2008-05-12 21:20:42 +02:00
|
|
|
#ifndef _LINUX_KERNEL_TRACE_H
|
|
|
|
#define _LINUX_KERNEL_TRACE_H
|
|
|
|
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <asm/atomic.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/clocksource.h>
|
2008-09-30 05:02:41 +02:00
|
|
|
#include <linux/ring_buffer.h>
|
ftrace: mmiotrace, updates
here is a patch that makes mmiotrace work almost well within the tracing
framework. The patch applies on top of my previous patch. I have my own
output formatting in place now.
Summary of changes:
- fix the NULL dereference that was due to not calling tracing_reset()
- add print_line() callback into struct tracer
- implement print_line() for mmiotrace, producing up-to-spec text
- add my output header, but that is not really called in the right place
- rewrote the main structs in mmiotrace
- added two new trace entry types: TRACE_MMIO_RW and TRACE_MMIO_MAP
- made some functions in trace.c non-static
- check current==NULL in tracing_generic_entry_update()
- fix(?) comparison in trace_seq_printf()
Things seem to work fine except a few issues. Markers (text lines injected
into mmiotrace log) are missing, I did not feel hacking them in before we
have variable length entries. My output header is printed only for 'trace'
file, but not 'trace_pipe'. For some reason, despite my quick fix,
iter->trace is NULL in print_trace_line() when called from 'trace_pipe'
file, which means I don't get proper output formatting.
I only tried by loading nouveau.ko, which just detects the card, and that
is traced fine. I didn't try further. Map, two reads and unmap. Works
perfectly.
I am missing the information about overflows, I'd prefer to have a
counter for lost events. I didn't try, but I guess currently there is no
way of knowning when it overflows?
So, not too far from being fully operational, it seems :-)
And looking at the diffstat, there also is some 700-900 lines of user space
code that just became obsolete.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 21:20:57 +02:00
|
|
|
#include <linux/mmiotrace.h>
|
2008-09-23 12:32:08 +02:00
|
|
|
#include <linux/ftrace.h>
|
2008-11-11 23:21:31 +01:00
|
|
|
#include <trace/boot.h>
|
2008-05-12 21:20:42 +02:00
|
|
|
|
2008-05-23 21:37:28 +02:00
|
|
|
enum trace_type {
|
|
|
|
__TRACE_FIRST_TYPE = 0,
|
|
|
|
|
|
|
|
TRACE_FN,
|
|
|
|
TRACE_CTX,
|
|
|
|
TRACE_WAKE,
|
2008-08-01 18:26:41 +02:00
|
|
|
TRACE_CONT,
|
2008-05-23 21:37:28 +02:00
|
|
|
TRACE_STACK,
|
2008-08-01 18:26:41 +02:00
|
|
|
TRACE_PRINT,
|
2008-05-23 21:37:28 +02:00
|
|
|
TRACE_SPECIAL,
|
ftrace: mmiotrace, updates
here is a patch that makes mmiotrace work almost well within the tracing
framework. The patch applies on top of my previous patch. I have my own
output formatting in place now.
Summary of changes:
- fix the NULL dereference that was due to not calling tracing_reset()
- add print_line() callback into struct tracer
- implement print_line() for mmiotrace, producing up-to-spec text
- add my output header, but that is not really called in the right place
- rewrote the main structs in mmiotrace
- added two new trace entry types: TRACE_MMIO_RW and TRACE_MMIO_MAP
- made some functions in trace.c non-static
- check current==NULL in tracing_generic_entry_update()
- fix(?) comparison in trace_seq_printf()
Things seem to work fine except a few issues. Markers (text lines injected
into mmiotrace log) are missing, I did not feel hacking them in before we
have variable length entries. My output header is printed only for 'trace'
file, but not 'trace_pipe'. For some reason, despite my quick fix,
iter->trace is NULL in print_trace_line() when called from 'trace_pipe'
file, which means I don't get proper output formatting.
I only tried by loading nouveau.ko, which just detects the card, and that
is traced fine. I didn't try further. Map, two reads and unmap. Works
perfectly.
I am missing the information about overflows, I'd prefer to have a
counter for lost events. I didn't try, but I guess currently there is no
way of knowning when it overflows?
So, not too far from being fully operational, it seems :-)
And looking at the diffstat, there also is some 700-900 lines of user space
code that just became obsolete.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 21:20:57 +02:00
|
|
|
TRACE_MMIO_RW,
|
|
|
|
TRACE_MMIO_MAP,
|
2008-11-12 21:24:24 +01:00
|
|
|
TRACE_BRANCH,
|
2008-11-11 23:24:42 +01:00
|
|
|
TRACE_BOOT_CALL,
|
|
|
|
TRACE_BOOT_RET,
|
2008-11-11 07:14:25 +01:00
|
|
|
TRACE_FN_RET,
|
2008-11-22 12:28:47 +01:00
|
|
|
TRACE_USER_STACK,
|
2008-11-25 09:24:15 +01:00
|
|
|
TRACE_BTS,
|
2008-05-23 21:37:28 +02:00
|
|
|
|
|
|
|
__TRACE_LAST_TYPE
|
|
|
|
};
|
|
|
|
|
2008-09-30 05:02:42 +02:00
|
|
|
/*
|
|
|
|
* The trace entry - the most basic unit of tracing. This is what
|
|
|
|
* is printed in the end as a single line in the trace output, such as:
|
|
|
|
*
|
|
|
|
* bash-15816 [01] 235.197585: idle_cpu <- irq_enter
|
|
|
|
*/
|
|
|
|
struct trace_entry {
|
|
|
|
unsigned char type;
|
|
|
|
unsigned char cpu;
|
|
|
|
unsigned char flags;
|
|
|
|
unsigned char preempt_count;
|
|
|
|
int pid;
|
2008-11-22 12:28:47 +01:00
|
|
|
int tgid;
|
2008-09-30 05:02:42 +02:00
|
|
|
};
|
|
|
|
|
2008-05-12 21:20:42 +02:00
|
|
|
/*
|
|
|
|
* Function trace entry - function address and parent function addres:
|
|
|
|
*/
|
|
|
|
struct ftrace_entry {
|
2008-09-30 05:02:42 +02:00
|
|
|
struct trace_entry ent;
|
2008-05-12 21:20:42 +02:00
|
|
|
unsigned long ip;
|
|
|
|
unsigned long parent_ip;
|
|
|
|
};
|
2008-11-11 07:14:25 +01:00
|
|
|
|
|
|
|
/* Function return entry */
|
|
|
|
struct ftrace_ret_entry {
|
|
|
|
struct trace_entry ent;
|
|
|
|
unsigned long ip;
|
|
|
|
unsigned long parent_ip;
|
|
|
|
unsigned long long calltime;
|
|
|
|
unsigned long long rettime;
|
2008-11-17 03:22:41 +01:00
|
|
|
unsigned long overrun;
|
2008-11-11 07:14:25 +01:00
|
|
|
};
|
2008-09-23 12:32:08 +02:00
|
|
|
extern struct tracer boot_tracer;
|
2008-05-12 21:20:42 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Context switch trace entry - which task (and prio) we switched from/to:
|
|
|
|
*/
|
|
|
|
struct ctx_switch_entry {
|
2008-09-30 05:02:42 +02:00
|
|
|
struct trace_entry ent;
|
2008-05-12 21:20:42 +02:00
|
|
|
unsigned int prev_pid;
|
|
|
|
unsigned char prev_prio;
|
|
|
|
unsigned char prev_state;
|
|
|
|
unsigned int next_pid;
|
|
|
|
unsigned char next_prio;
|
2008-05-12 21:20:53 +02:00
|
|
|
unsigned char next_state;
|
2008-09-04 10:24:16 +02:00
|
|
|
unsigned int next_cpu;
|
2008-05-12 21:20:42 +02:00
|
|
|
};
|
|
|
|
|
2008-05-12 21:20:47 +02:00
|
|
|
/*
|
|
|
|
* Special (free-form) trace entry:
|
|
|
|
*/
|
|
|
|
struct special_entry {
|
2008-09-30 05:02:42 +02:00
|
|
|
struct trace_entry ent;
|
2008-05-12 21:20:47 +02:00
|
|
|
unsigned long arg1;
|
|
|
|
unsigned long arg2;
|
|
|
|
unsigned long arg3;
|
|
|
|
};
|
|
|
|
|
2008-05-12 21:20:51 +02:00
|
|
|
/*
|
|
|
|
* Stack-trace entry:
|
|
|
|
*/
|
|
|
|
|
2008-05-12 21:21:15 +02:00
|
|
|
#define FTRACE_STACK_ENTRIES 8
|
2008-05-12 21:20:51 +02:00
|
|
|
|
|
|
|
struct stack_entry {
|
2008-09-30 05:02:42 +02:00
|
|
|
struct trace_entry ent;
|
2008-05-12 21:20:51 +02:00
|
|
|
unsigned long caller[FTRACE_STACK_ENTRIES];
|
|
|
|
};
|
|
|
|
|
2008-11-22 12:28:47 +01:00
|
|
|
struct userstack_entry {
|
|
|
|
struct trace_entry ent;
|
|
|
|
unsigned long caller[FTRACE_STACK_ENTRIES];
|
|
|
|
};
|
|
|
|
|
2008-08-01 18:26:41 +02:00
|
|
|
/*
|
|
|
|
* ftrace_printk entry:
|
|
|
|
*/
|
|
|
|
struct print_entry {
|
2008-09-30 05:02:42 +02:00
|
|
|
struct trace_entry ent;
|
2008-08-01 18:26:41 +02:00
|
|
|
unsigned long ip;
|
|
|
|
char buf[];
|
|
|
|
};
|
|
|
|
|
2008-09-30 05:02:42 +02:00
|
|
|
#define TRACE_OLD_SIZE 88
|
|
|
|
|
|
|
|
struct trace_field_cont {
|
|
|
|
unsigned char type;
|
|
|
|
/* Temporary till we get rid of this completely */
|
|
|
|
char buf[TRACE_OLD_SIZE - 1];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct trace_mmiotrace_rw {
|
|
|
|
struct trace_entry ent;
|
|
|
|
struct mmiotrace_rw rw;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct trace_mmiotrace_map {
|
|
|
|
struct trace_entry ent;
|
|
|
|
struct mmiotrace_map map;
|
|
|
|
};
|
|
|
|
|
2008-11-11 23:24:42 +01:00
|
|
|
struct trace_boot_call {
|
2008-09-30 05:02:42 +02:00
|
|
|
struct trace_entry ent;
|
2008-11-11 23:24:42 +01:00
|
|
|
struct boot_trace_call boot_call;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct trace_boot_ret {
|
|
|
|
struct trace_entry ent;
|
|
|
|
struct boot_trace_ret boot_ret;
|
2008-09-30 05:02:42 +02:00
|
|
|
};
|
|
|
|
|
2008-11-12 06:14:40 +01:00
|
|
|
#define TRACE_FUNC_SIZE 30
|
|
|
|
#define TRACE_FILE_SIZE 20
|
2008-11-12 21:24:24 +01:00
|
|
|
struct trace_branch {
|
2008-11-12 06:14:40 +01:00
|
|
|
struct trace_entry ent;
|
|
|
|
unsigned line;
|
|
|
|
char func[TRACE_FUNC_SIZE+1];
|
|
|
|
char file[TRACE_FILE_SIZE+1];
|
|
|
|
char correct;
|
|
|
|
};
|
|
|
|
|
2008-11-25 09:24:15 +01:00
|
|
|
struct bts_entry {
|
|
|
|
struct trace_entry ent;
|
|
|
|
unsigned long from;
|
|
|
|
unsigned long to;
|
|
|
|
};
|
|
|
|
|
2008-09-16 21:02:27 +02:00
|
|
|
/*
|
|
|
|
* trace_flag_type is an enumeration that holds different
|
|
|
|
* states when a trace occurs. These are:
|
2008-10-24 15:42:59 +02:00
|
|
|
* IRQS_OFF - interrupts were disabled
|
|
|
|
* IRQS_NOSUPPORT - arch does not support irqs_disabled_flags
|
|
|
|
* NEED_RESCED - reschedule is requested
|
|
|
|
* HARDIRQ - inside an interrupt handler
|
|
|
|
* SOFTIRQ - inside a softirq handler
|
|
|
|
* CONT - multiple entries hold the trace item
|
2008-09-16 21:02:27 +02:00
|
|
|
*/
|
|
|
|
enum trace_flag_type {
|
|
|
|
TRACE_FLAG_IRQS_OFF = 0x01,
|
2008-10-24 15:42:59 +02:00
|
|
|
TRACE_FLAG_IRQS_NOSUPPORT = 0x02,
|
|
|
|
TRACE_FLAG_NEED_RESCHED = 0x04,
|
|
|
|
TRACE_FLAG_HARDIRQ = 0x08,
|
|
|
|
TRACE_FLAG_SOFTIRQ = 0x10,
|
|
|
|
TRACE_FLAG_CONT = 0x20,
|
2008-09-16 21:02:27 +02:00
|
|
|
};
|
|
|
|
|
2008-09-16 21:06:42 +02:00
|
|
|
#define TRACE_BUF_SIZE 1024
|
2008-05-12 21:20:42 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The CPU trace array - it consists of thousands of trace entries
|
|
|
|
* plus some other descriptor data: (for example which task started
|
|
|
|
* the trace, etc.)
|
|
|
|
*/
|
|
|
|
struct trace_array_cpu {
|
|
|
|
atomic_t disabled;
|
2008-05-12 21:20:45 +02:00
|
|
|
|
2008-05-12 21:20:45 +02:00
|
|
|
/* these fields get copied into max-trace: */
|
|
|
|
unsigned long trace_idx;
|
2008-05-12 21:21:01 +02:00
|
|
|
unsigned long overrun;
|
2008-05-12 21:20:42 +02:00
|
|
|
unsigned long saved_latency;
|
|
|
|
unsigned long critical_start;
|
|
|
|
unsigned long critical_end;
|
|
|
|
unsigned long critical_sequence;
|
|
|
|
unsigned long nice;
|
|
|
|
unsigned long policy;
|
|
|
|
unsigned long rt_priority;
|
|
|
|
cycle_t preempt_timestamp;
|
|
|
|
pid_t pid;
|
|
|
|
uid_t uid;
|
|
|
|
char comm[TASK_COMM_LEN];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct trace_iterator;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The trace array - an array of per-CPU trace arrays. This is the
|
|
|
|
* highest level data structure that individual tracers deal with.
|
|
|
|
* They have on/off state as well:
|
|
|
|
*/
|
|
|
|
struct trace_array {
|
2008-09-30 05:02:41 +02:00
|
|
|
struct ring_buffer *buffer;
|
2008-05-12 21:20:42 +02:00
|
|
|
unsigned long entries;
|
|
|
|
int cpu;
|
|
|
|
cycle_t time_start;
|
2008-05-12 21:20:46 +02:00
|
|
|
struct task_struct *waiter;
|
2008-05-12 21:20:42 +02:00
|
|
|
struct trace_array_cpu *data[NR_CPUS];
|
|
|
|
};
|
|
|
|
|
2008-10-01 16:52:51 +02:00
|
|
|
#define FTRACE_CMP_TYPE(var, type) \
|
|
|
|
__builtin_types_compatible_p(typeof(var), type *)
|
|
|
|
|
|
|
|
#undef IF_ASSIGN
|
|
|
|
#define IF_ASSIGN(var, entry, etype, id) \
|
|
|
|
if (FTRACE_CMP_TYPE(var, etype)) { \
|
|
|
|
var = (typeof(var))(entry); \
|
|
|
|
WARN_ON(id && (entry)->type != id); \
|
|
|
|
break; \
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Will cause compile errors if type is not found. */
|
|
|
|
extern void __ftrace_bad_type(void);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The trace_assign_type is a verifier that the entry type is
|
|
|
|
* the same as the type being assigned. To add new types simply
|
|
|
|
* add a line with the following format:
|
|
|
|
*
|
|
|
|
* IF_ASSIGN(var, ent, type, id);
|
|
|
|
*
|
|
|
|
* Where "type" is the trace type that includes the trace_entry
|
|
|
|
* as the "ent" item. And "id" is the trace identifier that is
|
|
|
|
* used in the trace_type enum.
|
|
|
|
*
|
|
|
|
* If the type can have more than one id, then use zero.
|
|
|
|
*/
|
|
|
|
#define trace_assign_type(var, ent) \
|
|
|
|
do { \
|
|
|
|
IF_ASSIGN(var, ent, struct ftrace_entry, TRACE_FN); \
|
|
|
|
IF_ASSIGN(var, ent, struct ctx_switch_entry, 0); \
|
|
|
|
IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \
|
|
|
|
IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK); \
|
2008-11-22 12:28:47 +01:00
|
|
|
IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
|
2008-10-01 16:52:51 +02:00
|
|
|
IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \
|
|
|
|
IF_ASSIGN(var, ent, struct special_entry, 0); \
|
|
|
|
IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \
|
|
|
|
TRACE_MMIO_RW); \
|
|
|
|
IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \
|
|
|
|
TRACE_MMIO_MAP); \
|
2008-11-11 23:24:42 +01:00
|
|
|
IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\
|
|
|
|
IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\
|
2008-11-12 21:24:24 +01:00
|
|
|
IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
|
2008-11-11 23:24:42 +01:00
|
|
|
IF_ASSIGN(var, ent, struct ftrace_ret_entry, TRACE_FN_RET);\
|
2008-11-25 09:24:15 +01:00
|
|
|
IF_ASSIGN(var, ent, struct bts_entry, TRACE_BTS);\
|
2008-10-01 16:52:51 +02:00
|
|
|
__ftrace_bad_type(); \
|
|
|
|
} while (0)
|
2008-09-29 20:18:34 +02:00
|
|
|
|
|
|
|
/* Return values for print_line callback */
|
|
|
|
enum print_line_t {
|
|
|
|
TRACE_TYPE_PARTIAL_LINE = 0, /* Retry after flushing the seq */
|
|
|
|
TRACE_TYPE_HANDLED = 1,
|
|
|
|
TRACE_TYPE_UNHANDLED = 2 /* Relay to other output functions */
|
|
|
|
};
|
|
|
|
|
2008-11-17 19:23:42 +01:00
|
|
|
|
|
|
|
/*
|
|
|
|
* An option specific to a tracer. This is a boolean value.
|
|
|
|
* The bit is the bit index that sets its value on the
|
|
|
|
* flags value in struct tracer_flags.
|
|
|
|
*/
|
|
|
|
struct tracer_opt {
|
|
|
|
const char *name; /* Will appear on the trace_options file */
|
|
|
|
u32 bit; /* Mask assigned in val field in tracer_flags */
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The set of specific options for a tracer. Your tracer
|
|
|
|
* have to set the initial value of the flags val.
|
|
|
|
*/
|
|
|
|
struct tracer_flags {
|
|
|
|
u32 val;
|
|
|
|
struct tracer_opt *opts;
|
|
|
|
};
|
|
|
|
|
|
|
|
/* Makes more easy to define a tracer opt */
|
|
|
|
#define TRACER_OPT(s, b) .name = #s, .bit = b
|
|
|
|
|
2008-05-12 21:20:42 +02:00
|
|
|
/*
|
|
|
|
* A specific tracer, represented by methods that operate on a trace array:
|
|
|
|
*/
|
|
|
|
struct tracer {
|
|
|
|
const char *name;
|
2008-11-16 05:57:26 +01:00
|
|
|
/* Your tracer should raise a warning if init fails */
|
|
|
|
int (*init)(struct trace_array *tr);
|
2008-05-12 21:20:42 +02:00
|
|
|
void (*reset)(struct trace_array *tr);
|
ftrace: restructure tracing start/stop infrastructure
Impact: change where tracing is started up and stopped
Currently, when a new tracer is selected via echo'ing a tracer name into
the current_tracer file, the startup is only done if tracing_enabled is
set to one. If tracing_enabled is changed to zero (by echo'ing 0 into
the tracing_enabled file) a full shutdown is performed.
The full startup and shutdown of a tracer can be expensive and the
user can lose out traces when echo'ing in 0 to the tracing_enabled file,
because the process takes too long. There can also be places that
the user would like to start and stop the tracer several times and
doing the full startup and shutdown of a tracer might be too expensive.
This patch performs the full startup and shutdown when a tracer is
selected. It also adds a way to do a quick start or stop of a tracer.
The quick version is just a flag that prevents the tracing from
taking place, but the overhead of the code is still there.
For example, the startup of a tracer may enable tracepoints, or enable
the function tracer. The stop and start will just set a flag to
have the tracer ignore the calls when the tracepoint or function trace
is called. The overhead of the tracer may still be present when
the tracer is stopped, but no tracing will occur. Setting the tracer
to the 'nop' tracer (or any other tracer) will perform the shutdown
of the tracer which will disable the tracepoint or disable the
function tracer.
The tracing_enabled file will simply start or stop tracing.
This change is all internal. The end result for the user should be the same
as before. If tracing_enabled is not set, no trace will happen.
If tracing_enabled is set, then the trace will happen. The tracing_enabled
variable is static between tracers. Enabling tracing_enabled and
going to another tracer will keep tracing_enabled enabled. Same
is true with disabling tracing_enabled.
This patch will now provide a fast start/stop method to the users
for enabling or disabling tracing.
Note: There were two methods to the struct tracer that were never
used: The methods start and stop. These were to be used as a hook
to the reading of the trace output, but ended up not being
necessary. These two methods are now used to enable the start
and stop of each tracer, in case the tracer needs to do more than
just not write into the buffer. For example, the irqsoff tracer
must stop recording max latencies when tracing is stopped.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-05 22:05:44 +01:00
|
|
|
void (*start)(struct trace_array *tr);
|
|
|
|
void (*stop)(struct trace_array *tr);
|
2008-05-12 21:20:42 +02:00
|
|
|
void (*open)(struct trace_iterator *iter);
|
2008-05-12 21:21:01 +02:00
|
|
|
void (*pipe_open)(struct trace_iterator *iter);
|
2008-05-12 21:20:42 +02:00
|
|
|
void (*close)(struct trace_iterator *iter);
|
2008-05-12 21:21:01 +02:00
|
|
|
ssize_t (*read)(struct trace_iterator *iter,
|
|
|
|
struct file *filp, char __user *ubuf,
|
|
|
|
size_t cnt, loff_t *ppos);
|
2008-05-12 21:20:44 +02:00
|
|
|
#ifdef CONFIG_FTRACE_STARTUP_TEST
|
|
|
|
int (*selftest)(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
|
|
|
#endif
|
2008-11-25 09:12:31 +01:00
|
|
|
void (*print_header)(struct seq_file *m);
|
2008-09-29 20:18:34 +02:00
|
|
|
enum print_line_t (*print_line)(struct trace_iterator *iter);
|
2008-11-17 19:23:42 +01:00
|
|
|
/* If you handled the flag setting, return 0 */
|
|
|
|
int (*set_flag)(u32 old_flags, u32 bit, int set);
|
2008-05-12 21:20:42 +02:00
|
|
|
struct tracer *next;
|
|
|
|
int print_max;
|
2008-11-17 19:23:42 +01:00
|
|
|
struct tracer_flags *flags;
|
2008-05-12 21:20:42 +02:00
|
|
|
};
|
|
|
|
|
2008-05-12 21:20:46 +02:00
|
|
|
struct trace_seq {
|
|
|
|
unsigned char buffer[PAGE_SIZE];
|
|
|
|
unsigned int len;
|
2008-05-12 21:21:02 +02:00
|
|
|
unsigned int readpos;
|
2008-05-12 21:20:46 +02:00
|
|
|
};
|
|
|
|
|
2008-05-12 21:20:42 +02:00
|
|
|
/*
|
|
|
|
* Trace iterator - used by printout routines who present trace
|
|
|
|
* results to users and which routines might sleep, etc:
|
|
|
|
*/
|
|
|
|
struct trace_iterator {
|
|
|
|
struct trace_array *tr;
|
|
|
|
struct tracer *trace;
|
2008-05-12 21:21:01 +02:00
|
|
|
void *private;
|
2008-09-30 05:02:41 +02:00
|
|
|
struct ring_buffer_iter *buffer_iter[NR_CPUS];
|
2008-05-12 21:20:45 +02:00
|
|
|
|
2008-05-12 21:21:01 +02:00
|
|
|
/* The below is zeroed out in pipe_read */
|
|
|
|
struct trace_seq seq;
|
2008-05-12 21:20:42 +02:00
|
|
|
struct trace_entry *ent;
|
2008-05-12 21:20:45 +02:00
|
|
|
int cpu;
|
2008-09-30 05:02:41 +02:00
|
|
|
u64 ts;
|
2008-05-12 21:20:45 +02:00
|
|
|
|
2008-05-12 21:20:42 +02:00
|
|
|
unsigned long iter_flags;
|
|
|
|
loff_t pos;
|
2008-05-12 21:20:43 +02:00
|
|
|
long idx;
|
2008-11-08 04:36:02 +01:00
|
|
|
|
|
|
|
cpumask_t started;
|
2008-05-12 21:20:42 +02:00
|
|
|
};
|
|
|
|
|
ftrace: restructure tracing start/stop infrastructure
Impact: change where tracing is started up and stopped
Currently, when a new tracer is selected via echo'ing a tracer name into
the current_tracer file, the startup is only done if tracing_enabled is
set to one. If tracing_enabled is changed to zero (by echo'ing 0 into
the tracing_enabled file) a full shutdown is performed.
The full startup and shutdown of a tracer can be expensive and the
user can lose out traces when echo'ing in 0 to the tracing_enabled file,
because the process takes too long. There can also be places that
the user would like to start and stop the tracer several times and
doing the full startup and shutdown of a tracer might be too expensive.
This patch performs the full startup and shutdown when a tracer is
selected. It also adds a way to do a quick start or stop of a tracer.
The quick version is just a flag that prevents the tracing from
taking place, but the overhead of the code is still there.
For example, the startup of a tracer may enable tracepoints, or enable
the function tracer. The stop and start will just set a flag to
have the tracer ignore the calls when the tracepoint or function trace
is called. The overhead of the tracer may still be present when
the tracer is stopped, but no tracing will occur. Setting the tracer
to the 'nop' tracer (or any other tracer) will perform the shutdown
of the tracer which will disable the tracepoint or disable the
function tracer.
The tracing_enabled file will simply start or stop tracing.
This change is all internal. The end result for the user should be the same
as before. If tracing_enabled is not set, no trace will happen.
If tracing_enabled is set, then the trace will happen. The tracing_enabled
variable is static between tracers. Enabling tracing_enabled and
going to another tracer will keep tracing_enabled enabled. Same
is true with disabling tracing_enabled.
This patch will now provide a fast start/stop method to the users
for enabling or disabling tracing.
Note: There were two methods to the struct tracer that were never
used: The methods start and stop. These were to be used as a hook
to the reading of the trace output, but ended up not being
necessary. These two methods are now used to enable the start
and stop of each tracer, in case the tracer needs to do more than
just not write into the buffer. For example, the irqsoff tracer
must stop recording max latencies when tracing is stopped.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-05 22:05:44 +01:00
|
|
|
int tracing_is_enabled(void);
|
2008-09-16 20:56:41 +02:00
|
|
|
void trace_wake_up(void);
|
2008-09-30 05:02:41 +02:00
|
|
|
void tracing_reset(struct trace_array *tr, int cpu);
|
2008-05-12 21:20:42 +02:00
|
|
|
int tracing_open_generic(struct inode *inode, struct file *filp);
|
|
|
|
struct dentry *tracing_init_dentry(void);
|
2008-05-12 21:20:49 +02:00
|
|
|
void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
|
|
|
|
|
2008-09-16 20:56:41 +02:00
|
|
|
struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
|
|
|
|
struct trace_array_cpu *data);
|
|
|
|
void tracing_generic_entry_update(struct trace_entry *entry,
|
2008-10-01 19:14:09 +02:00
|
|
|
unsigned long flags,
|
|
|
|
int pc);
|
2008-09-16 20:56:41 +02:00
|
|
|
|
2008-05-12 21:20:42 +02:00
|
|
|
void ftrace(struct trace_array *tr,
|
|
|
|
struct trace_array_cpu *data,
|
|
|
|
unsigned long ip,
|
|
|
|
unsigned long parent_ip,
|
2008-10-01 19:14:09 +02:00
|
|
|
unsigned long flags, int pc);
|
2008-05-12 21:20:42 +02:00
|
|
|
void tracing_sched_switch_trace(struct trace_array *tr,
|
|
|
|
struct trace_array_cpu *data,
|
|
|
|
struct task_struct *prev,
|
|
|
|
struct task_struct *next,
|
2008-10-01 19:14:09 +02:00
|
|
|
unsigned long flags, int pc);
|
2008-05-12 21:20:42 +02:00
|
|
|
void tracing_record_cmdline(struct task_struct *tsk);
|
2008-05-12 21:20:51 +02:00
|
|
|
|
|
|
|
void tracing_sched_wakeup_trace(struct trace_array *tr,
|
|
|
|
struct trace_array_cpu *data,
|
|
|
|
struct task_struct *wakee,
|
|
|
|
struct task_struct *cur,
|
2008-10-01 19:14:09 +02:00
|
|
|
unsigned long flags, int pc);
|
2008-05-12 21:20:47 +02:00
|
|
|
void trace_special(struct trace_array *tr,
|
|
|
|
struct trace_array_cpu *data,
|
|
|
|
unsigned long arg1,
|
|
|
|
unsigned long arg2,
|
2008-10-01 19:14:09 +02:00
|
|
|
unsigned long arg3, int pc);
|
2008-05-12 21:20:49 +02:00
|
|
|
void trace_function(struct trace_array *tr,
|
|
|
|
struct trace_array_cpu *data,
|
|
|
|
unsigned long ip,
|
|
|
|
unsigned long parent_ip,
|
2008-10-01 19:14:09 +02:00
|
|
|
unsigned long flags, int pc);
|
2008-11-11 07:14:25 +01:00
|
|
|
void
|
|
|
|
trace_function_return(struct ftrace_retfunc *trace);
|
2008-05-12 21:20:42 +02:00
|
|
|
|
2008-11-25 09:24:15 +01:00
|
|
|
void trace_bts(struct trace_array *tr,
|
|
|
|
unsigned long from,
|
|
|
|
unsigned long to);
|
|
|
|
|
2008-05-22 17:49:22 +02:00
|
|
|
void tracing_start_cmdline_record(void);
|
|
|
|
void tracing_stop_cmdline_record(void);
|
2008-11-08 04:36:02 +01:00
|
|
|
void tracing_sched_switch_assign_trace(struct trace_array *tr);
|
|
|
|
void tracing_stop_sched_switch_record(void);
|
|
|
|
void tracing_start_sched_switch_record(void);
|
2008-05-12 21:20:42 +02:00
|
|
|
int register_tracer(struct tracer *type);
|
|
|
|
void unregister_tracer(struct tracer *type);
|
|
|
|
|
|
|
|
extern unsigned long nsecs_to_usecs(unsigned long nsecs);
|
|
|
|
|
|
|
|
extern unsigned long tracing_max_latency;
|
|
|
|
extern unsigned long tracing_thresh;
|
|
|
|
|
|
|
|
void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
|
|
|
|
void update_max_tr_single(struct trace_array *tr,
|
|
|
|
struct task_struct *tsk, int cpu);
|
|
|
|
|
2008-05-12 21:20:51 +02:00
|
|
|
extern cycle_t ftrace_now(int cpu);
|
2008-05-12 21:20:42 +02:00
|
|
|
|
2008-10-07 01:06:12 +02:00
|
|
|
#ifdef CONFIG_FUNCTION_TRACER
|
2008-07-11 02:58:10 +02:00
|
|
|
void tracing_start_function_trace(void);
|
|
|
|
void tracing_stop_function_trace(void);
|
|
|
|
#else
|
|
|
|
# define tracing_start_function_trace() do { } while (0)
|
|
|
|
# define tracing_stop_function_trace() do { } while (0)
|
|
|
|
#endif
|
|
|
|
|
2008-05-12 21:20:42 +02:00
|
|
|
#ifdef CONFIG_CONTEXT_SWITCH_TRACER
|
|
|
|
typedef void
|
|
|
|
(*tracer_switch_func_t)(void *private,
|
2008-05-12 21:21:10 +02:00
|
|
|
void *__rq,
|
2008-05-12 21:20:42 +02:00
|
|
|
struct task_struct *prev,
|
|
|
|
struct task_struct *next);
|
|
|
|
|
|
|
|
struct tracer_switch_ops {
|
|
|
|
tracer_switch_func_t func;
|
|
|
|
void *private;
|
|
|
|
struct tracer_switch_ops *next;
|
|
|
|
};
|
|
|
|
|
|
|
|
#endif /* CONFIG_CONTEXT_SWITCH_TRACER */
|
|
|
|
|
|
|
|
#ifdef CONFIG_DYNAMIC_FTRACE
|
|
|
|
extern unsigned long ftrace_update_tot_cnt;
|
2008-05-12 21:20:54 +02:00
|
|
|
#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
|
|
|
|
extern int DYN_FTRACE_TEST_NAME(void);
|
2008-05-12 21:20:42 +02:00
|
|
|
#endif
|
|
|
|
|
2008-05-12 21:20:44 +02:00
|
|
|
#ifdef CONFIG_FTRACE_STARTUP_TEST
|
|
|
|
extern int trace_selftest_startup_function(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
|
|
|
extern int trace_selftest_startup_irqsoff(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
|
|
|
extern int trace_selftest_startup_preemptoff(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
|
|
|
extern int trace_selftest_startup_preemptirqsoff(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
|
|
|
extern int trace_selftest_startup_wakeup(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
2008-09-19 12:06:43 +02:00
|
|
|
extern int trace_selftest_startup_nop(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
2008-05-12 21:20:44 +02:00
|
|
|
extern int trace_selftest_startup_sched_switch(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
2008-05-12 21:20:47 +02:00
|
|
|
extern int trace_selftest_startup_sysprof(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
2008-11-12 21:24:24 +01:00
|
|
|
extern int trace_selftest_startup_branch(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
2008-05-12 21:20:44 +02:00
|
|
|
#endif /* CONFIG_FTRACE_STARTUP_TEST */
|
|
|
|
|
2008-05-12 21:20:45 +02:00
|
|
|
extern void *head_page(struct trace_array_cpu *data);
|
2008-05-23 21:37:28 +02:00
|
|
|
extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
|
2008-09-16 21:02:27 +02:00
|
|
|
extern void trace_seq_print_cont(struct trace_seq *s,
|
|
|
|
struct trace_iterator *iter);
|
2008-11-11 07:14:25 +01:00
|
|
|
|
|
|
|
extern int
|
|
|
|
seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
|
|
|
|
unsigned long sym_flags);
|
2008-05-12 21:21:02 +02:00
|
|
|
extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
|
|
|
|
size_t cnt);
|
2008-05-23 21:37:28 +02:00
|
|
|
extern long ns2usecs(cycle_t nsec);
|
2008-09-16 20:58:24 +02:00
|
|
|
extern int trace_vprintk(unsigned long ip, const char *fmt, va_list args);
|
2008-05-12 21:20:45 +02:00
|
|
|
|
2008-05-12 21:20:52 +02:00
|
|
|
extern unsigned long trace_flags;
|
|
|
|
|
2008-11-11 07:14:25 +01:00
|
|
|
/* Standard output formatting function used for function return traces */
|
|
|
|
#ifdef CONFIG_FUNCTION_RET_TRACER
|
|
|
|
extern enum print_line_t print_return_function(struct trace_iterator *iter);
|
|
|
|
#else
|
|
|
|
static inline enum print_line_t
|
|
|
|
print_return_function(struct trace_iterator *iter)
|
|
|
|
{
|
|
|
|
return TRACE_TYPE_UNHANDLED;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2008-05-12 21:21:00 +02:00
|
|
|
/*
|
|
|
|
* trace_iterator_flags is an enumeration that defines bit
|
|
|
|
* positions into trace_flags that controls the output.
|
|
|
|
*
|
|
|
|
* NOTE: These bits must match the trace_options array in
|
|
|
|
* trace.c.
|
|
|
|
*/
|
2008-05-12 21:20:52 +02:00
|
|
|
enum trace_iterator_flags {
|
|
|
|
TRACE_ITER_PRINT_PARENT = 0x01,
|
|
|
|
TRACE_ITER_SYM_OFFSET = 0x02,
|
|
|
|
TRACE_ITER_SYM_ADDR = 0x04,
|
|
|
|
TRACE_ITER_VERBOSE = 0x08,
|
|
|
|
TRACE_ITER_RAW = 0x10,
|
|
|
|
TRACE_ITER_HEX = 0x20,
|
|
|
|
TRACE_ITER_BIN = 0x40,
|
|
|
|
TRACE_ITER_BLOCK = 0x80,
|
|
|
|
TRACE_ITER_STACKTRACE = 0x100,
|
2008-05-12 21:20:52 +02:00
|
|
|
TRACE_ITER_SCHED_TREE = 0x200,
|
2008-09-04 10:24:14 +02:00
|
|
|
TRACE_ITER_PRINTK = 0x400,
|
ftrace: function tracer with irqs disabled
Impact: disable interrupts during trace entry creation (as opposed to preempt)
To help with performance, I set the ftracer to not disable interrupts,
and only to disable preemption. If an interrupt occurred, it would not
be traced, because the function tracer protects itself from recursion.
This may be faster, but the trace output might miss some traces.
This patch makes the fuction trace disable interrupts, but it also
adds a runtime feature to disable preemption instead. It does this by
having two different tracer functions. When the function tracer is
enabled, it will check to see which version is requested (irqs disabled
or preemption disabled). Then it will use the corresponding function
as the tracer.
Irq disabling is the default behaviour, but if the user wants better
performance, with the chance of missing traces, then they can choose
the preempt disabled version.
Running hackbench 3 times with the irqs disabled and 3 times with
the preempt disabled function tracer yielded:
tracing type times entries recorded
------------ -------- ----------------
irq disabled 43.393 166433066
43.282 166172618
43.298 166256704
preempt disabled 38.969 159871710
38.943 159972935
39.325 161056510
Average:
irqs disabled: 43.324 166287462
preempt disabled: 39.079 160300385
preempt is 10.8 percent faster than irqs disabled.
I wrote a patch to count function trace recursion and reran hackbench.
With irq disabled: 1,150 times the function tracer did not trace due to
recursion.
with preempt disabled: 5,117,718 times.
The thousand times with irq disabled could be due to NMIs, or simply a case
where it called a function that was not protected by notrace.
But we also see that a large amount of the trace is lost with the
preempt version.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-04 05:15:57 +01:00
|
|
|
TRACE_ITER_PREEMPTONLY = 0x800,
|
2008-11-12 21:24:24 +01:00
|
|
|
TRACE_ITER_BRANCH = 0x1000,
|
2008-11-12 23:52:38 +01:00
|
|
|
TRACE_ITER_ANNOTATE = 0x2000,
|
2008-11-22 12:28:48 +01:00
|
|
|
TRACE_ITER_USERSTACKTRACE = 0x4000,
|
|
|
|
TRACE_ITER_SYM_USEROBJ = 0x8000
|
2008-05-12 21:20:52 +02:00
|
|
|
};
|
|
|
|
|
2008-11-11 07:14:25 +01:00
|
|
|
/*
|
|
|
|
* TRACE_ITER_SYM_MASK masks the options in trace_flags that
|
|
|
|
* control the output of kernel symbols.
|
|
|
|
*/
|
|
|
|
#define TRACE_ITER_SYM_MASK \
|
|
|
|
(TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)
|
|
|
|
|
2008-09-21 20:16:30 +02:00
|
|
|
extern struct tracer nop_trace;
|
|
|
|
|
2008-11-04 05:15:55 +01:00
|
|
|
/**
|
|
|
|
* ftrace_preempt_disable - disable preemption scheduler safe
|
|
|
|
*
|
|
|
|
* When tracing can happen inside the scheduler, there exists
|
|
|
|
* cases that the tracing might happen before the need_resched
|
|
|
|
* flag is checked. If this happens and the tracer calls
|
|
|
|
* preempt_enable (after a disable), a schedule might take place
|
|
|
|
* causing an infinite recursion.
|
|
|
|
*
|
|
|
|
* To prevent this, we read the need_recshed flag before
|
|
|
|
* disabling preemption. When we want to enable preemption we
|
|
|
|
* check the flag, if it is set, then we call preempt_enable_no_resched.
|
|
|
|
* Otherwise, we call preempt_enable.
|
|
|
|
*
|
|
|
|
* The rational for doing the above is that if need resched is set
|
|
|
|
* and we have yet to reschedule, we are either in an atomic location
|
|
|
|
* (where we do not need to check for scheduling) or we are inside
|
|
|
|
* the scheduler and do not want to resched.
|
|
|
|
*/
|
|
|
|
static inline int ftrace_preempt_disable(void)
|
|
|
|
{
|
|
|
|
int resched;
|
|
|
|
|
|
|
|
resched = need_resched();
|
|
|
|
preempt_disable_notrace();
|
|
|
|
|
|
|
|
return resched;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* ftrace_preempt_enable - enable preemption scheduler safe
|
|
|
|
* @resched: the return value from ftrace_preempt_disable
|
|
|
|
*
|
|
|
|
* This is a scheduler safe way to enable preemption and not miss
|
|
|
|
* any preemption checks. The disabled saved the state of preemption.
|
|
|
|
* If resched is set, then we were either inside an atomic or
|
|
|
|
* are inside the scheduler (we would have already scheduled
|
|
|
|
* otherwise). In this case, we do not want to call normal
|
|
|
|
* preempt_enable, but preempt_enable_no_resched instead.
|
|
|
|
*/
|
|
|
|
static inline void ftrace_preempt_enable(int resched)
|
|
|
|
{
|
|
|
|
if (resched)
|
|
|
|
preempt_enable_no_resched_notrace();
|
|
|
|
else
|
|
|
|
preempt_enable_notrace();
|
|
|
|
}
|
|
|
|
|
2008-11-12 21:24:24 +01:00
|
|
|
#ifdef CONFIG_BRANCH_TRACER
|
2008-11-12 21:24:24 +01:00
|
|
|
extern int enable_branch_tracing(struct trace_array *tr);
|
|
|
|
extern void disable_branch_tracing(void);
|
|
|
|
static inline int trace_branch_enable(struct trace_array *tr)
|
2008-11-12 06:14:40 +01:00
|
|
|
{
|
2008-11-12 21:24:24 +01:00
|
|
|
if (trace_flags & TRACE_ITER_BRANCH)
|
|
|
|
return enable_branch_tracing(tr);
|
2008-11-12 06:14:40 +01:00
|
|
|
return 0;
|
|
|
|
}
|
2008-11-12 21:24:24 +01:00
|
|
|
static inline void trace_branch_disable(void)
|
2008-11-12 06:14:40 +01:00
|
|
|
{
|
|
|
|
/* due to races, always disable */
|
2008-11-12 21:24:24 +01:00
|
|
|
disable_branch_tracing();
|
2008-11-12 06:14:40 +01:00
|
|
|
}
|
|
|
|
#else
|
2008-11-12 21:24:24 +01:00
|
|
|
static inline int trace_branch_enable(struct trace_array *tr)
|
2008-11-12 06:14:40 +01:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2008-11-12 21:24:24 +01:00
|
|
|
static inline void trace_branch_disable(void)
|
2008-11-12 06:14:40 +01:00
|
|
|
{
|
|
|
|
}
|
2008-11-12 21:24:24 +01:00
|
|
|
#endif /* CONFIG_BRANCH_TRACER */
|
2008-11-12 06:14:40 +01:00
|
|
|
|
2008-05-12 21:20:42 +02:00
|
|
|
#endif /* _LINUX_KERNEL_TRACE_H */
|