WSL2-Linux-Kernel/include/linux/ftrace.h

526 строки
14 KiB
C
Исходник Обычный вид История

#ifndef _LINUX_FTRACE_H
#define _LINUX_FTRACE_H
#include <linux/trace_clock.h>
#include <linux/kallsyms.h>
#include <linux/linkage.h>
ftrace: graph of a single function This patch adds the file: /debugfs/tracing/set_graph_function which can be used along with the function graph tracer. When this file is empty, the function graph tracer will act as usual. When the file has a function in it, the function graph tracer will only trace that function. For example: # echo blk_unplug > /debugfs/tracing/set_graph_function # cat /debugfs/tracing/trace [...] ------------------------------------------ | 2) make-19003 => kjournald-2219 ------------------------------------------ 2) | blk_unplug() { 2) | dm_unplug_all() { 2) | dm_get_table() { 2) 1.381 us | _read_lock(); 2) 0.911 us | dm_table_get(); 2) 1. 76 us | _read_unlock(); 2) + 12.912 us | } 2) | dm_table_unplug_all() { 2) | blk_unplug() { 2) 0.778 us | generic_unplug_device(); 2) 2.409 us | } 2) 5.992 us | } 2) 0.813 us | dm_table_put(); 2) + 29. 90 us | } 2) + 34.532 us | } You can add up to 32 functions into this file. Currently we limit it to 32, but this may change with later improvements. To add another function, use the append '>>': # echo sys_read >> /debugfs/tracing/set_graph_function # cat /debugfs/tracing/set_graph_function blk_unplug sys_read Using the '>' will clear out the function and write anew: # echo sys_write > /debug/tracing/set_graph_function # cat /debug/tracing/set_graph_function sys_write Note, if you have function graph running while doing this, the small time between clearing it and updating it will cause the graph to record all functions. This should not be an issue because after it sets the filter, only those functions will be recorded from then on. If you need to only record a particular function then set this file first before starting the function graph tracer. In the future this side effect may be corrected. The set_graph_function file is similar to the set_ftrace_filter but it does not take wild cards nor does it allow for more than one function to be set with a single write. There is no technical reason why this is the case, I just do not have the time yet to implement that. Note, dynamic ftrace must be enabled for this to appear because it uses the dynamic ftrace records to match the name to the mcount call sites. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-03 23:36:57 +03:00
#include <linux/bitops.h>
#include <linux/module.h>
#include <linux/ktime.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <asm/ftrace.h>
#ifdef CONFIG_FUNCTION_TRACER
extern int ftrace_enabled;
extern int
ftrace_enable_sysctl(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip);
struct ftrace_ops {
ftrace_func_t func;
struct ftrace_ops *next;
};
extern int function_trace_stop;
tracing/function-return-tracer: support for dynamic ftrace on function return tracer This patch adds the support for dynamic tracing on the function return tracer. The whole difference with normal dynamic function tracing is that we don't need to hook on a particular callback. The only pro that we want is to nop or set dynamically the calls to ftrace_caller (which is ftrace_return_caller here). Some security checks ensure that we are not trying to launch dynamic tracing for return tracing while normal function tracing is already running. An example of trace with getnstimeofday set as a filter: ktime_get_ts+0x22/0x50 -> getnstimeofday (2283 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1396 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1825 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1426 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1524 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1434 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1502 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1404 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1397 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1051 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1314 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1344 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1163 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1390 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1374 ns) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-16 08:02:06 +03:00
/*
* 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.
*
* A quick way to stop the function tracer. Note this an on off switch,
* it is not something that is recursive like preempt_disable.
* This does not disable the calling of mcount, it only stops the
* calling of functions from mcount.
*/
static inline void ftrace_stop(void)
{
function_trace_stop = 1;
}
/**
* ftrace_start - start the function tracer.
*
* This function is the inverse of ftrace_stop. This does not enable
* the function tracing if the function tracer is disabled. This only
* sets the function tracer flag to continue calling the functions
* from mcount.
*/
static inline void ftrace_start(void)
{
function_trace_stop = 0;
}
/*
* The ftrace_ops must be a static and should also
* be read_mostly. These functions do modify read_mostly variables
* so use them sparely. Never free an ftrace_op or modify the
* next pointer after it has been registered. Even after unregistering
* it, the next pointer may still be used internally.
*/
int register_ftrace_function(struct ftrace_ops *ops);
int unregister_ftrace_function(struct ftrace_ops *ops);
void clear_ftrace_function(void);
extern void ftrace_stub(unsigned long a0, unsigned long a1);
#else /* !CONFIG_FUNCTION_TRACER */
# define register_ftrace_function(ops) do { } while (0)
# define unregister_ftrace_function(ops) do { } while (0)
# define clear_ftrace_function(ops) do { } while (0)
static inline void ftrace_kill(void) { }
static inline void ftrace_stop(void) { }
static inline void ftrace_start(void) { }
#endif /* CONFIG_FUNCTION_TRACER */
ftrace: tracer for scheduler wakeup latency This patch adds the tracer that tracks the wakeup latency of the highest priority waking task. "wakeup" is added to /debugfs/tracing/available_tracers Also added to /debugfs/tracing tracing_max_latency holds the current max latency for the wakeup wakeup_thresh if set to other than zero, a log will be recorded for every wakeup that takes longer than the number entered in here (usecs for all counters) (deletes previous trace) Examples: (with ftrace_enabled = 0) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 26 us, #2/2, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/0-3 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / quilt-8551 0d..3 0us+: wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) quilt-8551 0d..4 26us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ (with ftrace_enabled = 1) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 -------------------------------------------------------------------- latency: 36 us, #45/45, CPU#0 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/1-5 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / bash-10653 1d..3 0us : wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) bash-10653 1d..3 1us : try_to_wake_up+0x271/0x2e7 <ffffffff80233dcf> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..2 2us : try_to_wake_up+0x296/0x2e7 <ffffffff80233df4> (update_rq_clock+0x9/0x20 <ffffffff802303f3>) bash-10653 1d..2 2us : update_rq_clock+0x1e/0x20 <ffffffff80230408> (__update_rq_clock+0xc/0x90 <ffffffff80230366>) bash-10653 1d..2 3us : __update_rq_clock+0x1b/0x90 <ffffffff80230375> (sched_clock+0x9/0x29 <ffffffff80214529>) bash-10653 1d..2 4us : try_to_wake_up+0x2a6/0x2e7 <ffffffff80233e04> (activate_task+0xc/0x3f <ffffffff8022ffca>) bash-10653 1d..2 4us : activate_task+0x2d/0x3f <ffffffff8022ffeb> (enqueue_task+0xe/0x66 <ffffffff8022ff66>) bash-10653 1d..2 5us : enqueue_task+0x5b/0x66 <ffffffff8022ffb3> (enqueue_task_rt+0x9/0x3c <ffffffff80233351>) bash-10653 1d..2 6us : try_to_wake_up+0x2ba/0x2e7 <ffffffff80233e18> (check_preempt_wakeup+0x12/0x99 <ffffffff80234f84>) [...] bash-10653 1d..5 33us : tracing_record_cmdline+0xcf/0xd4 <ffffffff80338aad> (_spin_unlock+0x9/0x33 <ffffffff8048d3ec>) bash-10653 1d..5 34us : _spin_unlock+0x19/0x33 <ffffffff8048d3fc> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..4 35us : wakeup_sched_switch+0x65/0x2ff <ffffffff80339f66> (_spin_lock_irqsave+0xc/0xa9 <ffffffff8048d08b>) bash-10653 1d..4 35us : _spin_lock_irqsave+0x19/0xa9 <ffffffff8048d098> (add_preempt_count+0xe/0x77 <ffffffff8023311a>) bash-10653 1d..4 36us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ The [...] was added here to not waste your email box space. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 23:20:42 +04:00
#ifdef CONFIG_STACK_TRACER
extern int stack_tracer_enabled;
int
stack_trace_sysctl(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
#endif
struct ftrace_func_command {
struct list_head list;
char *name;
int (*func)(char *func, char *cmd,
char *params, int enable);
};
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 23:20:42 +04:00
#ifdef CONFIG_DYNAMIC_FTRACE
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 03:21:19 +03:00
int ftrace_arch_code_modify_prepare(void);
int ftrace_arch_code_modify_post_process(void);
struct seq_file;
struct ftrace_probe_ops {
ftrace: trace different functions with a different tracer Impact: new feature Currently, the function tracer only gives you an ability to hook a tracer to all functions being traced. The dynamic function trace allows you to pick and choose which of those functions will be traced, but all functions being traced will call all tracers that registered with the function tracer. This patch adds a new feature that allows a tracer to hook to specific functions, even when all functions are being traced. It allows for different functions to call different tracer hooks. The way this is accomplished is by a special function that will hook to the function tracer and will set up a hash table knowing which tracer hook to call with which function. This is the most general and easiest method to accomplish this. Later, an arch may choose to supply their own method in changing the mcount call of a function to call a different tracer. But that will be an exercise for the future. To register a function: struct ftrace_hook_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); int (*callback)(unsigned long ip, void **data); void (*free)(void **data); }; int register_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data); glob is a simple glob to search for the functions to hook. ops is a pointer to the operations (listed below) data is the default data to be passed to the hook functions when traced ops: func is the hook function to call when the functions are traced callback is a callback function that is called when setting up the hash. That is, if the tracer needs to do something special for each function, that is being traced, and wants to give each function its own data. The address of the entry data is passed to this callback, so that the callback may wish to update the entry to whatever it would like. free is a callback for when the entry is freed. In case the tracer allocated any data, it is give the chance to free it. To unregister we have three functions: void unregister_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data) This will unregister all hooks that match glob, point to ops, and have its data matching data. (note, if glob is NULL, blank or '*', all functions will be tested). void unregister_ftrace_function_hook_func(char *glob, struct ftrace_hook_ops *ops) This will unregister all functions matching glob that has an entry pointing to ops. void unregister_ftrace_function_hook_all(char *glob) This simply unregisters all funcs. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-14 23:29:06 +03:00
void (*func)(unsigned long ip,
unsigned long parent_ip,
void **data);
int (*callback)(unsigned long ip, void **data);
void (*free)(void **data);
int (*print)(struct seq_file *m,
unsigned long ip,
struct ftrace_probe_ops *ops,
void *data);
ftrace: trace different functions with a different tracer Impact: new feature Currently, the function tracer only gives you an ability to hook a tracer to all functions being traced. The dynamic function trace allows you to pick and choose which of those functions will be traced, but all functions being traced will call all tracers that registered with the function tracer. This patch adds a new feature that allows a tracer to hook to specific functions, even when all functions are being traced. It allows for different functions to call different tracer hooks. The way this is accomplished is by a special function that will hook to the function tracer and will set up a hash table knowing which tracer hook to call with which function. This is the most general and easiest method to accomplish this. Later, an arch may choose to supply their own method in changing the mcount call of a function to call a different tracer. But that will be an exercise for the future. To register a function: struct ftrace_hook_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); int (*callback)(unsigned long ip, void **data); void (*free)(void **data); }; int register_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data); glob is a simple glob to search for the functions to hook. ops is a pointer to the operations (listed below) data is the default data to be passed to the hook functions when traced ops: func is the hook function to call when the functions are traced callback is a callback function that is called when setting up the hash. That is, if the tracer needs to do something special for each function, that is being traced, and wants to give each function its own data. The address of the entry data is passed to this callback, so that the callback may wish to update the entry to whatever it would like. free is a callback for when the entry is freed. In case the tracer allocated any data, it is give the chance to free it. To unregister we have three functions: void unregister_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data) This will unregister all hooks that match glob, point to ops, and have its data matching data. (note, if glob is NULL, blank or '*', all functions will be tested). void unregister_ftrace_function_hook_func(char *glob, struct ftrace_hook_ops *ops) This will unregister all functions matching glob that has an entry pointing to ops. void unregister_ftrace_function_hook_all(char *glob) This simply unregisters all funcs. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-14 23:29:06 +03:00
};
extern int
register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
ftrace: trace different functions with a different tracer Impact: new feature Currently, the function tracer only gives you an ability to hook a tracer to all functions being traced. The dynamic function trace allows you to pick and choose which of those functions will be traced, but all functions being traced will call all tracers that registered with the function tracer. This patch adds a new feature that allows a tracer to hook to specific functions, even when all functions are being traced. It allows for different functions to call different tracer hooks. The way this is accomplished is by a special function that will hook to the function tracer and will set up a hash table knowing which tracer hook to call with which function. This is the most general and easiest method to accomplish this. Later, an arch may choose to supply their own method in changing the mcount call of a function to call a different tracer. But that will be an exercise for the future. To register a function: struct ftrace_hook_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); int (*callback)(unsigned long ip, void **data); void (*free)(void **data); }; int register_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data); glob is a simple glob to search for the functions to hook. ops is a pointer to the operations (listed below) data is the default data to be passed to the hook functions when traced ops: func is the hook function to call when the functions are traced callback is a callback function that is called when setting up the hash. That is, if the tracer needs to do something special for each function, that is being traced, and wants to give each function its own data. The address of the entry data is passed to this callback, so that the callback may wish to update the entry to whatever it would like. free is a callback for when the entry is freed. In case the tracer allocated any data, it is give the chance to free it. To unregister we have three functions: void unregister_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data) This will unregister all hooks that match glob, point to ops, and have its data matching data. (note, if glob is NULL, blank or '*', all functions will be tested). void unregister_ftrace_function_hook_func(char *glob, struct ftrace_hook_ops *ops) This will unregister all functions matching glob that has an entry pointing to ops. void unregister_ftrace_function_hook_all(char *glob) This simply unregisters all funcs. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-14 23:29:06 +03:00
void *data);
extern void
unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
ftrace: trace different functions with a different tracer Impact: new feature Currently, the function tracer only gives you an ability to hook a tracer to all functions being traced. The dynamic function trace allows you to pick and choose which of those functions will be traced, but all functions being traced will call all tracers that registered with the function tracer. This patch adds a new feature that allows a tracer to hook to specific functions, even when all functions are being traced. It allows for different functions to call different tracer hooks. The way this is accomplished is by a special function that will hook to the function tracer and will set up a hash table knowing which tracer hook to call with which function. This is the most general and easiest method to accomplish this. Later, an arch may choose to supply their own method in changing the mcount call of a function to call a different tracer. But that will be an exercise for the future. To register a function: struct ftrace_hook_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); int (*callback)(unsigned long ip, void **data); void (*free)(void **data); }; int register_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data); glob is a simple glob to search for the functions to hook. ops is a pointer to the operations (listed below) data is the default data to be passed to the hook functions when traced ops: func is the hook function to call when the functions are traced callback is a callback function that is called when setting up the hash. That is, if the tracer needs to do something special for each function, that is being traced, and wants to give each function its own data. The address of the entry data is passed to this callback, so that the callback may wish to update the entry to whatever it would like. free is a callback for when the entry is freed. In case the tracer allocated any data, it is give the chance to free it. To unregister we have three functions: void unregister_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data) This will unregister all hooks that match glob, point to ops, and have its data matching data. (note, if glob is NULL, blank or '*', all functions will be tested). void unregister_ftrace_function_hook_func(char *glob, struct ftrace_hook_ops *ops) This will unregister all functions matching glob that has an entry pointing to ops. void unregister_ftrace_function_hook_all(char *glob) This simply unregisters all funcs. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-14 23:29:06 +03:00
void *data);
extern void
unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops);
extern void unregister_ftrace_function_probe_all(char *glob);
ftrace: trace different functions with a different tracer Impact: new feature Currently, the function tracer only gives you an ability to hook a tracer to all functions being traced. The dynamic function trace allows you to pick and choose which of those functions will be traced, but all functions being traced will call all tracers that registered with the function tracer. This patch adds a new feature that allows a tracer to hook to specific functions, even when all functions are being traced. It allows for different functions to call different tracer hooks. The way this is accomplished is by a special function that will hook to the function tracer and will set up a hash table knowing which tracer hook to call with which function. This is the most general and easiest method to accomplish this. Later, an arch may choose to supply their own method in changing the mcount call of a function to call a different tracer. But that will be an exercise for the future. To register a function: struct ftrace_hook_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); int (*callback)(unsigned long ip, void **data); void (*free)(void **data); }; int register_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data); glob is a simple glob to search for the functions to hook. ops is a pointer to the operations (listed below) data is the default data to be passed to the hook functions when traced ops: func is the hook function to call when the functions are traced callback is a callback function that is called when setting up the hash. That is, if the tracer needs to do something special for each function, that is being traced, and wants to give each function its own data. The address of the entry data is passed to this callback, so that the callback may wish to update the entry to whatever it would like. free is a callback for when the entry is freed. In case the tracer allocated any data, it is give the chance to free it. To unregister we have three functions: void unregister_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data) This will unregister all hooks that match glob, point to ops, and have its data matching data. (note, if glob is NULL, blank or '*', all functions will be tested). void unregister_ftrace_function_hook_func(char *glob, struct ftrace_hook_ops *ops) This will unregister all functions matching glob that has an entry pointing to ops. void unregister_ftrace_function_hook_all(char *glob) This simply unregisters all funcs. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-14 23:29:06 +03:00
extern int ftrace_text_reserved(void *start, void *end);
enum {
FTRACE_FL_FREE = (1 << 0),
FTRACE_FL_FAILED = (1 << 1),
FTRACE_FL_FILTER = (1 << 2),
FTRACE_FL_ENABLED = (1 << 3),
FTRACE_FL_NOTRACE = (1 << 4),
FTRACE_FL_CONVERTED = (1 << 5),
};
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 23:20:42 +04:00
struct dyn_ftrace {
union {
unsigned long ip; /* address of mcount call-site */
struct dyn_ftrace *freelist;
};
union {
unsigned long flags;
struct dyn_ftrace *newlist;
};
struct dyn_arch_ftrace arch;
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 23:20:42 +04:00
};
int ftrace_force_update(void);
void ftrace_set_filter(unsigned char *buf, int len, int reset);
int register_ftrace_command(struct ftrace_func_command *cmd);
int unregister_ftrace_command(struct ftrace_func_command *cmd);
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 23:20:42 +04:00
/* defined in arch */
extern int ftrace_ip_converted(unsigned long ip);
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);
#ifndef FTRACE_ADDR
#define FTRACE_ADDR ((unsigned long)ftrace_caller)
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
extern void ftrace_graph_caller(void);
extern int ftrace_enable_ftrace_graph_caller(void);
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; }
tracing/function-return-tracer: support for dynamic ftrace on function return tracer This patch adds the support for dynamic tracing on the function return tracer. The whole difference with normal dynamic function tracing is that we don't need to hook on a particular callback. The only pro that we want is to nop or set dynamically the calls to ftrace_caller (which is ftrace_return_caller here). Some security checks ensure that we are not trying to launch dynamic tracing for return tracing while normal function tracing is already running. An example of trace with getnstimeofday set as a filter: ktime_get_ts+0x22/0x50 -> getnstimeofday (2283 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1396 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1825 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1426 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1524 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1434 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1502 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1404 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1397 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1051 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1314 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1344 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1163 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1390 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1374 ns) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-16 08:02:06 +03:00
#endif
ftrace: user update and disable dynamic ftrace daemon In dynamic ftrace, the mcount function starts off pointing to a stub function that just returns. On start up, the call to the stub is modified to point to a "record_ip" function. The job of the record_ip function is to add the function to a pre-allocated hash list. If the function is already there, it simply is ignored, otherwise it is added to the list. Later, a ftraced daemon wakes up and calls kstop_machine if any functions have been recorded, and changes the calls to the recorded functions to a simple nop. If no functions were recorded, the daemon goes back to sleep. The daemon wakes up once a second to see if it needs to update any newly recorded functions into nops. Usually it does not, but if a lot of code has been executed for the first time in the kernel, the ftraced daemon will call kstop_machine to update those into nops. The problem currently is that there's no way to stop the daemon from doing this, and it can cause unneeded latencies (800us which for some is bothersome). This patch adds a new file /debugfs/tracing/ftraced_enabled. If the daemon is active, reading this will return "enabled\n" and "disabled\n" when the daemon is not running. To disable the daemon, the user can echo "0" or "disable" into this file, and "1" or "enable" to re-enable the daemon. Since the daemon is used to convert the functions into nops to increase the performance of the system, I also added that anytime something is written into the ftraced_enabled file, kstop_machine will run if there are new functions that have been detected that need to be converted. This way the user can disable the daemon but still be able to control the conversion of the mcount calls to nops by simply, "echo 0 > /debugfs/tracing/ftraced_enabled" when they need to do more conversions. To see the number of converted functions: "cat /debugfs/tracing/dyn_ftrace_total_info" Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-28 04:48:37 +04:00
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 03:21:19 +03:00
/**
* ftrace_make_nop - convert code into nop
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 03:21:19 +03:00
* @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: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 03:21:19 +03:00
* 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
* 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.
*
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 03:21:19 +03:00
* The code segment at @rec->ip should be a nop
*
* 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.
*/
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 03:21:19 +03:00
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);
extern void ftrace_disable_daemon(void);
extern void ftrace_enable_daemon(void);
#else
# define skip_trace(ip) ({ 0; })
# define ftrace_force_update() ({ 0; })
# define ftrace_set_filter(buf, len, reset) do { } while (0)
ftrace: user update and disable dynamic ftrace daemon In dynamic ftrace, the mcount function starts off pointing to a stub function that just returns. On start up, the call to the stub is modified to point to a "record_ip" function. The job of the record_ip function is to add the function to a pre-allocated hash list. If the function is already there, it simply is ignored, otherwise it is added to the list. Later, a ftraced daemon wakes up and calls kstop_machine if any functions have been recorded, and changes the calls to the recorded functions to a simple nop. If no functions were recorded, the daemon goes back to sleep. The daemon wakes up once a second to see if it needs to update any newly recorded functions into nops. Usually it does not, but if a lot of code has been executed for the first time in the kernel, the ftraced daemon will call kstop_machine to update those into nops. The problem currently is that there's no way to stop the daemon from doing this, and it can cause unneeded latencies (800us which for some is bothersome). This patch adds a new file /debugfs/tracing/ftraced_enabled. If the daemon is active, reading this will return "enabled\n" and "disabled\n" when the daemon is not running. To disable the daemon, the user can echo "0" or "disable" into this file, and "1" or "enable" to re-enable the daemon. Since the daemon is used to convert the functions into nops to increase the performance of the system, I also added that anytime something is written into the ftraced_enabled file, kstop_machine will run if there are new functions that have been detected that need to be converted. This way the user can disable the daemon but still be able to control the conversion of the mcount calls to nops by simply, "echo 0 > /debugfs/tracing/ftraced_enabled" when they need to do more conversions. To see the number of converted functions: "cat /debugfs/tracing/dyn_ftrace_total_info" Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-28 04:48:37 +04:00
# define ftrace_disable_daemon() do { } while (0)
# define ftrace_enable_daemon() do { } while (0)
static inline void ftrace_release_mod(struct module *mod) {}
static inline int register_ftrace_command(struct ftrace_func_command *cmd)
{
return -EINVAL;
}
static inline int unregister_ftrace_command(char *cmd_name)
{
return -EINVAL;
}
static inline int ftrace_text_reserved(void *start, void *end)
{
return 0;
}
#endif /* CONFIG_DYNAMIC_FTRACE */
ftrace: tracer for scheduler wakeup latency This patch adds the tracer that tracks the wakeup latency of the highest priority waking task. "wakeup" is added to /debugfs/tracing/available_tracers Also added to /debugfs/tracing tracing_max_latency holds the current max latency for the wakeup wakeup_thresh if set to other than zero, a log will be recorded for every wakeup that takes longer than the number entered in here (usecs for all counters) (deletes previous trace) Examples: (with ftrace_enabled = 0) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 26 us, #2/2, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/0-3 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / quilt-8551 0d..3 0us+: wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) quilt-8551 0d..4 26us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ (with ftrace_enabled = 1) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 -------------------------------------------------------------------- latency: 36 us, #45/45, CPU#0 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/1-5 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / bash-10653 1d..3 0us : wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) bash-10653 1d..3 1us : try_to_wake_up+0x271/0x2e7 <ffffffff80233dcf> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..2 2us : try_to_wake_up+0x296/0x2e7 <ffffffff80233df4> (update_rq_clock+0x9/0x20 <ffffffff802303f3>) bash-10653 1d..2 2us : update_rq_clock+0x1e/0x20 <ffffffff80230408> (__update_rq_clock+0xc/0x90 <ffffffff80230366>) bash-10653 1d..2 3us : __update_rq_clock+0x1b/0x90 <ffffffff80230375> (sched_clock+0x9/0x29 <ffffffff80214529>) bash-10653 1d..2 4us : try_to_wake_up+0x2a6/0x2e7 <ffffffff80233e04> (activate_task+0xc/0x3f <ffffffff8022ffca>) bash-10653 1d..2 4us : activate_task+0x2d/0x3f <ffffffff8022ffeb> (enqueue_task+0xe/0x66 <ffffffff8022ff66>) bash-10653 1d..2 5us : enqueue_task+0x5b/0x66 <ffffffff8022ffb3> (enqueue_task_rt+0x9/0x3c <ffffffff80233351>) bash-10653 1d..2 6us : try_to_wake_up+0x2ba/0x2e7 <ffffffff80233e18> (check_preempt_wakeup+0x12/0x99 <ffffffff80234f84>) [...] bash-10653 1d..5 33us : tracing_record_cmdline+0xcf/0xd4 <ffffffff80338aad> (_spin_unlock+0x9/0x33 <ffffffff8048d3ec>) bash-10653 1d..5 34us : _spin_unlock+0x19/0x33 <ffffffff8048d3fc> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..4 35us : wakeup_sched_switch+0x65/0x2ff <ffffffff80339f66> (_spin_lock_irqsave+0xc/0xa9 <ffffffff8048d08b>) bash-10653 1d..4 35us : _spin_lock_irqsave+0x19/0xa9 <ffffffff8048d098> (add_preempt_count+0xe/0x77 <ffffffff8023311a>) bash-10653 1d..4 36us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ The [...] was added here to not waste your email box space. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 23:20:42 +04:00
/* totally disable ftrace - can not re-enable after this */
void ftrace_kill(void);
static inline void tracer_disable(void)
{
#ifdef CONFIG_FUNCTION_TRACER
ftrace_enabled = 0;
#endif
}
/*
* Ftrace disable/restore without lock. Some synchronization mechanism
* must be used to prevent ftrace_enabled to be changed between
* disable/restore.
*/
static inline int __ftrace_enabled_save(void)
{
#ifdef CONFIG_FUNCTION_TRACER
int saved_ftrace_enabled = ftrace_enabled;
ftrace_enabled = 0;
return saved_ftrace_enabled;
#else
return 0;
#endif
}
static inline void __ftrace_enabled_restore(int enabled)
{
#ifdef CONFIG_FUNCTION_TRACER
ftrace_enabled = enabled;
#endif
}
#ifndef HAVE_ARCH_CALLER_ADDR
# ifdef CONFIG_FRAME_POINTER
# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
# define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
# define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2))
# define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3))
# define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4))
# define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5))
# define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6))
# else
# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
# define CALLER_ADDR1 0UL
# define CALLER_ADDR2 0UL
# define CALLER_ADDR3 0UL
# define CALLER_ADDR4 0UL
# define CALLER_ADDR5 0UL
# define CALLER_ADDR6 0UL
# endif
#endif /* ifndef HAVE_ARCH_CALLER_ADDR */
ftrace: tracer for scheduler wakeup latency This patch adds the tracer that tracks the wakeup latency of the highest priority waking task. "wakeup" is added to /debugfs/tracing/available_tracers Also added to /debugfs/tracing tracing_max_latency holds the current max latency for the wakeup wakeup_thresh if set to other than zero, a log will be recorded for every wakeup that takes longer than the number entered in here (usecs for all counters) (deletes previous trace) Examples: (with ftrace_enabled = 0) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 26 us, #2/2, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/0-3 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / quilt-8551 0d..3 0us+: wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) quilt-8551 0d..4 26us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ (with ftrace_enabled = 1) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 -------------------------------------------------------------------- latency: 36 us, #45/45, CPU#0 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/1-5 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / bash-10653 1d..3 0us : wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) bash-10653 1d..3 1us : try_to_wake_up+0x271/0x2e7 <ffffffff80233dcf> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..2 2us : try_to_wake_up+0x296/0x2e7 <ffffffff80233df4> (update_rq_clock+0x9/0x20 <ffffffff802303f3>) bash-10653 1d..2 2us : update_rq_clock+0x1e/0x20 <ffffffff80230408> (__update_rq_clock+0xc/0x90 <ffffffff80230366>) bash-10653 1d..2 3us : __update_rq_clock+0x1b/0x90 <ffffffff80230375> (sched_clock+0x9/0x29 <ffffffff80214529>) bash-10653 1d..2 4us : try_to_wake_up+0x2a6/0x2e7 <ffffffff80233e04> (activate_task+0xc/0x3f <ffffffff8022ffca>) bash-10653 1d..2 4us : activate_task+0x2d/0x3f <ffffffff8022ffeb> (enqueue_task+0xe/0x66 <ffffffff8022ff66>) bash-10653 1d..2 5us : enqueue_task+0x5b/0x66 <ffffffff8022ffb3> (enqueue_task_rt+0x9/0x3c <ffffffff80233351>) bash-10653 1d..2 6us : try_to_wake_up+0x2ba/0x2e7 <ffffffff80233e18> (check_preempt_wakeup+0x12/0x99 <ffffffff80234f84>) [...] bash-10653 1d..5 33us : tracing_record_cmdline+0xcf/0xd4 <ffffffff80338aad> (_spin_unlock+0x9/0x33 <ffffffff8048d3ec>) bash-10653 1d..5 34us : _spin_unlock+0x19/0x33 <ffffffff8048d3fc> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..4 35us : wakeup_sched_switch+0x65/0x2ff <ffffffff80339f66> (_spin_lock_irqsave+0xc/0xa9 <ffffffff8048d08b>) bash-10653 1d..4 35us : _spin_lock_irqsave+0x19/0xa9 <ffffffff8048d098> (add_preempt_count+0xe/0x77 <ffffffff8023311a>) bash-10653 1d..4 36us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ The [...] was added here to not waste your email box space. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 23:20:42 +04:00
ftrace: trace irq disabled critical timings This patch adds latency tracing for critical timings (how long interrupts are disabled for). "irqsoff" is added to /debugfs/tracing/available_tracers Note: tracing_max_latency also holds the max latency for irqsoff (in usecs). (default to large number so one must start latency tracing) tracing_thresh threshold (in usecs) to always print out if irqs off is detected to be longer than stated here. If irq_thresh is non-zero, then max_irq_latency is ignored. Here's an example of a trace with ftrace_enabled = 0 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 100 us, #3/3, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1d.s3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1d.s3 100us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1d.s3 100us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= And this is a trace with ftrace_enabled == 1 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 -------------------------------------------------------------------- latency: 102 us, #12/12, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1dNs3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_read_phy_reg+0x16/0x225 [e1000] (e1000_update_stats+0x5e2/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_swfw_sync_acquire+0x10/0x99 [e1000] (e1000_read_phy_reg+0x49/0x225 [e1000]) swapper-0 1dNs3 46us : e1000_get_hw_eeprom_semaphore+0x12/0xa6 [e1000] (e1000_swfw_sync_acquire+0x36/0x99 [e1000]) swapper-0 1dNs3 47us : __const_udelay+0x9/0x47 (e1000_read_phy_reg+0x116/0x225 [e1000]) swapper-0 1dNs3 47us+: __delay+0x9/0x50 (__const_udelay+0x45/0x47) swapper-0 1dNs3 97us : preempt_schedule+0xc/0x84 (__delay+0x4e/0x50) swapper-0 1dNs3 98us : e1000_swfw_sync_release+0xc/0x55 [e1000] (e1000_read_phy_reg+0x211/0x225 [e1000]) swapper-0 1dNs3 99us+: e1000_put_hw_eeprom_semaphore+0x9/0x35 [e1000] (e1000_swfw_sync_release+0x50/0x55 [e1000]) swapper-0 1dNs3 101us : _spin_unlock_irqrestore+0xe/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 23:20:42 +04:00
#ifdef CONFIG_IRQSOFF_TRACER
extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
extern void time_hardirqs_off(unsigned long a0, unsigned long a1);
ftrace: trace irq disabled critical timings This patch adds latency tracing for critical timings (how long interrupts are disabled for). "irqsoff" is added to /debugfs/tracing/available_tracers Note: tracing_max_latency also holds the max latency for irqsoff (in usecs). (default to large number so one must start latency tracing) tracing_thresh threshold (in usecs) to always print out if irqs off is detected to be longer than stated here. If irq_thresh is non-zero, then max_irq_latency is ignored. Here's an example of a trace with ftrace_enabled = 0 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 100 us, #3/3, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1d.s3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1d.s3 100us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1d.s3 100us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= And this is a trace with ftrace_enabled == 1 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 -------------------------------------------------------------------- latency: 102 us, #12/12, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1dNs3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_read_phy_reg+0x16/0x225 [e1000] (e1000_update_stats+0x5e2/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_swfw_sync_acquire+0x10/0x99 [e1000] (e1000_read_phy_reg+0x49/0x225 [e1000]) swapper-0 1dNs3 46us : e1000_get_hw_eeprom_semaphore+0x12/0xa6 [e1000] (e1000_swfw_sync_acquire+0x36/0x99 [e1000]) swapper-0 1dNs3 47us : __const_udelay+0x9/0x47 (e1000_read_phy_reg+0x116/0x225 [e1000]) swapper-0 1dNs3 47us+: __delay+0x9/0x50 (__const_udelay+0x45/0x47) swapper-0 1dNs3 97us : preempt_schedule+0xc/0x84 (__delay+0x4e/0x50) swapper-0 1dNs3 98us : e1000_swfw_sync_release+0xc/0x55 [e1000] (e1000_read_phy_reg+0x211/0x225 [e1000]) swapper-0 1dNs3 99us+: e1000_put_hw_eeprom_semaphore+0x9/0x35 [e1000] (e1000_swfw_sync_release+0x50/0x55 [e1000]) swapper-0 1dNs3 101us : _spin_unlock_irqrestore+0xe/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 23:20:42 +04:00
#else
# define time_hardirqs_on(a0, a1) do { } while (0)
# define time_hardirqs_off(a0, a1) do { } while (0)
#endif
#ifdef CONFIG_PREEMPT_TRACER
extern void trace_preempt_on(unsigned long a0, unsigned long a1);
extern void trace_preempt_off(unsigned long a0, unsigned long a1);
#else
# define trace_preempt_on(a0, a1) do { } while (0)
# define trace_preempt_off(a0, a1) do { } while (0)
#endif
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
extern void ftrace_init(void);
#else
static inline void ftrace_init(void) { }
#endif
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 02:57:25 +03:00
/*
* 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_graph_ret {
unsigned long func; /* Current function */
unsigned long long calltime;
unsigned long long rettime;
tracing/function-return-tracer: add the overrun field Impact: help to find the better depth of trace We decided to arbitrary define the depth of function return trace as "20". Perhaps this is not enough. To help finding an optimal depth, we measure now the overrun: the number of functions that have been missed for the current thread. By default this is not displayed, we have to do set a particular flag on the return tracer: echo overrun > /debug/tracing/trace_options And the overrun will be printed on the right. As the trace shows below, the current 20 depth is not enough. update_wall_time+0x37f/0x8c0 -> update_xtime_cache (345 ns) (Overruns: 2838) update_wall_time+0x384/0x8c0 -> clocksource_get_next (1141 ns) (Overruns: 2838) do_timer+0x23/0x100 -> update_wall_time (3882 ns) (Overruns: 2838) tick_do_update_jiffies64+0xbf/0x160 -> do_timer (5339 ns) (Overruns: 2838) tick_sched_timer+0x6a/0xf0 -> tick_do_update_jiffies64 (7209 ns) (Overruns: 2838) vgacon_set_cursor_size+0x98/0x120 -> native_io_delay (2613 ns) (Overruns: 274) vgacon_cursor+0x16e/0x1d0 -> vgacon_set_cursor_size (33151 ns) (Overruns: 274) set_cursor+0x5f/0x80 -> vgacon_cursor (36432 ns) (Overruns: 274) con_flush_chars+0x34/0x40 -> set_cursor (38790 ns) (Overruns: 274) release_console_sem+0x1ec/0x230 -> up (721 ns) (Overruns: 274) release_console_sem+0x225/0x230 -> wake_up_klogd (316 ns) (Overruns: 274) con_flush_chars+0x39/0x40 -> release_console_sem (2996 ns) (Overruns: 274) con_write+0x22/0x30 -> con_flush_chars (46067 ns) (Overruns: 274) n_tty_write+0x1cc/0x360 -> con_write (292670 ns) (Overruns: 274) smp_apic_timer_interrupt+0x2a/0x90 -> native_apic_mem_write (330 ns) (Overruns: 274) irq_enter+0x17/0x70 -> idle_cpu (413 ns) (Overruns: 274) smp_apic_timer_interrupt+0x2f/0x90 -> irq_enter (1525 ns) (Overruns: 274) ktime_get_ts+0x40/0x70 -> getnstimeofday (465 ns) (Overruns: 274) ktime_get_ts+0x60/0x70 -> set_normalized_timespec (436 ns) (Overruns: 274) ktime_get+0x16/0x30 -> ktime_get_ts (2501 ns) (Overruns: 274) hrtimer_interrupt+0x77/0x1a0 -> ktime_get (3439 ns) (Overruns: 274) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-17 05:22:41 +03:00
/* Number of functions that overran the depth limit for current task */
unsigned long overrun;
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 02:57:25 +03:00
int depth;
};
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/* for init task */
#define INIT_FTRACE_GRAPH .ret_stack = NULL,
/*
* Stack of return addresses for functions
* of a thread.
* Used in struct thread_info
*/
struct ftrace_ret_stack {
unsigned long ret;
unsigned long func;
unsigned long long calltime;
unsigned long long subtime;
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 20:45:08 +04:00
unsigned long fp;
};
/*
* Primary handler of a function return.
* It relays on ftrace_return_to_handler.
* Defined in entry_32/64.S
*/
extern void return_to_handler(void);
extern int
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 20:45:08 +04:00
ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
unsigned long frame_pointer);
/*
* Sometimes we don't want to trace a function with the function
* graph tracer but we want them to keep traced by the usual function
* tracer if the function graph tracer is not configured.
*/
#define __notrace_funcgraph notrace
/*
* We want to which function is an entrypoint of a hardirq.
* That will help us to put a signal on output.
*/
#define __irq_entry __attribute__((__section__(".irqentry.text")))
/* Limits of hardirq entrypoints */
extern char __irqentry_text_start[];
extern char __irqentry_text_end[];
#define FTRACE_RETFUNC_DEPTH 50
#define FTRACE_RETSTACK_ALLOC_SIZE 32
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 02:57:25 +03:00
/* Type of the callback handlers for tracing function graph*/
typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */
typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 02:57:25 +03:00
extern int register_ftrace_graph(trace_func_graph_ret_t retfunc,
trace_func_graph_ent_t entryfunc);
extern void ftrace_graph_stop(void);
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 02:57:25 +03:00
/* The current handlers in use */
extern trace_func_graph_ret_t ftrace_graph_return;
extern trace_func_graph_ent_t ftrace_graph_entry;
extern void unregister_ftrace_graph(void);
extern void ftrace_graph_init_task(struct task_struct *t);
extern void ftrace_graph_exit_task(struct task_struct *t);
static inline int task_curr_ret_stack(struct task_struct *t)
{
return t->curr_ret_stack;
}
static inline void pause_graph_tracing(void)
{
atomic_inc(&current->tracing_graph_pause);
}
static inline void unpause_graph_tracing(void)
{
atomic_dec(&current->tracing_graph_pause);
}
#else /* !CONFIG_FUNCTION_GRAPH_TRACER */
#define __notrace_funcgraph
#define __irq_entry
#define INIT_FTRACE_GRAPH
static inline void ftrace_graph_init_task(struct task_struct *t) { }
static inline void ftrace_graph_exit_task(struct task_struct *t) { }
static inline int task_curr_ret_stack(struct task_struct *tsk)
{
return -1;
}
static inline void pause_graph_tracing(void) { }
static inline void unpause_graph_tracing(void) { }
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
ftrace: graph of a single function This patch adds the file: /debugfs/tracing/set_graph_function which can be used along with the function graph tracer. When this file is empty, the function graph tracer will act as usual. When the file has a function in it, the function graph tracer will only trace that function. For example: # echo blk_unplug > /debugfs/tracing/set_graph_function # cat /debugfs/tracing/trace [...] ------------------------------------------ | 2) make-19003 => kjournald-2219 ------------------------------------------ 2) | blk_unplug() { 2) | dm_unplug_all() { 2) | dm_get_table() { 2) 1.381 us | _read_lock(); 2) 0.911 us | dm_table_get(); 2) 1. 76 us | _read_unlock(); 2) + 12.912 us | } 2) | dm_table_unplug_all() { 2) | blk_unplug() { 2) 0.778 us | generic_unplug_device(); 2) 2.409 us | } 2) 5.992 us | } 2) 0.813 us | dm_table_put(); 2) + 29. 90 us | } 2) + 34.532 us | } You can add up to 32 functions into this file. Currently we limit it to 32, but this may change with later improvements. To add another function, use the append '>>': # echo sys_read >> /debugfs/tracing/set_graph_function # cat /debugfs/tracing/set_graph_function blk_unplug sys_read Using the '>' will clear out the function and write anew: # echo sys_write > /debug/tracing/set_graph_function # cat /debug/tracing/set_graph_function sys_write Note, if you have function graph running while doing this, the small time between clearing it and updating it will cause the graph to record all functions. This should not be an issue because after it sets the filter, only those functions will be recorded from then on. If you need to only record a particular function then set this file first before starting the function graph tracer. In the future this side effect may be corrected. The set_graph_function file is similar to the set_ftrace_filter but it does not take wild cards nor does it allow for more than one function to be set with a single write. There is no technical reason why this is the case, I just do not have the time yet to implement that. Note, dynamic ftrace must be enabled for this to appear because it uses the dynamic ftrace records to match the name to the mcount call sites. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-03 23:36:57 +03:00
#ifdef CONFIG_TRACING
/* flags for current->trace */
enum {
TSK_TRACE_FL_TRACE_BIT = 0,
TSK_TRACE_FL_GRAPH_BIT = 1,
};
enum {
TSK_TRACE_FL_TRACE = 1 << TSK_TRACE_FL_TRACE_BIT,
TSK_TRACE_FL_GRAPH = 1 << TSK_TRACE_FL_GRAPH_BIT,
};
static inline void set_tsk_trace_trace(struct task_struct *tsk)
{
set_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace);
}
static inline void clear_tsk_trace_trace(struct task_struct *tsk)
{
clear_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace);
}
static inline int test_tsk_trace_trace(struct task_struct *tsk)
{
return tsk->trace & TSK_TRACE_FL_TRACE;
}
static inline void set_tsk_trace_graph(struct task_struct *tsk)
{
set_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace);
}
static inline void clear_tsk_trace_graph(struct task_struct *tsk)
{
clear_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace);
}
static inline int test_tsk_trace_graph(struct task_struct *tsk)
{
return tsk->trace & TSK_TRACE_FL_GRAPH;
}
extern int ftrace_dump_on_oops;
#ifdef CONFIG_PREEMPT
#define INIT_TRACE_RECURSION .trace_recursion = 0,
#endif
ftrace: graph of a single function This patch adds the file: /debugfs/tracing/set_graph_function which can be used along with the function graph tracer. When this file is empty, the function graph tracer will act as usual. When the file has a function in it, the function graph tracer will only trace that function. For example: # echo blk_unplug > /debugfs/tracing/set_graph_function # cat /debugfs/tracing/trace [...] ------------------------------------------ | 2) make-19003 => kjournald-2219 ------------------------------------------ 2) | blk_unplug() { 2) | dm_unplug_all() { 2) | dm_get_table() { 2) 1.381 us | _read_lock(); 2) 0.911 us | dm_table_get(); 2) 1. 76 us | _read_unlock(); 2) + 12.912 us | } 2) | dm_table_unplug_all() { 2) | blk_unplug() { 2) 0.778 us | generic_unplug_device(); 2) 2.409 us | } 2) 5.992 us | } 2) 0.813 us | dm_table_put(); 2) + 29. 90 us | } 2) + 34.532 us | } You can add up to 32 functions into this file. Currently we limit it to 32, but this may change with later improvements. To add another function, use the append '>>': # echo sys_read >> /debugfs/tracing/set_graph_function # cat /debugfs/tracing/set_graph_function blk_unplug sys_read Using the '>' will clear out the function and write anew: # echo sys_write > /debug/tracing/set_graph_function # cat /debug/tracing/set_graph_function sys_write Note, if you have function graph running while doing this, the small time between clearing it and updating it will cause the graph to record all functions. This should not be an issue because after it sets the filter, only those functions will be recorded from then on. If you need to only record a particular function then set this file first before starting the function graph tracer. In the future this side effect may be corrected. The set_graph_function file is similar to the set_ftrace_filter but it does not take wild cards nor does it allow for more than one function to be set with a single write. There is no technical reason why this is the case, I just do not have the time yet to implement that. Note, dynamic ftrace must be enabled for this to appear because it uses the dynamic ftrace records to match the name to the mcount call sites. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-03 23:36:57 +03:00
#endif /* CONFIG_TRACING */
#ifndef INIT_TRACE_RECURSION
#define INIT_TRACE_RECURSION
#endif
#ifdef CONFIG_HW_BRANCH_TRACER
void trace_hw_branch(u64 from, u64 to);
void trace_hw_branch_oops(void);
#else /* CONFIG_HW_BRANCH_TRACER */
static inline void trace_hw_branch(u64 from, u64 to) {}
static inline void trace_hw_branch_oops(void) {}
#endif /* CONFIG_HW_BRANCH_TRACER */
#ifdef CONFIG_FTRACE_SYSCALLS
unsigned long arch_syscall_addr(int nr);
#endif /* CONFIG_FTRACE_SYSCALLS */
#endif /* _LINUX_FTRACE_H */