Merge branches 'tracing/branch-tracer', 'tracing/ftrace',...

Merge branches 'tracing/branch-tracer', 'tracing/ftrace', 'tracing/function-return-tracer', 'tracing/tracepoints' and 'tracing/urgent' into tracing/core

Documentation/markers.txt

@@ -70,6 +70,20 @@ a printk warning which identifies the inconsistency:
 
 "Format mismatch for probe probe_name (format), marker (format)"
 
+Another way to use markers is to simply define the marker without generating any
+function call to actually call into the marker. This is useful in combination
+with tracepoint probes in a scheme like this :
+
+void probe_tracepoint_name(unsigned int arg1, struct task_struct *tsk);
+
+DEFINE_MARKER_TP(marker_eventname, tracepoint_name, probe_tracepoint_name,
+	"arg1 %u pid %d");
+
+notrace void probe_tracepoint_name(unsigned int arg1, struct task_struct *tsk)
+{
+	struct marker *marker = &GET_MARKER(kernel_irq_entry);
+	/* write data to trace buffers ... */
+}
 
 * Probe / marker example
 

Documentation/tracepoints.txt

@@ -3,28 +3,30 @@
 			    Mathieu Desnoyers
 
 
-This document introduces Linux Kernel Tracepoints and their use. It provides
-examples of how to insert tracepoints in the kernel and connect probe functions
-to them and provides some examples of probe functions.
+This document introduces Linux Kernel Tracepoints and their use. It
+provides examples of how to insert tracepoints in the kernel and
+connect probe functions to them and provides some examples of probe
+functions.
 
 
 * Purpose of tracepoints
 
-A tracepoint placed in code provides a hook to call a function (probe) that you
-can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or
-"off" (no probe is attached). When a tracepoint is "off" it has no effect,
-except for adding a tiny time penalty (checking a condition for a branch) and
-space penalty (adding a few bytes for the function call at the end of the
-instrumented function and adds a data structure in a separate section).  When a
-tracepoint is "on", the function you provide is called each time the tracepoint
-is executed, in the execution context of the caller. When the function provided
-ends its execution, it returns to the caller (continuing from the tracepoint
-site).
+A tracepoint placed in code provides a hook to call a function (probe)
+that you can provide at runtime. A tracepoint can be "on" (a probe is
+connected to it) or "off" (no probe is attached). When a tracepoint is
+"off" it has no effect, except for adding a tiny time penalty
+(checking a condition for a branch) and space penalty (adding a few
+bytes for the function call at the end of the instrumented function
+and adds a data structure in a separate section).  When a tracepoint
+is "on", the function you provide is called each time the tracepoint
+is executed, in the execution context of the caller. When the function
+provided ends its execution, it returns to the caller (continuing from
+the tracepoint site).
 
 You can put tracepoints at important locations in the code. They are
 lightweight hooks that can pass an arbitrary number of parameters,
-which prototypes are described in a tracepoint declaration placed in a header
-file.
+which prototypes are described in a tracepoint declaration placed in a
+header file.
 
 They can be used for tracing and performance accounting.
 
@@ -42,7 +44,7 @@ In include/trace/subsys.h :
 
 #include <linux/tracepoint.h>
 
-DEFINE_TRACE(subsys_eventname,
+DECLARE_TRACE(subsys_eventname,
 	TPPTOTO(int firstarg, struct task_struct *p),
 	TPARGS(firstarg, p));
 
@@ -50,6 +52,8 @@ In subsys/file.c (where the tracing statement must be added) :
 
 #include <trace/subsys.h>
 
+DEFINE_TRACE(subsys_eventname);
+
 void somefct(void)
 {
 	...
@@ -61,31 +65,41 @@ Where :
 - subsys_eventname is an identifier unique to your event
     - subsys is the name of your subsystem.
     - eventname is the name of the event to trace.
-- TPPTOTO(int firstarg, struct task_struct *p) is the prototype of the function
-  called by this tracepoint.
-- TPARGS(firstarg, p) are the parameters names, same as found in the prototype.
 
-Connecting a function (probe) to a tracepoint is done by providing a probe
-(function to call) for the specific tracepoint through
-register_trace_subsys_eventname().  Removing a probe is done through
-unregister_trace_subsys_eventname(); it will remove the probe sure there is no
-caller left using the probe when it returns. Probe removal is preempt-safe
-because preemption is disabled around the probe call. See the "Probe example"
-section below for a sample probe module.
-
-The tracepoint mechanism supports inserting multiple instances of the same
-tracepoint, but a single definition must be made of a given tracepoint name over
-all the kernel to make sure no type conflict will occur. Name mangling of the
-tracepoints is done using the prototypes to make sure typing is correct.
-Verification of probe type correctness is done at the registration site by the
-compiler. Tracepoints can be put in inline functions, inlined static functions,
-and unrolled loops as well as regular functions.
-
-The naming scheme "subsys_event" is suggested here as a convention intended
-to limit collisions. Tracepoint names are global to the kernel: they are
-considered as being the same whether they are in the core kernel image or in
-modules.
+- TPPTOTO(int firstarg, struct task_struct *p) is the prototype of the
+  function called by this tracepoint.
 
+- TPARGS(firstarg, p) are the parameters names, same as found in the
+  prototype.
+
+Connecting a function (probe) to a tracepoint is done by providing a
+probe (function to call) for the specific tracepoint through
+register_trace_subsys_eventname().  Removing a probe is done through
+unregister_trace_subsys_eventname(); it will remove the probe.
+
+tracepoint_synchronize_unregister() must be called before the end of
+the module exit function to make sure there is no caller left using
+the probe. This, and the fact that preemption is disabled around the
+probe call, make sure that probe removal and module unload are safe.
+See the "Probe example" section below for a sample probe module.
+
+The tracepoint mechanism supports inserting multiple instances of the
+same tracepoint, but a single definition must be made of a given
+tracepoint name over all the kernel to make sure no type conflict will
+occur. Name mangling of the tracepoints is done using the prototypes
+to make sure typing is correct. Verification of probe type correctness
+is done at the registration site by the compiler. Tracepoints can be
+put in inline functions, inlined static functions, and unrolled loops
+as well as regular functions.
+
+The naming scheme "subsys_event" is suggested here as a convention
+intended to limit collisions. Tracepoint names are global to the
+kernel: they are considered as being the same whether they are in the
+core kernel image or in modules.
+
+If the tracepoint has to be used in kernel modules, an
+EXPORT_TRACEPOINT_SYMBOL_GPL() or EXPORT_TRACEPOINT_SYMBOL() can be
+used to export the defined tracepoints.
 
 * Probe / tracepoint example
 

arch/x86/include/asm/ftrace.h

@@ -17,6 +17,14 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 	 */
 	return addr - 1;
 }
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+struct dyn_arch_ftrace {
+	/* No extra data needed for x86 */
+};
+
+#endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 

arch/x86/kernel/entry_32.S

@@ -1190,7 +1190,7 @@ ENTRY(mcount)
 	jnz trace
 #ifdef CONFIG_FUNCTION_RET_TRACER
 	cmpl $ftrace_stub, ftrace_function_return
-	jnz trace_return
+	jnz ftrace_return_caller
 #endif
 .globl ftrace_stub
 ftrace_stub:
@@ -1211,9 +1211,15 @@ trace:
 	popl %ecx
 	popl %eax
 	jmp ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_FUNCTION_RET_TRACER
-trace_return:
+ENTRY(ftrace_return_caller)
+	cmpl $0, function_trace_stop
+	jne ftrace_stub
+
 	pushl %eax
 	pushl %ecx
 	pushl %edx
@@ -1223,7 +1229,8 @@ trace_return:
 	popl %edx
 	popl %ecx
 	popl %eax
-	jmp ftrace_stub
+	ret
+END(ftrace_return_caller)
 
 .globl return_to_handler
 return_to_handler:
@@ -1237,10 +1244,7 @@ return_to_handler:
 	popl %ecx
 	popl %eax
 	ret
-#endif /* CONFIG_FUNCTION_RET_TRACER */
-END(mcount)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FUNCTION_TRACER */
+#endif
 
 .section .rodata,"a"
 #include "syscall_table_32.S"

arch/x86/kernel/ftrace.c

@@ -24,133 +24,6 @@
 #include <asm/nmi.h>
 
 
-
-#ifdef CONFIG_FUNCTION_RET_TRACER
-
-/*
- * These functions are picked from those used on
- * this page for dynamic ftrace. They have been
- * simplified to ignore all traces in NMI context.
- */
-static atomic_t in_nmi;
-
-void ftrace_nmi_enter(void)
-{
-	atomic_inc(&in_nmi);
-}
-
-void ftrace_nmi_exit(void)
-{
-	atomic_dec(&in_nmi);
-}
-
-/* Add a function return address to the trace stack on thread info.*/
-static int push_return_trace(unsigned long ret, unsigned long long time,
-				unsigned long func)
-{
-	int index;
-	struct thread_info *ti = current_thread_info();
-
-	/* The return trace stack is full */
-	if (ti->curr_ret_stack == FTRACE_RET_STACK_SIZE - 1)
-		return -EBUSY;
-
-	index = ++ti->curr_ret_stack;
-	ti->ret_stack[index].ret = ret;
-	ti->ret_stack[index].func = func;
-	ti->ret_stack[index].calltime = time;
-
-	return 0;
-}
-
-/* Retrieve a function return address to the trace stack on thread info.*/
-static void pop_return_trace(unsigned long *ret, unsigned long long *time,
-				unsigned long *func)
-{
-	int index;
-
-	struct thread_info *ti = current_thread_info();
-	index = ti->curr_ret_stack;
-	*ret = ti->ret_stack[index].ret;
-	*func = ti->ret_stack[index].func;
-	*time = ti->ret_stack[index].calltime;
-	ti->curr_ret_stack--;
-}
-
-/*
- * Send the trace to the ring-buffer.
- * @return the original return address.
- */
-unsigned long ftrace_return_to_handler(void)
-{
-	struct ftrace_retfunc trace;
-	pop_return_trace(&trace.ret, &trace.calltime, &trace.func);
-	trace.rettime = cpu_clock(raw_smp_processor_id());
-	ftrace_function_return(&trace);
-
-	return trace.ret;
-}
-
-/*
- * Hook the return address and push it in the stack of return addrs
- * in current thread info.
- */
-void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
-{
-	unsigned long old;
-	unsigned long long calltime;
-	int faulted;
-	unsigned long return_hooker = (unsigned long)
-				&return_to_handler;
-
-	/* Nmi's are currently unsupported */
-	if (atomic_read(&in_nmi))
-		return;
-
-	/*
-	 * Protect against fault, even if it shouldn't
-	 * happen. This tool is too much intrusive to
-	 * ignore such a protection.
-	 */
-	asm volatile(
-		"1: movl (%[parent_old]), %[old]\n"
-		"2: movl %[return_hooker], (%[parent_replaced])\n"
-		"   movl $0, %[faulted]\n"
-
-		".section .fixup, \"ax\"\n"
-		"3: movl $1, %[faulted]\n"
-		".previous\n"
-
-		".section __ex_table, \"a\"\n"
-		"   .long 1b, 3b\n"
-		"   .long 2b, 3b\n"
-		".previous\n"
-
-		: [parent_replaced] "=r" (parent), [old] "=r" (old),
-		  [faulted] "=r" (faulted)
-		: [parent_old] "0" (parent), [return_hooker] "r" (return_hooker)
-		: "memory"
-	);
-
-	if (WARN_ON(faulted)) {
-		unregister_ftrace_return();
-		return;
-	}
-
-	if (WARN_ON(!__kernel_text_address(old))) {
-		unregister_ftrace_return();
-		*parent = old;
-		return;
-	}
-
-	calltime = cpu_clock(raw_smp_processor_id());
-
-	if (push_return_trace(old, calltime, self_addr) == -EBUSY)
-		*parent = old;
-}
-
-#endif
-
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 union ftrace_code_union {
@@ -166,7 +39,7 @@ static int ftrace_calc_offset(long ip, long addr)
 	return (int)(addr - ip);
 }
 
-unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
 	static union ftrace_code_union calc;
 
@@ -311,12 +184,12 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
 
 static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
 
-unsigned char *ftrace_nop_replace(void)
+static unsigned char *ftrace_nop_replace(void)
 {
 	return ftrace_nop;
 }
 
-int
+static int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		   unsigned char *new_code)
 {
@@ -349,6 +222,29 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	return 0;
 }
 
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *new, *old;
+	unsigned long ip = rec->ip;
+
+	old = ftrace_call_replace(ip, addr);
+	new = ftrace_nop_replace();
+
+	return ftrace_modify_code(rec->ip, old, new);
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *new, *old;
+	unsigned long ip = rec->ip;
+
+	old = ftrace_nop_replace();
+	new = ftrace_call_replace(ip, addr);
+
+	return ftrace_modify_code(rec->ip, old, new);
+}
+
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned long ip = (unsigned long)(&ftrace_call);
@@ -426,3 +322,133 @@ int __init ftrace_dyn_arch_init(void *data)
 	return 0;
 }
 #endif
+
+#ifdef CONFIG_FUNCTION_RET_TRACER
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+
+/*
+ * These functions are picked from those used on
+ * this page for dynamic ftrace. They have been
+ * simplified to ignore all traces in NMI context.
+ */
+static atomic_t in_nmi;
+
+void ftrace_nmi_enter(void)
+{
+	atomic_inc(&in_nmi);
+}
+
+void ftrace_nmi_exit(void)
+{
+	atomic_dec(&in_nmi);
+}
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
+/* Add a function return address to the trace stack on thread info.*/
+static int push_return_trace(unsigned long ret, unsigned long long time,
+				unsigned long func)
+{
+	int index;
+	struct thread_info *ti = current_thread_info();
+
+	/* The return trace stack is full */
+	if (ti->curr_ret_stack == FTRACE_RET_STACK_SIZE - 1)
+		return -EBUSY;
+
+	index = ++ti->curr_ret_stack;
+	barrier();
+	ti->ret_stack[index].ret = ret;
+	ti->ret_stack[index].func = func;
+	ti->ret_stack[index].calltime = time;
+
+	return 0;
+}
+
+/* Retrieve a function return address to the trace stack on thread info.*/
+static void pop_return_trace(unsigned long *ret, unsigned long long *time,
+				unsigned long *func)
+{
+	int index;
+
+	struct thread_info *ti = current_thread_info();
+	index = ti->curr_ret_stack;
+	*ret = ti->ret_stack[index].ret;
+	*func = ti->ret_stack[index].func;
+	*time = ti->ret_stack[index].calltime;
+	ti->curr_ret_stack--;
+}
+
+/*
+ * Send the trace to the ring-buffer.
+ * @return the original return address.
+ */
+unsigned long ftrace_return_to_handler(void)
+{
+	struct ftrace_retfunc trace;
+	pop_return_trace(&trace.ret, &trace.calltime, &trace.func);
+	trace.rettime = cpu_clock(raw_smp_processor_id());
+	ftrace_function_return(&trace);
+
+	return trace.ret;
+}
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
+{
+	unsigned long old;
+	unsigned long long calltime;
+	int faulted;
+	unsigned long return_hooker = (unsigned long)
+				&return_to_handler;
+
+	/* Nmi's are currently unsupported */
+	if (atomic_read(&in_nmi))
+		return;
+
+	/*
+	 * Protect against fault, even if it shouldn't
+	 * happen. This tool is too much intrusive to
+	 * ignore such a protection.
+	 */
+	asm volatile(
+		"1: movl (%[parent_old]), %[old]\n"
+		"2: movl %[return_hooker], (%[parent_replaced])\n"
+		"   movl $0, %[faulted]\n"
+
+		".section .fixup, \"ax\"\n"
+		"3: movl $1, %[faulted]\n"
+		".previous\n"
+
+		".section __ex_table, \"a\"\n"
+		"   .long 1b, 3b\n"
+		"   .long 2b, 3b\n"
+		".previous\n"
+
+		: [parent_replaced] "=r" (parent), [old] "=r" (old),
+		  [faulted] "=r" (faulted)
+		: [parent_old] "0" (parent), [return_hooker] "r" (return_hooker)
+		: "memory"
+	);
+
+	if (WARN_ON(faulted)) {
+		unregister_ftrace_return();
+		return;
+	}
+
+	if (WARN_ON(!__kernel_text_address(old))) {
+		unregister_ftrace_return();
+		*parent = old;
+		return;
+	}
+
+	calltime = cpu_clock(raw_smp_processor_id());
+
+	if (push_return_trace(old, calltime, self_addr) == -EBUSY)
+		*parent = old;
+}
+
+#endif /* CONFIG_FUNCTION_RET_TRACER */

include/asm-generic/vmlinux.lds.h

@@ -71,6 +71,7 @@
 	VMLINUX_SYMBOL(__start___markers) = .;				\
 	*(__markers)							\
 	VMLINUX_SYMBOL(__stop___markers) = .;				\
+	. = ALIGN(32);							\
 	VMLINUX_SYMBOL(__start___tracepoints) = .;			\
 	*(__tracepoints)						\
 	VMLINUX_SYMBOL(__stop___tracepoints) = .;			\

include/linux/ftrace.h

@@ -25,6 +25,17 @@ struct ftrace_ops {
 
 extern int function_trace_stop;
 
+/*
+ * Type of the current tracing.
+ */
+enum ftrace_tracing_type_t {
+	FTRACE_TYPE_ENTER = 0, /* Hook the call of the function */
+	FTRACE_TYPE_RETURN,	/* Hook the return of the function */
+};
+
+/* Current tracing type, default is FTRACE_TYPE_ENTER */
+extern enum ftrace_tracing_type_t ftrace_tracing_type;
+
 /**
  * ftrace_stop - stop function tracer.
  *
@@ -74,6 +85,9 @@ static inline void ftrace_start(void) { }
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+/* asm/ftrace.h must be defined for archs supporting dynamic ftrace */
+#include <asm/ftrace.h>
+
 enum {
 	FTRACE_FL_FREE		= (1 << 0),
 	FTRACE_FL_FAILED	= (1 << 1),
@@ -88,6 +102,7 @@ struct dyn_ftrace {
 	struct list_head	list;
 	unsigned long		ip; /* address of mcount call-site */
 	unsigned long		flags;
+	struct dyn_arch_ftrace	arch;
 };
 
 int ftrace_force_update(void);
@@ -95,22 +110,43 @@ void ftrace_set_filter(unsigned char *buf, int len, int reset);
 
 /* defined in arch */
 extern int ftrace_ip_converted(unsigned long ip);
-extern unsigned char *ftrace_nop_replace(void);
-extern unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr);
 extern int ftrace_dyn_arch_init(void *data);
 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);
+#ifdef CONFIG_FUNCTION_RET_TRACER
+extern void ftrace_return_caller(void);
+#endif
 
-/* May be defined in arch */
-extern int ftrace_arch_read_dyn_info(char *buf, int size);
+/**
+ * ftrace_make_nop - convert code into top
+ * @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
+ *
+ * This is a very sensitive operation and great care needs
+ * to be taken by the arch.  The operation should carefully
+ * read the location, check to see if what is read is indeed
+ * what we expect it to be, and then on success of the compare,
+ * it should write to the location.
+ *
+ * The code segment at @rec->ip should be a caller to @addr
+ *
+ * Return must be:
+ *  0 on success
+ *  -EFAULT on error reading the location
+ *  -EINVAL on a failed compare of the contents
+ *  -EPERM  on error writing to the location
+ * Any other value will be considered a failure.
+ */
+extern int ftrace_make_nop(struct module *mod,
+			   struct dyn_ftrace *rec, unsigned long addr);
 
 /**
- * ftrace_modify_code - modify code segment
- * @ip: the address of the code segment
- * @old_code: the contents of what is expected to be there
- * @new_code: the code to patch in
+ * ftrace_make_call - convert a nop call site into a call to addr
+ * @rec: the mcount call site record
+ * @addr: the address that the call site should call
  *
  * This is a very sensitive operation and great care needs
  * to be taken by the arch.  The operation should carefully
@@ -118,6 +154,8 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size);
  * what we expect it to be, and then on success of the compare,
  * it should write to the location.
  *
+ * The code segment at @rec->ip should be a nop
+ *
  * Return must be:
  *  0 on success
  *  -EFAULT on error reading the location
@@ -125,8 +163,11 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size);
  *  -EPERM  on error writing to the location
  * Any other value will be considered a failure.
  */
-extern int ftrace_modify_code(unsigned long ip, unsigned char *old_code,
-			      unsigned char *new_code);
+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);
 
 extern int skip_trace(unsigned long ip);
 
@@ -259,11 +300,13 @@ static inline void ftrace_dump(void) { }
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
-extern void ftrace_init_module(unsigned long *start, unsigned long *end);
+extern void ftrace_init_module(struct module *mod,
+			       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) { }
+ftrace_init_module(struct module *mod,
+		   unsigned long *start, unsigned long *end) { }
 #endif
 
 
@@ -281,7 +324,7 @@ struct ftrace_retfunc {
 /* Type of a callback handler of tracing return function */
 typedef void (*trace_function_return_t)(struct ftrace_retfunc *);
 
-extern void register_ftrace_return(trace_function_return_t func);
+extern int register_ftrace_return(trace_function_return_t func);
 /* The current handler in use */
 extern trace_function_return_t ftrace_function_return;
 extern void unregister_ftrace_return(void);

include/linux/marker.h

@@ -12,6 +12,7 @@
  * See the file COPYING for more details.
  */
 
+#include <stdarg.h>
 #include <linux/types.h>
 
 struct module;
@@ -48,10 +49,28 @@ struct marker {
 	void (*call)(const struct marker *mdata, void *call_private, ...);
 	struct marker_probe_closure single;
 	struct marker_probe_closure *multi;
+	const char *tp_name;	/* Optional tracepoint name */
+	void *tp_cb;		/* Optional tracepoint callback */
 } __attribute__((aligned(8)));
 
 #ifdef CONFIG_MARKERS
 
+#define _DEFINE_MARKER(name, tp_name_str, tp_cb, format)		\
+		static const char __mstrtab_##name[]			\
+		__attribute__((section("__markers_strings")))		\
+		= #name "\0" format;					\
+		static struct marker __mark_##name			\
+		__attribute__((section("__markers"), aligned(8))) =	\
+		{ __mstrtab_##name, &__mstrtab_##name[sizeof(#name)],	\
+		  0, 0, marker_probe_cb, { __mark_empty_function, NULL},\
+		  NULL, tp_name_str, tp_cb }
+
+#define DEFINE_MARKER(name, format)					\
+		_DEFINE_MARKER(name, NULL, NULL, format)
+
+#define DEFINE_MARKER_TP(name, tp_name, tp_cb, format)			\
+		_DEFINE_MARKER(name, #tp_name, tp_cb, format)
+
 /*
  * Note : the empty asm volatile with read constraint is used here instead of a
  * "used" attribute to fix a gcc 4.1.x bug.
@@ -65,14 +84,7 @@ struct marker {
  */
 #define __trace_mark(generic, name, call_private, format, args...)	\
 	do {								\
-		static const char __mstrtab_##name[]			\
-		__attribute__((section("__markers_strings")))		\
-		= #name "\0" format;					\
-		static struct marker __mark_##name			\
-		__attribute__((section("__markers"), aligned(8))) =	\
-		{ __mstrtab_##name, &__mstrtab_##name[sizeof(#name)],	\
-		0, 0, marker_probe_cb,					\
-		{ __mark_empty_function, NULL}, NULL };			\
+		DEFINE_MARKER(name, format);				\
 		__mark_check_format(format, ## args);			\
 		if (unlikely(__mark_##name.state)) {			\
 			(*__mark_##name.call)				\
@@ -80,14 +92,39 @@ struct marker {
 		}							\
 	} while (0)
 
+#define __trace_mark_tp(name, call_private, tp_name, tp_cb, format, args...) \
+	do {								\
+		void __check_tp_type(void)				\
+		{							\
+			register_trace_##tp_name(tp_cb);		\
+		}							\
+		DEFINE_MARKER_TP(name, tp_name, tp_cb, format);		\
+		__mark_check_format(format, ## args);			\
+		(*__mark_##name.call)(&__mark_##name, call_private,	\
+					## args);			\
+	} while (0)
+
 extern void marker_update_probe_range(struct marker *begin,
 	struct marker *end);
+
+#define GET_MARKER(name)	(__mark_##name)
+
 #else /* !CONFIG_MARKERS */
+#define DEFINE_MARKER(name, tp_name, tp_cb, format)
 #define __trace_mark(generic, name, call_private, format, args...) \
 		__mark_check_format(format, ## args)
+#define __trace_mark_tp(name, call_private, tp_name, tp_cb, format, args...) \
+	do {								\
+		void __check_tp_type(void)				\
+		{							\
+			register_trace_##tp_name(tp_cb);		\
+		}							\
+		__mark_check_format(format, ## args);			\
+	} while (0)
 static inline void marker_update_probe_range(struct marker *begin,
 	struct marker *end)
 { }
+#define GET_MARKER(name)
 #endif /* CONFIG_MARKERS */
 
 /**
@@ -116,6 +153,20 @@ static inline void marker_update_probe_range(struct marker *begin,
 #define _trace_mark(name, format, args...) \
 	__trace_mark(1, name, NULL, format, ## args)
 
+/**
+ * trace_mark_tp - Marker in a tracepoint callback
+ * @name: marker name, not quoted.
+ * @tp_name: tracepoint name, not quoted.
+ * @tp_cb: tracepoint callback. Should have an associated global symbol so it
+ *         is not optimized away by the compiler (should not be static).
+ * @format: format string
+ * @args...: variable argument list
+ *
+ * Places a marker in a tracepoint callback.
+ */
+#define trace_mark_tp(name, tp_name, tp_cb, format, args...)	\
+	__trace_mark_tp(name, NULL, tp_name, tp_cb, format, ## args)
+
 /**
  * MARK_NOARGS - Format string for a marker with no argument.
  */

include/linux/rcupdate.h

@@ -142,6 +142,7 @@ struct rcu_head {
  * on the write-side to insure proper synchronization.
  */
 #define rcu_read_lock_sched() preempt_disable()
+#define rcu_read_lock_sched_notrace() preempt_disable_notrace()
 
 /*
  * rcu_read_unlock_sched - marks the end of a RCU-classic critical section
@@ -149,6 +150,7 @@ struct rcu_head {
  * See rcu_read_lock_sched for more information.
  */
 #define rcu_read_unlock_sched() preempt_enable()
+#define rcu_read_unlock_sched_notrace() preempt_enable_notrace()
 
 
 

include/linux/tracepoint.h

@@ -24,8 +24,12 @@ struct tracepoint {
 	const char *name;		/* Tracepoint name */
 	int state;			/* State. */
 	void **funcs;
-} __attribute__((aligned(8)));
-
+} __attribute__((aligned(32)));		/*
+					 * Aligned on 32 bytes because it is
+					 * globally visible and gcc happily
+					 * align these on the structure size.
+					 * Keep in sync with vmlinux.lds.h.
+					 */
 
 #define TPPROTO(args...)	args
 #define TPARGS(args...)		args
@@ -40,14 +44,14 @@ struct tracepoint {
 	do {								\
 		void **it_func;						\
 									\
-		rcu_read_lock_sched();					\
+		rcu_read_lock_sched_notrace();				\
 		it_func = rcu_dereference((tp)->funcs);			\
 		if (it_func) {						\
 			do {						\
 				((void(*)(proto))(*it_func))(args);	\
 			} while (*(++it_func));				\
 		}							\
-		rcu_read_unlock_sched();				\
+		rcu_read_unlock_sched_notrace();			\
 	} while (0)
 
 /*
@@ -55,35 +59,40 @@ struct tracepoint {
  * 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)					\
+#define DECLARE_TRACE(name, proto, args)				\
+	extern struct tracepoint __tracepoint_##name;			\
 	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);					\
+		return tracepoint_probe_register(#name, (void *)probe);	\
 	}								\
-	static inline void unregister_trace_##name(void (*probe)(proto))\
+	static inline int unregister_trace_##name(void (*probe)(proto))	\
 	{								\
-		tracepoint_probe_unregister(#name ":" #proto,		\
-			(void *)probe);					\
+		return tracepoint_probe_unregister(#name, (void *)probe);\
 	}
 
+#define DEFINE_TRACE(name)						\
+	static const char __tpstrtab_##name[]				\
+	__attribute__((section("__tracepoints_strings"))) = #name;	\
+	struct tracepoint __tracepoint_##name				\
+	__attribute__((section("__tracepoints"), aligned(32))) =	\
+		{ __tpstrtab_##name, 0, NULL }
+
+#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)				\
+	EXPORT_SYMBOL_GPL(__tracepoint_##name)
+#define EXPORT_TRACEPOINT_SYMBOL(name)					\
+	EXPORT_SYMBOL(__tracepoint_##name)
+
 extern void tracepoint_update_probe_range(struct tracepoint *begin,
 	struct tracepoint *end);
 
 #else /* !CONFIG_TRACEPOINTS */
-#define DEFINE_TRACE(name, proto, args)			\
+#define DECLARE_TRACE(name, proto, args)				\
 	static inline void _do_trace_##name(struct tracepoint *tp, proto) \
 	{ }								\
 	static inline void trace_##name(proto)				\
@@ -92,8 +101,14 @@ extern void tracepoint_update_probe_range(struct tracepoint *begin,
 	{								\
 		return -ENOSYS;						\
 	}								\
-	static inline void unregister_trace_##name(void (*probe)(proto))\
-	{ }
+	static inline int unregister_trace_##name(void (*probe)(proto))	\
+	{								\
+		return -ENOSYS;						\
+	}
+
+#define DEFINE_TRACE(name)
+#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
+#define EXPORT_TRACEPOINT_SYMBOL(name)
 
 static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 	struct tracepoint *end)

include/trace/sched.h

@@ -4,52 +4,52 @@
 #include <linux/sched.h>
 #include <linux/tracepoint.h>
 
-DEFINE_TRACE(sched_kthread_stop,
+DECLARE_TRACE(sched_kthread_stop,
 	TPPROTO(struct task_struct *t),
 		TPARGS(t));
 
-DEFINE_TRACE(sched_kthread_stop_ret,
+DECLARE_TRACE(sched_kthread_stop_ret,
 	TPPROTO(int ret),
 		TPARGS(ret));
 
-DEFINE_TRACE(sched_wait_task,
+DECLARE_TRACE(sched_wait_task,
 	TPPROTO(struct rq *rq, struct task_struct *p),
 		TPARGS(rq, p));
 
-DEFINE_TRACE(sched_wakeup,
+DECLARE_TRACE(sched_wakeup,
 	TPPROTO(struct rq *rq, struct task_struct *p),
 		TPARGS(rq, p));
 
-DEFINE_TRACE(sched_wakeup_new,
+DECLARE_TRACE(sched_wakeup_new,
 	TPPROTO(struct rq *rq, struct task_struct *p),
 		TPARGS(rq, p));
 
-DEFINE_TRACE(sched_switch,
+DECLARE_TRACE(sched_switch,
 	TPPROTO(struct rq *rq, struct task_struct *prev,
 		struct task_struct *next),
 		TPARGS(rq, prev, next));
 
-DEFINE_TRACE(sched_migrate_task,
+DECLARE_TRACE(sched_migrate_task,
 	TPPROTO(struct rq *rq, struct task_struct *p, int dest_cpu),
 		TPARGS(rq, p, dest_cpu));
 
-DEFINE_TRACE(sched_process_free,
+DECLARE_TRACE(sched_process_free,
 	TPPROTO(struct task_struct *p),
 		TPARGS(p));
 
-DEFINE_TRACE(sched_process_exit,
+DECLARE_TRACE(sched_process_exit,
 	TPPROTO(struct task_struct *p),
 		TPARGS(p));
 
-DEFINE_TRACE(sched_process_wait,
+DECLARE_TRACE(sched_process_wait,
 	TPPROTO(struct pid *pid),
 		TPARGS(pid));
 
-DEFINE_TRACE(sched_process_fork,
+DECLARE_TRACE(sched_process_fork,
 	TPPROTO(struct task_struct *parent, struct task_struct *child),
 		TPARGS(parent, child));
 
-DEFINE_TRACE(sched_signal_send,
+DECLARE_TRACE(sched_signal_send,
 	TPPROTO(int sig, struct task_struct *p),
 		TPARGS(sig, p));
 

init/Kconfig

@@ -808,6 +808,7 @@ config TRACEPOINTS
 
 config MARKERS
 	bool "Activate markers"
+	depends on TRACEPOINTS
 	help
 	  Place an empty function call at each marker site. Can be
 	  dynamically changed for a probe function.

kernel/exit.c

@@ -54,6 +54,10 @@
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
 
+DEFINE_TRACE(sched_process_free);
+DEFINE_TRACE(sched_process_exit);
+DEFINE_TRACE(sched_process_wait);
+
 static void exit_mm(struct task_struct * tsk);
 
 static inline int task_detached(struct task_struct *p)

kernel/fork.c

@@ -79,6 +79,8 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
 
+DEFINE_TRACE(sched_process_fork);
+
 int nr_processes(void)
 {
 	int cpu;

kernel/kthread.c

@@ -21,6 +21,9 @@ static DEFINE_SPINLOCK(kthread_create_lock);
 static LIST_HEAD(kthread_create_list);
 struct task_struct *kthreadd_task;
 
+DEFINE_TRACE(sched_kthread_stop);
+DEFINE_TRACE(sched_kthread_stop_ret);
+
 struct kthread_create_info
 {
 	/* Information passed to kthread() from kthreadd. */

kernel/marker.c

@@ -81,7 +81,7 @@ struct marker_entry {
  * though the function pointer change and the marker enabling are two distinct
  * operations that modifies the execution flow of preemptible code.
  */
-void __mark_empty_function(void *probe_private, void *call_private,
+notrace void __mark_empty_function(void *probe_private, void *call_private,
 	const char *fmt, va_list *args)
 {
 }
@@ -97,7 +97,8 @@ EXPORT_SYMBOL_GPL(__mark_empty_function);
  * need to put a full smp_rmb() in this branch. This is why we do not use
  * rcu_dereference() for the pointer read.
  */
-void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
+notrace void marker_probe_cb(const struct marker *mdata,
+		void *call_private, ...)
 {
 	va_list args;
 	char ptype;
@@ -107,7 +108,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
 	 * sure the teardown of the callbacks can be done correctly when they
 	 * are in modules and they insure RCU read coherency.
 	 */
-	rcu_read_lock_sched();
+	rcu_read_lock_sched_notrace();
 	ptype = mdata->ptype;
 	if (likely(!ptype)) {
 		marker_probe_func *func;
@@ -145,7 +146,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
 			va_end(args);
 		}
 	}
-	rcu_read_unlock_sched();
+	rcu_read_unlock_sched_notrace();
 }
 EXPORT_SYMBOL_GPL(marker_probe_cb);
 
@@ -157,12 +158,13 @@ EXPORT_SYMBOL_GPL(marker_probe_cb);
  *
  * Should be connected to markers "MARK_NOARGS".
  */
-static void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
+static notrace void marker_probe_cb_noarg(const struct marker *mdata,
+		void *call_private, ...)
 {
 	va_list args;	/* not initialized */
 	char ptype;
 
-	rcu_read_lock_sched();
+	rcu_read_lock_sched_notrace();
 	ptype = mdata->ptype;
 	if (likely(!ptype)) {
 		marker_probe_func *func;
@@ -195,7 +197,7 @@ static void marker_probe_cb_noarg(const struct marker *mdata, void *call_private
 			multi[i].func(multi[i].probe_private, call_private,
 				mdata->format, &args);
 	}
-	rcu_read_unlock_sched();
+	rcu_read_unlock_sched_notrace();
 }
 
 static void free_old_closure(struct rcu_head *head)
@@ -477,7 +479,7 @@ static int marker_set_format(struct marker_entry *entry, const char *format)
 static int set_marker(struct marker_entry *entry, struct marker *elem,
 		int active)
 {
-	int ret;
+	int ret = 0;
 	WARN_ON(strcmp(entry->name, elem->name) != 0);
 
 	if (entry->format) {
@@ -529,9 +531,40 @@ static int set_marker(struct marker_entry *entry, struct marker *elem,
 	 */
 	smp_wmb();
 	elem->ptype = entry->ptype;
+
+	if (elem->tp_name && (active ^ elem->state)) {
+		WARN_ON(!elem->tp_cb);
+		/*
+		 * It is ok to directly call the probe registration because type
+		 * checking has been done in the __trace_mark_tp() macro.
+		 */
+
+		if (active) {
+			/*
+			 * try_module_get should always succeed because we hold
+			 * lock_module() to get the tp_cb address.
+			 */
+			ret = try_module_get(__module_text_address(
+				(unsigned long)elem->tp_cb));
+			BUG_ON(!ret);
+			ret = tracepoint_probe_register_noupdate(
+				elem->tp_name,
+				elem->tp_cb);
+		} else {
+			ret = tracepoint_probe_unregister_noupdate(
+				elem->tp_name,
+				elem->tp_cb);
+			/*
+			 * tracepoint_probe_update_all() must be called
+			 * before the module containing tp_cb is unloaded.
+			 */
+			module_put(__module_text_address(
+				(unsigned long)elem->tp_cb));
+		}
+	}
 	elem->state = active;
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -542,7 +575,24 @@ static int set_marker(struct marker_entry *entry, struct marker *elem,
  */
 static void disable_marker(struct marker *elem)
 {
+	int ret;
+
 	/* leave "call" as is. It is known statically. */
+	if (elem->tp_name && elem->state) {
+		WARN_ON(!elem->tp_cb);
+		/*
+		 * It is ok to directly call the probe registration because type
+		 * checking has been done in the __trace_mark_tp() macro.
+		 */
+		ret = tracepoint_probe_unregister_noupdate(elem->tp_name,
+			elem->tp_cb);
+		WARN_ON(ret);
+		/*
+		 * tracepoint_probe_update_all() must be called
+		 * before the module containing tp_cb is unloaded.
+		 */
+		module_put(__module_text_address((unsigned long)elem->tp_cb));
+	}
 	elem->state = 0;
 	elem->single.func = __mark_empty_function;
 	/* Update the function before setting the ptype */
@@ -606,6 +656,7 @@ static void marker_update_probes(void)
 	marker_update_probe_range(__start___markers, __stop___markers);
 	/* Markers in modules. */
 	module_update_markers();
+	tracepoint_probe_update_all();
 }
 
 /**
@@ -653,10 +704,11 @@ int marker_probe_register(const char *name, const char *format,
 		goto end;
 	}
 	mutex_unlock(&markers_mutex);
-	marker_update_probes();		/* may update entry */
+	marker_update_probes();
 	mutex_lock(&markers_mutex);
 	entry = get_marker(name);
-	WARN_ON(!entry);
+	if (!entry)
+		goto end;
 	if (entry->rcu_pending)
 		rcu_barrier_sched();
 	entry->oldptr = old;
@@ -697,7 +749,7 @@ int marker_probe_unregister(const char *name,
 		rcu_barrier_sched();
 	old = marker_entry_remove_probe(entry, probe, probe_private);
 	mutex_unlock(&markers_mutex);
-	marker_update_probes();		/* may update entry */
+	marker_update_probes();
 	mutex_lock(&markers_mutex);
 	entry = get_marker(name);
 	if (!entry)
@@ -778,10 +830,11 @@ int marker_probe_unregister_private_data(marker_probe_func *probe,
 		rcu_barrier_sched();
 	old = marker_entry_remove_probe(entry, NULL, probe_private);
 	mutex_unlock(&markers_mutex);
-	marker_update_probes();		/* may update entry */
+	marker_update_probes();
 	mutex_lock(&markers_mutex);
 	entry = get_marker_from_private_data(probe, probe_private);
-	WARN_ON(!entry);
+	if (!entry)
+		goto end;
 	if (entry->rcu_pending)
 		rcu_barrier_sched();
 	entry->oldptr = old;
@@ -842,3 +895,36 @@ void *marker_get_private_data(const char *name, marker_probe_func *probe,
 	return ERR_PTR(-ENOENT);
 }
 EXPORT_SYMBOL_GPL(marker_get_private_data);
+
+#ifdef CONFIG_MODULES
+
+int marker_module_notify(struct notifier_block *self,
+			 unsigned long val, void *data)
+{
+	struct module *mod = data;
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		marker_update_probe_range(mod->markers,
+			mod->markers + mod->num_markers);
+		break;
+	case MODULE_STATE_GOING:
+		marker_update_probe_range(mod->markers,
+			mod->markers + mod->num_markers);
+		break;
+	}
+	return 0;
+}
+
+struct notifier_block marker_module_nb = {
+	.notifier_call = marker_module_notify,
+	.priority = 0,
+};
+
+static int init_markers(void)
+{
+	return register_module_notifier(&marker_module_nb);
+}
+__initcall(init_markers);
+
+#endif /* CONFIG_MODULES */

kernel/module.c

@@ -2184,24 +2184,15 @@ static noinline struct module *load_module(void __user *umod,
 		struct mod_debug *debug;
 		unsigned int num_debug;
 
-#ifdef CONFIG_MARKERS
-		marker_update_probe_range(mod->markers,
-			mod->markers + mod->num_markers);
-#endif
 		debug = section_objs(hdr, sechdrs, secstrings, "__verbose",
 				     sizeof(*debug), &num_debug);
 		dynamic_printk_setup(debug, num_debug);
-
-#ifdef CONFIG_TRACEPOINTS
-		tracepoint_update_probe_range(mod->tracepoints,
-			mod->tracepoints + mod->num_tracepoints);
-#endif
 	}
 
 	/* sechdrs[0].sh_size is always zero */
 	mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc",
 			    sizeof(*mseg), &num_mcount);
-	ftrace_init_module(mseg, mseg + num_mcount);
+	ftrace_init_module(mod, mseg, mseg + num_mcount);
 
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)

kernel/sched.c

@@ -118,6 +118,12 @@
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
+DEFINE_TRACE(sched_wait_task);
+DEFINE_TRACE(sched_wakeup);
+DEFINE_TRACE(sched_wakeup_new);
+DEFINE_TRACE(sched_switch);
+DEFINE_TRACE(sched_migrate_task);
+
 #ifdef CONFIG_SMP
 /*
  * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)

kernel/signal.c

@@ -41,6 +41,8 @@
 
 static struct kmem_cache *sigqueue_cachep;
 
+DEFINE_TRACE(sched_signal_send);
+
 static void __user *sig_handler(struct task_struct *t, int sig)
 {
 	return t->sighand->action[sig - 1].sa.sa_handler;

kernel/trace/Kconfig

@@ -59,7 +59,6 @@ config FUNCTION_TRACER
 
 config FUNCTION_RET_TRACER
 	bool "Kernel Function return Tracer"
-	depends on !DYNAMIC_FTRACE
 	depends on HAVE_FUNCTION_RET_TRACER
 	depends on FUNCTION_TRACER
 	help

kernel/trace/trace.c

@@ -1051,7 +1051,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
 	 * Need to use raw, since this must be called before the
 	 * recursive protection is performed.
 	 */
-	raw_local_irq_save(flags);
+	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
 	disabled = atomic_inc_return(&data->disabled);
@@ -1062,7 +1062,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
 	}
 
 	atomic_dec(&data->disabled);
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_FUNCTION_RET_TRACER
@@ -2638,8 +2638,11 @@ static int tracing_set_tracer(char *buf)
 		current_trace->reset(tr);
 
 	current_trace = t;
-	if (t->init)
-		t->init(tr);
+	if (t->init) {
+		ret = t->init(tr);
+		if (ret)
+			goto out;
+	}
 
 	trace_branch_enable(tr);
  out:
@@ -2655,6 +2658,9 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 	char buf[max_tracer_type_len+1];
 	int i;
 	size_t ret;
+	int err;
+
+	ret = cnt;
 
 	if (cnt > max_tracer_type_len)
 		cnt = max_tracer_type_len;
@@ -2668,12 +2674,11 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 	for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
 		buf[i] = 0;
 
-	ret = tracing_set_tracer(buf);
-	if (!ret)
-		ret = cnt;
+	err = tracing_set_tracer(buf);
+	if (err)
+		return err;
 
-	if (ret > 0)
-		filp->f_pos += ret;
+	filp->f_pos += ret;
 
 	return ret;
 }

kernel/trace/trace.h

@@ -264,7 +264,8 @@ enum print_line_t {
  */
 struct tracer {
 	const char		*name;
-	void			(*init)(struct trace_array *tr);
+	/* Your tracer should raise a warning if init fails */
+	int			(*init)(struct trace_array *tr);
 	void			(*reset)(struct trace_array *tr);
 	void			(*start)(struct trace_array *tr);
 	void			(*stop)(struct trace_array *tr);

kernel/trace/trace_boot.c

@@ -47,7 +47,7 @@ static void reset_boot_trace(struct trace_array *tr)
 		tracing_reset(tr, cpu);
 }
 
-static void boot_trace_init(struct trace_array *tr)
+static int boot_trace_init(struct trace_array *tr)
 {
 	int cpu;
 	boot_trace = tr;
@@ -56,6 +56,7 @@ static void boot_trace_init(struct trace_array *tr)
 		tracing_reset(tr, cpu);
 
 	tracing_sched_switch_assign_trace(tr);
+	return 0;
 }
 
 static enum print_line_t

kernel/trace/trace_branch.c

@@ -125,7 +125,7 @@ static void stop_branch_trace(struct trace_array *tr)
 	disable_branch_tracing();
 }
 
-static void branch_trace_init(struct trace_array *tr)
+static int branch_trace_init(struct trace_array *tr)
 {
 	int cpu;
 
@@ -133,6 +133,7 @@ static void branch_trace_init(struct trace_array *tr)
 		tracing_reset(tr, cpu);
 
 	start_branch_trace(tr);
+	return 0;
 }
 
 static void branch_trace_reset(struct trace_array *tr)

kernel/trace/trace_functions.c

@@ -42,9 +42,10 @@ static void stop_function_trace(struct trace_array *tr)
 	tracing_stop_cmdline_record();
 }
 
-static void function_trace_init(struct trace_array *tr)
+static int function_trace_init(struct trace_array *tr)
 {
 	start_function_trace(tr);
+	return 0;
 }
 
 static void function_trace_reset(struct trace_array *tr)

kernel/trace/trace_functions_return.c

@@ -14,28 +14,18 @@
 #include "trace.h"
 
 
-static void start_return_trace(struct trace_array *tr)
-{
-	register_ftrace_return(&trace_function_return);
-}
-
-static void stop_return_trace(struct trace_array *tr)
-{
-	unregister_ftrace_return();
-}
-
-static void return_trace_init(struct trace_array *tr)
+static int return_trace_init(struct trace_array *tr)
 {
 	int cpu;
 	for_each_online_cpu(cpu)
 		tracing_reset(tr, cpu);
 
-	start_return_trace(tr);
+	return register_ftrace_return(&trace_function_return);
 }
 
 static void return_trace_reset(struct trace_array *tr)
 {
-		stop_return_trace(tr);
+		unregister_ftrace_return();
 }
 
 

kernel/trace/trace_irqsoff.c

@@ -416,11 +416,12 @@ static void irqsoff_tracer_close(struct trace_iterator *iter)
 }
 
 #ifdef CONFIG_IRQSOFF_TRACER
-static void irqsoff_tracer_init(struct trace_array *tr)
+static int irqsoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_IRQS_OFF;
 
 	__irqsoff_tracer_init(tr);
+	return 0;
 }
 static struct tracer irqsoff_tracer __read_mostly =
 {
@@ -442,11 +443,12 @@ static struct tracer irqsoff_tracer __read_mostly =
 #endif
 
 #ifdef CONFIG_PREEMPT_TRACER
-static void preemptoff_tracer_init(struct trace_array *tr)
+static int preemptoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_PREEMPT_OFF;
 
 	__irqsoff_tracer_init(tr);
+	return 0;
 }
 
 static struct tracer preemptoff_tracer __read_mostly =
@@ -471,11 +473,12 @@ static struct tracer preemptoff_tracer __read_mostly =
 #if defined(CONFIG_IRQSOFF_TRACER) && \
 	defined(CONFIG_PREEMPT_TRACER)
 
-static void preemptirqsoff_tracer_init(struct trace_array *tr)
+static int preemptirqsoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF;
 
 	__irqsoff_tracer_init(tr);
+	return 0;
 }
 
 static struct tracer preemptirqsoff_tracer __read_mostly =

kernel/trace/trace_mmiotrace.c

@@ -30,13 +30,14 @@ static void mmio_reset_data(struct trace_array *tr)
 		tracing_reset(tr, cpu);
 }
 
-static void mmio_trace_init(struct trace_array *tr)
+static int mmio_trace_init(struct trace_array *tr)
 {
 	pr_debug("in %s\n", __func__);
 	mmio_trace_array = tr;
 
 	mmio_reset_data(tr);
 	enable_mmiotrace();
+	return 0;
 }
 
 static void mmio_trace_reset(struct trace_array *tr)

kernel/trace/trace_nop.c

@@ -24,7 +24,7 @@ static void stop_nop_trace(struct trace_array *tr)
 	/* Nothing to do! */
 }
 
-static void nop_trace_init(struct trace_array *tr)
+static int nop_trace_init(struct trace_array *tr)
 {
 	int cpu;
 	ctx_trace = tr;
@@ -33,6 +33,7 @@ static void nop_trace_init(struct trace_array *tr)
 		tracing_reset(tr, cpu);
 
 	start_nop_trace(tr);
+	return 0;
 }
 
 static void nop_trace_reset(struct trace_array *tr)

kernel/trace/trace_sched_switch.c

@@ -206,10 +206,11 @@ static void stop_sched_trace(struct trace_array *tr)
 	tracing_stop_sched_switch_record();
 }
 
-static void sched_switch_trace_init(struct trace_array *tr)
+static int sched_switch_trace_init(struct trace_array *tr)
 {
 	ctx_trace = tr;
 	start_sched_trace(tr);
+	return 0;
 }
 
 static void sched_switch_trace_reset(struct trace_array *tr)

kernel/trace/trace_sched_wakeup.c

@@ -331,10 +331,11 @@ static void stop_wakeup_tracer(struct trace_array *tr)
 	unregister_trace_sched_wakeup(probe_wakeup);
 }
 
-static void wakeup_tracer_init(struct trace_array *tr)
+static int wakeup_tracer_init(struct trace_array *tr)
 {
 	wakeup_trace = tr;
 	start_wakeup_tracer(tr);
+	return 0;
 }
 
 static void wakeup_tracer_reset(struct trace_array *tr)

kernel/trace/trace_selftest.c

@@ -52,7 +52,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 	int cpu, ret = 0;
 
 	/* Don't allow flipping of max traces now */
-	raw_local_irq_save(flags);
+	local_irq_save(flags);
 	__raw_spin_lock(&ftrace_max_lock);
 
 	cnt = ring_buffer_entries(tr->buffer);
@@ -63,7 +63,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 			break;
 	}
 	__raw_spin_unlock(&ftrace_max_lock);
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 
 	if (count)
 		*count = cnt;
@@ -71,6 +71,11 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 	return ret;
 }
 
+static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret)
+{
+	printk(KERN_WARNING "Failed to init %s tracer, init returned %d\n",
+		trace->name, init_ret);
+}
 #ifdef CONFIG_FUNCTION_TRACER
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -111,7 +116,11 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 	ftrace_set_filter(func_name, strlen(func_name), 1);
 
 	/* enable tracing */
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
 
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
@@ -181,7 +190,12 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 	ftrace_enabled = 1;
 	tracer_enabled = 1;
 
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
+
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 	/* stop the tracing. */
@@ -223,7 +237,12 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 	int ret;
 
 	/* start the tracing */
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* reset the max latency */
 	tracing_max_latency = 0;
 	/* disable interrupts for a bit */
@@ -272,7 +291,12 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 	}
 
 	/* start the tracing */
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* reset the max latency */
 	tracing_max_latency = 0;
 	/* disable preemption for a bit */
@@ -321,7 +345,11 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	}
 
 	/* start the tracing */
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
 
 	/* reset the max latency */
 	tracing_max_latency = 0;
@@ -449,7 +477,12 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	wait_for_completion(&isrt);
 
 	/* start the tracing */
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* reset the max latency */
 	tracing_max_latency = 0;
 
@@ -505,7 +538,12 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr
 	int ret;
 
 	/* start the tracing */
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 	/* stop the tracing. */
@@ -532,7 +570,12 @@ trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr)
 	int ret;
 
 	/* start the tracing */
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return 0;
+	}
+
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 	/* stop the tracing. */
@@ -554,7 +597,12 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
 	int ret;
 
 	/* start the tracing */
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 	/* stop the tracing. */

kernel/trace/trace_sysprof.c

@@ -261,11 +261,12 @@ static void stop_stack_trace(struct trace_array *tr)
 	mutex_unlock(&sample_timer_lock);
 }
 
-static void stack_trace_init(struct trace_array *tr)
+static int stack_trace_init(struct trace_array *tr)
 {
 	sysprof_trace = tr;
 
 	start_stack_trace(tr);
+	return 0;
 }
 
 static void stack_trace_reset(struct trace_array *tr)

kernel/tracepoint.c

@@ -262,6 +262,7 @@ static void set_tracepoint(struct tracepoint_entry **entry,
 static void disable_tracepoint(struct tracepoint *elem)
 {
 	elem->state = 0;
+	rcu_assign_pointer(elem->funcs, NULL);
 }
 
 /**
@@ -540,3 +541,36 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter)
 	iter->tracepoint = NULL;
 }
 EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
+
+#ifdef CONFIG_MODULES
+
+int tracepoint_module_notify(struct notifier_block *self,
+			     unsigned long val, void *data)
+{
+	struct module *mod = data;
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		tracepoint_update_probe_range(mod->tracepoints,
+			mod->tracepoints + mod->num_tracepoints);
+		break;
+	case MODULE_STATE_GOING:
+		tracepoint_update_probe_range(mod->tracepoints,
+			mod->tracepoints + mod->num_tracepoints);
+		break;
+	}
+	return 0;
+}
+
+struct notifier_block tracepoint_module_nb = {
+	.notifier_call = tracepoint_module_notify,
+	.priority = 0,
+};
+
+static int init_tracepoints(void)
+{
+	return register_module_notifier(&tracepoint_module_nb);
+}
+__initcall(init_tracepoints);
+
+#endif /* CONFIG_MODULES */

samples/tracepoints/tp-samples-trace.h

@@ -4,10 +4,10 @@
 #include <linux/proc_fs.h>	/* for struct inode and struct file */
 #include <linux/tracepoint.h>
 
-DEFINE_TRACE(subsys_event,
+DECLARE_TRACE(subsys_event,
 	TPPROTO(struct inode *inode, struct file *file),
 	TPARGS(inode, file));
-DEFINE_TRACE(subsys_eventb,
+DECLARE_TRACE(subsys_eventb,
 	TPPROTO(void),
 	TPARGS());
 #endif

samples/tracepoints/tracepoint-probe-sample.c

@@ -46,6 +46,7 @@ void __exit tp_sample_trace_exit(void)
 {
 	unregister_trace_subsys_eventb(probe_subsys_eventb);
 	unregister_trace_subsys_event(probe_subsys_event);
+	tracepoint_synchronize_unregister();
 }
 
 module_exit(tp_sample_trace_exit);

samples/tracepoints/tracepoint-probe-sample2.c

@@ -33,6 +33,7 @@ module_init(tp_sample_trace_init);
 void __exit tp_sample_trace_exit(void)
 {
 	unregister_trace_subsys_event(probe_subsys_event);
+	tracepoint_synchronize_unregister();
 }
 
 module_exit(tp_sample_trace_exit);

samples/tracepoints/tracepoint-sample.c

@@ -13,6 +13,9 @@
 #include <linux/proc_fs.h>
 #include "tp-samples-trace.h"
 
+DEFINE_TRACE(subsys_event);
+DEFINE_TRACE(subsys_eventb);
+
 struct proc_dir_entry *pentry_example;
 
 static int my_open(struct inode *inode, struct file *file)