kernel_optimize_test/kernel/trace/trace_branch.c
Frederic Weisbecker e302cf3f96 tracing/branch-tracer: adapt to the stat tracing API
Impact: refactor the branch tracer

This patch adapts the branch tracer to the tracing API.

This is a proof of concept because the branch tracer implements two
"stat tracing" that were split in two files.

So I added an option to the branch tracer: stat_all_branch.
If it is set, then trace_stat will output all of the branches
entries stats. Otherwise, it will print the annotated branches.

Its is a kind of quick trick, waiting for a better solution.

By default, the annotated branches stat are sorted by incorrect branch
prediction percentage.

Ie:

 correct incorrect  %        Function                  File              Line
 ------- ---------  -        --------                  ----              ----
       0        1 100 native_smp_prepare_cpus        smpboot.c            1228
       0        1 100 hpet_rtc_timer_reinit          hpet.c               1057
       0    18032 100 sched_info_queued              sched_stats.h        223
       0      684 100 yield_task_fair                sched_fair.c         984
       0      282 100 pre_schedule_rt                sched_rt.c           1263
       0    13414 100 sched_info_dequeued            sched_stats.h        178
       0    21724 100 sched_info_switch              sched_stats.h        270
       0        1 100 get_signal_to_deliver          signal.c             1820
       0        8 100 __cancel_work_timer            workqueue.c          560
       0      212 100 verify_export_symbols          module.c             1509
       0       17 100 __rmqueue_fallback             page_alloc.c         793
       0       43 100 clear_page_mlock               internal.h           129
       0      124 100 try_to_unmap_anon              rmap.c               1021
       0       53 100 try_to_unmap_anon              rmap.c               1013
       0        6 100 vma_address                    rmap.c               232
       0     3301 100 try_to_unmap_file              rmap.c               1082
       0      466 100 try_to_unmap_file              rmap.c               1077
       0        1 100 mem_cgroup_create              memcontrol.c         1090
       0        3 100 inotify_find_update_watch      inotify.c            726
       2    30163  99 perf_counter_task_sched_out    perf_counter.c       385
       1     2935  99 percpu_free                    allocpercpu.c        138
    1544   297672  99 dentry_lru_del_init            dcache.c             153
       8     1074  99 input_pass_event               input.c              86
    1390    76781  98 mapping_unevictable            pagemap.h            50
     280     6665  95 pick_next_task_rt              sched_rt.c           889
     750     4826  86 next_pidmap                    pid.c                194
       2        8  80 blocking_notifier_chain_regist notifier.c           220
      36      130  78 ioremap_pte_range              ioremap.c            22
    1093     3247  74 IS_ERR                         err.h                34
    1023     2908  73 sched_slice                    sched_fair.c         445
      22       60  73 disk_put_part                  genhd.h              206
[...]

It enables a developer to quickly address the source of incorrect branch
predictions.  Note that this sorting would be better with a second sort on
the number of incorrect predictions.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-29 12:55:46 +01:00

412 lines
8.9 KiB
C

/*
* unlikely profiler
*
* Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
*/
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
#include <linux/irqflags.h>
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ftrace.h>
#include <linux/hash.h>
#include <linux/fs.h>
#include <asm/local.h>
#include "trace.h"
#include "trace_output.h"
static struct tracer branch_trace;
#ifdef CONFIG_BRANCH_TRACER
static int branch_tracing_enabled __read_mostly;
static DEFINE_MUTEX(branch_tracing_mutex);
static struct trace_array *branch_tracer;
static void
probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
{
struct trace_array *tr = branch_tracer;
struct ring_buffer_event *event;
struct trace_branch *entry;
unsigned long flags, irq_flags;
int cpu, pc;
const char *p;
/*
* I would love to save just the ftrace_likely_data pointer, but
* this code can also be used by modules. Ugly things can happen
* if the module is unloaded, and then we go and read the
* pointer. This is slower, but much safer.
*/
if (unlikely(!tr))
return;
local_irq_save(flags);
cpu = raw_smp_processor_id();
if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
goto out;
event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
&irq_flags);
if (!event)
goto out;
pc = preempt_count();
entry = ring_buffer_event_data(event);
tracing_generic_entry_update(&entry->ent, flags, pc);
entry->ent.type = TRACE_BRANCH;
/* Strip off the path, only save the file */
p = f->file + strlen(f->file);
while (p >= f->file && *p != '/')
p--;
p++;
strncpy(entry->func, f->func, TRACE_FUNC_SIZE);
strncpy(entry->file, p, TRACE_FILE_SIZE);
entry->func[TRACE_FUNC_SIZE] = 0;
entry->file[TRACE_FILE_SIZE] = 0;
entry->line = f->line;
entry->correct = val == expect;
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
out:
atomic_dec(&tr->data[cpu]->disabled);
local_irq_restore(flags);
}
static inline
void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
{
if (!branch_tracing_enabled)
return;
probe_likely_condition(f, val, expect);
}
int enable_branch_tracing(struct trace_array *tr)
{
int ret = 0;
mutex_lock(&branch_tracing_mutex);
branch_tracer = tr;
/*
* Must be seen before enabling. The reader is a condition
* where we do not need a matching rmb()
*/
smp_wmb();
branch_tracing_enabled++;
mutex_unlock(&branch_tracing_mutex);
return ret;
}
void disable_branch_tracing(void)
{
mutex_lock(&branch_tracing_mutex);
if (!branch_tracing_enabled)
goto out_unlock;
branch_tracing_enabled--;
out_unlock:
mutex_unlock(&branch_tracing_mutex);
}
static void start_branch_trace(struct trace_array *tr)
{
enable_branch_tracing(tr);
}
static void stop_branch_trace(struct trace_array *tr)
{
disable_branch_tracing();
}
static int branch_trace_init(struct trace_array *tr)
{
int cpu;
for_each_online_cpu(cpu)
tracing_reset(tr, cpu);
start_branch_trace(tr);
return 0;
}
static void branch_trace_reset(struct trace_array *tr)
{
stop_branch_trace(tr);
}
static int
trace_print_print(struct trace_seq *s, struct trace_entry *entry, int flags)
{
struct print_entry *field;
trace_assign_type(field, entry);
if (seq_print_ip_sym(s, field->ip, flags))
goto partial;
if (trace_seq_printf(s, ": %s", field->buf))
goto partial;
partial:
return TRACE_TYPE_PARTIAL_LINE;
}
static int
trace_branch_print(struct trace_seq *s, struct trace_entry *entry, int flags)
{
struct trace_branch *field;
trace_assign_type(field, entry);
if (trace_seq_printf(s, "[%s] %s:%s:%d\n",
field->correct ? " ok " : " MISS ",
field->func,
field->file,
field->line))
return TRACE_TYPE_PARTIAL_LINE;
return 0;
}
static struct trace_event trace_branch_event = {
.type = TRACE_BRANCH,
.trace = trace_branch_print,
.latency_trace = trace_branch_print,
.raw = trace_nop_print,
.hex = trace_nop_print,
.binary = trace_nop_print,
};
#else
static inline
void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
{
}
#endif /* CONFIG_BRANCH_TRACER */
void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect)
{
/*
* I would love to have a trace point here instead, but the
* trace point code is so inundated with unlikely and likely
* conditions that the recursive nightmare that exists is too
* much to try to get working. At least for now.
*/
trace_likely_condition(f, val, expect);
/* FIXME: Make this atomic! */
if (val == expect)
f->correct++;
else
f->incorrect++;
}
EXPORT_SYMBOL(ftrace_likely_update);
extern unsigned long __start_annotated_branch_profile[];
extern unsigned long __stop_annotated_branch_profile[];
static int annotated_branch_stat_headers(struct seq_file *m)
{
seq_printf(m, " correct incorrect %% ");
seq_printf(m, " Function "
" File Line\n"
" ------- --------- - "
" -------- "
" ---- ----\n");
return 0;
}
static inline long get_incorrect_percent(struct ftrace_branch_data *p)
{
long percent;
if (p->correct) {
percent = p->incorrect * 100;
percent /= p->correct + p->incorrect;
} else
percent = p->incorrect ? 100 : -1;
return percent;
}
static int branch_stat_show(struct seq_file *m, void *v)
{
struct ftrace_branch_data *p = v;
const char *f;
long percent;
/* Only print the file, not the path */
f = p->file + strlen(p->file);
while (f >= p->file && *f != '/')
f--;
f++;
/*
* The miss is overlayed on correct, and hit on incorrect.
*/
percent = get_incorrect_percent(p);
seq_printf(m, "%8lu %8lu ", p->correct, p->incorrect);
if (percent < 0)
seq_printf(m, " X ");
else
seq_printf(m, "%3ld ", percent);
seq_printf(m, "%-30.30s %-20.20s %d\n", p->func, f, p->line);
return 0;
}
static void *annotated_branch_stat_start(void)
{
return __start_annotated_branch_profile;
}
static void *
annotated_branch_stat_next(void *v, int idx)
{
struct ftrace_branch_data *p = v;
++p;
if ((void *)p >= (void *)__stop_annotated_branch_profile)
return NULL;
return p;
}
static int annotated_branch_stat_cmp(void *p1, void *p2)
{
struct ftrace_branch_data *a = p1;
struct ftrace_branch_data *b = p2;
long percent_a, percent_b;
percent_a = get_incorrect_percent(a);
percent_b = get_incorrect_percent(b);
if (percent_a < percent_b)
return -1;
if (percent_a > percent_b)
return 1;
else
return 0;
}
#ifdef CONFIG_PROFILE_ALL_BRANCHES
enum {
TRACE_BRANCH_OPT_ALL = 0x1
};
static struct tracer_opt branch_opts[] = {
{ TRACER_OPT(stat_all_branch, TRACE_BRANCH_OPT_ALL) },
{ }
};
static struct tracer_flags branch_flags = {
.val = 0,
.opts = branch_opts
};
extern unsigned long __start_branch_profile[];
extern unsigned long __stop_branch_profile[];
static int all_branch_stat_headers(struct seq_file *m)
{
seq_printf(m, " miss hit %% ");
seq_printf(m, " Function "
" File Line\n"
" ------- --------- - "
" -------- "
" ---- ----\n");
return 0;
}
static void *all_branch_stat_start(void)
{
return __start_branch_profile;
}
static void *
all_branch_stat_next(void *v, int idx)
{
struct ftrace_branch_data *p = v;
++p;
if ((void *)p >= (void *)__stop_branch_profile)
return NULL;
return p;
}
static int branch_set_flag(u32 old_flags, u32 bit, int set)
{
if (bit == TRACE_BRANCH_OPT_ALL) {
if (set) {
branch_trace.stat_headers = all_branch_stat_headers;
branch_trace.stat_start = all_branch_stat_start;
branch_trace.stat_next = all_branch_stat_next;
branch_trace.stat_cmp = NULL;
} else {
branch_trace.stat_headers =
annotated_branch_stat_headers;
branch_trace.stat_start = annotated_branch_stat_start;
branch_trace.stat_next = annotated_branch_stat_next;
branch_trace.stat_cmp = annotated_branch_stat_cmp;
}
init_tracer_stat(&branch_trace);
}
return 0;
}
#endif /* CONFIG_PROFILE_ALL_BRANCHES */
static struct tracer branch_trace __read_mostly =
{
.name = "branch",
#ifdef CONFIG_BRANCH_TRACER
.init = branch_trace_init,
.reset = branch_trace_reset,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_branch,
#endif /* CONFIG_FTRACE_SELFTEST */
#endif /* CONFIG_BRANCH_TRACER */
.stat_start = annotated_branch_stat_start,
.stat_next = annotated_branch_stat_next,
.stat_show = branch_stat_show,
.stat_headers = annotated_branch_stat_headers,
.stat_cmp = annotated_branch_stat_cmp,
#ifdef CONFIG_PROFILE_ALL_BRANCHES
.flags = &branch_flags,
.set_flag = branch_set_flag,
#endif
};
__init static int init_branch_trace(void)
{
#ifdef CONFIG_BRANCH_TRACER
int ret;
ret = register_ftrace_event(&trace_branch_event);
if (!ret) {
printk(KERN_WARNING "Warning: could not register branch events\n");
return 1;
}
#endif
return register_tracer(&branch_trace);
}
device_initcall(init_branch_trace);