Commit 40d9d82c authored by Ingo Molnar's avatar Ingo Molnar

Merge branch 'tip/tracing/core4' of...

Merge branch 'tip/tracing/core4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/core
parents 983f2163 b36461da
function tracer guts
====================
Introduction
------------
Here we will cover the architecture pieces that the common function tracing
code relies on for proper functioning. Things are broken down into increasing
complexity so that you can start simple and at least get basic functionality.
Note that this focuses on architecture implementation details only. If you
want more explanation of a feature in terms of common code, review the common
ftrace.txt file.
Prerequisites
-------------
Ftrace relies on these features being implemented:
STACKTRACE_SUPPORT - implement save_stack_trace()
TRACE_IRQFLAGS_SUPPORT - implement include/asm/irqflags.h
HAVE_FUNCTION_TRACER
--------------------
You will need to implement the mcount and the ftrace_stub functions.
The exact mcount symbol name will depend on your toolchain. Some call it
"mcount", "_mcount", or even "__mcount". You can probably figure it out by
running something like:
$ echo 'main(){}' | gcc -x c -S -o - - -pg | grep mcount
call mcount
We'll make the assumption below that the symbol is "mcount" just to keep things
nice and simple in the examples.
Keep in mind that the ABI that is in effect inside of the mcount function is
*highly* architecture/toolchain specific. We cannot help you in this regard,
sorry. Dig up some old documentation and/or find someone more familiar than
you to bang ideas off of. Typically, register usage (argument/scratch/etc...)
is a major issue at this point, especially in relation to the location of the
mcount call (before/after function prologue). You might also want to look at
how glibc has implemented the mcount function for your architecture. It might
be (semi-)relevant.
The mcount function should check the function pointer ftrace_trace_function
to see if it is set to ftrace_stub. If it is, there is nothing for you to do,
so return immediately. If it isn't, then call that function in the same way
the mcount function normally calls __mcount_internal -- the first argument is
the "frompc" while the second argument is the "selfpc" (adjusted to remove the
size of the mcount call that is embedded in the function).
For example, if the function foo() calls bar(), when the bar() function calls
mcount(), the arguments mcount() will pass to the tracer are:
"frompc" - the address bar() will use to return to foo()
"selfpc" - the address bar() (with _mcount() size adjustment)
Also keep in mind that this mcount function will be called *a lot*, so
optimizing for the default case of no tracer will help the smooth running of
your system when tracing is disabled. So the start of the mcount function is
typically the bare min with checking things before returning. That also means
the code flow should usually kept linear (i.e. no branching in the nop case).
This is of course an optimization and not a hard requirement.
Here is some pseudo code that should help (these functions should actually be
implemented in assembly):
void ftrace_stub(void)
{
return;
}
void mcount(void)
{
/* save any bare state needed in order to do initial checking */
extern void (*ftrace_trace_function)(unsigned long, unsigned long);
if (ftrace_trace_function != ftrace_stub)
goto do_trace;
/* restore any bare state */
return;
do_trace:
/* save all state needed by the ABI (see paragraph above) */
unsigned long frompc = ...;
unsigned long selfpc = <return address> - MCOUNT_INSN_SIZE;
ftrace_trace_function(frompc, selfpc);
/* restore all state needed by the ABI */
}
Don't forget to export mcount for modules !
extern void mcount(void);
EXPORT_SYMBOL(mcount);
HAVE_FUNCTION_TRACE_MCOUNT_TEST
-------------------------------
This is an optional optimization for the normal case when tracing is turned off
in the system. If you do not enable this Kconfig option, the common ftrace
code will take care of doing the checking for you.
To support this feature, you only need to check the function_trace_stop
variable in the mcount function. If it is non-zero, there is no tracing to be
done at all, so you can return.
This additional pseudo code would simply be:
void mcount(void)
{
/* save any bare state needed in order to do initial checking */
+ if (function_trace_stop)
+ return;
extern void (*ftrace_trace_function)(unsigned long, unsigned long);
if (ftrace_trace_function != ftrace_stub)
...
HAVE_FUNCTION_GRAPH_TRACER
--------------------------
Deep breath ... time to do some real work. Here you will need to update the
mcount function to check ftrace graph function pointers, as well as implement
some functions to save (hijack) and restore the return address.
The mcount function should check the function pointers ftrace_graph_return
(compare to ftrace_stub) and ftrace_graph_entry (compare to
ftrace_graph_entry_stub). If either of those are not set to the relevant stub
function, call the arch-specific function ftrace_graph_caller which in turn
calls the arch-specific function prepare_ftrace_return. Neither of these
function names are strictly required, but you should use them anyways to stay
consistent across the architecture ports -- easier to compare & contrast
things.
The arguments to prepare_ftrace_return are slightly different than what are
passed to ftrace_trace_function. The second argument "selfpc" is the same,
but the first argument should be a pointer to the "frompc". Typically this is
located on the stack. This allows the function to hijack the return address
temporarily to have it point to the arch-specific function return_to_handler.
That function will simply call the common ftrace_return_to_handler function and
that will return the original return address with which, you can return to the
original call site.
Here is the updated mcount pseudo code:
void mcount(void)
{
...
if (ftrace_trace_function != ftrace_stub)
goto do_trace;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ extern void (*ftrace_graph_return)(...);
+ extern void (*ftrace_graph_entry)(...);
+ if (ftrace_graph_return != ftrace_stub ||
+ ftrace_graph_entry != ftrace_graph_entry_stub)
+ ftrace_graph_caller();
+#endif
/* restore any bare state */
...
Here is the pseudo code for the new ftrace_graph_caller assembly function:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
void ftrace_graph_caller(void)
{
/* save all state needed by the ABI */
unsigned long *frompc = &...;
unsigned long selfpc = <return address> - MCOUNT_INSN_SIZE;
prepare_ftrace_return(frompc, selfpc);
/* restore all state needed by the ABI */
}
#endif
For information on how to implement prepare_ftrace_return(), simply look at
the x86 version. The only architecture-specific piece in it is the setup of
the fault recovery table (the asm(...) code). The rest should be the same
across architectures.
Here is the pseudo code for the new return_to_handler assembly function. Note
that the ABI that applies here is different from what applies to the mcount
code. Since you are returning from a function (after the epilogue), you might
be able to skimp on things saved/restored (usually just registers used to pass
return values).
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
void return_to_handler(void)
{
/* save all state needed by the ABI (see paragraph above) */
void (*original_return_point)(void) = ftrace_return_to_handler();
/* restore all state needed by the ABI */
/* this is usually either a return or a jump */
original_return_point();
}
#endif
HAVE_FTRACE_NMI_ENTER
---------------------
If you can't trace NMI functions, then skip this option.
<details to be filled>
HAVE_FTRACE_SYSCALLS
---------------------
<details to be filled>
HAVE_FTRACE_MCOUNT_RECORD
-------------------------
See scripts/recordmcount.pl for more info.
<details to be filled>
HAVE_DYNAMIC_FTRACE
---------------------
<details to be filled>
......@@ -26,6 +26,12 @@ disabled, and more (ftrace allows for tracer plugins, which
means that the list of tracers can always grow).
Implementation Details
----------------------
See ftrace-design.txt for details for arch porters and such.
The File System
---------------
......
......@@ -48,13 +48,13 @@
#define KPROBE_HIT_SSDONE 0x00000008
/* Attach to insert probes on any functions which should be ignored*/
#define __kprobes __attribute__((__section__(".kprobes.text"))) notrace
#define __kprobes __attribute__((__section__(".kprobes.text")))
#else /* CONFIG_KPROBES */
typedef int kprobe_opcode_t;
struct arch_specific_insn {
int dummy;
};
#define __kprobes notrace
#define __kprobes
#endif /* CONFIG_KPROBES */
struct kprobe;
......
......@@ -239,9 +239,9 @@ ftrace_format_##call(struct ftrace_event_call *unused, \
#undef __print_flags
#define __print_flags(flag, delim, flag_array...) \
({ \
static const struct trace_print_flags flags[] = \
static const struct trace_print_flags __flags[] = \
{ flag_array, { -1, NULL }}; \
ftrace_print_flags_seq(p, delim, flag, flags); \
ftrace_print_flags_seq(p, delim, flag, __flags); \
})
#undef __print_symbolic
......@@ -254,7 +254,7 @@ ftrace_format_##call(struct ftrace_event_call *unused, \
#undef TRACE_EVENT
#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \
enum print_line_t \
static enum print_line_t \
ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \
{ \
struct trace_seq *s = &iter->seq; \
......@@ -317,7 +317,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \
#undef TRACE_EVENT
#define TRACE_EVENT(call, proto, args, tstruct, func, print) \
int \
static int \
ftrace_define_fields_##call(struct ftrace_event_call *event_call) \
{ \
struct ftrace_raw_##call field; \
......
......@@ -11,12 +11,18 @@ config NOP_TRACER
config HAVE_FTRACE_NMI_ENTER
bool
help
See Documentation/trace/ftrace-implementation.txt
config HAVE_FUNCTION_TRACER
bool
help
See Documentation/trace/ftrace-implementation.txt
config HAVE_FUNCTION_GRAPH_TRACER
bool
help
See Documentation/trace/ftrace-implementation.txt
config HAVE_FUNCTION_GRAPH_FP_TEST
bool
......@@ -28,21 +34,25 @@ config HAVE_FUNCTION_GRAPH_FP_TEST
config HAVE_FUNCTION_TRACE_MCOUNT_TEST
bool
help
This gets selected when the arch tests the function_trace_stop
variable at the mcount call site. Otherwise, this variable
is tested by the called function.
See Documentation/trace/ftrace-implementation.txt
config HAVE_DYNAMIC_FTRACE
bool
help
See Documentation/trace/ftrace-implementation.txt
config HAVE_FTRACE_MCOUNT_RECORD
bool
help
See Documentation/trace/ftrace-implementation.txt
config HAVE_HW_BRANCH_TRACER
bool
config HAVE_SYSCALL_TRACEPOINTS
bool
help
See Documentation/trace/ftrace-implementation.txt
config TRACER_MAX_TRACE
bool
......@@ -469,6 +479,18 @@ config FTRACE_STARTUP_TEST
functioning properly. It will do tests on all the configured
tracers of ftrace.
config EVENT_TRACE_TEST_SYSCALLS
bool "Run selftest on syscall events"
depends on FTRACE_STARTUP_TEST
help
This option will also enable testing every syscall event.
It only enables the event and disables it and runs various loads
with the event enabled. This adds a bit more time for kernel boot
up since it runs this on every system call defined.
TBD - enable a way to actually call the syscalls as we test their
events
config MMIOTRACE
bool "Memory mapped IO tracing"
depends on HAVE_MMIOTRACE_SUPPORT && PCI
......
......@@ -2062,9 +2062,9 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
int i, len = 0;
char *search;
if (glob && (strcmp(glob, "*") || !strlen(glob)))
if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
glob = NULL;
else {
else if (glob) {
int not;
type = ftrace_setup_glob(glob, strlen(glob), &search, &not);
......
......@@ -66,10 +66,14 @@ u64 notrace trace_clock(void)
* Used by plugins that need globally coherent timestamps.
*/
static u64 prev_trace_clock_time;
static raw_spinlock_t trace_clock_lock ____cacheline_aligned_in_smp =
(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
/* keep prev_time and lock in the same cacheline. */
static struct {
u64 prev_time;
raw_spinlock_t lock;
} trace_clock_struct ____cacheline_aligned_in_smp =
{
.lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED,
};
u64 notrace trace_clock_global(void)
{
......@@ -88,19 +92,19 @@ u64 notrace trace_clock_global(void)
if (unlikely(in_nmi()))
goto out;
__raw_spin_lock(&trace_clock_lock);
__raw_spin_lock(&trace_clock_struct.lock);
/*
* TODO: if this happens often then maybe we should reset
* my_scd->clock to prev_trace_clock_time+1, to make sure
* my_scd->clock to prev_time+1, to make sure
* we start ticking with the local clock from now on?
*/
if ((s64)(now - prev_trace_clock_time) < 0)
now = prev_trace_clock_time + 1;
if ((s64)(now - trace_clock_struct.prev_time) < 0)
now = trace_clock_struct.prev_time + 1;
prev_trace_clock_time = now;
trace_clock_struct.prev_time = now;
__raw_spin_unlock(&trace_clock_lock);
__raw_spin_unlock(&trace_clock_struct.lock);
out:
raw_local_irq_restore(flags);
......
......@@ -78,7 +78,7 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
__field_desc( int, graph_ent, depth )
),
F_printk("--> %lx (%d)", __entry->graph_ent.func, __entry->depth)
F_printk("--> %lx (%d)", __entry->func, __entry->depth)
);
/* Function return entry */
......@@ -97,8 +97,8 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
F_printk("<-- %lx (%d) (start: %llx end: %llx) over: %d",
__entry->func, __entry->depth,
__entry->calltime, __entry->rettim,
__entrty->depth)
__entry->calltime, __entry->rettime,
__entry->depth)
);
/*
......@@ -116,15 +116,6 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
__field( unsigned char, next_state ) \
__field( unsigned int, next_cpu )
#if 0
FTRACE_ENTRY_STRUCT_ONLY(ctx_switch_entry,
F_STRUCT(
FTRACE_CTX_FIELDS
)
);
#endif
FTRACE_ENTRY(context_switch, ctx_switch_entry,
TRACE_CTX,
......@@ -133,7 +124,7 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry,
FTRACE_CTX_FIELDS
),
F_printk(b"%u:%u:%u ==> %u:%u:%u [%03u]",
F_printk("%u:%u:%u ==> %u:%u:%u [%03u]",
__entry->prev_pid, __entry->prev_prio, __entry->prev_state,
__entry->next_pid, __entry->next_prio, __entry->next_state,
__entry->next_cpu
......@@ -257,8 +248,8 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
__field_desc( unsigned char, rw, width )
),
F_printk("%lx %lx %lx %d %lx %lx",
__entry->phs, __entry->value, __entry->pc,
F_printk("%lx %lx %lx %d %x %x",
(unsigned long)__entry->phys, __entry->value, __entry->pc,
__entry->map_id, __entry->opcode, __entry->width)
);
......@@ -275,8 +266,8 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
__field_desc( unsigned char, map, opcode )
),
F_printk("%lx %lx %lx %d %lx",
__entry->phs, __entry->virt, __entry->len,
F_printk("%lx %lx %lx %d %x",
(unsigned long)__entry->phys, __entry->virt, __entry->len,
__entry->map_id, __entry->opcode)
);
......@@ -370,7 +361,7 @@ FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry,
__field( int, node )
),
F_printk("type:%u call_site:%lx ptr:%p req:%lu alloc:%lu"
F_printk("type:%u call_site:%lx ptr:%p req:%zi alloc:%zi"
" flags:%x node:%d",
__entry->type_id, __entry->call_site, __entry->ptr,
__entry->bytes_req, __entry->bytes_alloc,
......
......@@ -1154,7 +1154,7 @@ static int trace_module_notify(struct notifier_block *self,
}
#endif /* CONFIG_MODULES */
struct notifier_block trace_module_nb = {
static struct notifier_block trace_module_nb = {
.notifier_call = trace_module_notify,
.priority = 0,
};
......@@ -1326,6 +1326,18 @@ static __init void event_trace_self_tests(void)
if (!call->regfunc)
continue;
/*
* Testing syscall events here is pretty useless, but
* we still do it if configured. But this is time consuming.
* What we really need is a user thread to perform the
* syscalls as we test.
*/
#ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS
if (call->system &&
strcmp(call->system, "syscalls") == 0)
continue;
#endif
pr_info("Testing event %s: ", call->name);
/*
......
......@@ -22,6 +22,47 @@
#undef __field_struct
#define __field_struct(type, item)
#undef __field
#define __field(type, item) type item;
#undef __field_desc
#define __field_desc(type, container, item) type item;
#undef __array
#define __array(type, item, size) type item[size];
#undef __array_desc
#define __array_desc(type, container, item, size) type item[size];
#undef __dynamic_array
#define __dynamic_array(type, item) type item[];
#undef F_STRUCT
#define F_STRUCT(args...) args
#undef F_printk
#define F_printk(fmt, args...) fmt, args
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
struct ____ftrace_##name { \
tstruct \
}; \
static void __used ____ftrace_check_##name(void) \
{ \
struct ____ftrace_##name *__entry = NULL; \
\
/* force cmpile-time check on F_printk() */ \
printk(print); \
}
#undef FTRACE_ENTRY_DUP
#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
#include "trace_entries.h"
#undef __field
#define __field(type, item) \
ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
......@@ -88,10 +129,6 @@ ftrace_format_##name(struct ftrace_event_call *unused, \
return ret; \
}
#undef FTRACE_ENTRY_DUP
#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
#include "trace_entries.h"
......@@ -172,32 +209,6 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
#undef __dynamic_array
#define __dynamic_array(type, item)
#undef TRACE_ZERO_CHAR
#define TRACE_ZERO_CHAR(arg)
#undef TRACE_FIELD
#define TRACE_FIELD(type, item, assign)\
entry->item = assign;
#undef TRACE_FIELD
#define TRACE_FIELD(type, item, assign)\
entry->item = assign;
#undef TRACE_FIELD_SIGN
#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \
TRACE_FIELD(type, item, assign)
#undef TP_CMD
#define TP_CMD(cmd...) cmd
#undef TRACE_ENTRY
#define TRACE_ENTRY entry
#undef TRACE_FIELD_SPECIAL
#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd) \
cmd;
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \
static int ftrace_raw_init_event_##call(void); \
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment