ftrace(一)原理简介

参考：http://lwn.net/Articles/322666/

           http://blog.csdn.net/lcw_202/article/details/7290775

         http://m.blog.chinaunix.net/uid-14528823-id-4567325.html

1、静态探测点，是在内核代码中调用ftrace提供的相应接口实现，称之为静态是因为，是在内核代码中写死的，静态编译到内核代码中的，在内核编译后，就不能再动态修改。在开启ftrace相关的内核配置选项后，内核中已经在一些关键的地方设置了静态探测点，需要使用时，即可查看到相应的信息。
2、动态探测点，基本原理为：利用mcount机制，在内核编译时，在每个函数入口保留数个字节，然后在使用ftrace时，将保留的字节替换为需要的指令，比如跳转到需要的执行探测操作的代码。

 

ftrace利用了gcc的profile特性，gcc 的 -pg 选项将在每个函数的入口处加入对mcount的代码调用。

 

如果ftrace编写了自己的mcount stub函数，则可借此实现trace功能。
但是，在每个内核函数入口加入trace代码，必然影响内核的性能，为了减小对内核性能的影响，ftrace支持动态trace功能。
当COFNIG_DYNAMIC_FTRACE被选中后，内核编译时会调用recordmcount.pl脚本，将每个函数的地址写入一个特殊的段：__mcount_loc
1、scripts/Makefile.build：

ifdef CONFIG_FTRACE_MCOUNT_RECORD
ifdef BUILD_C_RECORDMCOUNT
ifeq ("$(origin RECORDMCOUNT_WARN)", "command line")
  RECORDMCOUNT_FLAGS = -w
endif
# Due to recursion, we must skip empty.o.
# The empty.o file is created in the make process in order to determine
#  the target endianness and word size. It is made before all other C
#  files, including recordmcount.
sub_cmd_record_mcount =                 \
    if [ $(@) != "scripts/mod/empty.o" ]; then  \
        $(objtree)/scripts/recordmcount $(RECORDMCOUNT_FLAGS) "$(@)";   \
    fi;
recordmcount_source := $(srctree)/scripts/recordmcount.c \
            $(srctree)/scripts/recordmcount.h
else
sub_cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
    "$(if $(CONFIG_CPU_BIG_ENDIAN),big,little)" \
    "$(if $(CONFIG_64BIT),64,32)" \
    "$(OBJDUMP)" "$(OBJCOPY)" "$(CC) $(KBUILD_CFLAGS)" \
    "$(LD)" "$(NM)" "$(RM)" "$(MV)" \
    "$(if $(part-of-module),1,0)" "$(@)";
recordmcount_source := $(srctree)/scripts/recordmcount.pl
endif
cmd_record_mcount =                         \
    if [ "$(findstring -pg,$(_c_flags))" = "-pg" ]; then    \
        $(sub_cmd_record_mcount)            \
    fi;
endif

define rule_cc_o_c
    $(call echo-cmd,checksrc) $(cmd_checksrc)             \
    $(call echo-cmd,cc_o_c) $(cmd_cc_o_c);                \
    $(cmd_modversions)                        \
    $(call echo-cmd,record_mcount)                    \
    $(cmd_record_mcount)                          \
    scripts/basic/fixdep $(depfile) $@ '$(call make-cmd,cc_o_c)' >    \
                                                  $(dot-target).tmp;  \
    rm -f $(depfile);                         \
    mv -f $(dot-target).tmp $(dot-target).cmd
endef

# Built-in and composite module parts
$(obj)/%.o: $(src)/%.c $(recordmcount_source) FORCE
    $(call cmd,force_checksrc)
    $(call if_changed_rule,cc_o_c)

2、include/asm-generic/vmlinux.lds.h

#ifdef CONFIG_FTRACE_MCOUNT_RECORD
#define MCOUNT_REC()    . = ALIGN(8);  \
    VMLINUX_SYMBOL(__start_mcount_loc) = .; \        
    *(__mcount_loc)             \       
    VMLINUX_SYMBOL(__stop_mcount_loc) = .;
#else
#define MCOUNT_REC()
#endif

 

ftrace_init初始化：

start_kernel
|-->ftrace_init();
|-->rest_init();

 

在function_trace_call函数内，ftrace记录函数调用堆栈信息，并将结果写入ring buffer。用户可以通过debugfs的trace文件读取该ring buffer中的内容。

function_trace_call
|-->trace_function(tr, ip, parent_ip, flags, pc);
    |-->struct ftrace_event_call *call = &event_function;
    |   struct ring_buffer *buffer = tr->trace_buffer.buffer;
    |   struct ring_buffer_event *event;
    |   struct ftrace_entry *entry;
    |-->event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry), flags, pc);
    |           |-->struct task_struct *tsk = current;
    |           |   entry->preempt_count  = pc & 0xff;
    |           |   entry->pid  = (tsk) ? tsk->pid : 0;
    |-->entry   = ring_buffer_event_data(event);
    |-->entry->ip  = ip;   
    |-->entry->parent_ip  = parent_ip;

 

irqsoff tracer的实现
irqsoff tracer的实现依赖于IRQ-Flags。在中断关闭时，记录下当时的时间戳，此后，中断被打开时，再计算时间差，由此便可得到中断禁止时间。

#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
#define local_irq_enable() \
do { trace_hardirqs_on(); raw_local_irq_enable(); } while (0)