diff options
-rw-r--r-- | Documentation/ftrace.txt | 79 | ||||
-rw-r--r-- | arch/x86/Kconfig | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/ftrace.h | 4 | ||||
-rw-r--r-- | arch/x86/kernel/Makefile | 4 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/entry_32.S | 17 | ||||
-rw-r--r-- | arch/x86/kernel/ftrace.c | 90 | ||||
-rw-r--r-- | arch/x86/kernel/process.c | 16 | ||||
-rw-r--r-- | include/linux/ftrace.h | 77 | ||||
-rw-r--r-- | include/linux/ftrace_irq.h | 2 | ||||
-rw-r--r-- | include/linux/sched.h | 2 | ||||
-rw-r--r-- | kernel/Makefile | 2 | ||||
-rw-r--r-- | kernel/fork.c | 4 | ||||
-rw-r--r-- | kernel/sched.c | 2 | ||||
-rw-r--r-- | kernel/trace/Kconfig | 30 | ||||
-rw-r--r-- | kernel/trace/Makefile | 3 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 306 | ||||
-rw-r--r-- | kernel/trace/trace.c | 79 | ||||
-rw-r--r-- | kernel/trace/trace.h | 42 | ||||
-rw-r--r-- | kernel/trace/trace_functions_graph.c | 175 | ||||
-rw-r--r-- | kernel/trace/trace_functions_return.c | 98 | ||||
-rw-r--r-- | kernel/trace/trace_power.c | 179 | ||||
-rwxr-xr-x | scripts/recordmcount.pl | 2 | ||||
-rw-r--r-- | scripts/trace/power.pl | 108 |
24 files changed, 1054 insertions, 273 deletions
diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt index 35a78bc6651..de05042f11b 100644 --- a/Documentation/ftrace.txt +++ b/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 -------------- diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e49a4fd718f..0842b112768 100644 --- a/arch/x86/Kconfig +++ b/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 diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 754a3e082f9..7e61b4ceb9a 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/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 */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index af2bc36ca1c..64939a0c398 100644 --- a/arch/x86/kernel/Makefile +++ b/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 diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 8e48c5d4467..88ea02dcb62 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/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; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 74defe21ba4..958af86186c 100644 --- a/arch/x86/kernel/entry_32.S +++ b/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: diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index bb137f7297e..7ef914e6a2f 100644 --- a/arch/x86/kernel/ftrace.c +++ b/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(¤t->trace_overrun); + trace->func = current->ret_stack[index].func; + trace->calltime = current->ret_stack[index].calltime; + trace->overrun = atomic_read(¤t->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 */ diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index c622772744d..c27af49a4ed 100644 --- a/arch/x86/kernel/process.c +++ b/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 *)¤t_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 *)¤t_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); } /* diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 7854d87b97b..afba918c623 100644 --- a/include/linux/ftrace.h +++ b/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 */ diff --git a/include/linux/ftrace_irq.h b/include/linux/ftrace_irq.h index 0b4df55d7a7..366a054d0b0 100644 --- a/include/linux/ftrace_irq.h +++ b/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 diff --git a/include/linux/sched.h b/include/linux/sched.h index d02a0ca70ee..7ad48f2a275 100644 --- a/include/linux/sched.h +++ b/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 */ diff --git a/kernel/Makefile b/kernel/Makefile index 03a45e7e87b..703cf3b7389 100644 --- a/kernel/Makefile +++ b/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 diff --git a/kernel/fork.c b/kernel/fork.c index d6e1a3205f6..5f82a999c03 100644 --- a/kernel/fork.c +++ b/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(¤t->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; diff --git a/kernel/sched.c b/kernel/sched.c index 388d9db044a..52490bf6b88 100644 --- a/kernel/sched.c +++ b/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); } /* diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 620feadff67..8b6b673b4d6 100644 --- a/kernel/trace/Kconfig +++ b/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 diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index cef4bcb4e82..62dc561b667 100644 --- a/kernel/trace/Makefile +++ b/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 diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 53042f118f2..cbf8b09f63a 100644 --- a/kernel/trace/ftrace.c +++ b/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_ca |