From d2ccde1c8e90d38cee87a1b0309ad2827f3fd30d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 02:45:28 +0000
Subject: [PATCH] add boot partition size
---
kernel/kernel/trace/trace_events.c | 672 ++++++++++++++++++++++++++++++++++++++++---------------
1 files changed, 483 insertions(+), 189 deletions(-)
diff --git a/kernel/kernel/trace/trace_events.c b/kernel/kernel/trace/trace_events.c
index 1ca64a9..ca64598 100644
--- a/kernel/kernel/trace/trace_events.c
+++ b/kernel/kernel/trace/trace_events.c
@@ -12,6 +12,7 @@
#define pr_fmt(fmt) fmt
#include <linux/workqueue.h>
+#include <linux/security.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/tracefs.h>
@@ -23,6 +24,7 @@
#include <linux/delay.h>
#include <trace/events/sched.h>
+#include <trace/syscall.h>
#include <asm/setup.h>
@@ -36,6 +38,7 @@
LIST_HEAD(ftrace_events);
static LIST_HEAD(ftrace_generic_fields);
static LIST_HEAD(ftrace_common_fields);
+static bool eventdir_initialized;
#define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)
@@ -69,14 +72,6 @@
#define while_for_each_event_file() \
}
-
-static struct list_head *
-trace_get_fields(struct trace_event_call *event_call)
-{
- if (!event_call->class->get_fields)
- return &event_call->class->fields;
- return event_call->class->get_fields(event_call);
-}
static struct ftrace_event_field *
__find_event_field(struct list_head *head, char *name)
@@ -173,6 +168,7 @@
__generic_field(int, CPU, FILTER_CPU);
__generic_field(int, cpu, FILTER_CPU);
+ __generic_field(int, common_cpu, FILTER_CPU);
__generic_field(char *, COMM, FILTER_COMM);
__generic_field(char *, comm, FILTER_COMM);
@@ -188,6 +184,8 @@
__common_field(unsigned char, flags);
__common_field(unsigned char, preempt_count);
__common_field(int, pid);
+ __common_field(unsigned char, migrate_disable);
+ __common_field(unsigned char, preempt_lazy_count);
return ret;
}
@@ -238,13 +236,16 @@
{
struct trace_array *tr = trace_file->tr;
struct trace_array_cpu *data;
+ struct trace_pid_list *no_pid_list;
struct trace_pid_list *pid_list;
pid_list = rcu_dereference_raw(tr->filtered_pids);
- if (!pid_list)
+ no_pid_list = rcu_dereference_raw(tr->filtered_no_pids);
+
+ if (!pid_list && !no_pid_list)
return false;
- data = this_cpu_ptr(tr->trace_buffer.data);
+ data = this_cpu_ptr(tr->array_buffer.data);
return data->ignore_pid;
}
@@ -260,25 +261,23 @@
trace_event_ignore_this_pid(trace_file))
return NULL;
- local_save_flags(fbuffer->flags);
- fbuffer->pc = preempt_count();
/*
- * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables
+ * If CONFIG_PREEMPTION is enabled, then the tracepoint itself disables
* preemption (adding one to the preempt_count). Since we are
* interested in the preempt_count at the time the tracepoint was
* hit, we need to subtract one to offset the increment.
*/
- if (IS_ENABLED(CONFIG_PREEMPT))
- fbuffer->pc--;
+ fbuffer->trace_ctx = tracing_gen_ctx_dec();
fbuffer->trace_file = trace_file;
fbuffer->event =
trace_event_buffer_lock_reserve(&fbuffer->buffer, trace_file,
event_call->event.type, len,
- fbuffer->flags, fbuffer->pc);
+ fbuffer->trace_ctx);
if (!fbuffer->event)
return NULL;
+ fbuffer->regs = NULL;
fbuffer->entry = ring_buffer_event_data(fbuffer->event);
return fbuffer->entry;
}
@@ -515,6 +514,9 @@
pid_list = rcu_dereference_raw(tr->filtered_pids);
trace_filter_add_remove_task(pid_list, NULL, task);
+
+ pid_list = rcu_dereference_raw(tr->filtered_no_pids);
+ trace_filter_add_remove_task(pid_list, NULL, task);
}
static void
@@ -526,6 +528,9 @@
struct trace_array *tr = data;
pid_list = rcu_dereference_sched(tr->filtered_pids);
+ trace_filter_add_remove_task(pid_list, self, task);
+
+ pid_list = rcu_dereference_sched(tr->filtered_no_pids);
trace_filter_add_remove_task(pid_list, self, task);
}
@@ -549,13 +554,23 @@
struct task_struct *prev, struct task_struct *next)
{
struct trace_array *tr = data;
+ struct trace_pid_list *no_pid_list;
struct trace_pid_list *pid_list;
+ bool ret;
pid_list = rcu_dereference_sched(tr->filtered_pids);
+ no_pid_list = rcu_dereference_sched(tr->filtered_no_pids);
- this_cpu_write(tr->trace_buffer.data->ignore_pid,
- trace_ignore_this_task(pid_list, prev) &&
- trace_ignore_this_task(pid_list, next));
+ /*
+ * Sched switch is funny, as we only want to ignore it
+ * in the notrace case if both prev and next should be ignored.
+ */
+ ret = trace_ignore_this_task(NULL, no_pid_list, prev) &&
+ trace_ignore_this_task(NULL, no_pid_list, next);
+
+ this_cpu_write(tr->array_buffer.data->ignore_pid, ret ||
+ (trace_ignore_this_task(pid_list, NULL, prev) &&
+ trace_ignore_this_task(pid_list, NULL, next)));
}
static void
@@ -563,58 +578,55 @@
struct task_struct *prev, struct task_struct *next)
{
struct trace_array *tr = data;
+ struct trace_pid_list *no_pid_list;
struct trace_pid_list *pid_list;
pid_list = rcu_dereference_sched(tr->filtered_pids);
+ no_pid_list = rcu_dereference_sched(tr->filtered_no_pids);
- this_cpu_write(tr->trace_buffer.data->ignore_pid,
- trace_ignore_this_task(pid_list, next));
+ this_cpu_write(tr->array_buffer.data->ignore_pid,
+ trace_ignore_this_task(pid_list, no_pid_list, next));
}
static void
event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task)
{
struct trace_array *tr = data;
+ struct trace_pid_list *no_pid_list;
struct trace_pid_list *pid_list;
/* Nothing to do if we are already tracing */
- if (!this_cpu_read(tr->trace_buffer.data->ignore_pid))
+ if (!this_cpu_read(tr->array_buffer.data->ignore_pid))
return;
pid_list = rcu_dereference_sched(tr->filtered_pids);
+ no_pid_list = rcu_dereference_sched(tr->filtered_no_pids);
- this_cpu_write(tr->trace_buffer.data->ignore_pid,
- trace_ignore_this_task(pid_list, task));
+ this_cpu_write(tr->array_buffer.data->ignore_pid,
+ trace_ignore_this_task(pid_list, no_pid_list, task));
}
static void
event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task)
{
struct trace_array *tr = data;
+ struct trace_pid_list *no_pid_list;
struct trace_pid_list *pid_list;
/* Nothing to do if we are not tracing */
- if (this_cpu_read(tr->trace_buffer.data->ignore_pid))
+ if (this_cpu_read(tr->array_buffer.data->ignore_pid))
return;
pid_list = rcu_dereference_sched(tr->filtered_pids);
+ no_pid_list = rcu_dereference_sched(tr->filtered_no_pids);
/* Set tracing if current is enabled */
- this_cpu_write(tr->trace_buffer.data->ignore_pid,
- trace_ignore_this_task(pid_list, current));
+ this_cpu_write(tr->array_buffer.data->ignore_pid,
+ trace_ignore_this_task(pid_list, no_pid_list, current));
}
-static void __ftrace_clear_event_pids(struct trace_array *tr)
+static void unregister_pid_events(struct trace_array *tr)
{
- struct trace_pid_list *pid_list;
- struct trace_event_file *file;
- int cpu;
-
- pid_list = rcu_dereference_protected(tr->filtered_pids,
- lockdep_is_held(&event_mutex));
- if (!pid_list)
- return;
-
unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_pre, tr);
unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_post, tr);
@@ -626,26 +638,55 @@
unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_pre, tr);
unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_post, tr);
+}
- list_for_each_entry(file, &tr->events, list) {
- clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
+static void __ftrace_clear_event_pids(struct trace_array *tr, int type)
+{
+ struct trace_pid_list *pid_list;
+ struct trace_pid_list *no_pid_list;
+ struct trace_event_file *file;
+ int cpu;
+
+ pid_list = rcu_dereference_protected(tr->filtered_pids,
+ lockdep_is_held(&event_mutex));
+ no_pid_list = rcu_dereference_protected(tr->filtered_no_pids,
+ lockdep_is_held(&event_mutex));
+
+ /* Make sure there's something to do */
+ if (!pid_type_enabled(type, pid_list, no_pid_list))
+ return;
+
+ if (!still_need_pid_events(type, pid_list, no_pid_list)) {
+ unregister_pid_events(tr);
+
+ list_for_each_entry(file, &tr->events, list) {
+ clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
+ }
+
+ for_each_possible_cpu(cpu)
+ per_cpu_ptr(tr->array_buffer.data, cpu)->ignore_pid = false;
}
- for_each_possible_cpu(cpu)
- per_cpu_ptr(tr->trace_buffer.data, cpu)->ignore_pid = false;
+ if (type & TRACE_PIDS)
+ rcu_assign_pointer(tr->filtered_pids, NULL);
- rcu_assign_pointer(tr->filtered_pids, NULL);
+ if (type & TRACE_NO_PIDS)
+ rcu_assign_pointer(tr->filtered_no_pids, NULL);
/* Wait till all users are no longer using pid filtering */
tracepoint_synchronize_unregister();
- trace_free_pid_list(pid_list);
+ if ((type & TRACE_PIDS) && pid_list)
+ trace_free_pid_list(pid_list);
+
+ if ((type & TRACE_NO_PIDS) && no_pid_list)
+ trace_free_pid_list(no_pid_list);
}
-static void ftrace_clear_event_pids(struct trace_array *tr)
+static void ftrace_clear_event_pids(struct trace_array *tr, int type)
{
mutex_lock(&event_mutex);
- __ftrace_clear_event_pids(tr);
+ __ftrace_clear_event_pids(tr, type);
mutex_unlock(&event_mutex);
}
@@ -704,7 +745,7 @@
return;
if (!--dir->nr_events) {
- tracefs_remove_recursive(dir->entry);
+ tracefs_remove(dir->entry);
list_del(&dir->list);
__put_system_dir(dir);
}
@@ -723,7 +764,7 @@
}
spin_unlock(&dir->d_lock);
- tracefs_remove_recursive(dir);
+ tracefs_remove(dir);
}
list_del(&file->list);
@@ -795,7 +836,7 @@
return ret;
}
-static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
+int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
{
char *event = NULL, *sub = NULL, *match;
int ret;
@@ -857,6 +898,32 @@
return __ftrace_set_clr_event(tr, NULL, system, event, set);
}
EXPORT_SYMBOL_GPL(trace_set_clr_event);
+
+/**
+ * trace_array_set_clr_event - enable or disable an event for a trace array.
+ * @tr: concerned trace array.
+ * @system: system name to match (NULL for any system)
+ * @event: event name to match (NULL for all events, within system)
+ * @enable: true to enable, false to disable
+ *
+ * This is a way for other parts of the kernel to enable or disable
+ * event recording.
+ *
+ * Returns 0 on success, -EINVAL if the parameters do not match any
+ * registered events.
+ */
+int trace_array_set_clr_event(struct trace_array *tr, const char *system,
+ const char *event, bool enable)
+{
+ int set;
+
+ if (!tr)
+ return -ENOENT;
+
+ set = (enable == true) ? 1 : 0;
+ return __ftrace_set_clr_event(tr, NULL, system, event, set);
+}
+EXPORT_SYMBOL_GPL(trace_array_set_clr_event);
/* 128 should be much more than enough */
#define EVENT_BUF_SIZE 127
@@ -992,15 +1059,32 @@
}
static void *
-p_next(struct seq_file *m, void *v, loff_t *pos)
+__next(struct seq_file *m, void *v, loff_t *pos, int type)
{
struct trace_array *tr = m->private;
- struct trace_pid_list *pid_list = rcu_dereference_sched(tr->filtered_pids);
+ struct trace_pid_list *pid_list;
+
+ if (type == TRACE_PIDS)
+ pid_list = rcu_dereference_sched(tr->filtered_pids);
+ else
+ pid_list = rcu_dereference_sched(tr->filtered_no_pids);
return trace_pid_next(pid_list, v, pos);
}
-static void *p_start(struct seq_file *m, loff_t *pos)
+static void *
+p_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ return __next(m, v, pos, TRACE_PIDS);
+}
+
+static void *
+np_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ return __next(m, v, pos, TRACE_NO_PIDS);
+}
+
+static void *__start(struct seq_file *m, loff_t *pos, int type)
__acquires(RCU)
{
struct trace_pid_list *pid_list;
@@ -1015,12 +1099,27 @@
mutex_lock(&event_mutex);
rcu_read_lock_sched();
- pid_list = rcu_dereference_sched(tr->filtered_pids);
+ if (type == TRACE_PIDS)
+ pid_list = rcu_dereference_sched(tr->filtered_pids);
+ else
+ pid_list = rcu_dereference_sched(tr->filtered_no_pids);
if (!pid_list)
return NULL;
return trace_pid_start(pid_list, pos);
+}
+
+static void *p_start(struct seq_file *m, loff_t *pos)
+ __acquires(RCU)
+{
+ return __start(m, pos, TRACE_PIDS);
+}
+
+static void *np_start(struct seq_file *m, loff_t *pos)
+ __acquires(RCU)
+{
+ return __start(m, pos, TRACE_NO_PIDS);
}
static void p_stop(struct seq_file *m, void *p)
@@ -1254,7 +1353,7 @@
*/
array_descriptor = strchr(field->type, '[');
- if (!strncmp(field->type, "__data_loc", 10))
+ if (str_has_prefix(field->type, "__data_loc"))
array_descriptor = NULL;
if (!array_descriptor)
@@ -1303,6 +1402,8 @@
{
struct seq_file *m;
int ret;
+
+ /* Do we want to hide event format files on tracefs lockdown? */
ret = seq_open(file, &trace_format_seq_ops);
if (ret < 0)
@@ -1450,28 +1551,17 @@
struct trace_array *tr = inode->i_private;
int ret;
- if (tracing_is_disabled())
- return -ENODEV;
-
- if (trace_array_get(tr) < 0)
- return -ENODEV;
-
/* Make a temporary dir that has no system but points to tr */
dir = kzalloc(sizeof(*dir), GFP_KERNEL);
- if (!dir) {
- trace_array_put(tr);
+ if (!dir)
return -ENOMEM;
- }
- dir->tr = tr;
-
- ret = tracing_open_generic(inode, filp);
+ ret = tracing_open_generic_tr(inode, filp);
if (ret < 0) {
- trace_array_put(tr);
kfree(dir);
return ret;
}
-
+ dir->tr = tr;
filp->private_data = dir;
return 0;
@@ -1577,6 +1667,7 @@
{
struct trace_array *tr = data;
struct trace_pid_list *pid_list;
+ struct trace_pid_list *no_pid_list;
/*
* This function is called by on_each_cpu() while the
@@ -1584,18 +1675,50 @@
*/
pid_list = rcu_dereference_protected(tr->filtered_pids,
mutex_is_locked(&event_mutex));
+ no_pid_list = rcu_dereference_protected(tr->filtered_no_pids,
+ mutex_is_locked(&event_mutex));
- this_cpu_write(tr->trace_buffer.data->ignore_pid,
- trace_ignore_this_task(pid_list, current));
+ this_cpu_write(tr->array_buffer.data->ignore_pid,
+ trace_ignore_this_task(pid_list, no_pid_list, current));
+}
+
+static void register_pid_events(struct trace_array *tr)
+{
+ /*
+ * Register a probe that is called before all other probes
+ * to set ignore_pid if next or prev do not match.
+ * Register a probe this is called after all other probes
+ * to only keep ignore_pid set if next pid matches.
+ */
+ register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_pre,
+ tr, INT_MAX);
+ register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_post,
+ tr, 0);
+
+ register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre,
+ tr, INT_MAX);
+ register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post,
+ tr, 0);
+
+ register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre,
+ tr, INT_MAX);
+ register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post,
+ tr, 0);
+
+ register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre,
+ tr, INT_MAX);
+ register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post,
+ tr, 0);
}
static ssize_t
-ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
- size_t cnt, loff_t *ppos)
+event_pid_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos, int type)
{
struct seq_file *m = filp->private_data;
struct trace_array *tr = m->private;
struct trace_pid_list *filtered_pids = NULL;
+ struct trace_pid_list *other_pids = NULL;
struct trace_pid_list *pid_list;
struct trace_event_file *file;
ssize_t ret;
@@ -1609,14 +1732,26 @@
mutex_lock(&event_mutex);
- filtered_pids = rcu_dereference_protected(tr->filtered_pids,
- lockdep_is_held(&event_mutex));
+ if (type == TRACE_PIDS) {
+ filtered_pids = rcu_dereference_protected(tr->filtered_pids,
+ lockdep_is_held(&event_mutex));
+ other_pids = rcu_dereference_protected(tr->filtered_no_pids,
+ lockdep_is_held(&event_mutex));
+ } else {
+ filtered_pids = rcu_dereference_protected(tr->filtered_no_pids,
+ lockdep_is_held(&event_mutex));
+ other_pids = rcu_dereference_protected(tr->filtered_pids,
+ lockdep_is_held(&event_mutex));
+ }
ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
if (ret < 0)
goto out;
- rcu_assign_pointer(tr->filtered_pids, pid_list);
+ if (type == TRACE_PIDS)
+ rcu_assign_pointer(tr->filtered_pids, pid_list);
+ else
+ rcu_assign_pointer(tr->filtered_no_pids, pid_list);
list_for_each_entry(file, &tr->events, list) {
set_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
@@ -1625,32 +1760,8 @@
if (filtered_pids) {
tracepoint_synchronize_unregister();
trace_free_pid_list(filtered_pids);
- } else if (pid_list) {
- /*
- * Register a probe that is called before all other probes
- * to set ignore_pid if next or prev do not match.
- * Register a probe this is called after all other probes
- * to only keep ignore_pid set if next pid matches.
- */
- register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_pre,
- tr, INT_MAX);
- register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_post,
- tr, 0);
-
- register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre,
- tr, INT_MAX);
- register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post,
- tr, 0);
-
- register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre,
- tr, INT_MAX);
- register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post,
- tr, 0);
-
- register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre,
- tr, INT_MAX);
- register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post,
- tr, 0);
+ } else if (pid_list && !other_pids) {
+ register_pid_events(tr);
}
/*
@@ -1669,9 +1780,24 @@
return ret;
}
+static ssize_t
+ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ return event_pid_write(filp, ubuf, cnt, ppos, TRACE_PIDS);
+}
+
+static ssize_t
+ftrace_event_npid_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ return event_pid_write(filp, ubuf, cnt, ppos, TRACE_NO_PIDS);
+}
+
static int ftrace_event_avail_open(struct inode *inode, struct file *file);
static int ftrace_event_set_open(struct inode *inode, struct file *file);
static int ftrace_event_set_pid_open(struct inode *inode, struct file *file);
+static int ftrace_event_set_npid_open(struct inode *inode, struct file *file);
static int ftrace_event_release(struct inode *inode, struct file *file);
static const struct seq_operations show_event_seq_ops = {
@@ -1695,6 +1821,13 @@
.stop = p_stop,
};
+static const struct seq_operations show_set_no_pid_seq_ops = {
+ .start = np_start,
+ .next = np_next,
+ .show = trace_pid_show,
+ .stop = p_stop,
+};
+
static const struct file_operations ftrace_avail_fops = {
.open = ftrace_event_avail_open,
.read = seq_read,
@@ -1714,6 +1847,14 @@
.open = ftrace_event_set_pid_open,
.read = seq_read,
.write = ftrace_event_pid_write,
+ .llseek = seq_lseek,
+ .release = ftrace_event_release,
+};
+
+static const struct file_operations ftrace_set_event_notrace_pid_fops = {
+ .open = ftrace_event_set_npid_open,
+ .read = seq_read,
+ .write = ftrace_event_npid_write,
.llseek = seq_lseek,
.release = ftrace_event_release,
};
@@ -1781,6 +1922,10 @@
struct seq_file *m;
int ret;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
ret = seq_open(file, seq_ops);
if (ret < 0)
return ret;
@@ -1805,6 +1950,7 @@
{
const struct seq_operations *seq_ops = &show_event_seq_ops;
+ /* Checks for tracefs lockdown */
return ftrace_event_open(inode, file, seq_ops);
}
@@ -1815,8 +1961,9 @@
struct trace_array *tr = inode->i_private;
int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC))
@@ -1835,12 +1982,34 @@
struct trace_array *tr = inode->i_private;
int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC))
- ftrace_clear_event_pids(tr);
+ ftrace_clear_event_pids(tr, TRACE_PIDS);
+
+ ret = ftrace_event_open(inode, file, seq_ops);
+ if (ret < 0)
+ trace_array_put(tr);
+ return ret;
+}
+
+static int
+ftrace_event_set_npid_open(struct inode *inode, struct file *file)
+{
+ const struct seq_operations *seq_ops = &show_set_no_pid_seq_ops;
+ struct trace_array *tr = inode->i_private;
+ int ret;
+
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
+
+ if ((file->f_mode & FMODE_WRITE) &&
+ (file->f_flags & O_TRUNC))
+ ftrace_clear_event_pids(tr, TRACE_NO_PIDS);
ret = ftrace_event_open(inode, file, seq_ops);
if (ret < 0)
@@ -1957,11 +2126,47 @@
}
static int
+event_define_fields(struct trace_event_call *call)
+{
+ struct list_head *head;
+ int ret = 0;
+
+ /*
+ * Other events may have the same class. Only update
+ * the fields if they are not already defined.
+ */
+ head = trace_get_fields(call);
+ if (list_empty(head)) {
+ struct trace_event_fields *field = call->class->fields_array;
+ unsigned int offset = sizeof(struct trace_entry);
+
+ for (; field->type; field++) {
+ if (field->type == TRACE_FUNCTION_TYPE) {
+ field->define_fields(call);
+ break;
+ }
+
+ offset = ALIGN(offset, field->align);
+ ret = trace_define_field(call, field->type, field->name,
+ offset, field->size,
+ field->is_signed, field->filter_type);
+ if (WARN_ON_ONCE(ret)) {
+ pr_err("error code is %d\n", ret);
+ break;
+ }
+
+ offset += field->size;
+ }
+ }
+
+ return ret;
+}
+
+static int
event_create_dir(struct dentry *parent, struct trace_event_file *file)
{
struct trace_event_call *call = file->event_call;
struct trace_array *tr = file->tr;
- struct list_head *head;
struct dentry *d_events;
const char *name;
int ret;
@@ -1995,18 +2200,10 @@
&ftrace_event_id_fops);
#endif
- /*
- * Other events may have the same class. Only update
- * the fields if they are not already defined.
- */
- head = trace_get_fields(call);
- if (list_empty(head)) {
- ret = call->class->define_fields(call);
- if (ret < 0) {
- pr_warn("Could not initialize trace point events/%s\n",
- name);
- return -1;
- }
+ ret = event_define_fields(call);
+ if (ret < 0) {
+ pr_warn("Could not initialize trace point events/%s\n", name);
+ return ret;
}
/*
@@ -2025,8 +2222,18 @@
trace_create_file("hist", 0444, file->dir, file,
&event_hist_fops);
#endif
+#ifdef CONFIG_HIST_TRIGGERS_DEBUG
+ trace_create_file("hist_debug", 0444, file->dir, file,
+ &event_hist_debug_fops);
+#endif
trace_create_file("format", 0444, file->dir, call,
&ftrace_event_format_fops);
+
+#ifdef CONFIG_TRACE_EVENT_INJECT
+ if (call->event.type && call->class->reg)
+ trace_create_file("inject", 0200, file->dir, file,
+ &event_inject_fops);
+#endif
return 0;
}
@@ -2255,6 +2462,7 @@
trace_create_new_event(struct trace_event_call *call,
struct trace_array *tr)
{
+ struct trace_pid_list *no_pid_list;
struct trace_pid_list *pid_list;
struct trace_event_file *file;
@@ -2264,8 +2472,10 @@
pid_list = rcu_dereference_protected(tr->filtered_pids,
lockdep_is_held(&event_mutex));
+ no_pid_list = rcu_dereference_protected(tr->filtered_no_pids,
+ lockdep_is_held(&event_mutex));
- if (pid_list)
+ if (pid_list || no_pid_list)
file->flags |= EVENT_FILE_FL_PID_FILTER;
file->event_call = call;
@@ -2288,7 +2498,10 @@
if (!file)
return -ENOMEM;
- return event_create_dir(tr->event_dir, file);
+ if (eventdir_initialized)
+ return event_create_dir(tr->event_dir, file);
+ else
+ return event_define_fields(call);
}
/*
@@ -2296,7 +2509,7 @@
* for enabling events at boot. We want to enable events before
* the filesystem is initialized.
*/
-static __init int
+static int
__trace_early_add_new_event(struct trace_event_call *call,
struct trace_array *tr)
{
@@ -2306,13 +2519,14 @@
if (!file)
return -ENOMEM;
- return 0;
+ return event_define_fields(call);
}
struct ftrace_module_file_ops;
static void __add_event_to_tracers(struct trace_event_call *call);
-int trace_add_event_call_nolock(struct trace_event_call *call)
+/* Add an additional event_call dynamically */
+int trace_add_event_call(struct trace_event_call *call)
{
int ret;
lockdep_assert_held(&event_mutex);
@@ -2324,17 +2538,6 @@
__add_event_to_tracers(call);
mutex_unlock(&trace_types_lock);
- return ret;
-}
-
-/* Add an additional event_call dynamically */
-int trace_add_event_call(struct trace_event_call *call)
-{
- int ret;
-
- mutex_lock(&event_mutex);
- ret = trace_add_event_call_nolock(call);
- mutex_unlock(&event_mutex);
return ret;
}
@@ -2368,7 +2571,10 @@
* TRACE_REG_UNREGISTER.
*/
if (file->flags & EVENT_FILE_FL_ENABLED)
- return -EBUSY;
+ goto busy;
+
+ if (file->flags & EVENT_FILE_FL_WAS_ENABLED)
+ tr->clear_trace = true;
/*
* The do_for_each_event_file_safe() is
* a double loop. After finding the call for this
@@ -2381,10 +2587,16 @@
__trace_remove_event_call(call);
return 0;
+ busy:
+ /* No need to clear the trace now */
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ tr->clear_trace = false;
+ }
+ return -EBUSY;
}
-/* no event_mutex version */
-int trace_remove_event_call_nolock(struct trace_event_call *call)
+/* Remove an event_call */
+int trace_remove_event_call(struct trace_event_call *call)
{
int ret;
@@ -2395,18 +2607,6 @@
ret = probe_remove_event_call(call);
up_write(&trace_event_sem);
mutex_unlock(&trace_types_lock);
-
- return ret;
-}
-
-/* Remove an event_call */
-int trace_remove_event_call(struct trace_event_call *call)
-{
- int ret;
-
- mutex_lock(&event_mutex);
- ret = trace_remove_event_call_nolock(call);
- mutex_unlock(&event_mutex);
return ret;
}
@@ -2481,7 +2681,7 @@
mutex_unlock(&trace_types_lock);
mutex_unlock(&event_mutex);
- return 0;
+ return NOTIFY_OK;
}
static struct notifier_block trace_module_nb = {
@@ -2541,6 +2741,91 @@
return file;
}
+
+/**
+ * trace_get_event_file - Find and return a trace event file
+ * @instance: The name of the trace instance containing the event
+ * @system: The name of the system containing the event
+ * @event: The name of the event
+ *
+ * Return a trace event file given the trace instance name, trace
+ * system, and trace event name. If the instance name is NULL, it
+ * refers to the top-level trace array.
+ *
+ * This function will look it up and return it if found, after calling
+ * trace_array_get() to prevent the instance from going away, and
+ * increment the event's module refcount to prevent it from being
+ * removed.
+ *
+ * To release the file, call trace_put_event_file(), which will call
+ * trace_array_put() and decrement the event's module refcount.
+ *
+ * Return: The trace event on success, ERR_PTR otherwise.
+ */
+struct trace_event_file *trace_get_event_file(const char *instance,
+ const char *system,
+ const char *event)
+{
+ struct trace_array *tr = top_trace_array();
+ struct trace_event_file *file = NULL;
+ int ret = -EINVAL;
+
+ if (instance) {
+ tr = trace_array_find_get(instance);
+ if (!tr)
+ return ERR_PTR(-ENOENT);
+ } else {
+ ret = trace_array_get(tr);
+ if (ret)
+ return ERR_PTR(ret);
+ }
+
+ mutex_lock(&event_mutex);
+
+ file = find_event_file(tr, system, event);
+ if (!file) {
+ trace_array_put(tr);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* Don't let event modules unload while in use */
+ ret = try_module_get(file->event_call->mod);
+ if (!ret) {
+ trace_array_put(tr);
+ ret = -EBUSY;
+ goto out;
+ }
+
+ ret = 0;
+ out:
+ mutex_unlock(&event_mutex);
+
+ if (ret)
+ file = ERR_PTR(ret);
+
+ return file;
+}
+EXPORT_SYMBOL_GPL(trace_get_event_file);
+
+/**
+ * trace_put_event_file - Release a file from trace_get_event_file()
+ * @file: The trace event file
+ *
+ * If a file was retrieved using trace_get_event_file(), this should
+ * be called when it's no longer needed. It will cancel the previous
+ * trace_array_get() called by that function, and decrement the
+ * event's module refcount.
+ */
+void trace_put_event_file(struct trace_event_file *file)
+{
+ mutex_lock(&event_mutex);
+ module_put(file->event_call->mod);
+ mutex_unlock(&event_mutex);
+
+ trace_array_put(file->tr);
+}
+EXPORT_SYMBOL_GPL(trace_put_event_file);
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -2866,14 +3151,13 @@
#endif /* CONFIG_DYNAMIC_FTRACE */
/*
- * The top level array has already had its trace_event_file
- * descriptors created in order to allow for early events to
- * be recorded. This function is called after the tracefs has been
- * initialized, and we now have to create the files associated
- * to the events.
+ * The top level array and trace arrays created by boot-time tracing
+ * have already had its trace_event_file descriptors created in order
+ * to allow for early events to be recorded.
+ * This function is called after the tracefs has been initialized,
+ * and we now have to create the files associated to the events.
*/
-static __init void
-__trace_early_add_event_dirs(struct trace_array *tr)
+static void __trace_early_add_event_dirs(struct trace_array *tr)
{
struct trace_event_file *file;
int ret;
@@ -2888,13 +3172,12 @@
}
/*
- * For early boot up, the top trace array requires to have
- * a list of events that can be enabled. This must be done before
- * the filesystem is set up in order to allow events to be traced
- * early.
+ * For early boot up, the top trace array and the trace arrays created
+ * by boot-time tracing require to have a list of events that can be
+ * enabled. This must be done before the filesystem is set up in order
+ * to allow events to be traced early.
*/
-static __init void
-__trace_early_add_events(struct trace_array *tr)
+void __trace_early_add_events(struct trace_array *tr)
{
struct trace_event_call *call;
int ret;
@@ -2938,7 +3221,7 @@
{
strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
ring_buffer_expanded = true;
- tracing_selftest_disabled = true;
+ disable_tracing_selftest("running event tracing");
return 1;
}
@@ -2977,6 +3260,11 @@
tr, &ftrace_set_event_pid_fops);
if (!entry)
pr_warn("Could not create tracefs 'set_event_pid' entry\n");
+
+ entry = tracefs_create_file("set_event_notrace_pid", 0644, parent,
+ tr, &ftrace_set_event_notrace_pid_fops);
+ if (!entry)
+ pr_warn("Could not create tracefs 'set_event_notrace_pid' entry\n");
/* ring buffer internal formats */
entry = trace_create_file("header_page", 0444, d_events,
@@ -3020,7 +3308,11 @@
goto out;
down_write(&trace_event_sem);
- __trace_add_event_dirs(tr);
+ /* If tr already has the event list, it is initialized in early boot. */
+ if (unlikely(!list_empty(&tr->events)))
+ __trace_early_add_event_dirs(tr);
+ else
+ __trace_add_event_dirs(tr);
up_write(&trace_event_sem);
out:
@@ -3061,7 +3353,7 @@
clear_event_triggers(tr);
/* Clear the pid list */
- __ftrace_clear_event_pids(tr);
+ __ftrace_clear_event_pids(tr, TRACE_PIDS | TRACE_NO_PIDS);
/* Disable any running events */
__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
@@ -3071,7 +3363,7 @@
down_write(&trace_event_sem);
__trace_remove_event_dirs(tr);
- tracefs_remove_recursive(tr->event_dir);
+ tracefs_remove(tr->event_dir);
up_write(&trace_event_sem);
tr->event_dir = NULL;
@@ -3176,10 +3468,21 @@
early_initcall(event_trace_enable_again);
+/* Init fields which doesn't related to the tracefs */
+static __init int event_trace_init_fields(void)
+{
+ if (trace_define_generic_fields())
+ pr_warn("tracing: Failed to allocated generic fields");
+
+ if (trace_define_common_fields())
+ pr_warn("tracing: Failed to allocate common fields");
+
+ return 0;
+}
+
__init int event_trace_init(void)
{
struct trace_array *tr;
- struct dentry *d_tracer;
struct dentry *entry;
int ret;
@@ -3187,22 +3490,12 @@
if (!tr)
return -ENODEV;
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
- return 0;
-
- entry = tracefs_create_file("available_events", 0444, d_tracer,
+ entry = tracefs_create_file("available_events", 0444, NULL,
tr, &ftrace_avail_fops);
if (!entry)
pr_warn("Could not create tracefs 'available_events' entry\n");
- if (trace_define_generic_fields())
- pr_warn("tracing: Failed to allocated generic fields");
-
- if (trace_define_common_fields())
- pr_warn("tracing: Failed to allocate common fields");
-
- ret = early_event_add_tracer(d_tracer, tr);
+ ret = early_event_add_tracer(NULL, tr);
if (ret)
return ret;
@@ -3211,6 +3504,9 @@
if (ret)
pr_warn("Failed to register trace events module notifier\n");
#endif
+
+ eventdir_initialized = true;
+
return 0;
}
@@ -3219,9 +3515,10 @@
event_trace_memsetup();
init_ftrace_syscalls();
event_trace_enable();
+ event_trace_init_fields();
}
-#ifdef CONFIG_FTRACE_STARTUP_TEST
+#ifdef CONFIG_EVENT_TRACE_STARTUP_TEST
static DEFINE_SPINLOCK(test_spinlock);
static DEFINE_SPINLOCK(test_spinlock_irq);
@@ -3398,15 +3695,14 @@
function_test_events_call(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *pt_regs)
{
+ struct trace_buffer *buffer;
struct ring_buffer_event *event;
- struct ring_buffer *buffer;
struct ftrace_entry *entry;
- unsigned long flags;
+ unsigned int trace_ctx;
long disabled;
int cpu;
- int pc;
- pc = preempt_count();
+ trace_ctx = tracing_gen_ctx();
preempt_disable_notrace();
cpu = raw_smp_processor_id();
disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu));
@@ -3414,11 +3710,9 @@
if (disabled != 1)
goto out;
- local_save_flags(flags);
-
event = trace_event_buffer_lock_reserve(&buffer, &event_trace_file,
TRACE_FN, sizeof(*entry),
- flags, pc);
+ trace_ctx);
if (!event)
goto out;
entry = ring_buffer_event_data(event);
@@ -3426,7 +3720,7 @@
entry->parent_ip = parent_ip;
event_trigger_unlock_commit(&event_trace_file, buffer, event,
- entry, flags, pc);
+ entry, trace_ctx);
out:
atomic_dec(&per_cpu(ftrace_test_event_disable, cpu));
preempt_enable_notrace();
--
Gitblit v1.6.2