Merge branches 'tracing/blktrace', 'tracing/ftrace',...

Merge branches 'tracing/blktrace', 'tracing/ftrace', 'tracing/function-graph-tracer' and 'tracing/power-tracer' into tracing/core

Documentation/ftrace.txt

@@ -127,6 +127,8 @@ of ftrace. Here is a list of some of the key files:
 		be traced. If a function exists in both set_ftrace_filter
 		and set_ftrace_notrace,	the function will _not_ be traced.
 
+  set_ftrace_pid: Have the function tracer only trace a single thread.
+
   available_filter_functions: This lists the functions that ftrace
 		has processed and can trace. These are the function
 		names that you can pass to "set_ftrace_filter" or
@@ -1073,6 +1075,83 @@ For simple one time traces, the above is sufficent. For anything else,
 a search through /proc/mounts may be needed to find where the debugfs
 file-system is mounted.
 
+
+Single thread tracing
+---------------------
+
+By writing into /debug/tracing/set_ftrace_pid you can trace a
+single thread. For example:
+
+# cat /debug/tracing/set_ftrace_pid
+no pid
+# echo 3111 > /debug/tracing/set_ftrace_pid
+# cat /debug/tracing/set_ftrace_pid
+3111
+# echo function > /debug/tracing/current_tracer
+# cat /debug/tracing/trace | head
+ # tracer: function
+ #
+ #           TASK-PID    CPU#    TIMESTAMP  FUNCTION
+ #              | |       |          |         |
+     yum-updatesd-3111  [003]  1637.254676: finish_task_switch <-thread_return
+     yum-updatesd-3111  [003]  1637.254681: hrtimer_cancel <-schedule_hrtimeout_range
+     yum-updatesd-3111  [003]  1637.254682: hrtimer_try_to_cancel <-hrtimer_cancel
+     yum-updatesd-3111  [003]  1637.254683: lock_hrtimer_base <-hrtimer_try_to_cancel
+     yum-updatesd-3111  [003]  1637.254685: fget_light <-do_sys_poll
+     yum-updatesd-3111  [003]  1637.254686: pipe_poll <-do_sys_poll
+# echo -1 > /debug/tracing/set_ftrace_pid
+# cat /debug/tracing/trace |head
+ # tracer: function
+ #
+ #           TASK-PID    CPU#    TIMESTAMP  FUNCTION
+ #              | |       |          |         |
+ ##### CPU 3 buffer started ####
+     yum-updatesd-3111  [003]  1701.957688: free_poll_entry <-poll_freewait
+     yum-updatesd-3111  [003]  1701.957689: remove_wait_queue <-free_poll_entry
+     yum-updatesd-3111  [003]  1701.957691: fput <-free_poll_entry
+     yum-updatesd-3111  [003]  1701.957692: audit_syscall_exit <-sysret_audit
+     yum-updatesd-3111  [003]  1701.957693: path_put <-audit_syscall_exit
+
+If you want to trace a function when executing, you could use
+something like this simple program:
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+int main (int argc, char **argv)
+{
+        if (argc < 1)
+                exit(-1);
+
+        if (fork() > 0) {
+                int fd, ffd;
+                char line[64];
+                int s;
+
+                ffd = open("/debug/tracing/current_tracer", O_WRONLY);
+                if (ffd < 0)
+                        exit(-1);
+                write(ffd, "nop", 3);
+
+                fd = open("/debug/tracing/set_ftrace_pid", O_WRONLY);
+                s = sprintf(line, "%d\n", getpid());
+                write(fd, line, s);
+
+                write(ffd, "function", 8);
+
+                close(fd);
+                close(ffd);
+
+                execvp(argv[1], argv+1);
+        }
+
+        return 0;
+}
+
 dynamic ftrace
 --------------
 

arch/x86/Kconfig

@@ -29,7 +29,7 @@ config X86
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_TRACER
-	select HAVE_FUNCTION_RET_TRACER if X86_32
+	select HAVE_FUNCTION_GRAPH_TRACER if X86_32
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER

arch/x86/include/asm/ftrace.h

@@ -28,7 +28,7 @@ struct dyn_arch_ftrace {
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 #ifndef __ASSEMBLY__
 
@@ -51,6 +51,6 @@ struct ftrace_ret_stack {
 extern void return_to_handler(void);
 
 #endif /* __ASSEMBLY__ */
-#endif /* CONFIG_FUNCTION_RET_TRACER */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 #endif /* _ASM_X86_FTRACE_H */

arch/x86/kernel/Makefile

@@ -14,7 +14,7 @@ CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
 endif
 
-ifdef CONFIG_FUNCTION_RET_TRACER
+ifdef CONFIG_FUNCTION_GRAPH_TRACER
 # Don't trace __switch_to() but let it for function tracer
 CFLAGS_REMOVE_process_32.o = -pg
 endif
@@ -70,7 +70,7 @@ obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o nmi.o
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_FUNCTION_RET_TRACER)	+= ftrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o

arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c

@@ -33,6 +33,7 @@
 #include <linux/cpufreq.h>
 #include <linux/compiler.h>
 #include <linux/dmi.h>
+#include <linux/ftrace.h>
 
 #include <linux/acpi.h>
 #include <acpi/processor.h>
@@ -391,6 +392,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	unsigned int next_perf_state = 0; /* Index into perf table */
 	unsigned int i;
 	int result = 0;
+	struct power_trace it;
 
 	dprintk("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu);
 
@@ -427,6 +429,8 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 		}
 	}
 
+	trace_power_mark(&it, POWER_PSTATE, next_perf_state);
+
 	switch (data->cpu_feature) {
 	case SYSTEM_INTEL_MSR_CAPABLE:
 		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;

arch/x86/kernel/entry_32.S

@@ -1174,6 +1174,11 @@ ftrace_call:
 	popl %edx
 	popl %ecx
 	popl %eax
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+	jmp ftrace_stub
+#endif
 
 .globl ftrace_stub
 ftrace_stub:
@@ -1188,9 +1193,9 @@ ENTRY(mcount)
 
 	cmpl $ftrace_stub, ftrace_trace_function
 	jnz trace
-#ifdef CONFIG_FUNCTION_RET_TRACER
-	cmpl $ftrace_stub, ftrace_function_return
-	jnz ftrace_return_caller
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	cmpl $ftrace_stub, ftrace_graph_return
+	jnz ftrace_graph_caller
 #endif
 .globl ftrace_stub
 ftrace_stub:
@@ -1215,8 +1220,8 @@ END(mcount)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_TRACER */
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
-ENTRY(ftrace_return_caller)
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
 	cmpl $0, function_trace_stop
 	jne ftrace_stub
 
@@ -1230,7 +1235,7 @@ ENTRY(ftrace_return_caller)
 	popl %ecx
 	popl %eax
 	ret
-END(ftrace_return_caller)
+END(ftrace_graph_caller)
 
 .globl return_to_handler
 return_to_handler:

arch/x86/kernel/ftrace.c

@@ -111,7 +111,6 @@ static void ftrace_mod_code(void)
 	 */
 	mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
 					     MCOUNT_INSN_SIZE);
-
 }
 
 void ftrace_nmi_enter(void)
@@ -323,9 +322,53 @@ int __init ftrace_dyn_arch_init(void *data)
 }
 #endif
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
+
+static int ftrace_mod_jmp(unsigned long ip,
+			  int old_offset, int new_offset)
+{
+	unsigned char code[MCOUNT_INSN_SIZE];
+
+	if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	if (code[0] != 0xe9 || old_offset != *(int *)(&code[1]))
+		return -EINVAL;
+
+	*(int *)(&code[1]) = new_offset;
+
+	if (do_ftrace_mod_code(ip, &code))
+		return -EPERM;
+
+	return 0;
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	unsigned long ip = (unsigned long)(&ftrace_graph_call);
+	int old_offset, new_offset;
+
+	old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
+	new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
+
+	return ftrace_mod_jmp(ip, old_offset, new_offset);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	unsigned long ip = (unsigned long)(&ftrace_graph_call);
+	int old_offset, new_offset;
+
+	old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
+	new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
+
+	return ftrace_mod_jmp(ip, old_offset, new_offset);
+}
 
-#ifndef CONFIG_DYNAMIC_FTRACE
+#else /* CONFIG_DYNAMIC_FTRACE */
 
 /*
  * These functions are picked from those used on
@@ -343,11 +386,12 @@ 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)
+				unsigned long func, int *depth)
 {
 	int index;
 
@@ -365,21 +409,22 @@ static int push_return_trace(unsigned long ret, unsigned long long time,
 	current->ret_stack[index].ret = ret;
 	current->ret_stack[index].func = func;
 	current->ret_stack[index].calltime = time;
+	*depth = index;
 
 	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, unsigned long *overrun)
+static void pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
 {
 	int index;
 
 	index = current->curr_ret_stack;
 	*ret = current->ret_stack[index].ret;
-	*func = current->ret_stack[index].func;
-	*time = current->ret_stack[index].calltime;
-	*overrun = atomic_read(&current->trace_overrun);
+	trace->func = current->ret_stack[index].func;
+	trace->calltime = current->ret_stack[index].calltime;
+	trace->overrun = atomic_read(&current->trace_overrun);
+	trace->depth = index;
 	current->curr_ret_stack--;
 }
 
@@ -389,13 +434,14 @@ static void pop_return_trace(unsigned long *ret, unsigned long long *time,
  */
 unsigned long ftrace_return_to_handler(void)
 {
-	struct ftrace_retfunc trace;
-	pop_return_trace(&trace.ret, &trace.calltime, &trace.func,
-			&trace.overrun);
+	struct ftrace_graph_ret trace;
+	unsigned long ret;
+
+	pop_return_trace(&trace, &ret);
 	trace.rettime = cpu_clock(raw_smp_processor_id());
-	ftrace_function_return(&trace);
+	ftrace_graph_return(&trace);
 
-	return trace.ret;
+	return ret;
 }
 
 /*
@@ -407,6 +453,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	unsigned long old;
 	unsigned long long calltime;
 	int faulted;
+	struct ftrace_graph_ent trace;
 	unsigned long return_hooker = (unsigned long)
 				&return_to_handler;
 
@@ -440,20 +487,27 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	);
 
 	if (WARN_ON(faulted)) {
-		unregister_ftrace_return();
+		unregister_ftrace_graph();
 		return;
 	}
 
 	if (WARN_ON(!__kernel_text_address(old))) {
-		unregister_ftrace_return();
+		unregister_ftrace_graph();
 		*parent = old;
 		return;
 	}
 
 	calltime = cpu_clock(raw_smp_processor_id());
 
-	if (push_return_trace(old, calltime, self_addr) == -EBUSY)
+	if (push_return_trace(old, calltime,
+				self_addr, &trace.depth) == -EBUSY) {
 		*parent = old;
+		return;
+	}
+
+	trace.func = self_addr;
+	ftrace_graph_entry(&trace);
+
 }
 
-#endif /* CONFIG_FUNCTION_RET_TRACER */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */

arch/x86/kernel/process.c

@@ -7,6 +7,7 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/clockchips.h>
+#include <linux/ftrace.h>
 #include <asm/system.h>
 
 unsigned long idle_halt;
@@ -100,6 +101,9 @@ static inline int hlt_use_halt(void)
 void default_idle(void)
 {
 	if (hlt_use_halt()) {
+		struct power_trace it;
+
+		trace_power_start(&it, POWER_CSTATE, 1);
 		current_thread_info()->status &= ~TS_POLLING;
 		/*
 		 * TS_POLLING-cleared state must be visible before we
@@ -112,6 +116,7 @@ void default_idle(void)
 		else
 			local_irq_enable();
 		current_thread_info()->status |= TS_POLLING;
+		trace_power_end(&it);
 	} else {
 		local_irq_enable();
 		/* loop is done by the caller */
@@ -154,24 +159,31 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
  */
 void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
 {
+	struct power_trace it;
+
+	trace_power_start(&it, POWER_CSTATE, (ax>>4)+1);
 	if (!need_resched()) {
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();
 		if (!need_resched())
 			__mwait(ax, cx);
 	}
+	trace_power_end(&it);
 }
 
 /* Default MONITOR/MWAIT with no hints, used for default C1 state */
 static void mwait_idle(void)
 {
+	struct power_trace it;
 	if (!need_resched()) {
+		trace_power_start(&it, POWER_CSTATE, 1);
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();
 		if (!need_resched())
 			__sti_mwait(0, 0);
 		else
 			local_irq_enable();
+		trace_power_end(&it);
 	} else
 		local_irq_enable();
 }
@@ -183,9 +195,13 @@ static void mwait_idle(void)
  */
 static void poll_idle(void)
 {
+	struct power_trace it;
+
+	trace_power_start(&it, POWER_CSTATE, 0);
 	local_irq_enable();
 	while (!need_resched())
 		cpu_relax();
+	trace_power_end(&it);
 }
 
 /*

include/linux/ftrace.h

@@ -115,8 +115,13 @@ 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);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+extern void ftrace_graph_caller(void);
+extern int ftrace_enable_ftrace_graph_caller(void);
+extern int ftrace_disable_ftrace_graph_caller(void);
+#else
+static inline int ftrace_enable_ftrace_graph_caller(void) { return 0; }
+static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; }
 #endif
 
 /**
@@ -311,35 +316,77 @@ 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.
+ */
+struct ftrace_graph_ent {
+	unsigned long func; /* Current function */
+	int depth;
+};
 
 /*
  * Structure that defines a return function trace.
  */
-struct ftrace_retfunc {
-	unsigned long ret; /* Return address */
+struct ftrace_graph_ret {
 	unsigned long func; /* Current function */
 	unsigned long long calltime;
 	unsigned long long rettime;
 	/* Number of functions that overran the depth limit for current task */
 	unsigned long overrun;
+	int depth;
 };
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 #define FTRACE_RETFUNC_DEPTH 50
 #define FTRACE_RETSTACK_ALLOC_SIZE 32
-/* Type of a callback handler of tracing return function */
-typedef void (*trace_function_return_t)(struct ftrace_retfunc *);
+/* Type of the callback handlers for tracing function graph*/
+typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */
+typedef void (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */
+
+extern int register_ftrace_graph(trace_func_graph_ret_t retfunc,
+				trace_func_graph_ent_t entryfunc);
+
+/* The current handlers in use */
+extern trace_func_graph_ret_t ftrace_graph_return;
+extern trace_func_graph_ent_t ftrace_graph_entry;
 
-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);
+extern void unregister_ftrace_graph(void);
 
-extern void ftrace_retfunc_init_task(struct task_struct *t);
-extern void ftrace_retfunc_exit_task(struct task_struct *t);
+extern void ftrace_graph_init_task(struct task_struct *t);
+extern void ftrace_graph_exit_task(struct task_struct *t);
 #else
-static inline void ftrace_retfunc_init_task(struct task_struct *t) { }
-static inline void ftrace_retfunc_exit_task(struct task_struct *t) { }
+static inline void ftrace_graph_init_task(struct task_struct *t) { }
+static inline void ftrace_graph_exit_task(struct task_struct *t) { }
 #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_RET_TRACER)
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_FUNCTION_GRAPH_TRACER)
 extern void ftrace_nmi_enter(void);
 extern void ftrace_nmi_exit(void);
 #else

include/linux/sched.h

@@ -1365,7 +1365,7 @@ struct task_struct {
 	unsigned long default_timer_slack_ns;
 
 	struct list_head	*scm_work_list;
-#ifdef CONFIG_FUNCTION_RET_TRACER
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	/* Index of current stored adress in ret_stack */
 	int curr_ret_stack;
 	/* Stack of return addresses for return function tracing */

kernel/Makefile

@@ -21,7 +21,7 @@ CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_sched_clock.o = -pg
 CFLAGS_REMOVE_sched.o = -pg
 endif
-ifdef CONFIG_FUNCTION_RET_TRACER
+ifdef CONFIG_FUNCTION_GRAPH_TRACER
 CFLAGS_REMOVE_extable.o = -pg # For __kernel_text_address()
 CFLAGS_REMOVE_module.o = -pg # For __module_text_address()
 endif

kernel/fork.c

@@ -140,7 +140,7 @@ void free_task(struct task_struct *tsk)
 	prop_local_destroy_single(&tsk->dirties);
 	free_thread_info(tsk->stack);
 	rt_mutex_debug_task_free(tsk);
-	ftrace_retfunc_exit_task(tsk);
+	ftrace_graph_exit_task(tsk);
 	free_task_struct(tsk);
 }
 EXPORT_SYMBOL(free_task);
@@ -1271,7 +1271,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	total_forks++;
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
-	ftrace_retfunc_init_task(p);
+	ftrace_graph_init_task(p);
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
 	return p;

kernel/sched.c

@@ -5901,7 +5901,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 * The idle tasks have their own, simple scheduling class:
 	 */
 	idle->sched_class = &idle_sched_class;
-	ftrace_retfunc_init_task(idle);
+	ftrace_graph_init_task(idle);
 }
 
 /*

kernel/trace/Kconfig

@@ -12,7 +12,7 @@ config NOP_TRACER
 config HAVE_FUNCTION_TRACER
 	bool
 
-config HAVE_FUNCTION_RET_TRACER
+config HAVE_FUNCTION_GRAPH_TRACER
 	bool
 
 config HAVE_FUNCTION_TRACE_MCOUNT_TEST
@@ -63,15 +63,18 @@ config FUNCTION_TRACER
 	  (the bootup default), then the overhead of the instructions is very
 	  small and not measurable even in micro-benchmarks.
 
-config FUNCTION_RET_TRACER
-	bool "Kernel Function return Tracer"
-	depends on HAVE_FUNCTION_RET_TRACER
+config FUNCTION_GRAPH_TRACER
+	bool "Kernel Function Graph Tracer"
+	depends on HAVE_FUNCTION_GRAPH_TRACER
 	depends on FUNCTION_TRACER
 	help
-	  Enable the kernel to trace a function at its return.
-	  It's first purpose is to trace the duration of functions.
-	  This is done by setting the current return address on the thread
-	  info structure of the current task.
+	  Enable the kernel to trace a function at both its return
+	  and its entry.
+	  It's first purpose is to trace the duration of functions and
+	  draw a call graph for each thread with some informations like
+	  the return value.
+	  This is done by setting the current return address on the current
+	  task structure into a stack of calls.
 
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
@@ -217,6 +220,17 @@ config BRANCH_TRACER
 
 	  Say N if unsure.
 
+config POWER_TRACER
+	bool "Trace power consumption behavior"
+	depends on DEBUG_KERNEL
+	depends on X86
+	select TRACING
+	help
+	  This tracer helps developers to analyze and optimize the kernels
+	  power management decisions, specifically the C-state and P-state
+	  behavior.
+
+
 config STACK_TRACER
 	bool "Trace max stack"
 	depends on HAVE_FUNCTION_TRACER

kernel/trace/Makefile

@@ -29,8 +29,9 @@ obj-$(CONFIG_NOP_TRACER) += trace_nop.o
 obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
 obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
-obj-$(CONFIG_FUNCTION_RET_TRACER) += trace_functions_return.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
 obj-$(CONFIG_BTS_TRACER) += trace_bts.o
+obj-$(CONFIG_POWER_TRACER) += trace_power.o
 
 libftrace-y := ftrace.o

kernel/trace/ftrace.c

@@ -47,12 +47,12 @@
 int ftrace_enabled __read_mostly;
 static int last_ftrace_enabled;
 
+/* ftrace_pid_trace >= 0 will only trace threads with this pid */
+static int ftrace_pid_trace = -1;
+
 /* Quick disabling of function tracer. */
 int function_trace_stop;
 
-/* By default, current tracing type is normal tracing. */
-enum ftrace_tracing_type_t ftrace_tracing_type = FTRACE_TYPE_ENTER;
-
 /*
  * ftrace_disabled is set when an anomaly is discovered.
  * ftrace_disabled is much stronger than ftrace_enabled.
@@ -61,6 +61,7 @@ static int ftrace_disabled __read_mostly;
 
 static DEFINE_SPINLOCK(ftrace_lock);
 static DEFINE_MUTEX(ftrace_sysctl_lock);
+static DEFINE_MUTEX(ftrace_start_lock);
 
 static struct ftrace_ops ftrace_list_end __read_mostly =
 {
@@ -70,6 +71,7 @@ static struct ftrace_ops ftrace_list_end __read_mostly =
 static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
+ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 
 static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 {
@@ -86,6 +88,21 @@ static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 	};
 }
 
+static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip)
+{
+	if (current->pid != ftrace_pid_trace)
+		return;
+
+	ftrace_pid_function(ip, parent_ip);
+}
+
+static void set_ftrace_pid_function(ftrace_func_t func)
+{
+	/* do not set ftrace_pid_function to itself! */
+	if (func != ftrace_pid_func)
+		ftrace_pid_function = func;
+}
+
 /**
  * clear_ftrace_function - reset the ftrace function
  *
@@ -96,6 +113,7 @@ void clear_ftrace_function(void)
 {
 	ftrace_trace_function = ftrace_stub;
 	__ftrace_trace_function = ftrace_stub;
+	ftrace_pid_function = ftrace_stub;
 }
 
 #ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
@@ -128,20 +146,26 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	ftrace_list = ops;
 
 	if (ftrace_enabled) {
+		ftrace_func_t func;
+
+		if (ops->next == &ftrace_list_end)
+			func = ops->func;
+		else
+			func = ftrace_list_func;
+
+		if (ftrace_pid_trace >= 0) {
+			set_ftrace_pid_function(func);
+			func = ftrace_pid_func;
+		}
+
 		/*
 		 * For one func, simply call it directly.
 		 * For more than one func, call the chain.
 		 */
 #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-		if (ops->next == &ftrace_list_end)
-			ftrace_trace_function = ops->func;
-		else
-			ftrace_trace_function = ftrace_list_func;
+		ftrace_trace_function = func;
 #else
-		if (ops->next == &ftrace_list_end)
-			__ftrace_trace_function = ops->func;
-		else
-			__ftrace_trace_function = ftrace_list_func;
+		__ftrace_trace_function = func;
 		ftrace_trace_function = ftrace_test_stop_func;
 #endif
 	}
@@ -182,8 +206,19 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 
 	if (ftrace_enabled) {
 		/* If we only have one func left, then call that directly */
-		if (ftrace_list->next == &ftrace_list_end)
-			ftrace_trace_function = ftrace_list->func;
+		if (ftrace_list->next == &ftrace_list_end) {
+			ftrace_func_t func = ftrace_list->func;
+
+			if (ftrace_pid_trace >= 0) {
+				set_ftrace_pid_function(func);
+				func = ftrace_pid_func;
+			}
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+			ftrace_trace_function = func;
+#else
+			__ftrace_trace_function = func;
+#endif
+		}
 	}
 
  out:
@@ -192,6 +227,38 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	return ret;
 }
 
+static void ftrace_update_pid_func(void)
+{
+	ftrace_func_t func;
+
+	/* should not be called from interrupt context */
+	spin_lock(&ftrace_lock);
+
+	if (ftrace_trace_function == ftrace_stub)
+		goto out;
+
+	func = ftrace_trace_function;
+
+	if (ftrace_pid_trace >= 0) {
+		set_ftrace_pid_function(func);
+		func = ftrace_pid_func;
+	} else {
+		if (func != ftrace_pid_func)
+			goto out;
+
+		set_ftrace_pid_function(func);
+	}
+
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	ftrace_trace_function = func;
+#else
+	__ftrace_trace_function = func;
+#endif
+
+ out:
+	spin_unlock(&ftrace_lock);
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 #ifndef CONFIG_FTRACE_MCOUNT_RECORD
 # error Dynamic ftrace depends on MCOUNT_RECORD
@@ -211,6 +278,8 @@ enum {
 	FTRACE_UPDATE_TRACE_FUNC	= (1 << 2),
 	FTRACE_ENABLE_MCOUNT		= (1 << 3),
 	FTRACE_DISABLE_MCOUNT		= (1 << 4),
+	FTRACE_START_FUNC_RET		= (1 << 5),
+	FTRACE_STOP_FUNC_RET		= (1 << 6),
 };
 
 static int ftrace_filtered;
@@ -395,14 +464,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 	unsigned long ip, fl;
 	unsigned long ftrace_addr;
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
-	if (ftrace_tracing_type == FTRACE_TYPE_ENTER)
-		ftrace_addr = (unsigned long)ftrace_caller;
-	else
-		ftrace_addr = (unsigned long)ftrace_return_caller;
-#else
 	ftrace_addr = (unsigned long)ftrace_caller;
-#endif
 
 	ip = rec->ip;
 
@@ -535,6 +597,11 @@ static int __ftrace_modify_code(void *data)
 	if (*command & FTRACE_UPDATE_TRACE_FUNC)
 		ftrace_update_ftrace_func(ftrace_trace_function);
 
+	if (*command & FTRACE_START_FUNC_RET)
+		ftrace_enable_ftrace_graph_caller();
+	else if (*command & FTRACE_STOP_FUNC_RET)
+		ftrace_disable_ftrace_graph_caller();
+
 	return 0;
 }
 
@@ -545,12 +612,22 @@ static void ftrace_run_update_code(int command)
 
 static ftrace_func_t saved_ftrace_func;
 static int ftrace_start_up;
-static DEFINE_MUTEX(ftrace_start_lock);
 
-static void ftrace_startup(void)
+static void ftrace_startup_enable(int command)
 {
-	int command = 0;
+	if (saved_ftrace_func != ftrace_trace_function) {
+		saved_ftrace_func = ftrace_trace_function;
+		command |= FTRACE_UPDATE_TRACE_FUNC;
+	}
+
+	if (!command || !ftrace_enabled)
+		return;
+
+	ftrace_run_update_code(command);
+}
 
+static void ftrace_startup(int command)
+{
 	if (unlikely(ftrace_disabled))
 		return;
 
@@ -558,23 +635,13 @@ static void ftrace_startup(void)
 	ftrace_start_up++;
 	command |= FTRACE_ENABLE_CALLS;
 
-	if (saved_ftrace_func != ftrace_trace_function) {
-		saved_ftrace_func = ftrace_trace_function;
-		command |= FTRACE_UPDATE_TRACE_FUNC;
-	}
+	ftrace_startup_enable(command);
 
-	if (!command || !ftrace_enabled)
-		goto out;
-
-	ftrace_run_update_code(command);
- out:
 	mutex_unlock(&ftrace_start_lock);
 }
 
-static void ftrace_shutdown(void)
+static void ftrace_shutdown(int command)
 {
-	int command = 0;
-
 	if (unlikely(ftrace_disabled))
 		return;
 
@@ -1262,13 +1329,10 @@ static struct file_operations ftrace_notrace_fops = {
 	.release = ftrace_notrace_release,
 };
 
-static __init int ftrace_init_debugfs(void)
+static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
 {
-	struct dentry *d_tracer;
 	struct dentry *entry;
 
-	d_tracer = tracing_init_dentry();
-
 	entry = debugfs_create_file("available_filter_functions", 0444,
 				    d_tracer, NULL, &ftrace_avail_fops);
 	if (!entry)
@@ -1295,8 +1359,6 @@ static __init int ftrace_init_debugfs(void)
 	return 0;
 }
 
-fs_initcall(ftrace_init_debugfs);
-
 static int ftrace_convert_nops(struct module *mod,
 			       unsigned long *start,
 			       unsigned long *end)
@@ -1382,12 +1444,101 @@ static int __init ftrace_nodyn_init(void)
 }
 device_initcall(ftrace_nodyn_init);
 
-# define ftrace_startup()		do { } while (0)
-# define ftrace_shutdown()		do { } while (0)
+static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
+static inline void ftrace_startup_enable(int command) { }
+/* Keep as macros so we do not need to define the commands */
+# define ftrace_startup(command)	do { } while (0)
+# define ftrace_shutdown(command)	do { } while (0)
 # define ftrace_startup_sysctl()	do { } while (0)
 # define ftrace_shutdown_sysctl()	do { } while (0)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
+static ssize_t
+ftrace_pid_read(struct file *file, char __user *ubuf,
+		       size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	int r;
+
+	if (ftrace_pid_trace >= 0)
+		r = sprintf(buf, "%u\n", ftrace_pid_trace);
+	else
+		r = sprintf(buf, "no pid\n");
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+ftrace_pid_write(struct file *filp, const char __user *ubuf,
+		   size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	long val;
+	int ret;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	ret = strict_strtol(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&ftrace_start_lock);
+	if (ret < 0) {
+		/* disable pid tracing */
+		if (ftrace_pid_trace < 0)
+			goto out;
+		ftrace_pid_trace = -1;
+
+	} else {
+
+		if (ftrace_pid_trace == val)
+			goto out;
+
+		ftrace_pid_trace = val;
+	}
+
+	/* update the function call */
+	ftrace_update_pid_func();
+	ftrace_startup_enable(0);
+
+ out:
+	mutex_unlock(&ftrace_start_lock);
+
+	return cnt;
+}
+
+static struct file_operations ftrace_pid_fops = {
+	.read = ftrace_pid_read,
+	.write = ftrace_pid_write,
+};
+
+static __init int ftrace_init_debugfs(void)
+{
+	struct dentry *d_tracer;
+	struct dentry *entry;
+
+	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
+
+	ftrace_init_dyn_debugfs(d_tracer);
+
+	entry = debugfs_create_file("set_ftrace_pid", 0644, d_tracer,
+				    NULL, &ftrace_pid_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'set_ftrace_pid' entry\n");
+	return 0;
+}
+
+fs_initcall(ftrace_init_debugfs);
+
 /**
  * ftrace_kill - kill ftrace
  *
@@ -1422,15 +1573,9 @@ int register_ftrace_function(struct ftrace_ops *ops)
 
 	mutex_lock(&ftrace_sysctl_lock);
 
-	if (ftrace_tracing_type == FTRACE_TYPE_RETURN) {
-		ret = -EBUSY;
-		goto out;
-	}
-
 	ret = __register_ftrace_function(ops);
-	ftrace_startup();
+	ftrace_startup(0);
 
-out:
 	mutex_unlock(&ftrace_sysctl_lock);
 	return ret;
 }
@@ -1447,7 +1592,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 
 	mutex_lock(&ftrace_sysctl_lock);
 	ret = __unregister_ftrace_function(ops);
-	ftrace_shutdown();
+	ftrace_shutdown(0);
 	mutex_unlock(&ftrace_sysctl_lock);
 
 	return ret;
@@ -1496,14 +1641,15 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 	return ret;
 }
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
-
-static atomic_t ftrace_retfunc_active;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
-/* The callback that hooks the return of a function */
-trace_function_return_t ftrace_function_return =
-			(trace_function_return_t)ftrace_stub;
+static atomic_t ftrace_graph_active;
 
+/* The callbacks that hook a function */
+trace_func_graph_ret_t ftrace_graph_return =
+			(trace_func_graph_ret_t)ftrace_stub;
+trace_func_graph_ent_t ftrace_graph_entry =
+			(trace_func_graph_ent_t)ftrace_stub;
 
 /* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
 static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
@@ -1549,7 +1695,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 }
 
 /* Allocate a return stack for each task */
-static int start_return_tracing(void)
+static int start_graph_tracing(void)
 {
 	struct ftrace_ret_stack **ret_stack_list;
 	int ret;
@@ -1569,52 +1715,46 @@ static int start_return_tracing(void)
 	return ret;
 }
 
-int register_ftrace_return(trace_function_return_t func)
+int register_ftrace_graph(trace_func_graph_ret_t retfunc,
+			trace_func_graph_ent_t entryfunc)
 {
 	int ret = 0;
 
 	mutex_lock(&ftrace_sysctl_lock);
 
-	/*
-	 * Don't launch return tracing if normal function
-	 * tracing is already running.
-	 */
-	if (ftrace_trace_function != ftrace_stub) {
-		ret = -EBUSY;
-		goto out;
-	}
-	atomic_inc(&ftrace_retfunc_active);
-	ret = start_return_tracing();
+	atomic_inc(&ftrace_graph_active);
+	ret = start_graph_tracing();
 	if (ret) {
-		atomic_dec(&ftrace_retfunc_active);
+		atomic_dec(&ftrace_graph_active);
 		goto out;
 	}
-	ftrace_tracing_type = FTRACE_TYPE_RETURN;
-	ftrace_function_return = func;
-	ftrace_startup();
+
+	ftrace_graph_return = retfunc;
+	ftrace_graph_entry = entryfunc;
+
+	ftrace_startup(FTRACE_START_FUNC_RET);
 
 out:
 	mutex_unlock(&ftrace_sysctl_lock);
 	return ret;
 }
 
-void unregister_ftrace_return(void)
+void unregister_ftrace_graph(void)
 {
 	mutex_lock(&ftrace_sysctl_lock);
 
-	atomic_dec(&ftrace_retfunc_active);
-	ftrace_function_return = (trace_function_return_t)ftrace_stub;
-	ftrace_shutdown();
-	/* Restore normal tracing type */
-	ftrace_tracing_type = FTRACE_TYPE_ENTER;
+	atomic_dec(&ftrace_graph_active);
+	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
+	ftrace_graph_entry = (trace_func_graph_ent_t)ftrace_stub;
+	ftrace_shutdown(FTRACE_STOP_FUNC_RET);
 
 	mutex_unlock(&ftrace_sysctl_lock);
 }
 
 /* Allocate a return stack for newly created task */
-void ftrace_retfunc_init_task(struct task_struct *t)
+void ftrace_graph_init_task(struct task_struct *t)
 {
-	if (atomic_read(&ftrace_retfunc_active)) {
+	if (atomic_read(&ftrace_graph_active)) {
 		t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
 				* sizeof(struct ftrace_ret_stack),
 				GFP_KERNEL);
@@ -1626,7 +1766,7 @@ void ftrace_retfunc_init_task(struct task_struct *t)
 		t->ret_stack = NULL;
 }
 
-void ftrace_retfunc_exit_task(struct task_struct *t)
+void ftrace_graph_exit_task(struct task_struct *t)
 {
 	struct ftrace_ret_stack	*ret_stack = t->ret_stack;
 
@@ -1638,5 +1778,3 @@ void ftrace_retfunc_exit_task(struct task_struct *t)
 }
 #endif
 
-
-

kernel/trace/trace.c

@@ -804,7 +804,7 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	spin_unlock(&trace_cmdline_lock);
 }
 
-static char *trace_find_cmdline(int pid)
+char *trace_find_cmdline(int pid)
 {
 	char *cmdline = "<...>";
 	unsigned map;
@@ -878,15 +878,15 @@ trace_function(struct trace_array *tr, struct trace_array_cpu *data,
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 }
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
-static void __trace_function_return(struct trace_array *tr,
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static void __trace_graph_entry(struct trace_array *tr,
 				struct trace_array_cpu *data,
-				struct ftrace_retfunc *trace,
+				struct ftrace_graph_ent *trace,
 				unsigned long flags,
 				int pc)
 {
 	struct ring_buffer_event *event;
-	struct ftrace_ret_entry *entry;
+	struct ftrace_graph_ent_entry *entry;
 	unsigned long irq_flags;
 
 	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
@@ -898,12 +898,32 @@ static void __trace_function_return(struct trace_array *tr,
 		return;
 	entry	= ring_buffer_event_data(event);
 	tracing_generic_entry_update(&entry->ent, flags, pc);
-	entry->ent.type			= TRACE_FN_RET;
-	entry->ip			= trace->func;
-	entry->parent_ip	= trace->ret;
-	entry->rettime		= trace->rettime;
-	entry->calltime		= trace->calltime;
-	entry->overrun		= trace->overrun;
+	entry->ent.type			= TRACE_GRAPH_ENT;
+	entry->graph_ent			= *trace;
+	ring_buffer_unlock_commit(global_trace.buffer, event, irq_flags);
+}
+
+static void __trace_graph_return(struct trace_array *tr,
+				struct trace_array_cpu *data,
+				struct ftrace_graph_ret *trace,
+				unsigned long flags,
+				int pc)
+{
+	struct ring_buffer_event *event;
+	struct ftrace_graph_ret_entry *entry;
+	unsigned long irq_flags;
+
+	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+		return;
+
+	event = ring_buffer_lock_reserve(global_trace.buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, flags, pc);
+	entry->ent.type			= TRACE_GRAPH_RET;
+	entry->ret				= *trace;
 	ring_buffer_unlock_commit(global_trace.buffer, event, irq_flags);
 }
 #endif
@@ -1177,8 +1197,29 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
 	local_irq_restore(flags);
 }
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
-void trace_function_return(struct ftrace_retfunc *trace)
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+void trace_graph_entry(struct ftrace_graph_ent *trace)
+{
+	struct trace_array *tr = &global_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int cpu;
+	int pc;
+
+	raw_local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		__trace_graph_entry(tr, data, trace, flags, pc);
+	}
+	atomic_dec(&data->disabled);
+	raw_local_irq_restore(flags);
+}
+
+void trace_graph_return(struct ftrace_graph_ret *trace)
 {
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
@@ -1193,12 +1234,12 @@ void trace_function_return(struct ftrace_retfunc *trace)
 	disabled = atomic_inc_return(&data->disabled);
 	if (likely(disabled == 1)) {
 		pc = preempt_count();
-		__trace_function_return(tr, data, trace, flags, pc);
+		__trace_graph_return(tr, data, trace, flags, pc);
 	}
 	atomic_dec(&data->disabled);
 	raw_local_irq_restore(flags);
 }
-#endif /* CONFIG_FUNCTION_RET_TRACER */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 static struct ftrace_ops trace_ops __read_mostly =
 {
@@ -2000,9 +2041,11 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 			trace_seq_print_cont(s, iter);
 		break;
 	}
-	case TRACE_FN_RET: {
-		return print_return_function(iter);
-		break;
+	case TRACE_GRAPH_RET: {
+		return print_graph_function(iter);
+	}
+	case TRACE_GRAPH_ENT: {
+		return print_graph_function(iter);
 	}
 	case TRACE_BRANCH: {
 		struct trace_branch *field;

kernel/trace/trace.h

@@ -25,9 +25,11 @@ enum trace_type {
 	TRACE_BRANCH,
 	TRACE_BOOT_CALL,
 	TRACE_BOOT_RET,
-	TRACE_FN_RET,
+	TRACE_GRAPH_RET,
+	TRACE_GRAPH_ENT,
 	TRACE_USER_STACK,
 	TRACE_BTS,
+	TRACE_POWER,
 
 	__TRACE_LAST_TYPE
 };
@@ -56,14 +58,16 @@ struct ftrace_entry {
 	unsigned long		parent_ip;
 };
 
+/* Function call entry */
+struct ftrace_graph_ent_entry {
+	struct trace_entry			ent;
+	struct ftrace_graph_ent		graph_ent;
+};
+
 /* Function return entry */
-struct ftrace_ret_entry {
-	struct trace_entry	ent;
-	unsigned long		ip;
-	unsigned long		parent_ip;
-	unsigned long long	calltime;
-	unsigned long long	rettime;
-	unsigned long		overrun;
+struct ftrace_graph_ret_entry {
+	struct trace_entry			ent;
+	struct ftrace_graph_ret		ret;
 };
 extern struct tracer boot_tracer;
 
@@ -160,6 +164,11 @@ struct bts_entry {
 	unsigned long		to;
 };
 
+struct trace_power {
+	struct trace_entry	ent;
+	struct power_trace	state_data;
+};
+
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
@@ -264,8 +273,12 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\
 		IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\
 		IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
-		IF_ASSIGN(var, ent, struct ftrace_ret_entry, TRACE_FN_RET);\
+		IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry,	\
+			  TRACE_GRAPH_ENT);		\
+		IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,	\
+			  TRACE_GRAPH_RET);		\
 		IF_ASSIGN(var, ent, struct bts_entry, TRACE_BTS);\
+ 		IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \
 		__ftrace_bad_type();					\
 	} while (0)
 
@@ -397,9 +410,9 @@ void trace_function(struct trace_array *tr,
 		    unsigned long ip,
 		    unsigned long parent_ip,
 		    unsigned long flags, int pc);
-void
-trace_function_return(struct ftrace_retfunc *trace);
 
+void trace_graph_return(struct ftrace_graph_ret *trace);
+void trace_graph_entry(struct ftrace_graph_ent *trace);
 void trace_bts(struct trace_array *tr,
 	       unsigned long from,
 	       unsigned long to);
@@ -444,6 +457,7 @@ struct tracer_switch_ops {
 	struct tracer_switch_ops	*next;
 };
 
+char *trace_find_cmdline(int pid);
 #endif /* CONFIG_CONTEXT_SWITCH_TRACER */
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -489,11 +503,11 @@ extern int trace_vprintk(unsigned long ip, const char *fmt, va_list args);
 extern unsigned long trace_flags;
 
 /* Standard output formatting function used for function return traces */
-#ifdef CONFIG_FUNCTION_RET_TRACER
-extern enum print_line_t print_return_function(struct trace_iterator *iter);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+extern enum print_line_t print_graph_function(struct trace_iterator *iter);
 #else
 static inline enum print_line_t
-print_return_function(struct trace_iterator *iter)
+print_graph_function(struct trace_iterator *iter)
 {
 	return TRACE_TYPE_UNHANDLED;
 }

kernel/trace/trace_functions_graph.c

+/*
+ *
+ * Function graph tracer.
+ * Copyright (c) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ * Mostly borrowed from function tracer which
+ * is Copyright (c) Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+
+#define TRACE_GRAPH_INDENT	2
+
+#define TRACE_GRAPH_PRINT_OVERRUN	0x1
+static struct tracer_opt trace_opts[] = {
+	/* Display overruns or not */
+	{ TRACER_OPT(overrun, TRACE_GRAPH_PRINT_OVERRUN) },
+	{ } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+	.val = 0, /* Don't display overruns by default */
+	.opts = trace_opts
+};
+
+/* pid on the last trace processed */
+static pid_t last_pid[NR_CPUS] = { [0 ... NR_CPUS-1] = -1 };
+
+static int graph_trace_init(struct trace_array *tr)
+{
+	int cpu, ret;
+
+	for_each_online_cpu(cpu)
+		tracing_reset(tr, cpu);
+
+	ret = register_ftrace_graph(&trace_graph_return,
+					&trace_graph_entry);
+	if (ret)
+		return ret;
+	tracing_start_cmdline_record();
+
+	return 0;
+}
+
+static void graph_trace_reset(struct trace_array *tr)
+{
+	tracing_stop_cmdline_record();
+	unregister_ftrace_graph();
+}
+
+/* If the pid changed since the last trace, output this event */
+static int verif_pid(struct trace_seq *s, pid_t pid, int cpu)
+{
+	char *comm;
+
+	if (last_pid[cpu] != -1 && last_pid[cpu] == pid)
+		return 1;
+
+	last_pid[cpu] = pid;
+	comm = trace_find_cmdline(pid);
+
+	return trace_seq_printf(s, "\nCPU[%03d]"
+				    " ------------8<---------- thread %s-%d"
+				    " ------------8<----------\n\n",
+				    cpu, comm, pid);
+}
+
+static enum print_line_t
+print_graph_entry(struct ftrace_graph_ent *call, struct trace_seq *s,
+		  struct trace_entry *ent, int cpu)
+{
+	int i;
+	int ret;
+
+	if (!verif_pid(s, ent->pid, cpu))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	ret = trace_seq_printf(s, "CPU[%03d] ", cpu);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
+		ret = trace_seq_printf(s, " ");
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+	}
+
+	ret = seq_print_ip_sym(s, call->func, 0);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	ret = trace_seq_printf(s, "() {\n");
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
+		   struct trace_entry *ent, int cpu)
+{
+	int i;
+	int ret;
+
+	if (!verif_pid(s, ent->pid, cpu))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	ret = trace_seq_printf(s, "CPU[%03d] ", cpu);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) {
+		ret = trace_seq_printf(s, " ");
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+	}
+
+	ret = trace_seq_printf(s, "} ");
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	ret = trace_seq_printf(s, "%llu\n", trace->rettime - trace->calltime);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERRUN) {
+		ret = trace_seq_printf(s, " (Overruns: %lu)\n",
+					trace->overrun);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+	}
+	return TRACE_TYPE_HANDLED;
+}
+
+enum print_line_t
+print_graph_function(struct trace_iterator *iter)
+{
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *entry = iter->ent;
+
+	switch (entry->type) {
+	case TRACE_GRAPH_ENT: {
+		struct ftrace_graph_ent_entry *field;
+		trace_assign_type(field, entry);
+		return print_graph_entry(&field->graph_ent, s, entry,
+					 iter->cpu);
+	}
+	case TRACE_GRAPH_RET: {
+		struct ftrace_graph_ret_entry *field;
+		trace_assign_type(field, entry);
+		return print_graph_return(&field->ret, s, entry, iter->cpu);
+	}
+	default:
+		return TRACE_TYPE_UNHANDLED;
+	}
+}
+
+static struct tracer graph_trace __read_mostly = {
+	.name	     = "function-graph",
+	.init	     = graph_trace_init,
+	.reset	     = graph_trace_reset,
+	.print_line = print_graph_function,
+	.flags		= &tracer_flags,
+};
+
+static __init int init_graph_trace(void)
+{
+	return register_tracer(&graph_trace);
+}
+
+device_initcall(init_graph_trace);

kernel/trace/trace_functions_return.c

-/*
- *
- * Function return tracer.
- * Copyright (c) 2008 Frederic Weisbecker <fweisbec@gmail.com>
- * Mostly borrowed from function tracer which
- * is Copyright (c) Steven Rostedt <srostedt@redhat.com>
- *
- */
-#include <linux/debugfs.h>
-#include <linux/uaccess.h>
-#include <linux/ftrace.h>
-#include <linux/fs.h>
-
-#include "trace.h"
-
-
-#define TRACE_RETURN_PRINT_OVERRUN	0x1
-static struct tracer_opt trace_opts[] = {
-	/* Display overruns or not */
-	{ TRACER_OPT(overrun, TRACE_RETURN_PRINT_OVERRUN) },
-	{ } /* Empty entry */
-};
-
-static struct tracer_flags tracer_flags = {
-	.val = 0, /* Don't display overruns by default */
-	.opts = trace_opts
-};
-
-
-static int return_trace_init(struct trace_array *tr)
-{
-	int cpu;
-	for_each_online_cpu(cpu)
-		tracing_reset(tr, cpu);
-
-	return register_ftrace_return(&trace_function_return);
-}
-
-static void return_trace_reset(struct trace_array *tr)
-{
-		unregister_ftrace_return();
-}
-
-
-enum print_line_t
-print_return_function(struct trace_iterator *iter)
-{
-	struct trace_seq *s = &iter->seq;
-	struct trace_entry *entry = iter->ent;
-	struct ftrace_ret_entry *field;
-	int ret;
-
-	if (entry->type == TRACE_FN_RET) {
-		trace_assign_type(field, entry);
-		ret = trace_seq_printf(s, "%pF -> ", (void *)field->parent_ip);
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-
-		ret = seq_print_ip_sym(s, field->ip,
-					trace_flags & TRACE_ITER_SYM_MASK);
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-
-		ret = trace_seq_printf(s, " (%llu ns)",
-					field->rettime - field->calltime);
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-
-		if (tracer_flags.val & TRACE_RETURN_PRINT_OVERRUN) {
-			ret = trace_seq_printf(s, " (Overruns: %lu)",
-						field->overrun);
-			if (!ret)
-				return TRACE_TYPE_PARTIAL_LINE;
-		}
-
-		ret = trace_seq_printf(s, "\n");
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-
-		return TRACE_TYPE_HANDLED;
-	}
-	return TRACE_TYPE_UNHANDLED;
-}
-
-static struct tracer return_trace __read_mostly = {
-	.name	     = "return",
-	.init	     = return_trace_init,
-	.reset	     = return_trace_reset,
-	.print_line = print_return_function,
-	.flags		= &tracer_flags,
-};
-
-static __init int init_return_trace(void)
-{
-	return register_tracer(&return_trace);
-}
-
-device_initcall(init_return_trace);

kernel/trace/trace_power.c

+/*
+ * ring buffer based C-state tracer
+ *
+ * Arjan van de Ven <arjan@linux.intel.com>
+ * Copyright (C) 2008 Intel Corporation
+ *
+ * Much is borrowed from trace_boot.c which is
+ * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+
+#include "trace.h"
+
+static struct trace_array *power_trace;
+static int __read_mostly trace_power_enabled;
+
+
+static void start_power_trace(struct trace_array *tr)
+{
+	trace_power_enabled = 1;
+}
+
+static void stop_power_trace(struct trace_array *tr)
+{
+	trace_power_enabled = 0;
+}
+
+
+static int power_trace_init(struct trace_array *tr)
+{
+	int cpu;
+	power_trace = tr;
+
+	trace_power_enabled = 1;
+
+	for_each_cpu_mask(cpu, cpu_possible_map)
+		tracing_reset(tr, cpu);
+	return 0;
+}
+
+static enum print_line_t power_print_line(struct trace_iterator *iter)
+{
+	int ret = 0;
+	struct trace_entry *entry = iter->ent;
+	struct trace_power *field ;
+	struct power_trace *it;
+	struct trace_seq *s = &iter->seq;
+	struct timespec stamp;
+	struct timespec duration;
+
+	trace_assign_type(field, entry);
+	it = &field->state_data;
+	stamp = ktime_to_timespec(it->stamp);
+	duration = ktime_to_timespec(ktime_sub(it->end, it->stamp));
+
+	if (entry->type == TRACE_POWER) {
+		if (it->type == POWER_CSTATE)
+			ret = trace_seq_printf(s, "[%5ld.%09ld] CSTATE: Going to C%i on cpu %i for %ld.%09ld\n",
+					  stamp.tv_sec,
+					  stamp.tv_nsec,
+					  it->state, iter->cpu,
+					  duration.tv_sec,
+					  duration.tv_nsec);
+		if (it->type == POWER_PSTATE)
+			ret = trace_seq_printf(s, "[%5ld.%09ld] PSTATE: Going to P%i on cpu %i\n",
+					  stamp.tv_sec,
+					  stamp.tv_nsec,
+					  it->state, iter->cpu);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+		return TRACE_TYPE_HANDLED;
+	}
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static struct tracer power_tracer __read_mostly =
+{
+	.name		= "power",
+	.init		= power_trace_init,
+	.start		= start_power_trace,
+	.stop		= stop_power_trace,
+	.reset		= stop_power_trace,
+	.print_line	= power_print_line,
+};
+
+static int init_power_trace(void)
+{
+	return register_tracer(&power_tracer);
+}
+device_initcall(init_power_trace);
+
+void trace_power_start(struct power_trace *it, unsigned int type,
+			 unsigned int level)
+{
+	if (!trace_power_enabled)
+		return;
+
+	memset(it, 0, sizeof(struct power_trace));
+	it->state = level;
+	it->type = type;
+	it->stamp = ktime_get();
+}
+EXPORT_SYMBOL_GPL(trace_power_start);
+
+
+void trace_power_end(struct power_trace *it)
+{
+	struct ring_buffer_event *event;
+	struct trace_power *entry;
+	struct trace_array_cpu *data;
+	unsigned long irq_flags;
+	struct trace_array *tr = power_trace;
+
+	if (!trace_power_enabled)
+		return;
+
+	preempt_disable();
+	it->end = ktime_get();
+	data = tr->data[smp_processor_id()];
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		goto out;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+	entry->ent.type = TRACE_POWER;
+	entry->state_data = *it;
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+	trace_wake_up();
+
+ out:
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(trace_power_end);
+
+void trace_power_mark(struct power_trace *it, unsigned int type,
+			 unsigned int level)
+{
+	struct ring_buffer_event *event;
+	struct trace_power *entry;
+	struct trace_array_cpu *data;
+	unsigned long irq_flags;
+	struct trace_array *tr = power_trace;
+
+	if (!trace_power_enabled)
+		return;
+
+	memset(it, 0, sizeof(struct power_trace));
+	it->state = level;
+	it->type = type;
+	it->stamp = ktime_get();
+	preempt_disable();
+	it->end = it->stamp;
+	data = tr->data[smp_processor_id()];
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		goto out;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+	entry->ent.type = TRACE_POWER;
+	entry->state_data = *it;
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+	trace_wake_up();
+
+ out:
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(trace_power_mark);

scripts/recordmcount.pl

@@ -112,6 +112,8 @@ my ($arch, $bits, $objdump, $objcopy, $cc,
 # Acceptable sections to record.
 my %text_sections = (
      ".text" => 1,
+     ".sched.text" => 1,
+     ".spinlock.text" => 1,
 );
 
 $objdump = "objdump" if ((length $objdump) == 0);

scripts/trace/power.pl

+#!/usr/bin/perl
+
+# Copyright 2008, Intel Corporation
+#
+# This file is part of the Linux kernel
+#
+# This program file is free software; you can redistribute it and/or modify it
+# under the terms of the GNU General Public License as published by the
+# Free Software Foundation; version 2 of the License.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+# for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program in a file named COPYING; if not, write to the
+# Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor,
+# Boston, MA 02110-1301 USA
+#
+# Authors:
+# 	Arjan van de Ven <arjan@linux.intel.com>
+
+
+#
+# This script turns a cstate ftrace output into a SVG graphic that shows
+# historic C-state information
+#
+#
+# 	cat /sys/kernel/debug/tracing/trace | perl power.pl > out.svg
+#
+
+my @styles;
+my $base = 0;
+
+my @pstate_last;
+my @pstate_level;
+
+$styles[0] = "fill:rgb(0,0,255);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)";
+$styles[1] = "fill:rgb(0,255,0);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)";
+$styles[2] = "fill:rgb(255,0,20);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)";
+$styles[3] = "fill:rgb(255,255,20);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)";
+$styles[4] = "fill:rgb(255,0,255);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)";
+$styles[5] = "fill:rgb(0,255,255);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)";
+$styles[6] = "fill:rgb(0,128,255);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)";
+$styles[7] = "fill:rgb(0,255,128);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)";
+$styles[8] = "fill:rgb(0,25,20);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)";
+
+
+print "<?xml version=\"1.0\" standalone=\"no\"?> \n";
+print "<svg width=\"10000\" height=\"100%\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n";
+
+my $scale = 30000.0;
+while (<>) {
+	my $line = $_;
+	if ($line =~ /([0-9\.]+)\] CSTATE: Going to C([0-9]) on cpu ([0-9]+) for ([0-9\.]+)/) {
+		if ($base == 0) {
+			$base = $1;
+		}
+		my $time = $1 - $base;
+		$time = $time * $scale;
+		my $C = $2;
+		my $cpu = $3;
+		my $y = 400 * $cpu;
+		my $duration = $4 * $scale;
+		my $msec = int($4 * 100000)/100.0;
+		my $height = $C * 20;
+		$style = $styles[$C];
+
+		$y = $y + 140 - $height;
+
+		$x2 = $time + 4;
+		$y2 = $y + 4;
+
+
+		print "<rect x=\"$time\" width=\"$duration\" y=\"$y\" height=\"$height\" style=\"$style\"/>\n";
+		print "<text transform=\"translate($x2,$y2) rotate(90)\">C$C $msec</text>\n";
+	}
+	if ($line =~ /([0-9\.]+)\] PSTATE: Going to P([0-9]) on cpu ([0-9]+)/) {
+		my $time = $1 - $base;
+		my $state = $2;
+		my $cpu = $3;
+
+		if (defined($pstate_last[$cpu])) {
+			my $from = $pstate_last[$cpu];
+			my $oldstate = $pstate_state[$cpu];
+			my $duration = ($time-$from) * $scale;
+
+			$from = $from * $scale;
+			my $to = $from + $duration;
+			my $height = 140 - ($oldstate * (140/8));
+
+			my $y = 400 * $cpu + 200 + $height;
+			my $y2 = $y+4;
+			my $style = $styles[8];
+
+			print "<rect x=\"$from\" y=\"$y\" width=\"$duration\" height=\"5\" style=\"$style\"/>\n";
+			print "<text transform=\"translate($from,$y2)\">P$oldstate (cpu $cpu)</text>\n";
+		};
+
+		$pstate_last[$cpu] = $time;
+		$pstate_state[$cpu] = $state;
+	}
+}
+
+
+print "</svg>\n";