *data);
+extern void
+unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops);
+extern void unregister_ftrace_function_probe_all(char *glob);
 
 enum {
 	FTRACE_FL_FREE		= (1 << 0),
@@ -110,15 +145,23 @@ enum {
 };
 
 struct dyn_ftrace {
-	struct list_head	list;
-	unsigned long		ip; /* address of mcount call-site */
-	unsigned long		flags;
-	struct dyn_arch_ftrace	arch;
+	union {
+		unsigned long		ip; /* address of mcount call-site */
+		struct dyn_ftrace	*freelist;
+	};
+	union {
+		unsigned long		flags;
+		struct dyn_ftrace	*newlist;
+	};
+	struct dyn_arch_ftrace		arch;
 };
 
 int ftrace_force_update(void);
 void ftrace_set_filter(unsigned char *buf, int len, int reset);
 
+int register_ftrace_command(struct ftrace_func_command *cmd);
+int unregister_ftrace_command(struct ftrace_func_command *cmd);
+
 /* defined in arch */
 extern int ftrace_ip_converted(unsigned long ip);
 extern int ftrace_dyn_arch_init(void *data);
@@ -126,6 +169,10 @@ 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);
+
+#ifndef FTRACE_ADDR
+#define FTRACE_ADDR ((unsigned long)ftrace_caller)
+#endif
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 extern void ftrace_graph_caller(void);
 extern int ftrace_enable_ftrace_graph_caller(void);
@@ -136,7 +183,7 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; }
 #endif
 
 /**
- * ftrace_make_nop - convert code into top
+ * ftrace_make_nop - convert code into nop
  * @mod: module structure if called by module load initialization
  * @rec: the mcount call site record
  * @addr: the address that the call site should be calling
@@ -181,7 +228,6 @@ extern int ftrace_make_nop(struct module *mod,
  */
 extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
 
-
 /* May be defined in arch */
 extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
@@ -198,6 +244,14 @@ extern void ftrace_enable_daemon(void);
 # define ftrace_disable_daemon()		do { } while (0)
 # define ftrace_enable_daemon()			do { } while (0)
 static inline void ftrace_release(void *start, unsigned long size) { }
+static inline int register_ftrace_command(struct ftrace_func_command *cmd)
+{
+	return -EINVAL;
+}
+static inline int unregister_ftrace_command(char *cmd_name)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /* totally disable ftrace - can not re-enable after this */
@@ -233,24 +287,25 @@ static inline void __ftrace_enabled_restore(int enabled)
 #endif
 }
 
-#ifdef CONFIG_FRAME_POINTER
-/* TODO: need to fix this for ARM */
-# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-# define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
-# define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2))
-# define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3))
-# define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4))
-# define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5))
-# define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6))
-#else
-# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-# define CALLER_ADDR1 0UL
-# define CALLER_ADDR2 0UL
-# define CALLER_ADDR3 0UL
-# define CALLER_ADDR4 0UL
-# define CALLER_ADDR5 0UL
-# define CALLER_ADDR6 0UL
-#endif
+#ifndef HAVE_ARCH_CALLER_ADDR
+# ifdef CONFIG_FRAME_POINTER
+#  define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#  define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
+#  define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2))
+#  define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3))
+#  define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4))
+#  define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5))
+#  define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6))
+# else
+#  define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#  define CALLER_ADDR1 0UL
+#  define CALLER_ADDR2 0UL
+#  define CALLER_ADDR3 0UL
+#  define CALLER_ADDR4 0UL
+#  define CALLER_ADDR5 0UL
+#  define CALLER_ADDR6 0UL
+# endif
+#endif /* ifndef HAVE_ARCH_CALLER_ADDR */
 
 #ifdef CONFIG_IRQSOFF_TRACER
   extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
@@ -268,54 +323,6 @@ static inline void __ftrace_enabled_restore(int enabled)
 # define trace_preempt_off(a0, a1)		do { } while (0)
 #endif
 
-#ifdef CONFIG_TRACING
-extern int ftrace_dump_on_oops;
-
-extern void tracing_start(void);
-extern void tracing_stop(void);
-extern void ftrace_off_permanent(void);
-
-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, 2)));
-
-static inline void tracing_start(void) { }
-static inline void tracing_stop(void) { }
-static inline void ftrace_off_permanent(void) { }
-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(struct module *mod,
@@ -327,36 +334,6 @@ ftrace_init_module(struct module *mod,
 		   unsigned long *start, unsigned long *end) { }
 #endif
 
-enum {
-	POWER_NONE = 0,
-	POWER_CSTATE = 1,
-	POWER_PSTATE = 2,
-};
-
-struct power_trace {
-#ifdef CONFIG_POWER_TRACER
-	ktime_t			stamp;
-	ktime_t			end;
-	int			type;
-	int			state;
-#endif
-};
-
-#ifdef CONFIG_POWER_TRACER
-extern void trace_power_start(struct power_trace *it, unsigned int type,
-					unsigned int state);
-extern void trace_power_mark(struct power_trace *it, unsigned int type,
-					unsigned int state);
-extern void trace_power_end(struct power_trace *it);
-#else
-static inline void trace_power_start(struct power_trace *it, unsigned int type,
-					unsigned int state) { }
-static inline void trace_power_mark(struct power_trace *it, unsigned int type,
-					unsigned int state) { }
-static inline void trace_power_end(struct power_trace *it) { }
-#endif
-
-
 /*
  * Structure that defines an entry function trace.
  */
@@ -398,8 +375,7 @@ struct ftrace_ret_stack {
 extern void return_to_handler(void);
 
 extern int
-ftrace_push_return_trace(unsigned long ret, unsigned long long time,
-			 unsigned long func, int *depth);
+ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth);
 extern void
 ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret);
 
@@ -514,6 +490,50 @@ static inline int test_tsk_trace_graph(struct task_struct *tsk)
 	return tsk->trace & TSK_TRACE_FL_GRAPH;
 }
 
+extern int ftrace_dump_on_oops;
+
 #endif /* CONFIG_TRACING */
 
+
+#ifdef CONFIG_HW_BRANCH_TRACER
+
+void trace_hw_branch(u64 from, u64 to);
+void trace_hw_branch_oops(void);
+
+#else /* CONFIG_HW_BRANCH_TRACER */
+
+static inline void trace_hw_branch(u64 from, u64 to) {}
+static inline void trace_hw_branch_oops(void) {}
+
+#endif /* CONFIG_HW_BRANCH_TRACER */
+
+/*
+ * A syscall entry in the ftrace syscalls array.
+ *
+ * @name: name of the syscall
+ * @nb_args: number of parameters it takes
+ * @types: list of types as strings
+ * @args: list of args as strings (args[i] matches types[i])
+ */
+struct syscall_metadata {
+	const char	*name;
+	int		nb_args;
+	const char	**types;
+	const char	**args;
+};
+
+#ifdef CONFIG_FTRACE_SYSCALLS
+extern void arch_init_ftrace_syscalls(void);
+extern struct syscall_metadata *syscall_nr_to_meta(int nr);
+extern void start_ftrace_syscalls(void);
+extern void stop_ftrace_syscalls(void);
+extern void ftrace_syscall_enter(struct pt_regs *regs);
+extern void ftrace_syscall_exit(struct pt_regs *regs);
+#else
+static inline void start_ftrace_syscalls(void) { }
+static inline void stop_ftrace_syscalls(void) { }
+static inline void ftrace_syscall_enter(struct pt_regs *regs) { }
+static inline void ftrace_syscall_exit(struct pt_regs *regs) { }
+#endif
+
 #endif /* _LINUX_FTRACE_H */

include/linux/ftrace_irq.h

@@ -2,7 +2,7 @@
 #define _LINUX_FTRACE_IRQ_H
 
 
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_FUNCTION_GRAPH_TRACER)
+#ifdef CONFIG_FTRACE_NMI_ENTER
 extern void ftrace_nmi_enter(void);
 extern void ftrace_nmi_exit(void);
 #else

include/linux/hardirq.h

@@ -15,55 +15,61 @@
  * - bits 0-7 are the preemption count (max preemption depth: 256)
  * - bits 8-15 are the softirq count (max # of softirqs: 256)
  *
- * The hardirq count can be overridden per architecture, the default is:
+ * The hardirq count can in theory reach the same as NR_IRQS.
+ * In reality, the number of nested IRQS is limited to the stack
+ * size as well. For archs with over 1000 IRQS it is not practical
+ * to expect that they will all nest. We give a max of 10 bits for
+ * hardirq nesting. An arch may choose to give less than 10 bits.
+ * m68k expects it to be 8.
  *
- * - bits 16-27 are the hardirq count (max # of hardirqs: 4096)
- * - ( bit 28 is the PREEMPT_ACTIVE flag. )
+ * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024)
+ * - bit 26 is the NMI_MASK
+ * - bit 28 is the PREEMPT_ACTIVE flag
  *
  * PREEMPT_MASK: 0x000000ff
  * SOFTIRQ_MASK: 0x0000ff00
- * HARDIRQ_MASK: 0x0fff0000
+ * HARDIRQ_MASK: 0x03ff0000
+ *     NMI_MASK: 0x04000000
  */
 #define PREEMPT_BITS	8
 #define SOFTIRQ_BITS	8
+#define NMI_BITS	1
+
+#define MAX_HARDIRQ_BITS 10
 
 #ifndef HARDIRQ_BITS
-#define HARDIRQ_BITS	12
-
-#ifndef MAX_HARDIRQS_PER_CPU
-#define MAX_HARDIRQS_PER_CPU NR_IRQS
+# define HARDIRQ_BITS	MAX_HARDIRQ_BITS
 #endif
 
-/*
- * The hardirq mask has to be large enough to have space for potentially
- * all IRQ sources in the system nesting on a single CPU.
- */
-#if (1 << HARDIRQ_BITS) < MAX_HARDIRQS_PER_CPU
-# error HARDIRQ_BITS is too low!
-#endif
+#if HARDIRQ_BITS > MAX_HARDIRQ_BITS
+#error HARDIRQ_BITS too high!
 #endif
 
 #define PREEMPT_SHIFT	0
 #define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
 #define HARDIRQ_SHIFT	(SOFTIRQ_SHIFT + SOFTIRQ_BITS)
+#define NMI_SHIFT	(HARDIRQ_SHIFT + HARDIRQ_BITS)
 
 #define __IRQ_MASK(x)	((1UL << (x))-1)
 
 #define PREEMPT_MASK	(__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
 #define SOFTIRQ_MASK	(__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
 #define HARDIRQ_MASK	(__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
+#define NMI_MASK	(__IRQ_MASK(NMI_BITS)     << NMI_SHIFT)
 
 #define PREEMPT_OFFSET	(1UL << PREEMPT_SHIFT)
 #define SOFTIRQ_OFFSET	(1UL << SOFTIRQ_SHIFT)
 #define HARDIRQ_OFFSET	(1UL << HARDIRQ_SHIFT)
+#define NMI_OFFSET	(1UL << NMI_SHIFT)
 
-#if PREEMPT_ACTIVE < (1 << (HARDIRQ_SHIFT + HARDIRQ_BITS))
+#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS))
 #error PREEMPT_ACTIVE is too low!
 #endif
 
 #define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
 #define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
-#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK))
+#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
+				 | NMI_MASK))
 
 /*
  * Are we doing bottom half or hardware interrupt processing?
@@ -73,6 +79,11 @@
 #define in_softirq()		(softirq_count())
 #define in_interrupt()		(irq_count())
 
+/*
+ * Are we in NMI context?
+ */
+#define in_nmi()	(preempt_count() & NMI_MASK)
+
 #if defined(CONFIG_PREEMPT)
 # define PREEMPT_INATOMIC_BASE kernel_locked()
 # define PREEMPT_CHECK_OFFSET 1
@@ -164,20 +175,24 @@ extern void irq_enter(void);
  */
 extern void irq_exit(void);
 
-#define nmi_enter()				\
-	do {					\
-		ftrace_nmi_enter();		\
-		lockdep_off();			\
-		rcu_nmi_enter();		\
-		__irq_enter();			\
+#define nmi_enter()						\
+	do {							\
+		ftrace_nmi_enter();				\
+		BUG_ON(in_nmi());				\
+		add_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		lockdep_off();					\
+		rcu_nmi_enter();				\
+		trace_hardirq_enter();				\
 	} while (0)
 
-#define nmi_exit()				\
-	do {					\
-		__irq_exit();			\
-		rcu_nmi_exit();			\
-		lockdep_on();			\
-		ftrace_nmi_exit();		\
+#define nmi_exit()						\
+	do {							\
+		trace_hardirq_exit();				\
+		rcu_nmi_exit();					\
+		lockdep_on();					\
+		BUG_ON(!in_nmi());				\
+		sub_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		ftrace_nmi_exit();				\
 	} while (0)
 
 #endif /* LINUX_HARDIRQ_H */

include/linux/interrupt.h

@@ -278,6 +278,11 @@ enum
 	NR_SOFTIRQS
 };
 
+/* map softirq index to softirq name. update 'softirq_to_name' in
+ * kernel/softirq.c when adding a new softirq.
+ */
+extern char *softirq_to_name[NR_SOFTIRQS];
+
 /* softirq mask and active fields moved to irq_cpustat_t in
  * asm/hardirq.h to get better cache usage.  KAO
  */

include/linux/kernel.h

@@ -391,6 +391,139 @@ static inline char *pack_hex_byte(char *buf, u8 byte)
 	({ if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); 0; })
 #endif
 
+/*
+ * General tracing related utility functions - trace_printk(),
+ * tracing_on/tracing_off and tracing_start()/tracing_stop
+ *
+ * Use tracing_on/tracing_off when you want to quickly turn on or off
+ * tracing. It simply enables or disables the recording of the trace events.
+ * This also corresponds to the user space debugfs/tracing/tracing_on
+ * file, which gives a means for the kernel and userspace to interact.
+ * Place a tracing_off() in the kernel where you want tracing to end.
+ * From user space, examine the trace, and then echo 1 > tracing_on
+ * to continue tracing.
+ *
+ * tracing_stop/tracing_start has slightly more overhead. It is used
+ * by things like suspend to ram where disabling the recording of the
+ * trace is not enough, but tracing must actually stop because things
+ * like calling smp_processor_id() may crash the system.
+ *
+ * Most likely, you want to use tracing_on/tracing_off.
+ */
+#ifdef CONFIG_RING_BUFFER
+void tracing_on(void);
+void tracing_off(void);
+/* trace_off_permanent stops recording with no way to bring it back */
+void tracing_off_permanent(void);
+int tracing_is_on(void);
+#else
+static inline void tracing_on(void) { }
+static inline void tracing_off(void) { }
+static inline void tracing_off_permanent(void) { }
+static inline int tracing_is_on(void) { return 0; }
+#endif
+#ifdef CONFIG_TRACING
+extern void tracing_start(void);
+extern void tracing_stop(void);
+extern void ftrace_off_permanent(void);
+
+extern void
+ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
+
+static inline void __attribute__ ((format (printf, 1, 2)))
+____trace_printk_check_format(const char *fmt, ...)
+{
+}
+#define __trace_printk_check_format(fmt, args...)			\
+do {									\
+	if (0)								\
+		____trace_printk_check_format(fmt, ##args);		\
+} while (0)
+
+/**
+ * trace_printk - printf formatting in the ftrace buffer
+ * @fmt: the printf format for printing
+ *
+ * Note: __trace_printk is an internal function for trace_printk and
+ *       the @ip is passed in via the trace_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 trace_printks scattered around in
+ * your code.
+ */
+
+#define trace_printk(fmt, args...)					\
+do {									\
+	__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;		\
+									\
+		__trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args);	\
+	} else								\
+		__trace_printk(_THIS_IP_, fmt, ##args);		\
+} while (0)
+
+extern int
+__trace_bprintk(unsigned long ip, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+
+extern int
+__trace_printk(unsigned long ip, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+
+/*
+ * The double __builtin_constant_p is because gcc will give us an error
+ * if we try to allocate the static variable to fmt if it is not a
+ * constant. Even with the outer if statement.
+ */
+#define ftrace_vprintk(fmt, vargs)					\
+do {									\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
+									\
+		__ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs);	\
+	} else								\
+		__ftrace_vprintk(_THIS_IP_, fmt, vargs);		\
+} while (0)
+
+extern int
+__ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
+
+extern int
+__ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
+
+extern void ftrace_dump(void);
+#else
+static inline void
+ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
+static inline int
+trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2)));
+
+static inline void tracing_start(void) { }
+static inline void tracing_stop(void) { }
+static inline void ftrace_off_permanent(void) { }
+static inline int
+trace_printk(const char *fmt, ...)
+{
+	return 0;
+}
+static inline int
+ftrace_vprintk(const char *fmt, va_list ap)
+{
+	return 0;
+}
+static inline void ftrace_dump(void) { }
+#endif /* CONFIG_TRACING */
+
 /*
  *      Display an IP address in readable format.
  */

include/linux/memory.h

@@ -110,4 +110,10 @@ struct memory_accessor {
 			 off_t offset, size_t count);
 };
 
+/*
+ * Kernel text modification mutex, used for code patching. Users of this lock
+ * can sleep.
+ */
+extern struct mutex text_mutex;
+
 #endif /* _LINUX_MEMORY_H_ */

include/linux/module.h

@@ -333,6 +333,11 @@ struct module
 	unsigned int num_tracepoints;
 #endif
 
+#ifdef CONFIG_TRACING
+	const char **trace_bprintk_fmt_start;
+	unsigned int num_trace_bprintk_fmt;
+#endif
+
 #ifdef CONFIG_MODULE_UNLOAD
 	/* What modules depend on me? */
 	struct list_head modules_which_use_me;

include/linux/ring_buffer.h

@@ -8,7 +8,7 @@ struct ring_buffer;
 struct ring_buffer_iter;
 
 /*
- * Don't reference this struct directly, use functions below.
+ * Don't refer to this struct directly, use functions below.
  */
 struct ring_buffer_event {
 	u32		type:2, len:3, time_delta:27;
@@ -18,10 +18,13 @@ struct ring_buffer_event {
 /**
  * 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
+ * @RINGBUF_TYPE_PADDING:	Left over page padding or discarded event
+ *				 If time_delta is 0:
+ *				  array is ignored
+ *				  size is variable depending on how much
  *				  padding is needed
+ *				 If time_delta is non zero:
+ *				  everything else same as RINGBUF_TYPE_DATA
  *
  * @RINGBUF_TYPE_TIME_EXTEND:	Extend the time delta
  *				 array[0] = time delta (28 .. 59)
@@ -65,6 +68,8 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event)
 	return event->time_delta;
 }
 
+void ring_buffer_event_discard(struct ring_buffer_event *event);
+
 /*
  * size is in bytes for each per CPU buffer.
  */
@@ -74,13 +79,10 @@ 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);
+struct ring_buffer_event *ring_buffer_lock_reserve(struct ring_buffer *buffer,
+						   unsigned long length);
 int ring_buffer_unlock_commit(struct ring_buffer *buffer,
-			      struct ring_buffer_event *event,
-			      unsigned long flags);
+			      struct ring_buffer_event *event);
 int ring_buffer_write(struct ring_buffer *buffer,
 		      unsigned long length, void *data);
 
@@ -121,17 +123,19 @@ 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);
 
-u64 ring_buffer_time_stamp(int cpu);
-void ring_buffer_normalize_time_stamp(int cpu, u64 *ts);
+u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
+void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
+				      int cpu, u64 *ts);
+void ring_buffer_set_clock(struct ring_buffer *buffer,
+			   u64 (*clock)(void));
+
+size_t ring_buffer_page_len(void *page);
 
-void tracing_on(void);
-void tracing_off(void);
-void tracing_off_permanent(void);
 
 void *ring_buffer_alloc_read_page(struct ring_buffer *buffer);
 void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data);
-int ring_buffer_read_page(struct ring_buffer *buffer,
-			  void **data_page, int cpu, int full);
+int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page,
+			  size_t len, int cpu, int full);
 
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,

include/linux/sched.h

@@ -138,6 +138,8 @@ extern unsigned long nr_uninterruptible(void);
 extern unsigned long nr_active(void);
 extern unsigned long nr_iowait(void);
 
+extern unsigned long get_parent_ip(unsigned long addr);
+
 struct seq_file;
 struct cfs_rq;
 struct task_group;
@@ -1405,6 +1407,8 @@ struct task_struct {
 	int curr_ret_stack;
 	/* Stack of return addresses for return function tracing */
 	struct ftrace_ret_stack	*ret_stack;
+	/* time stamp for last schedule */
+	unsigned long long ftrace_timestamp;
 	/*
 	 * Number of functions that haven't been traced
 	 * because of depth overrun.

include/linux/slab_def.h

@@ -14,6 +14,7 @@
 #include <asm/page.h>		/* kmalloc_sizes.h needs PAGE_SIZE */
 #include <asm/cache.h>		/* kmalloc_sizes.h needs L1_CACHE_BYTES */
 #include <linux/compiler.h>
+#include <trace/kmemtrace.h>
 
 /* Size description struct for general caches. */
 struct cache_sizes {
@@ -28,8 +29,26 @@ extern struct cache_sizes malloc_sizes[];
 void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
 void *__kmalloc(size_t size, gfp_t flags);
 
-static inline void *kmalloc(size_t size, gfp_t flags)
+#ifdef CONFIG_KMEMTRACE
+extern void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags);
+extern size_t slab_buffer_size(struct kmem_cache *cachep);
+#else
+static __always_inline void *
+kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags)
 {
+	return kmem_cache_alloc(cachep, flags);
+}
+static inline size_t slab_buffer_size(struct kmem_cache *cachep)
+{
+	return 0;
+}
+#endif
+
+static __always_inline void *kmalloc(size_t size, gfp_t flags)
+{
+	struct kmem_cache *cachep;
+	void *ret;
+
 	if (__builtin_constant_p(size)) {
 		int i = 0;
 
@@ -47,10 +66,17 @@ static inline void *kmalloc(size_t size, gfp_t flags)
 found:
 #ifdef CONFIG_ZONE_DMA
 		if (flags & GFP_DMA)
-			return kmem_cache_alloc(malloc_sizes[i].cs_dmacachep,
-						flags);
+			cachep = malloc_sizes[i].cs_dmacachep;
+		else
 #endif
-		return kmem_cache_alloc(malloc_sizes[i].cs_cachep, flags);
+			cachep = malloc_sizes[i].cs_cachep;
+
+		ret = kmem_cache_alloc_notrace(cachep, flags);
+
+		kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, _THIS_IP_, ret,
+				     size, slab_buffer_size(cachep), flags);
+
+		return ret;
 	}
 	return __kmalloc(size, flags);
 }
@@ -59,8 +85,25 @@ found:
 extern void *__kmalloc_node(size_t size, gfp_t flags, int node);
 extern void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
 
-static inline void *kmalloc_node(size_t size, gfp_t flags, int node)
+#ifdef CONFIG_KMEMTRACE
+extern void *kmem_cache_alloc_node_notrace(struct kmem_cache *cachep,
+					   gfp_t flags,
+					   int nodeid);
+#else
+static __always_inline void *
+kmem_cache_alloc_node_notrace(struct kmem_cache *cachep,
+			      gfp_t flags,
+			      int nodeid)
 {
+	return kmem_cache_alloc_node(cachep, flags, nodeid);
+}
+#endif
+
+static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
+{
+	struct kmem_cache *cachep;
+	void *ret;
+
 	if (__builtin_constant_p(size)) {
 		int i = 0;
 
@@ -78,11 +121,18 @@ static inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 found:
 #ifdef CONFIG_ZONE_DMA
 		if (flags & GFP_DMA)
-			return kmem_cache_alloc_node(malloc_sizes[i].cs_dmacachep,
-						flags, node);
+			cachep = malloc_sizes[i].cs_dmacachep;
+		else
 #endif
-		return kmem_cache_alloc_node(malloc_sizes[i].cs_cachep,
-						flags, node);
+			cachep = malloc_sizes[i].cs_cachep;
+
+		ret = kmem_cache_alloc_node_notrace(cachep, flags, node);
+
+		kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, _THIS_IP_,
+					  ret, size, slab_buffer_size(cachep),
+					  flags, node);
+
+		return ret;
 	}
 	return __kmalloc_node(size, flags, node);
 }

include/linux/slob_def.h

@@ -3,14 +3,15 @@
 
 void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
 
-static inline void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
+static __always_inline void *kmem_cache_alloc(struct kmem_cache *cachep,
+					      gfp_t flags)
 {
 	return kmem_cache_alloc_node(cachep, flags, -1);
 }
 
 void *__kmalloc_node(size_t size, gfp_t flags, int node);
 
-static inline void *kmalloc_node(size_t size, gfp_t flags, int node)
+static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 {
 	return __kmalloc_node(size, flags, node);
 }
@@ -23,12 +24,12 @@ static inline void *kmalloc_node(size_t size, gfp_t flags, int node)
  * kmalloc is the normal method of allocating memory
  * in the kernel.
  */
-static inline void *kmalloc(size_t size, gfp_t flags)
+static __always_inline void *kmalloc(size_t size, gfp_t flags)
 {
 	return __kmalloc_node(size, flags, -1);
 }
 
-static inline void *__kmalloc(size_t size, gfp_t flags)
+static __always_inline void *__kmalloc(size_t size, gfp_t flags)
 {
 	return kmalloc(size, flags);
 }

include/linux/slub_def.h

@@ -10,6 +10,7 @@
 #include <linux/gfp.h>
 #include <linux/workqueue.h>
 #include <linux/kobject.h>
+#include <trace/kmemtrace.h>
 
 enum stat_item {
 	ALLOC_FASTPATH,		/* Allocation from cpu slab */
@@ -217,13 +218,31 @@ static __always_inline struct kmem_cache *kmalloc_slab(size_t size)
 void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
 void *__kmalloc(size_t size, gfp_t flags);
 
+#ifdef CONFIG_KMEMTRACE
+extern void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags);
+#else
+static __always_inline void *
+kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags)
+{
+	return kmem_cache_alloc(s, gfpflags);
+}
+#endif
+
 static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
 {
-	return (void *)__get_free_pages(flags | __GFP_COMP, get_order(size));
+	unsigned int order = get_order(size);
+	void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order);
+
+	kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, _THIS_IP_, ret,
+			     size, PAGE_SIZE << order, flags);
+
+	return ret;
 }
 
 static __always_inline void *kmalloc(size_t size, gfp_t flags)
 {
+	void *ret;
+
 	if (__builtin_constant_p(size)) {
 		if (size > SLUB_MAX_SIZE)
 			return kmalloc_large(size, flags);
@@ -234,7 +253,13 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
 			if (!s)
 				return ZERO_SIZE_PTR;
 
-			return kmem_cache_alloc(s, flags);
+			ret = kmem_cache_alloc_notrace(s, flags);
+
+			kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC,
+					     _THIS_IP_, ret,
+					     size, s->size, flags);
+
+			return ret;
 		}
 	}
 	return __kmalloc(size, flags);
@@ -244,8 +269,24 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
 void *__kmalloc_node(size_t size, gfp_t flags, int node);
 void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
 
+#ifdef CONFIG_KMEMTRACE
+extern void *kmem_cache_alloc_node_notrace(struct kmem_cache *s,
+					   gfp_t gfpflags,
+					   int node);
+#else
+static __always_inline void *
+kmem_cache_alloc_node_notrace(struct kmem_cache *s,
+			      gfp_t gfpflags,
+			      int node)
+{
+	return kmem_cache_alloc_node(s, gfpflags, node);
+}
+#endif
+
 static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 {
+	void *ret;
+
 	if (__builtin_constant_p(size) &&
 		size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) {
 			struct kmem_cache *s = kmalloc_slab(size);
@@ -253,7 +294,13 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 		if (!s)
 			return ZERO_SIZE_PTR;
 
-		return kmem_cache_alloc_node(s, flags, node);
+		ret = kmem_cache_alloc_node_notrace(s, flags, node);
+
+		kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC,
+					  _THIS_IP_, ret,
+					  size, s->size, flags, node);
+
+		return ret;
 	}
 	return __kmalloc_node(size, flags, node);
 }

include/linux/syscalls.h

@@ -65,6 +65,7 @@ struct old_linux_dirent;
 #include <asm/signal.h>
 #include <linux/quota.h>
 #include <linux/key.h>
+#include <linux/ftrace.h>
 
 #define __SC_DECL1(t1, a1)	t1 a1
 #define __SC_DECL2(t2, a2, ...) t2 a2, __SC_DECL1(__VA_ARGS__)
@@ -95,7 +96,46 @@ struct old_linux_dirent;
 #define __SC_TEST5(t5, a5, ...)	__SC_TEST(t5); __SC_TEST4(__VA_ARGS__)
 #define __SC_TEST6(t6, a6, ...)	__SC_TEST(t6); __SC_TEST5(__VA_ARGS__)
 
+#ifdef CONFIG_FTRACE_SYSCALLS
+#define __SC_STR_ADECL1(t, a)		#a
+#define __SC_STR_ADECL2(t, a, ...)	#a, __SC_STR_ADECL1(__VA_ARGS__)
+#define __SC_STR_ADECL3(t, a, ...)	#a, __SC_STR_ADECL2(__VA_ARGS__)
+#define __SC_STR_ADECL4(t, a, ...)	#a, __SC_STR_ADECL3(__VA_ARGS__)
+#define __SC_STR_ADECL5(t, a, ...)	#a, __SC_STR_ADECL4(__VA_ARGS__)
+#define __SC_STR_ADECL6(t, a, ...)	#a, __SC_STR_ADECL5(__VA_ARGS__)
+
+#define __SC_STR_TDECL1(t, a)		#t
+#define __SC_STR_TDECL2(t, a, ...)	#t, __SC_STR_TDECL1(__VA_ARGS__)
+#define __SC_STR_TDECL3(t, a, ...)	#t, __SC_STR_TDECL2(__VA_ARGS__)
+#define __SC_STR_TDECL4(t, a, ...)	#t, __SC_STR_TDECL3(__VA_ARGS__)
+#define __SC_STR_TDECL5(t, a, ...)	#t, __SC_STR_TDECL4(__VA_ARGS__)
+#define __SC_STR_TDECL6(t, a, ...)	#t, __SC_STR_TDECL5(__VA_ARGS__)
+
+#define SYSCALL_METADATA(sname, nb)				\
+	static const struct syscall_metadata __used		\
+	  __attribute__((__aligned__(4)))			\
+	  __attribute__((section("__syscalls_metadata")))	\
+	  __syscall_meta_##sname = {				\
+		.name 		= "sys"#sname,			\
+		.nb_args 	= nb,				\
+		.types		= types_##sname,		\
+		.args		= args_##sname,			\
+	}
+
+#define SYSCALL_DEFINE0(sname)					\
+	static const struct syscall_metadata __used		\
+	  __attribute__((__aligned__(4)))			\
+	  __attribute__((section("__syscalls_metadata")))	\
+	  __syscall_meta_##sname = {				\
+		.name 		= "sys_"#sname,			\
+		.nb_args 	= 0,				\
+	};							\
+	asmlinkage long sys_##sname(void)
+
+#else
 #define SYSCALL_DEFINE0(name)	   asmlinkage long sys_##name(void)
+#endif
+
 #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
 #define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__)
 #define SYSCALL_DEFINE3(name, ...) SYSCALL_DEFINEx(3, _##name, __VA_ARGS__)
@@ -117,10 +157,26 @@ struct old_linux_dirent;
 #endif
 #endif
 
+#ifdef CONFIG_FTRACE_SYSCALLS
+#define SYSCALL_DEFINEx(x, sname, ...)				\
+	static const char *types_##sname[] = {			\
+		__SC_STR_TDECL##x(__VA_ARGS__)			\
+	};							\
+	static const char *args_##sname[] = {			\
+		__SC_STR_ADECL##x(__VA_ARGS__)			\
+	};							\
+	SYSCALL_METADATA(sname, x);				\
+	__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
+#else
+#define SYSCALL_DEFINEx(x, sname, ...)				\
+	__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
+#endif
+
 #ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
 
 #define SYSCALL_DEFINE(name) static inline long SYSC_##name
-#define SYSCALL_DEFINEx(x, name, ...)					\
+
+#define __SYSCALL_DEFINEx(x, name, ...)					\
 	asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__));		\
 	static inline long SYSC##name(__SC_DECL##x(__VA_ARGS__));	\
 	asmlinkage long SyS##name(__SC_LONG##x(__VA_ARGS__))		\
@@ -134,7 +190,7 @@ struct old_linux_dirent;
 #else /* CONFIG_HAVE_SYSCALL_WRAPPERS */
 
 #define SYSCALL_DEFINE(name) asmlinkage long sys_##name
-#define SYSCALL_DEFINEx(x, name, ...)					\
+#define __SYSCALL_DEFINEx(x, name, ...)					\
 	asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__))
 
 #endif /* CONFIG_HAVE_SYSCALL_WRAPPERS */

include/linux/trace_clock.h

@@ -0,0 +1,19 @@
+#ifndef _LINUX_TRACE_CLOCK_H
+#define _LINUX_TRACE_CLOCK_H
+
+/*
+ * 3 trace clock variants, with differing scalability/precision
+ * tradeoffs:
+ *
+ *  -   local: CPU-local trace clock
+ *  -  medium: scalable global clock with some jitter
+ *  -  global: globally monotonic, serialized clock
+ */
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+extern u64 notrace trace_clock_local(void);
+extern u64 notrace trace_clock(void);
+extern u64 notrace trace_clock_global(void);
+
+#endif /* _LINUX_TRACE_CLOCK_H */

include/linux/tracepoint.h

@@ -31,8 +31,8 @@ struct tracepoint {
 					 * Keep in sync with vmlinux.lds.h.
 					 */
 
-#define TPPROTO(args...)	args
-#define TPARGS(args...)		args
+#define TP_PROTO(args...)	args
+#define TP_ARGS(args...)		args
 
 #ifdef CONFIG_TRACEPOINTS
 
@@ -65,7 +65,7 @@ struct tracepoint {
 	{								\
 		if (unlikely(__tracepoint_##name.state))		\
 			__DO_TRACE(&__tracepoint_##name,		\
-				TPPROTO(proto), TPARGS(args));		\
+				TP_PROTO(proto), TP_ARGS(args));	\
 	}								\
 	static inline int register_trace_##name(void (*probe)(proto))	\
 	{								\
@@ -153,4 +153,114 @@ static inline void tracepoint_synchronize_unregister(void)
 	synchronize_sched();
 }
 
+#define PARAMS(args...) args
+#define TRACE_FORMAT(name, proto, args, fmt)		\
+	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+
+
+/*
+ * For use with the TRACE_EVENT macro:
+ *
+ * We define a tracepoint, its arguments, its printk format
+ * and its 'fast binay record' layout.
+ *
+ * Firstly, name your tracepoint via TRACE_EVENT(name : the
+ * 'subsystem_event' notation is fine.
+ *
+ * Think about this whole construct as the
+ * 'trace_sched_switch() function' from now on.
+ *
+ *
+ *  TRACE_EVENT(sched_switch,
+ *
+ *	*
+ *	* A function has a regular function arguments
+ *	* prototype, declare it via TP_PROTO():
+ *	*
+ *
+ *	TP_PROTO(struct rq *rq, struct task_struct *prev,
+ *		 struct task_struct *next),
+ *
+ *	*
+ *	* Define the call signature of the 'function'.
+ *	* (Design sidenote: we use this instead of a
+ *	*  TP_PROTO1/TP_PROTO2/TP_PROTO3 ugliness.)
+ *	*
+ *
+ *	TP_ARGS(rq, prev, next),
+ *
+ *	*
+ *	* Fast binary tracing: define the trace record via
+ *	* TP_STRUCT__entry(). You can think about it like a
+ *	* regular C structure local variable definition.
+ *	*
+ *	* This is how the trace record is structured and will
+ *	* be saved into the ring buffer. These are the fields
+ *	* that will be exposed to user-space in
+ *	* /debug/tracing/events/<*>/format.
+ *	*
+ *	* The declared 'local variable' is called '__entry'
+ *	*
+ *	* __field(pid_t, prev_prid) is equivalent to a standard declariton:
+ *	*
+ *	*	pid_t	prev_pid;
+ *	*
+ *	* __array(char, prev_comm, TASK_COMM_LEN) is equivalent to:
+ *	*
+ *	*	char	prev_comm[TASK_COMM_LEN];
+ *	*
+ *
+ *	TP_STRUCT__entry(
+ *		__array(	char,	prev_comm,	TASK_COMM_LEN	)
+ *		__field(	pid_t,	prev_pid			)
+ *		__field(	int,	prev_prio			)
+ *		__array(	char,	next_comm,	TASK_COMM_LEN	)
+ *		__field(	pid_t,	next_pid			)
+ *		__field(	int,	next_prio			)
+ *	),
+ *
+ *	*
+ *	* Assign the entry into the trace record, by embedding
+ *	* a full C statement block into TP_fast_assign(). You
+ *	* can refer to the trace record as '__entry' -
+ *	* otherwise you can put arbitrary C code in here.
+ *	*
+ *	* Note: this C code will execute every time a trace event
+ *	* happens, on an active tracepoint.
+ *	*
+ *
+ *	TP_fast_assign(
+ *		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
+ *		__entry->prev_pid	= prev->pid;
+ *		__entry->prev_prio	= prev->prio;
+ *		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
+ *		__entry->next_pid	= next->pid;
+ *		__entry->next_prio	= next->prio;
+ *	)
+ *
+ *	*
+ *	* Formatted output of a trace record via TP_printk().
+ *	* This is how the tracepoint will appear under ftrace
+ *	* plugins that make use of this tracepoint.
+ *	*
+ *	* (raw-binary tracing wont actually perform this step.)
+ *	*
+ *
+ *	TP_printk("task %s:%d [%d] ==> %s:%d [%d]",
+ *		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
+ *		__entry->next_comm, __entry->next_pid, __entry->next_prio),
+ *
+ * );
+ *
+ * This macro construct is thus used for the regular printk format
+ * tracing setup, it is used to construct a function pointer based
+ * tracepoint callback (this is used by programmatic plugins and
+ * can also by used by generic instrumentation like SystemTap), and
+ * it is also used to expose a structured trace record in
+ * /debug/tracing/events/.
+ */
+
+#define TRACE_EVENT(name, proto, args, struct, assign, print)	\
+	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+
 #endif