aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig24
-rw-r--r--kernel/trace/ftrace.c98
-rw-r--r--kernel/trace/trace.c123
-rw-r--r--kernel/trace/trace.h7
-rw-r--r--kernel/trace/trace_irqsoff.c19
-rw-r--r--kernel/trace/trace_sched_wakeup.c18
-rw-r--r--kernel/trace/trace_selftest.c9
-rw-r--r--kernel/trace/trace_stack.c76
-rw-r--r--kernel/trace/trace_stat.c2
-rw-r--r--kernel/trace/trace_syscalls.c21
10 files changed, 275 insertions, 122 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 2ad39e5..57c92f2 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -386,24 +386,28 @@ config KPROBE_EVENT
If you want to use perf tools, this option is strongly recommended.
config DYNAMIC_FTRACE
- bool "enable/disable ftrace tracepoints dynamically"
+ bool "enable/disable function tracing dynamically"
depends on FUNCTION_TRACER
depends on HAVE_DYNAMIC_FTRACE
default y
help
- This option will modify all the calls to ftrace dynamically
- (will patch them out of the binary image and replace them
- with a No-Op instruction) as they are called. A table is
- created to dynamically enable them again.
+ This option will modify all the calls to function tracing
+ dynamically (will patch them out of the binary image and
+ replace them with a No-Op instruction) on boot up. During
+ compile time, a table is made of all the locations that ftrace
+ can function trace, and this table is linked into the kernel
+ image. When this is enabled, functions can be individually
+ enabled, and the functions not enabled will not affect
+ performance of the system.
+
+ See the files in /sys/kernel/debug/tracing:
+ available_filter_functions
+ set_ftrace_filter
+ set_ftrace_notrace
This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
otherwise has native performance as long as no tracing is active.
- The changes to the code are done by a kernel thread that
- wakes up once a second and checks to see if any ftrace calls
- were made. If so, it runs stop_machine (stops all CPUS)
- and modifies the code to jump over the call to ftrace.
-
config FUNCTION_PROFILER
bool "Kernel function profiler"
depends on FUNCTION_TRACER
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index e96eee3..0d704b0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -548,7 +548,7 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
- for (i = 0; i < pages; i++) {
+ for (i = 1; i < pages; i++) {
pg->next = (void *)get_zeroed_page(GFP_KERNEL);
if (!pg->next)
goto out_free;
@@ -566,7 +566,6 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
free_page(tmp);
}
- free_page((unsigned long)stat->pages);
stat->pages = NULL;
stat->start = NULL;
@@ -934,6 +933,19 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
+static loff_t
+ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
+{
+ loff_t ret;
+
+ if (file->f_mode & FMODE_READ)
+ ret = seq_lseek(file, offset, whence);
+ else
+ file->f_pos = ret = 1;
+
+ return ret;
+}
+
#ifdef CONFIG_DYNAMIC_FTRACE
#ifndef CONFIG_FTRACE_MCOUNT_RECORD
@@ -2300,19 +2312,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
inode, file);
}
-static loff_t
-ftrace_regex_lseek(struct file *file, loff_t offset, int origin)
-{
- loff_t ret;
-
- if (file->f_mode & FMODE_READ)
- ret = seq_lseek(file, offset, origin);
- else
- file->f_pos = ret = 1;
-
- return ret;
-}
-
static int ftrace_match(char *str, char *regex, int len, int type)
{
int matched = 0;
@@ -2709,8 +2708,8 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
continue;
}
- hlist_del(&entry->node);
- call_rcu(&entry->rcu, ftrace_free_entry_rcu);
+ hlist_del_rcu(&entry->node);
+ call_rcu_sched(&entry->rcu, ftrace_free_entry_rcu);
}
}
__disable_ftrace_function_probe();
@@ -3119,7 +3118,7 @@ static const struct file_operations ftrace_filter_fops = {
.open = ftrace_filter_open,
.read = seq_read,
.write = ftrace_filter_write,
- .llseek = ftrace_regex_lseek,
+ .llseek = ftrace_filter_lseek,
.release = ftrace_regex_release,
};
@@ -3127,7 +3126,7 @@ static const struct file_operations ftrace_notrace_fops = {
.open = ftrace_notrace_open,
.read = seq_read,
.write = ftrace_notrace_write,
- .llseek = ftrace_regex_lseek,
+ .llseek = ftrace_filter_lseek,
.release = ftrace_regex_release,
};
@@ -3288,7 +3287,8 @@ out:
if (fail)
return -EINVAL;
- ftrace_graph_filter_enabled = 1;
+ ftrace_graph_filter_enabled = !!(*idx);
+
return 0;
}
@@ -3335,8 +3335,8 @@ static const struct file_operations ftrace_graph_fops = {
.open = ftrace_graph_open,
.read = seq_read,
.write = ftrace_graph_write,
+ .llseek = ftrace_filter_lseek,
.release = ftrace_graph_release,
- .llseek = seq_lseek,
};
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -3432,37 +3432,51 @@ static void ftrace_init_module(struct module *mod,
ftrace_process_locs(mod, start, end);
}
-static int ftrace_module_notify(struct notifier_block *self,
- unsigned long val, void *data)
+static int ftrace_module_notify_enter(struct notifier_block *self,
+ unsigned long val, void *data)
{
struct module *mod = data;
- switch (val) {
- case MODULE_STATE_COMING:
+ if (val == MODULE_STATE_COMING)
ftrace_init_module(mod, mod->ftrace_callsites,
mod->ftrace_callsites +
mod->num_ftrace_callsites);
- break;
- case MODULE_STATE_GOING:
+ return 0;
+}
+
+static int ftrace_module_notify_exit(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+
+ if (val == MODULE_STATE_GOING)
ftrace_release_mod(mod);
- break;
- }
return 0;
}
#else
-static int ftrace_module_notify(struct notifier_block *self,
- unsigned long val, void *data)
+static int ftrace_module_notify_enter(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ return 0;
+}
+static int ftrace_module_notify_exit(struct notifier_block *self,
+ unsigned long val, void *data)
{
return 0;
}
#endif /* CONFIG_MODULES */
-struct notifier_block ftrace_module_nb = {
- .notifier_call = ftrace_module_notify,
+struct notifier_block ftrace_module_enter_nb = {
+ .notifier_call = ftrace_module_notify_enter,
.priority = INT_MAX, /* Run before anything that can use kprobes */
};
+struct notifier_block ftrace_module_exit_nb = {
+ .notifier_call = ftrace_module_notify_exit,
+ .priority = INT_MIN, /* Run after anything that can remove kprobes */
+};
+
extern unsigned long __start_mcount_loc[];
extern unsigned long __stop_mcount_loc[];
@@ -3494,9 +3508,13 @@ void __init ftrace_init(void)
__start_mcount_loc,
__stop_mcount_loc);
- ret = register_module_notifier(&ftrace_module_nb);
+ ret = register_module_notifier(&ftrace_module_enter_nb);
+ if (ret)
+ pr_warning("Failed to register trace ftrace module enter notifier\n");
+
+ ret = register_module_notifier(&ftrace_module_exit_nb);
if (ret)
- pr_warning("Failed to register trace ftrace module notifier\n");
+ pr_warning("Failed to register trace ftrace module exit notifier\n");
set_ftrace_early_filters();
@@ -3804,7 +3822,7 @@ static const struct file_operations ftrace_pid_fops = {
.open = ftrace_pid_open,
.write = ftrace_pid_write,
.read = seq_read,
- .llseek = seq_lseek,
+ .llseek = ftrace_filter_lseek,
.release = ftrace_pid_release,
};
@@ -3916,12 +3934,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
ftrace_startup_sysctl();
/* we are starting ftrace again */
- if (ftrace_ops_list != &ftrace_list_end) {
- if (ftrace_ops_list->next == &ftrace_list_end)
- ftrace_trace_function = ftrace_ops_list->func;
- else
- ftrace_trace_function = ftrace_ops_list_func;
- }
+ if (ftrace_ops_list != &ftrace_list_end)
+ update_ftrace_function();
} else {
/* stopping ftrace calls (just send to ftrace_stub) */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 672a749..34d15ba 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -628,7 +628,15 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
max_data->pid = tsk->pid;
- max_data->uid = task_uid(tsk);
+ /*
+ * If tsk == current, then use current_uid(), as that does not use
+ * RCU. The irq tracer can be called out of RCU scope.
+ */
+ if (tsk == current)
+ max_data->uid = current_uid();
+ else
+ max_data->uid = task_uid(tsk);
+
max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
max_data->policy = tsk->policy;
max_data->rt_priority = tsk->rt_priority;
@@ -649,7 +657,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
void
update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
- struct ring_buffer *buf = tr->buffer;
+ struct ring_buffer *buf;
if (trace_stop_count)
return;
@@ -661,6 +669,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
}
arch_spin_lock(&ftrace_max_lock);
+ buf = tr->buffer;
tr->buffer = max_tr.buffer;
max_tr.buffer = buf;
@@ -2526,11 +2535,25 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
return -EINVAL;
}
-static void set_tracer_flags(unsigned int mask, int enabled)
+/* Some tracers require overwrite to stay enabled */
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
+{
+ if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set)
+ return -1;
+
+ return 0;
+}
+
+int set_tracer_flag(unsigned int mask, int enabled)
{
/* do nothing if flag is already set */
if (!!(trace_flags & mask) == !!enabled)
- return;
+ return 0;
+
+ /* Give the tracer a chance to approve the change */
+ if (current_trace->flag_changed)
+ if (current_trace->flag_changed(current_trace, mask, !!enabled))
+ return -EINVAL;
if (enabled)
trace_flags |= mask;
@@ -2542,6 +2565,8 @@ static void set_tracer_flags(unsigned int mask, int enabled)
if (mask == TRACE_ITER_OVERWRITE)
ring_buffer_change_overwrite(global_trace.buffer, enabled);
+
+ return 0;
}
static ssize_t
@@ -2551,7 +2576,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
char buf[64];
char *cmp;
int neg = 0;
- int ret;
+ int ret = -ENODEV;
int i;
if (cnt >= sizeof(buf))
@@ -2568,21 +2593,23 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
cmp += 2;
}
+ mutex_lock(&trace_types_lock);
+
for (i = 0; trace_options[i]; i++) {
if (strcmp(cmp, trace_options[i]) == 0) {
- set_tracer_flags(1 << i, !neg);
+ ret = set_tracer_flag(1 << i, !neg);
break;
}
}
/* If no option could be set, test the specific tracer options */
- if (!trace_options[i]) {
- mutex_lock(&trace_types_lock);
+ if (!trace_options[i])
ret = set_tracer_option(current_trace, cmp, neg);
- mutex_unlock(&trace_types_lock);
- if (ret)
- return ret;
- }
+
+ mutex_unlock(&trace_types_lock);
+
+ if (ret < 0)
+ return ret;
*ppos += cnt;
@@ -2880,6 +2907,9 @@ static int tracing_set_tracer(const char *buf)
goto out;
trace_branch_disable();
+
+ current_trace->enabled = false;
+
if (current_trace && current_trace->reset)
current_trace->reset(tr);
if (current_trace && current_trace->use_max_tr) {
@@ -2909,6 +2939,7 @@ static int tracing_set_tracer(const char *buf)
goto out;
}
+ current_trace->enabled = true;
trace_branch_enable(tr);
out:
mutex_unlock(&trace_types_lock);
@@ -3214,6 +3245,7 @@ waitagain:
memset(&iter->seq, 0,
sizeof(struct trace_iterator) -
offsetof(struct trace_iterator, seq));
+ cpumask_clear(iter->started);
iter->pos = -1;
trace_event_read_lock();
@@ -3332,6 +3364,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
.pages = pages_def,
.partial = partial_def,
.nr_pages = 0, /* This gets updated below. */
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &tracing_pipe_buf_ops,
.spd_release = tracing_spd_release_pipe,
@@ -3403,7 +3436,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
ret = splice_to_pipe(pipe, &spd);
out:
- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
return ret;
out_err:
@@ -3816,6 +3849,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
struct splice_pipe_desc spd = {
.pages = pages_def,
.partial = partial_def,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &buffer_pipe_buf_ops,
.spd_release = buffer_spd_release,
@@ -3904,7 +3938,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
}
ret = splice_to_pipe(pipe, &spd);
- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
out:
return ret;
}
@@ -4179,7 +4213,13 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (val != 0 && val != 1)
return -EINVAL;
- set_tracer_flags(1 << index, val);
+
+ mutex_lock(&trace_types_lock);
+ ret = set_tracer_flag(1 << index, val);
+ mutex_unlock(&trace_types_lock);
+
+ if (ret < 0)
+ return ret;
*ppos += cnt;
@@ -4331,6 +4371,8 @@ static __init int tracer_init_debugfs(void)
trace_access_lock_init();
d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
trace_create_file("tracing_enabled", 0644, d_tracer,
&global_trace, &tracing_ctrl_fops);
@@ -4458,30 +4500,32 @@ void trace_init_global_iter(struct trace_iterator *iter)
iter->cpu_file = TRACE_PIPE_ALL_CPU;
}
-static void
-__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
{
- static arch_spinlock_t ftrace_dump_lock =
- (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
/* use static because iter can be a bit big for the stack */
static struct trace_iterator iter;
+ static atomic_t dump_running;
unsigned int old_userobj;
- static int dump_ran;
unsigned long flags;
int cnt = 0, cpu;
- /* only one dump */
- local_irq_save(flags);
- arch_spin_lock(&ftrace_dump_lock);
- if (dump_ran)
- goto out;
-
- dump_ran = 1;
+ /* Only allow one dump user at a time. */
+ if (atomic_inc_return(&dump_running) != 1) {
+ atomic_dec(&dump_running);
+ return;
+ }
+ /*
+ * Always turn off tracing when we dump.
+ * We don't need to show trace output of what happens
+ * between multiple crashes.
+ *
+ * If the user does a sysrq-z, then they can re-enable
+ * tracing with echo 1 > tracing_on.
+ */
tracing_off();
- if (disable_tracing)
- ftrace_kill();
+ local_irq_save(flags);
trace_init_global_iter(&iter);
@@ -4552,26 +4596,15 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
printk(KERN_TRACE "---------------------------------\n");
out_enable:
- /* Re-enable tracing if requested */
- if (!disable_tracing) {
- trace_flags |= old_userobj;
+ trace_flags |= old_userobj;
- for_each_tracing_cpu(cpu) {
- atomic_dec(&iter.tr->data[cpu]->disabled);
- }
- tracing_on();
+ for_each_tracing_cpu(cpu) {
+ atomic_dec(&iter.tr->data[cpu]->disabled);
}
-
- out:
- arch_spin_unlock(&ftrace_dump_lock);
+ atomic_dec(&dump_running);
local_irq_restore(flags);
}
-
-/* By default: disable tracing after the dump */
-void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
-{
- __ftrace_dump(true, oops_dump_mode);
-}
+EXPORT_SYMBOL_GPL(ftrace_dump);
__init static int tracer_alloc_buffers(void)
{
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f807407..123ee28 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -271,10 +271,14 @@ struct tracer {
enum print_line_t (*print_line)(struct trace_iterator *iter);
/* If you handled the flag setting, return 0 */
int (*set_flag)(u32 old_flags, u32 bit, int set);
+ /* Return 0 if OK with change, else return non-zero */
+ int (*flag_changed)(struct tracer *tracer,
+ u32 mask, int set);
struct tracer *next;
struct tracer_flags *flags;
int print_max;
int use_max_tr;
+ bool enabled;
};
@@ -776,6 +780,9 @@ extern struct list_head ftrace_events;
extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
+int set_tracer_flag(unsigned int mask, int enabled);
+
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \
extern struct ftrace_event_call \
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index c77424b..984aad8 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -32,7 +32,7 @@ enum {
static int trace_type __read_mostly;
-static int save_lat_flag;
+static int save_flags;
static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
static int start_irqsoff_tracer(struct trace_array *tr, int graph);
@@ -544,8 +544,11 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
static void __irqsoff_tracer_init(struct trace_array *tr)
{
- save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
- trace_flags |= TRACE_ITER_LATENCY_FMT;
+ save_flags = trace_flags;
+
+ /* non overwrite screws up the latency tracers */
+ set_tracer_flag(TRACE_ITER_OVERWRITE, 1);
+ set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1);
tracing_max_latency = 0;
irqsoff_trace = tr;
@@ -559,10 +562,13 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
static void irqsoff_tracer_reset(struct trace_array *tr)
{
+ int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+ int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
stop_irqsoff_tracer(tr, is_graph());
- if (!save_lat_flag)
- trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+ set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag);
+ set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag);
}
static void irqsoff_tracer_start(struct trace_array *tr)
@@ -595,6 +601,7 @@ static struct tracer irqsoff_tracer __read_mostly =
.print_line = irqsoff_print_line,
.flags = &tracer_flags,
.set_flag = irqsoff_set_flag,
+ .flag_changed = trace_keep_overwrite,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_irqsoff,
#endif
@@ -628,6 +635,7 @@ static struct tracer preemptoff_tracer __read_mostly =
.print_line = irqsoff_print_line,
.flags = &tracer_flags,
.set_flag = irqsoff_set_flag,
+ .flag_changed = trace_keep_overwrite,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_preemptoff,
#endif
@@ -663,6 +671,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
.print_line = irqsoff_print_line,
.flags = &tracer_flags,
.set_flag = irqsoff_set_flag,
+ .flag_changed = trace_keep_overwrite,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_preemptirqsoff,
#endif
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index f029dd4..1beb25e 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -36,7 +36,7 @@ static void __wakeup_reset(struct trace_array *tr);
static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
static void wakeup_graph_return(struct ftrace_graph_ret *trace);
-static int save_lat_flag;
+static int save_flags;
#define TRACE_DISPLAY_GRAPH 1
@@ -526,8 +526,11 @@ static void stop_wakeup_tracer(struct trace_array *tr)
static int __wakeup_tracer_init(struct trace_array *tr)
{
- save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
- trace_flags |= TRACE_ITER_LATENCY_FMT;
+ save_flags = trace_flags;
+
+ /* non overwrite screws up the latency tracers */
+ set_tracer_flag(TRACE_ITER_OVERWRITE, 1);
+ set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1);
tracing_max_latency = 0;
wakeup_trace = tr;
@@ -549,12 +552,15 @@ static int wakeup_rt_tracer_init(struct trace_array *tr)
static void wakeup_tracer_reset(struct trace_array *tr)
{
+ int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+ int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
stop_wakeup_tracer(tr);
/* make sure we put back any tasks we are tracing */
wakeup_reset(tr);
- if (!save_lat_flag)
- trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+ set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag);
+ set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag);
}
static void wakeup_tracer_start(struct trace_array *tr)
@@ -580,6 +586,7 @@ static struct tracer wakeup_tracer __read_mostly =
.print_line = wakeup_print_line,
.flags = &tracer_flags,
.set_flag = wakeup_set_flag,
+ .flag_changed = trace_keep_overwrite,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_wakeup,
#endif
@@ -601,6 +608,7 @@ static struct tracer wakeup_rt_tracer __read_mostly =
.print_line = wakeup_print_line,
.flags = &tracer_flags,
.set_flag = wakeup_set_flag,
+ .flag_changed = trace_keep_overwrite,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_wakeup,
#endif
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 288541f..09fd98a 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -461,8 +461,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
/* Maximum number of functions to trace before diagnosing a hang */
#define GRAPH_MAX_FUNC_TEST 100000000
-static void
-__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode);
static unsigned int graph_hang_thresh;
/* Wrap the real function entry probe to avoid possible hanging */
@@ -472,8 +470,11 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
ftrace_graph_stop();
printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
- if (ftrace_dump_on_oops)
- __ftrace_dump(false, DUMP_ALL);
+ if (ftrace_dump_on_oops) {
+ ftrace_dump(DUMP_ALL);
+ /* ftrace_dump() disables tracing */
+ tracing_on();
+ }
return 0;
}
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index b0b53b8..2d43977 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -17,13 +17,24 @@
#define STACK_TRACE_ENTRIES 500
+#ifdef CC_USING_FENTRY
+# define fentry 1
+#else
+# define fentry 0
+#endif
+
static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
{ [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
+/*
+ * Reserve one entry for the passed in ip. This will allow
+ * us to remove most or all of the stack size overhead
+ * added by the stack tracer itself.
+ */
static struct stack_trace max_stack_trace = {
- .max_entries = STACK_TRACE_ENTRIES,
- .entries = stack_dump_trace,
+ .max_entries = STACK_TRACE_ENTRIES - 1,
+ .entries = &stack_dump_trace[1],
};
static unsigned long max_stack_size;
@@ -37,25 +48,34 @@ static DEFINE_MUTEX(stack_sysctl_mutex);
int stack_tracer_enabled;
static int last_stack_tracer_enabled;
-static inline void check_stack(void)
+static inline void
+check_stack(unsigned long ip, unsigned long *stack)
{
unsigned long this_size, flags;
unsigned long *p, *top, *start;
+ static int tracer_frame;
+ int frame_size = ACCESS_ONCE(tracer_frame);
int i;
- this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1);
+ this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
this_size = THREAD_SIZE - this_size;
+ /* Remove the frame of the tracer */
+ this_size -= frame_size;
if (this_size <= max_stack_size)
return;
/* we do not handle interrupt stacks yet */
- if (!object_is_on_stack(&this_size))
+ if (!object_is_on_stack(stack))
return;
local_irq_save(flags);
arch_spin_lock(&max_stack_lock);
+ /* In case another CPU set the tracer_frame on us */
+ if (unlikely(!frame_size))
+ this_size -= tracer_frame;
+
/* a race could have already updated it */
if (this_size <= max_stack_size)
goto out;
@@ -68,10 +88,18 @@ static inline void check_stack(void)
save_stack_trace(&max_stack_trace);
/*
+ * Add the passed in ip from the function tracer.
+ * Searching for this on the stack will skip over
+ * most of the overhead from the stack tracer itself.
+ */
+ stack_dump_trace[0] = ip;
+ max_stack_trace.nr_entries++;
+
+ /*
* Now find where in the stack these are.
*/
i = 0;
- start = &this_size;
+ start = stack;
top = (unsigned long *)
(((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
@@ -95,6 +123,18 @@ static inline void check_stack(void)
found = 1;
/* Start the search from here */
start = p + 1;
+ /*
+ * We do not want to show the overhead
+ * of the stack tracer stack in the
+ * max stack. If we haven't figured
+ * out what that is, then figure it out
+ * now.
+ */
+ if (unlikely(!tracer_frame) && i == 1) {
+ tracer_frame = (p - stack) *
+ sizeof(unsigned long);
+ max_stack_size -= tracer_frame;
+ }
}
}
@@ -110,6 +150,7 @@ static inline void check_stack(void)
static void
stack_trace_call(unsigned long ip, unsigned long parent_ip)
{
+ unsigned long stack;
int cpu;
if (unlikely(!ftrace_enabled || stack_trace_disabled))
@@ -122,7 +163,26 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
if (per_cpu(trace_active, cpu)++ != 0)
goto out;
- check_stack();
+ /*
+ * When fentry is used, the traced function does not get
+ * its stack frame set up, and we lose the parent.
+ * The ip is pretty useless because the function tracer
+ * was called before that function set up its stack frame.
+ * In this case, we use the parent ip.
+ *
+ * By adding the return address of either the parent ip
+ * or the current ip we can disregard most of the stack usage
+ * caused by the stack tracer itself.
+ *
+ * The function tracer always reports the address of where the
+ * mcount call was, but the stack will hold the return address.
+ */
+ if (fentry)
+ ip = parent_ip;
+ else
+ ip += MCOUNT_INSN_SIZE;
+
+ check_stack(ip, &stack);
out:
per_cpu(trace_active, cpu)--;
@@ -360,6 +420,8 @@ static __init int stack_trace_init(void)
struct dentry *d_tracer;
d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
trace_create_file("stack_max_size", 0644, d_tracer,
&max_stack_size, &stack_max_size_fops);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 96cffb2..847f88a 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -307,6 +307,8 @@ static int tracing_stat_init(void)
struct dentry *d_tracing;
d_tracing = tracing_init_dentry();
+ if (!d_tracing)
+ return 0;
stat_dir = debugfs_create_dir("trace_stat", d_tracing);
if (!stat_dir)
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index ee7b5a0..5819cd5 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -304,6 +304,8 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
struct ring_buffer *buffer;
int size;
int syscall_nr;
+ unsigned long irq_flags;
+ int pc;
syscall_nr = syscall_get_nr(current, regs);
if (syscall_nr < 0)
@@ -317,8 +319,11 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
+ local_save_flags(irq_flags);
+ pc = preempt_count();
+
event = trace_current_buffer_lock_reserve(&buffer,
- sys_data->enter_event->event.type, size, 0, 0);
+ sys_data->enter_event->event.type, size, irq_flags, pc);
if (!event)
return;
@@ -328,7 +333,8 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
if (!filter_current_check_discard(buffer, sys_data->enter_event,
entry, event))
- trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+ trace_current_buffer_unlock_commit(buffer, event,
+ irq_flags, pc);
}
void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
@@ -338,6 +344,8 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
struct ring_buffer_event *event;
struct ring_buffer *buffer;
int syscall_nr;
+ unsigned long irq_flags;
+ int pc;
syscall_nr = syscall_get_nr(current, regs);
if (syscall_nr < 0)
@@ -349,8 +357,12 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
if (!sys_data)
return;
+ local_save_flags(irq_flags);
+ pc = preempt_count();
+
event = trace_current_buffer_lock_reserve(&buffer,
- sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
+ sys_data->exit_event->event.type, sizeof(*entry),
+ irq_flags, pc);
if (!event)
return;
@@ -360,7 +372,8 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
if (!filter_current_check_discard(buffer, sys_data->exit_event,
entry, event))
- trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+ trace_current_buffer_unlock_commit(buffer, event,
+ irq_flags, pc);
}
int reg_event_syscall_enter(struct ftrace_event_call *call)
generated by cgit v1.1 at 2024-05-18 01:30:59 +0000