* [for-next][PATCH 01/10] tracing: Add basic event trigger framework
2013-12-23 21:38 [for-next][PATCH 00/10] tracing: Addition of trace event trigeers Steven Rostedt
@ 2013-12-23 21:38 ` Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 02/10] tracing: Add traceon and traceoff event trigger commands Steven Rostedt
` (8 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Steven Rostedt @ 2013-12-23 21:38 UTC (permalink / raw)
To: linux-kernel; +Cc: Ingo Molnar, Frederic Weisbecker, Tom Zanussi, Andrew Morton
[-- Attachment #1: 0001-tracing-Add-basic-event-trigger-framework.patch --]
[-- Type: text/plain, Size: 28212 bytes --]
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Add a 'trigger' file for each trace event, enabling 'trace event
triggers' to be set for trace events.
'trace event triggers' are patterned after the existing 'ftrace
function triggers' implementation except that triggers are written to
per-event 'trigger' files instead of to a single file such as the
'set_ftrace_filter' used for ftrace function triggers.
The implementation is meant to be entirely separate from ftrace
function triggers, in order to keep the respective implementations
relatively simple and to allow them to diverge.
The event trigger functionality is built on top of SOFT_DISABLE
functionality. It adds a TRIGGER_MODE bit to the ftrace_event_file
flags which is checked when any trace event fires. Triggers set for a
particular event need to be checked regardless of whether that event
is actually enabled or not - getting an event to fire even if it's not
enabled is what's already implemented by SOFT_DISABLE mode, so trigger
mode directly reuses that. Event trigger essentially inherit the soft
disable logic in __ftrace_event_enable_disable() while adding a bit of
logic and trigger reference counting via tm_ref on top of that in a
new trace_event_trigger_enable_disable() function. Because the base
__ftrace_event_enable_disable() code now needs to be invoked from
outside trace_events.c, a wrapper is also added for those usages.
The triggers for an event are actually invoked via a new function,
event_triggers_call(), and code is also added to invoke them for
ftrace_raw_event calls as well as syscall events.
The main part of the patch creates a new trace_events_trigger.c file
to contain the trace event triggers implementation.
The standard open, read, and release file operations are implemented
here.
The open() implementation sets up for the various open modes of the
'trigger' file. It creates and attaches the trigger iterator and sets
up the command parser. If opened for reading set up the trigger
seq_ops.
The read() implementation parses the event trigger written to the
'trigger' file, looks up the trigger command, and passes it along to
that event_command's func() implementation for command-specific
processing.
The release() implementation does whatever cleanup is needed to
release the 'trigger' file, like releasing the parser and trigger
iterator, etc.
A couple of functions for event command registration and
unregistration are added, along with a list to add them to and a mutex
to protect them, as well as an (initially empty) registration function
to add the set of commands that will be added by future commits, and
call to it from the trace event initialization code.
also added are a couple trigger-specific data structures needed for
these implementations such as a trigger iterator and a struct for
trigger-specific data.
A couple structs consisting mostly of function meant to be implemented
in command-specific ways, event_command and event_trigger_ops, are
used by the generic event trigger command implementations. They're
being put into trace.h alongside the other trace_event data structures
and functions, in the expectation that they'll be needed in several
trace_event-related files such as trace_events_trigger.c and
trace_events.c.
The event_command.func() function is meant to be called by the trigger
parsing code in order to add a trigger instance to the corresponding
event. It essentially coordinates adding a live trigger instance to
the event, and arming the triggering the event.
Every event_command func() implementation essentially does the
same thing for any command:
- choose ops - use the value of param to choose either a number or
count version of event_trigger_ops specific to the command
- do the register or unregister of those ops
- associate a filter, if specified, with the triggering event
The reg() and unreg() ops allow command-specific implementations for
event_trigger_op registration and unregistration, and the
get_trigger_ops() op allows command-specific event_trigger_ops
selection to be parameterized. When a trigger instance is added, the
reg() op essentially adds that trigger to the triggering event and
arms it, while unreg() does the opposite. The set_filter() function
is used to associate a filter with the trigger - if the command
doesn't specify a set_filter() implementation, the command will ignore
filters.
Each command has an associated trigger_type, which serves double duty,
both as a unique identifier for the command as well as a value that
can be used for setting a trigger mode bit during trigger invocation.
The signature of func() adds a pointer to the event_command struct,
used to invoke those functions, along with a command_data param that
can be passed to the reg/unreg functions. This allows func()
implementations to use command-specific blobs and supports code
re-use.
The event_trigger_ops.func() command corrsponds to the trigger 'probe'
function that gets called when the triggering event is actually
invoked. The other functions are used to list the trigger when
needed, along with a couple mundane book-keeping functions.
This also moves event_file_data() into trace.h so it can be used
outside of trace_events.c.
Link: http://lkml.kernel.org/r/316d95061accdee070aac8e5750afba0192fa5b9.1382622043.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Idea-by: Steve Rostedt <rostedt@goodmis.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 11 ++
include/trace/ftrace.h | 4 +
kernel/trace/Makefile | 1 +
kernel/trace/trace.h | 181 +++++++++++++++++++++++
kernel/trace/trace_events.c | 21 ++-
kernel/trace/trace_events_trigger.c | 278 ++++++++++++++++++++++++++++++++++++
kernel/trace/trace_syscalls.c | 4 +
7 files changed, 495 insertions(+), 5 deletions(-)
create mode 100644 kernel/trace/trace_events_trigger.c
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 8c9b7a1..211e7ad 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -264,6 +264,7 @@ enum {
FTRACE_EVENT_FL_NO_SET_FILTER_BIT,
FTRACE_EVENT_FL_SOFT_MODE_BIT,
FTRACE_EVENT_FL_SOFT_DISABLED_BIT,
+ FTRACE_EVENT_FL_TRIGGER_MODE_BIT,
};
/*
@@ -275,6 +276,7 @@ enum {
* SOFT_MODE - The event is enabled/disabled by SOFT_DISABLED
* SOFT_DISABLED - When set, do not trace the event (even though its
* tracepoint may be enabled)
+ * TRIGGER_MODE - When set, invoke the triggers associated with the event
*/
enum {
FTRACE_EVENT_FL_ENABLED = (1 << FTRACE_EVENT_FL_ENABLED_BIT),
@@ -283,6 +285,7 @@ enum {
FTRACE_EVENT_FL_NO_SET_FILTER = (1 << FTRACE_EVENT_FL_NO_SET_FILTER_BIT),
FTRACE_EVENT_FL_SOFT_MODE = (1 << FTRACE_EVENT_FL_SOFT_MODE_BIT),
FTRACE_EVENT_FL_SOFT_DISABLED = (1 << FTRACE_EVENT_FL_SOFT_DISABLED_BIT),
+ FTRACE_EVENT_FL_TRIGGER_MODE = (1 << FTRACE_EVENT_FL_TRIGGER_MODE_BIT),
};
struct ftrace_event_file {
@@ -292,6 +295,7 @@ struct ftrace_event_file {
struct dentry *dir;
struct trace_array *tr;
struct ftrace_subsystem_dir *system;
+ struct list_head triggers;
/*
* 32 bit flags:
@@ -299,6 +303,7 @@ struct ftrace_event_file {
* bit 1: enabled cmd record
* bit 2: enable/disable with the soft disable bit
* bit 3: soft disabled
+ * bit 4: trigger enabled
*
* Note: The bits must be set atomically to prevent races
* from other writers. Reads of flags do not need to be in
@@ -310,6 +315,7 @@ struct ftrace_event_file {
*/
unsigned long flags;
atomic_t sm_ref; /* soft-mode reference counter */
+ atomic_t tm_ref; /* trigger-mode reference counter */
};
#define __TRACE_EVENT_FLAGS(name, value) \
@@ -337,6 +343,10 @@ struct ftrace_event_file {
#define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */
+enum event_trigger_type {
+ ETT_NONE = (0),
+};
+
extern void destroy_preds(struct ftrace_event_file *file);
extern void destroy_call_preds(struct ftrace_event_call *call);
extern int filter_match_preds(struct event_filter *filter, void *rec);
@@ -347,6 +357,7 @@ extern int filter_check_discard(struct ftrace_event_file *file, void *rec,
extern int call_filter_check_discard(struct ftrace_event_call *call, void *rec,
struct ring_buffer *buffer,
struct ring_buffer_event *event);
+extern void event_triggers_call(struct ftrace_event_file *file);
enum {
FILTER_OTHER = 0,
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 5c38606..0a48bff 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -539,6 +539,10 @@ ftrace_raw_event_##call(void *__data, proto) \
int __data_size; \
int pc; \
\
+ if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, \
+ &ftrace_file->flags)) \
+ event_triggers_call(ftrace_file); \
+ \
if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, \
&ftrace_file->flags)) \
return; \
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index d7e2068..1378e84 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -50,6 +50,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y)
obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
endif
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
obj-$(CONFIG_TRACEPOINTS) += power-traces.o
ifeq ($(CONFIG_PM_RUNTIME),y)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index ea189e0..9775e51 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1028,9 +1028,190 @@ extern void trace_event_enable_cmd_record(bool enable);
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
extern int event_trace_del_tracer(struct trace_array *tr);
+static inline void *event_file_data(struct file *filp)
+{
+ return ACCESS_ONCE(file_inode(filp)->i_private);
+}
+
extern struct mutex event_mutex;
extern struct list_head ftrace_events;
+extern const struct file_operations event_trigger_fops;
+
+extern int register_trigger_cmds(void);
+extern void clear_event_triggers(struct trace_array *tr);
+
+struct event_trigger_data {
+ unsigned long count;
+ int ref;
+ struct event_trigger_ops *ops;
+ struct event_command *cmd_ops;
+ struct event_filter *filter;
+ char *filter_str;
+ void *private_data;
+ struct list_head list;
+};
+
+/**
+ * struct event_trigger_ops - callbacks for trace event triggers
+ *
+ * The methods in this structure provide per-event trigger hooks for
+ * various trigger operations.
+ *
+ * All the methods below, except for @init() and @free(), must be
+ * implemented.
+ *
+ * @func: The trigger 'probe' function called when the triggering
+ * event occurs. The data passed into this callback is the data
+ * that was supplied to the event_command @reg() function that
+ * registered the trigger (see struct event_command).
+ *
+ * @init: An optional initialization function called for the trigger
+ * when the trigger is registered (via the event_command reg()
+ * function). This can be used to perform per-trigger
+ * initialization such as incrementing a per-trigger reference
+ * count, for instance. This is usually implemented by the
+ * generic utility function @event_trigger_init() (see
+ * trace_event_triggers.c).
+ *
+ * @free: An optional de-initialization function called for the
+ * trigger when the trigger is unregistered (via the
+ * event_command @reg() function). This can be used to perform
+ * per-trigger de-initialization such as decrementing a
+ * per-trigger reference count and freeing corresponding trigger
+ * data, for instance. This is usually implemented by the
+ * generic utility function @event_trigger_free() (see
+ * trace_event_triggers.c).
+ *
+ * @print: The callback function invoked to have the trigger print
+ * itself. This is usually implemented by a wrapper function
+ * that calls the generic utility function @event_trigger_print()
+ * (see trace_event_triggers.c).
+ */
+struct event_trigger_ops {
+ void (*func)(struct event_trigger_data *data);
+ int (*init)(struct event_trigger_ops *ops,
+ struct event_trigger_data *data);
+ void (*free)(struct event_trigger_ops *ops,
+ struct event_trigger_data *data);
+ int (*print)(struct seq_file *m,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data);
+};
+
+/**
+ * struct event_command - callbacks and data members for event commands
+ *
+ * Event commands are invoked by users by writing the command name
+ * into the 'trigger' file associated with a trace event. The
+ * parameters associated with a specific invocation of an event
+ * command are used to create an event trigger instance, which is
+ * added to the list of trigger instances associated with that trace
+ * event. When the event is hit, the set of triggers associated with
+ * that event is invoked.
+ *
+ * The data members in this structure provide per-event command data
+ * for various event commands.
+ *
+ * All the data members below, except for @post_trigger, must be set
+ * for each event command.
+ *
+ * @name: The unique name that identifies the event command. This is
+ * the name used when setting triggers via trigger files.
+ *
+ * @trigger_type: A unique id that identifies the event command
+ * 'type'. This value has two purposes, the first to ensure that
+ * only one trigger of the same type can be set at a given time
+ * for a particular event e.g. it doesn't make sense to have both
+ * a traceon and traceoff trigger attached to a single event at
+ * the same time, so traceon and traceoff have the same type
+ * though they have different names. The @trigger_type value is
+ * also used as a bit value for deferring the actual trigger
+ * action until after the current event is finished. Some
+ * commands need to do this if they themselves log to the trace
+ * buffer (see the @post_trigger() member below). @trigger_type
+ * values are defined by adding new values to the trigger_type
+ * enum in include/linux/ftrace_event.h.
+ *
+ * @post_trigger: A flag that says whether or not this command needs
+ * to have its action delayed until after the current event has
+ * been closed. Some triggers need to avoid being invoked while
+ * an event is currently in the process of being logged, since
+ * the trigger may itself log data into the trace buffer. Thus
+ * we make sure the current event is committed before invoking
+ * those triggers. To do that, the trigger invocation is split
+ * in two - the first part checks the filter using the current
+ * trace record; if a command has the @post_trigger flag set, it
+ * sets a bit for itself in the return value, otherwise it
+ * directly invokes the trigger. Once all commands have been
+ * either invoked or set their return flag, the current record is
+ * either committed or discarded. At that point, if any commands
+ * have deferred their triggers, those commands are finally
+ * invoked following the close of the current event. In other
+ * words, if the event_trigger_ops @func() probe implementation
+ * itself logs to the trace buffer, this flag should be set,
+ * otherwise it can be left unspecified.
+ *
+ * All the methods below, except for @set_filter(), must be
+ * implemented.
+ *
+ * @func: The callback function responsible for parsing and
+ * registering the trigger written to the 'trigger' file by the
+ * user. It allocates the trigger instance and registers it with
+ * the appropriate trace event. It makes use of the other
+ * event_command callback functions to orchestrate this, and is
+ * usually implemented by the generic utility function
+ * @event_trigger_callback() (see trace_event_triggers.c).
+ *
+ * @reg: Adds the trigger to the list of triggers associated with the
+ * event, and enables the event trigger itself, after
+ * initializing it (via the event_trigger_ops @init() function).
+ * This is also where commands can use the @trigger_type value to
+ * make the decision as to whether or not multiple instances of
+ * the trigger should be allowed. This is usually implemented by
+ * the generic utility function @register_trigger() (see
+ * trace_event_triggers.c).
+ *
+ * @unreg: Removes the trigger from the list of triggers associated
+ * with the event, and disables the event trigger itself, after
+ * initializing it (via the event_trigger_ops @free() function).
+ * This is usually implemented by the generic utility function
+ * @unregister_trigger() (see trace_event_triggers.c).
+ *
+ * @set_filter: An optional function called to parse and set a filter
+ * for the trigger. If no @set_filter() method is set for the
+ * event command, filters set by the user for the command will be
+ * ignored. This is usually implemented by the generic utility
+ * function @set_trigger_filter() (see trace_event_triggers.c).
+ *
+ * @get_trigger_ops: The callback function invoked to retrieve the
+ * event_trigger_ops implementation associated with the command.
+ */
+struct event_command {
+ struct list_head list;
+ char *name;
+ enum event_trigger_type trigger_type;
+ bool post_trigger;
+ int (*func)(struct event_command *cmd_ops,
+ struct ftrace_event_file *file,
+ char *glob, char *cmd, char *params);
+ int (*reg)(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file);
+ void (*unreg)(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file);
+ int (*set_filter)(char *filter_str,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file);
+ struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param);
+};
+
+extern int trace_event_enable_disable(struct ftrace_event_file *file,
+ int enable, int soft_disable);
+
extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index a11800a..442775c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -342,6 +342,12 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file,
return ret;
}
+int trace_event_enable_disable(struct ftrace_event_file *file,
+ int enable, int soft_disable)
+{
+ return __ftrace_event_enable_disable(file, enable, soft_disable);
+}
+
static int ftrace_event_enable_disable(struct ftrace_event_file *file,
int enable)
{
@@ -421,11 +427,6 @@ static void remove_subsystem(struct ftrace_subsystem_dir *dir)
}
}
-static void *event_file_data(struct file *filp)
-{
- return ACCESS_ONCE(file_inode(filp)->i_private);
-}
-
static void remove_event_file_dir(struct ftrace_event_file *file)
{
struct dentry *dir = file->dir;
@@ -1549,6 +1550,9 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
trace_create_file("filter", 0644, file->dir, file,
&ftrace_event_filter_fops);
+ trace_create_file("trigger", 0644, file->dir, file,
+ &event_trigger_fops);
+
trace_create_file("format", 0444, file->dir, call,
&ftrace_event_format_fops);
@@ -1645,6 +1649,8 @@ trace_create_new_event(struct ftrace_event_call *call,
file->event_call = call;
file->tr = tr;
atomic_set(&file->sm_ref, 0);
+ atomic_set(&file->tm_ref, 0);
+ INIT_LIST_HEAD(&file->triggers);
list_add(&file->list, &tr->events);
return file;
@@ -2311,6 +2317,9 @@ int event_trace_del_tracer(struct trace_array *tr)
{
mutex_lock(&event_mutex);
+ /* Disable any event triggers and associated soft-disabled events */
+ clear_event_triggers(tr);
+
/* Disable any running events */
__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
@@ -2377,6 +2386,8 @@ static __init int event_trace_enable(void)
register_event_cmds();
+ register_trigger_cmds();
+
return 0;
}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
new file mode 100644
index 0000000..60a6a6d
--- /dev/null
+++ b/kernel/trace/trace_events_trigger.c
@@ -0,0 +1,278 @@
+/*
+ * trace_events_trigger - trace event triggers
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2013 Tom Zanussi <tom.zanussi@linux.intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+#include "trace.h"
+
+static LIST_HEAD(trigger_commands);
+static DEFINE_MUTEX(trigger_cmd_mutex);
+
+/**
+ * event_triggers_call - Call triggers associated with a trace event
+ * @file: The ftrace_event_file associated with the event
+ *
+ * For each trigger associated with an event, invoke the trigger
+ * function registered with the associated trigger command.
+ *
+ * Called from tracepoint handlers (with rcu_read_lock_sched() held).
+ *
+ * Return: an enum event_trigger_type value containing a set bit for
+ * any trigger that should be deferred, ETT_NONE if nothing to defer.
+ */
+void event_triggers_call(struct ftrace_event_file *file)
+{
+ struct event_trigger_data *data;
+
+ if (list_empty(&file->triggers))
+ return;
+
+ list_for_each_entry_rcu(data, &file->triggers, list)
+ data->ops->func(data);
+}
+EXPORT_SYMBOL_GPL(event_triggers_call);
+
+static void *trigger_next(struct seq_file *m, void *t, loff_t *pos)
+{
+ struct ftrace_event_file *event_file = event_file_data(m->private);
+
+ return seq_list_next(t, &event_file->triggers, pos);
+}
+
+static void *trigger_start(struct seq_file *m, loff_t *pos)
+{
+ struct ftrace_event_file *event_file;
+
+ /* ->stop() is called even if ->start() fails */
+ mutex_lock(&event_mutex);
+ event_file = event_file_data(m->private);
+ if (unlikely(!event_file))
+ return ERR_PTR(-ENODEV);
+
+ return seq_list_start(&event_file->triggers, *pos);
+}
+
+static void trigger_stop(struct seq_file *m, void *t)
+{
+ mutex_unlock(&event_mutex);
+}
+
+static int trigger_show(struct seq_file *m, void *v)
+{
+ struct event_trigger_data *data;
+
+ data = list_entry(v, struct event_trigger_data, list);
+ data->ops->print(m, data->ops, data);
+
+ return 0;
+}
+
+static const struct seq_operations event_triggers_seq_ops = {
+ .start = trigger_start,
+ .next = trigger_next,
+ .stop = trigger_stop,
+ .show = trigger_show,
+};
+
+static int event_trigger_regex_open(struct inode *inode, struct file *file)
+{
+ int ret = 0;
+
+ mutex_lock(&event_mutex);
+
+ if (unlikely(!event_file_data(file))) {
+ mutex_unlock(&event_mutex);
+ return -ENODEV;
+ }
+
+ if (file->f_mode & FMODE_READ) {
+ ret = seq_open(file, &event_triggers_seq_ops);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = file;
+ }
+ }
+
+ mutex_unlock(&event_mutex);
+
+ return ret;
+}
+
+static int trigger_process_regex(struct ftrace_event_file *file, char *buff)
+{
+ char *command, *next = buff;
+ struct event_command *p;
+ int ret = -EINVAL;
+
+ command = strsep(&next, ": \t");
+ command = (command[0] != '!') ? command : command + 1;
+
+ mutex_lock(&trigger_cmd_mutex);
+ list_for_each_entry(p, &trigger_commands, list) {
+ if (strcmp(p->name, command) == 0) {
+ ret = p->func(p, file, buff, command, next);
+ goto out_unlock;
+ }
+ }
+ out_unlock:
+ mutex_unlock(&trigger_cmd_mutex);
+
+ return ret;
+}
+
+static ssize_t event_trigger_regex_write(struct file *file,
+ const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct ftrace_event_file *event_file;
+ ssize_t ret;
+ char *buf;
+
+ if (!cnt)
+ return 0;
+
+ if (cnt >= PAGE_SIZE)
+ return -EINVAL;
+
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, ubuf, cnt)) {
+ free_page((unsigned long)buf);
+ return -EFAULT;
+ }
+ buf[cnt] = '\0';
+ strim(buf);
+
+ mutex_lock(&event_mutex);
+ event_file = event_file_data(file);
+ if (unlikely(!event_file)) {
+ mutex_unlock(&event_mutex);
+ free_page((unsigned long)buf);
+ return -ENODEV;
+ }
+ ret = trigger_process_regex(event_file, buf);
+ mutex_unlock(&event_mutex);
+
+ free_page((unsigned long)buf);
+ if (ret < 0)
+ goto out;
+
+ *ppos += cnt;
+ ret = cnt;
+ out:
+ return ret;
+}
+
+static int event_trigger_regex_release(struct inode *inode, struct file *file)
+{
+ mutex_lock(&event_mutex);
+
+ if (file->f_mode & FMODE_READ)
+ seq_release(inode, file);
+
+ mutex_unlock(&event_mutex);
+
+ return 0;
+}
+
+static ssize_t
+event_trigger_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ return event_trigger_regex_write(filp, ubuf, cnt, ppos);
+}
+
+static int
+event_trigger_open(struct inode *inode, struct file *filp)
+{
+ return event_trigger_regex_open(inode, filp);
+}
+
+static int
+event_trigger_release(struct inode *inode, struct file *file)
+{
+ return event_trigger_regex_release(inode, file);
+}
+
+const struct file_operations event_trigger_fops = {
+ .open = event_trigger_open,
+ .read = seq_read,
+ .write = event_trigger_write,
+ .llseek = ftrace_filter_lseek,
+ .release = event_trigger_release,
+};
+
+static int trace_event_trigger_enable_disable(struct ftrace_event_file *file,
+ int trigger_enable)
+{
+ int ret = 0;
+
+ if (trigger_enable) {
+ if (atomic_inc_return(&file->tm_ref) > 1)
+ return ret;
+ set_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &file->flags);
+ ret = trace_event_enable_disable(file, 1, 1);
+ } else {
+ if (atomic_dec_return(&file->tm_ref) > 0)
+ return ret;
+ clear_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &file->flags);
+ ret = trace_event_enable_disable(file, 0, 1);
+ }
+
+ return ret;
+}
+
+/**
+ * clear_event_triggers - Clear all triggers associated with a trace array
+ * @tr: The trace array to clear
+ *
+ * For each trigger, the triggering event has its tm_ref decremented
+ * via trace_event_trigger_enable_disable(), and any associated event
+ * (in the case of enable/disable_event triggers) will have its sm_ref
+ * decremented via free()->trace_event_enable_disable(). That
+ * combination effectively reverses the soft-mode/trigger state added
+ * by trigger registration.
+ *
+ * Must be called with event_mutex held.
+ */
+void
+clear_event_triggers(struct trace_array *tr)
+{
+ struct ftrace_event_file *file;
+
+ list_for_each_entry(file, &tr->events, list) {
+ struct event_trigger_data *data;
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ trace_event_trigger_enable_disable(file, 0);
+ if (data->ops->free)
+ data->ops->free(data->ops, data);
+ }
+ }
+}
+
+__init int register_trigger_cmds(void)
+{
+ return 0;
+}
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index ea90eb5..936ec39 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -321,6 +321,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
if (!ftrace_file)
return;
+ if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &ftrace_file->flags))
+ event_triggers_call(ftrace_file);
if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
return;
@@ -369,6 +371,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
if (!ftrace_file)
return;
+ if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &ftrace_file->flags))
+ event_triggers_call(ftrace_file);
if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
return;
--
1.8.4.3
^ permalink raw reply related [flat|nested] 11+ messages in thread* [for-next][PATCH 02/10] tracing: Add traceon and traceoff event trigger commands
2013-12-23 21:38 [for-next][PATCH 00/10] tracing: Addition of trace event trigeers Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 01/10] tracing: Add basic event trigger framework Steven Rostedt
@ 2013-12-23 21:38 ` Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 03/10] tracing: Add snapshot event trigger command Steven Rostedt
` (7 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Steven Rostedt @ 2013-12-23 21:38 UTC (permalink / raw)
To: linux-kernel; +Cc: Ingo Molnar, Frederic Weisbecker, Tom Zanussi, Andrew Morton
[-- Attachment #1: 0002-tracing-Add-traceon-and-traceoff-event-trigger-comma.patch --]
[-- Type: text/plain, Size: 14422 bytes --]
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Add 'traceon' and 'traceoff' event_command commands. traceon and
traceoff event triggers are added by the user via these commands in a
similar way and using practically the same syntax as the analagous
'traceon' and 'traceoff' ftrace function commands, but instead of
writing to the set_ftrace_filter file, the traceon and traceoff
triggers are written to the per-event 'trigger' files:
echo 'traceon' > .../tracing/events/somesys/someevent/trigger
echo 'traceoff' > .../tracing/events/somesys/someevent/trigger
The above command will turn tracing on or off whenever someevent is
hit.
This also adds a 'count' version that limits the number of times the
command will be invoked:
echo 'traceon:N' > .../tracing/events/somesys/someevent/trigger
echo 'traceoff:N' > .../tracing/events/somesys/someevent/trigger
Where N is the number of times the command will be invoked.
The above commands will will turn tracing on or off whenever someevent
is hit, but only N times.
Some common register/unregister_trigger() implementations of the
event_command reg()/unreg() callbacks are also provided, which add and
remove trigger instances to the per-event list of triggers, and
arm/disarm them as appropriate. event_trigger_callback() is a
general-purpose event_command func() implementation that orchestrates
command parsing and registration for most normal commands.
Most event commands will use these, but some will override and
possibly reuse them.
The event_trigger_init(), event_trigger_free(), and
event_trigger_print() functions are meant to be common implementations
of the event_trigger_ops init(), free(), and print() ops,
respectively.
Most trigger_ops implementations will use these, but some will
override and possibly reuse them.
Link: http://lkml.kernel.org/r/00a52816703b98d2072947478dd6e2d70cde5197.1382622043.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 1 +
kernel/trace/trace_events_trigger.c | 446 ++++++++++++++++++++++++++++++++++++
2 files changed, 447 insertions(+)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 211e7ad..711c4dc 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -345,6 +345,7 @@ struct ftrace_event_file {
enum event_trigger_type {
ETT_NONE = (0),
+ ETT_TRACE_ONOFF = (1 << 0),
};
extern void destroy_preds(struct ftrace_event_file *file);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 60a6a6d..4ea72ee 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -28,6 +28,13 @@
static LIST_HEAD(trigger_commands);
static DEFINE_MUTEX(trigger_cmd_mutex);
+static void
+trigger_data_free(struct event_trigger_data *data)
+{
+ synchronize_sched(); /* make sure current triggers exit before free */
+ kfree(data);
+}
+
/**
* event_triggers_call - Call triggers associated with a trace event
* @file: The ftrace_event_file associated with the event
@@ -224,6 +231,129 @@ const struct file_operations event_trigger_fops = {
.release = event_trigger_release,
};
+/*
+ * Currently we only register event commands from __init, so mark this
+ * __init too.
+ */
+static __init int register_event_command(struct event_command *cmd)
+{
+ struct event_command *p;
+ int ret = 0;
+
+ mutex_lock(&trigger_cmd_mutex);
+ list_for_each_entry(p, &trigger_commands, list) {
+ if (strcmp(cmd->name, p->name) == 0) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
+ }
+ list_add(&cmd->list, &trigger_commands);
+ out_unlock:
+ mutex_unlock(&trigger_cmd_mutex);
+
+ return ret;
+}
+
+/*
+ * Currently we only unregister event commands from __init, so mark
+ * this __init too.
+ */
+static __init int unregister_event_command(struct event_command *cmd)
+{
+ struct event_command *p, *n;
+ int ret = -ENODEV;
+
+ mutex_lock(&trigger_cmd_mutex);
+ list_for_each_entry_safe(p, n, &trigger_commands, list) {
+ if (strcmp(cmd->name, p->name) == 0) {
+ ret = 0;
+ list_del_init(&p->list);
+ goto out_unlock;
+ }
+ }
+ out_unlock:
+ mutex_unlock(&trigger_cmd_mutex);
+
+ return ret;
+}
+
+/**
+ * event_trigger_print - Generic event_trigger_ops @print implementation
+ * @name: The name of the event trigger
+ * @m: The seq_file being printed to
+ * @data: Trigger-specific data
+ * @filter_str: filter_str to print, if present
+ *
+ * Common implementation for event triggers to print themselves.
+ *
+ * Usually wrapped by a function that simply sets the @name of the
+ * trigger command and then invokes this.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_print(const char *name, struct seq_file *m,
+ void *data, char *filter_str)
+{
+ long count = (long)data;
+
+ seq_printf(m, "%s", name);
+
+ if (count == -1)
+ seq_puts(m, ":unlimited");
+ else
+ seq_printf(m, ":count=%ld", count);
+
+ if (filter_str)
+ seq_printf(m, " if %s\n", filter_str);
+ else
+ seq_puts(m, "\n");
+
+ return 0;
+}
+
+/**
+ * event_trigger_init - Generic event_trigger_ops @init implementation
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data
+ *
+ * Common implementation of event trigger initialization.
+ *
+ * Usually used directly as the @init method in event trigger
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_init(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ data->ref++;
+ return 0;
+}
+
+/**
+ * event_trigger_free - Generic event_trigger_ops @free implementation
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data
+ *
+ * Common implementation of event trigger de-initialization.
+ *
+ * Usually used directly as the @free method in event trigger
+ * implementations.
+ */
+static void
+event_trigger_free(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ if (WARN_ON_ONCE(data->ref <= 0))
+ return;
+
+ data->ref--;
+ if (!data->ref)
+ trigger_data_free(data);
+}
+
static int trace_event_trigger_enable_disable(struct ftrace_event_file *file,
int trigger_enable)
{
@@ -272,7 +402,323 @@ clear_event_triggers(struct trace_array *tr)
}
}
+/**
+ * register_trigger - Generic event_command @reg implementation
+ * @glob: The raw string used to register the trigger
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data to associate with the trigger
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event trigger registration.
+ *
+ * Usually used directly as the @reg method in event command
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int register_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file)
+{
+ struct event_trigger_data *test;
+ int ret = 0;
+
+ list_for_each_entry_rcu(test, &file->triggers, list) {
+ if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+
+ if (data->ops->init) {
+ ret = data->ops->init(data->ops, data);
+ if (ret < 0)
+ goto out;
+ }
+
+ list_add_rcu(&data->list, &file->triggers);
+ ret++;
+
+ if (trace_event_trigger_enable_disable(file, 1) < 0) {
+ list_del_rcu(&data->list);
+ ret--;
+ }
+out:
+ return ret;
+}
+
+/**
+ * unregister_trigger - Generic event_command @unreg implementation
+ * @glob: The raw string used to register the trigger
+ * @ops: The trigger ops associated with the trigger
+ * @test: Trigger-specific data used to find the trigger to remove
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event trigger unregistration.
+ *
+ * Usually used directly as the @unreg method in event command
+ * implementations.
+ */
+static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *test,
+ struct ftrace_event_file *file)
+{
+ struct event_trigger_data *data;
+ bool unregistered = false;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
+ unregistered = true;
+ list_del_rcu(&data->list);
+ trace_event_trigger_enable_disable(file, 0);
+ break;
+ }
+ }
+
+ if (unregistered && data->ops->free)
+ data->ops->free(data->ops, data);
+}
+
+/**
+ * event_trigger_callback - Generic event_command @func implementation
+ * @cmd_ops: The command ops, used for trigger registration
+ * @file: The ftrace_event_file associated with the event
+ * @glob: The raw string used to register the trigger
+ * @cmd: The cmd portion of the string used to register the trigger
+ * @param: The params portion of the string used to register the trigger
+ *
+ * Common implementation for event command parsing and trigger
+ * instantiation.
+ *
+ * Usually used directly as the @func method in event command
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_callback(struct event_command *cmd_ops,
+ struct ftrace_event_file *file,
+ char *glob, char *cmd, char *param)
+{
+ struct event_trigger_data *trigger_data;
+ struct event_trigger_ops *trigger_ops;
+ char *trigger = NULL;
+ char *number;
+ int ret;
+
+ /* separate the trigger from the filter (t:n [if filter]) */
+ if (param && isdigit(param[0]))
+ trigger = strsep(¶m, " \t");
+
+ trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+
+ ret = -ENOMEM;
+ trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+ if (!trigger_data)
+ goto out;
+
+ trigger_data->count = -1;
+ trigger_data->ops = trigger_ops;
+ trigger_data->cmd_ops = cmd_ops;
+ INIT_LIST_HEAD(&trigger_data->list);
+
+ if (glob[0] == '!') {
+ cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+ kfree(trigger_data);
+ ret = 0;
+ goto out;
+ }
+
+ if (trigger) {
+ number = strsep(&trigger, ":");
+
+ ret = -EINVAL;
+ if (!strlen(number))
+ goto out_free;
+
+ /*
+ * We use the callback data field (which is a pointer)
+ * as our counter.
+ */
+ ret = kstrtoul(number, 0, &trigger_data->count);
+ if (ret)
+ goto out_free;
+ }
+
+ if (!param) /* if param is non-empty, it's supposed to be a filter */
+ goto out_reg;
+
+ if (!cmd_ops->set_filter)
+ goto out_reg;
+
+ ret = cmd_ops->set_filter(param, trigger_data, file);
+ if (ret < 0)
+ goto out_free;
+
+ out_reg:
+ ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
+ /*
+ * The above returns on success the # of functions enabled,
+ * but if it didn't find any functions it returns zero.
+ * Consider no functions a failure too.
+ */
+ if (!ret) {
+ ret = -ENOENT;
+ goto out_free;
+ } else if (ret < 0)
+ goto out_free;
+ ret = 0;
+ out:
+ return ret;
+
+ out_free:
+ kfree(trigger_data);
+ goto out;
+}
+
+static void
+traceon_trigger(struct event_trigger_data *data)
+{
+ if (tracing_is_on())
+ return;
+
+ tracing_on();
+}
+
+static void
+traceon_count_trigger(struct event_trigger_data *data)
+{
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ traceon_trigger(data);
+}
+
+static void
+traceoff_trigger(struct event_trigger_data *data)
+{
+ if (!tracing_is_on())
+ return;
+
+ tracing_off();
+}
+
+static void
+traceoff_count_trigger(struct event_trigger_data *data)
+{
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ traceoff_trigger(data);
+}
+
+static int
+traceon_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("traceon", m, (void *)data->count,
+ data->filter_str);
+}
+
+static int
+traceoff_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("traceoff", m, (void *)data->count,
+ data->filter_str);
+}
+
+static struct event_trigger_ops traceon_trigger_ops = {
+ .func = traceon_trigger,
+ .print = traceon_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops traceon_count_trigger_ops = {
+ .func = traceon_count_trigger,
+ .print = traceon_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops traceoff_trigger_ops = {
+ .func = traceoff_trigger,
+ .print = traceoff_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops traceoff_count_trigger_ops = {
+ .func = traceoff_count_trigger,
+ .print = traceoff_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops *
+onoff_get_trigger_ops(char *cmd, char *param)
+{
+ struct event_trigger_ops *ops;
+
+ /* we register both traceon and traceoff to this callback */
+ if (strcmp(cmd, "traceon") == 0)
+ ops = param ? &traceon_count_trigger_ops :
+ &traceon_trigger_ops;
+ else
+ ops = param ? &traceoff_count_trigger_ops :
+ &traceoff_trigger_ops;
+
+ return ops;
+}
+
+static struct event_command trigger_traceon_cmd = {
+ .name = "traceon",
+ .trigger_type = ETT_TRACE_ONOFF,
+ .func = event_trigger_callback,
+ .reg = register_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = onoff_get_trigger_ops,
+};
+
+static struct event_command trigger_traceoff_cmd = {
+ .name = "traceoff",
+ .trigger_type = ETT_TRACE_ONOFF,
+ .func = event_trigger_callback,
+ .reg = register_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = onoff_get_trigger_ops,
+};
+
+static __init void unregister_trigger_traceon_traceoff_cmds(void)
+{
+ unregister_event_command(&trigger_traceon_cmd);
+ unregister_event_command(&trigger_traceoff_cmd);
+}
+
+static __init int register_trigger_traceon_traceoff_cmds(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_traceon_cmd);
+ if (WARN_ON(ret < 0))
+ return ret;
+ ret = register_event_command(&trigger_traceoff_cmd);
+ if (WARN_ON(ret < 0))
+ unregister_trigger_traceon_traceoff_cmds();
+
+ return ret;
+}
+
__init int register_trigger_cmds(void)
{
+ register_trigger_traceon_traceoff_cmds();
+
return 0;
}
--
1.8.4.3
^ permalink raw reply related [flat|nested] 11+ messages in thread* [for-next][PATCH 03/10] tracing: Add snapshot event trigger command
2013-12-23 21:38 [for-next][PATCH 00/10] tracing: Addition of trace event trigeers Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 01/10] tracing: Add basic event trigger framework Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 02/10] tracing: Add traceon and traceoff event trigger commands Steven Rostedt
@ 2013-12-23 21:38 ` Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 04/10] tracing: Add stacktrace " Steven Rostedt
` (6 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Steven Rostedt @ 2013-12-23 21:38 UTC (permalink / raw)
To: linux-kernel; +Cc: Ingo Molnar, Frederic Weisbecker, Tom Zanussi, Andrew Morton
[-- Attachment #1: 0003-tracing-Add-snapshot-event-trigger-command.patch --]
[-- Type: text/plain, Size: 6990 bytes --]
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Add 'snapshot' event_command. snapshot event triggers are added by
the user via this command in a similar way and using practically the
same syntax as the analogous 'snapshot' ftrace function command, but
instead of writing to the set_ftrace_filter file, the snapshot event
trigger is written to the per-event 'trigger' files:
echo 'snapshot' > .../somesys/someevent/trigger
The above command will turn on snapshots for someevent i.e. whenever
someevent is hit, a snapshot will be done.
This also adds a 'count' version that limits the number of times the
command will be invoked:
echo 'snapshot:N' > .../somesys/someevent/trigger
Where N is the number of times the command will be invoked.
The above command will snapshot N times for someevent i.e. whenever
someevent is hit N times, a snapshot will be done.
Also adds a new tracing_alloc_snapshot() function - the existing
tracing_snapshot_alloc() function is a special version of
tracing_snapshot() that also does the snapshot allocation - the
snapshot triggers would like to be able to do just the allocation but
not take a snapshot; the existing tracing_snapshot_alloc() in turn now
also calls tracing_alloc_snapshot() underneath to do that allocation.
Link: http://lkml.kernel.org/r/c9524dd07ce01f9dcbd59011290e0a8d5b47d7ad.1382622043.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
[ fix up from kbuild test robot <fengguang.wu@intel.com report ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 1 +
kernel/trace/trace.c | 33 ++++++++++++--
kernel/trace/trace.h | 1 +
kernel/trace/trace_events_trigger.c | 85 +++++++++++++++++++++++++++++++++++++
4 files changed, 117 insertions(+), 3 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 711c4dc..6efa8c2 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -346,6 +346,7 @@ struct ftrace_event_file {
enum event_trigger_type {
ETT_NONE = (0),
ETT_TRACE_ONOFF = (1 << 0),
+ ETT_SNAPSHOT = (1 << 1),
};
extern void destroy_preds(struct ftrace_event_file *file);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9d20cd9..59bf5b5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -595,6 +595,28 @@ void free_snapshot(struct trace_array *tr)
}
/**
+ * tracing_alloc_snapshot - allocate snapshot buffer.
+ *
+ * This only allocates the snapshot buffer if it isn't already
+ * allocated - it doesn't also take a snapshot.
+ *
+ * This is meant to be used in cases where the snapshot buffer needs
+ * to be set up for events that can't sleep but need to be able to
+ * trigger a snapshot.
+ */
+int tracing_alloc_snapshot(void)
+{
+ struct trace_array *tr = &global_trace;
+ int ret;
+
+ ret = alloc_snapshot(tr);
+ WARN_ON(ret < 0);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);
+
+/**
* trace_snapshot_alloc - allocate and take a snapshot of the current buffer.
*
* This is similar to trace_snapshot(), but it will allocate the
@@ -607,11 +629,10 @@ void free_snapshot(struct trace_array *tr)
*/
void tracing_snapshot_alloc(void)
{
- struct trace_array *tr = &global_trace;
int ret;
- ret = alloc_snapshot(tr);
- if (WARN_ON(ret < 0))
+ ret = tracing_alloc_snapshot();
+ if (ret < 0)
return;
tracing_snapshot();
@@ -623,6 +644,12 @@ void tracing_snapshot(void)
WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used");
}
EXPORT_SYMBOL_GPL(tracing_snapshot);
+int tracing_alloc_snapshot(void)
+{
+ WARN_ONCE(1, "Snapshot feature not enabled, but snapshot allocation used");
+ return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);
void tracing_snapshot_alloc(void)
{
/* Give warning */
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 9775e51..50723e5 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1211,6 +1211,7 @@ struct event_command {
extern int trace_event_enable_disable(struct ftrace_event_file *file,
int enable, int soft_disable);
+extern int tracing_alloc_snapshot(void);
extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 4ea72ee..d775c3d 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -696,6 +696,90 @@ static struct event_command trigger_traceoff_cmd = {
.get_trigger_ops = onoff_get_trigger_ops,
};
+#ifdef CONFIG_TRACER_SNAPSHOT
+static void
+snapshot_trigger(struct event_trigger_data *data)
+{
+ tracing_snapshot();
+}
+
+static void
+snapshot_count_trigger(struct event_trigger_data *data)
+{
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ snapshot_trigger(data);
+}
+
+static int
+register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file)
+{
+ int ret = register_trigger(glob, ops, data, file);
+
+ if (ret > 0 && tracing_alloc_snapshot() != 0) {
+ unregister_trigger(glob, ops, data, file);
+ ret = 0;
+ }
+
+ return ret;
+}
+
+static int
+snapshot_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("snapshot", m, (void *)data->count,
+ data->filter_str);
+}
+
+static struct event_trigger_ops snapshot_trigger_ops = {
+ .func = snapshot_trigger,
+ .print = snapshot_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops snapshot_count_trigger_ops = {
+ .func = snapshot_count_trigger,
+ .print = snapshot_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops *
+snapshot_get_trigger_ops(char *cmd, char *param)
+{
+ return param ? &snapshot_count_trigger_ops : &snapshot_trigger_ops;
+}
+
+static struct event_command trigger_snapshot_cmd = {
+ .name = "snapshot",
+ .trigger_type = ETT_SNAPSHOT,
+ .func = event_trigger_callback,
+ .reg = register_snapshot_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = snapshot_get_trigger_ops,
+};
+
+static __init int register_trigger_snapshot_cmd(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_snapshot_cmd);
+ WARN_ON(ret < 0);
+
+ return ret;
+}
+#else
+static __init int register_trigger_snapshot_cmd(void) { return 0; }
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
static __init void unregister_trigger_traceon_traceoff_cmds(void)
{
unregister_event_command(&trigger_traceon_cmd);
@@ -719,6 +803,7 @@ static __init int register_trigger_traceon_traceoff_cmds(void)
__init int register_trigger_cmds(void)
{
register_trigger_traceon_traceoff_cmds();
+ register_trigger_snapshot_cmd();
return 0;
}
--
1.8.4.3
^ permalink raw reply related [flat|nested] 11+ messages in thread* [for-next][PATCH 04/10] tracing: Add stacktrace event trigger command
2013-12-23 21:38 [for-next][PATCH 00/10] tracing: Addition of trace event trigeers Steven Rostedt
` (2 preceding siblings ...)
2013-12-23 21:38 ` [for-next][PATCH 03/10] tracing: Add snapshot event trigger command Steven Rostedt
@ 2013-12-23 21:38 ` Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 05/10] tracing: Add enable_event and disable_event event trigger commands Steven Rostedt
` (5 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Steven Rostedt @ 2013-12-23 21:38 UTC (permalink / raw)
To: linux-kernel; +Cc: Ingo Molnar, Frederic Weisbecker, Tom Zanussi, Andrew Morton
[-- Attachment #1: 0004-tracing-Add-stacktrace-event-trigger-command.patch --]
[-- Type: text/plain, Size: 4265 bytes --]
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Add 'stacktrace' event_command. stacktrace event triggers are added
by the user via this command in a similar way and using practically
the same syntax as the analogous 'stacktrace' ftrace function command,
but instead of writing to the set_ftrace_filter file, the stacktrace
event trigger is written to the per-event 'trigger' files:
echo 'stacktrace' > .../tracing/events/somesys/someevent/trigger
The above command will turn on stacktraces for someevent i.e. whenever
someevent is hit, a stacktrace will be logged.
This also adds a 'count' version that limits the number of times the
command will be invoked:
echo 'stacktrace:N' > .../tracing/events/somesys/someevent/trigger
Where N is the number of times the command will be invoked.
The above command will log N stacktraces for someevent i.e. whenever
someevent is hit N times, a stacktrace will be logged.
Link: http://lkml.kernel.org/r/0c30c008a0828c660aa0e1bbd3255cf179ed5c30.1382622043.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 1 +
kernel/trace/trace_events_trigger.c | 79 +++++++++++++++++++++++++++++++++++++
2 files changed, 80 insertions(+)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 6efa8c2..65caee4 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -347,6 +347,7 @@ enum event_trigger_type {
ETT_NONE = (0),
ETT_TRACE_ONOFF = (1 << 0),
ETT_SNAPSHOT = (1 << 1),
+ ETT_STACKTRACE = (1 << 2),
};
extern void destroy_preds(struct ftrace_event_file *file);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d775c3d..a3bd1da 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -780,6 +780,84 @@ static __init int register_trigger_snapshot_cmd(void)
static __init int register_trigger_snapshot_cmd(void) { return 0; }
#endif /* CONFIG_TRACER_SNAPSHOT */
+#ifdef CONFIG_STACKTRACE
+/*
+ * Skip 3:
+ * stacktrace_trigger()
+ * event_triggers_post_call()
+ * ftrace_raw_event_xxx()
+ */
+#define STACK_SKIP 3
+
+static void
+stacktrace_trigger(struct event_trigger_data *data)
+{
+ trace_dump_stack(STACK_SKIP);
+}
+
+static void
+stacktrace_count_trigger(struct event_trigger_data *data)
+{
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ stacktrace_trigger(data);
+}
+
+static int
+stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("stacktrace", m, (void *)data->count,
+ data->filter_str);
+}
+
+static struct event_trigger_ops stacktrace_trigger_ops = {
+ .func = stacktrace_trigger,
+ .print = stacktrace_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops stacktrace_count_trigger_ops = {
+ .func = stacktrace_count_trigger,
+ .print = stacktrace_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops *
+stacktrace_get_trigger_ops(char *cmd, char *param)
+{
+ return param ? &stacktrace_count_trigger_ops : &stacktrace_trigger_ops;
+}
+
+static struct event_command trigger_stacktrace_cmd = {
+ .name = "stacktrace",
+ .trigger_type = ETT_STACKTRACE,
+ .post_trigger = true,
+ .func = event_trigger_callback,
+ .reg = register_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = stacktrace_get_trigger_ops,
+};
+
+static __init int register_trigger_stacktrace_cmd(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_stacktrace_cmd);
+ WARN_ON(ret < 0);
+
+ return ret;
+}
+#else
+static __init int register_trigger_stacktrace_cmd(void) { return 0; }
+#endif /* CONFIG_STACKTRACE */
+
static __init void unregister_trigger_traceon_traceoff_cmds(void)
{
unregister_event_command(&trigger_traceon_cmd);
@@ -804,6 +882,7 @@ __init int register_trigger_cmds(void)
{
register_trigger_traceon_traceoff_cmds();
register_trigger_snapshot_cmd();
+ register_trigger_stacktrace_cmd();
return 0;
}
--
1.8.4.3
^ permalink raw reply related [flat|nested] 11+ messages in thread* [for-next][PATCH 05/10] tracing: Add enable_event and disable_event event trigger commands
2013-12-23 21:38 [for-next][PATCH 00/10] tracing: Addition of trace event trigeers Steven Rostedt
` (3 preceding siblings ...)
2013-12-23 21:38 ` [for-next][PATCH 04/10] tracing: Add stacktrace " Steven Rostedt
@ 2013-12-23 21:38 ` Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 06/10] tracing: Move ftrace_event_file() out of DYNAMIC_FTRACE ifdef Steven Rostedt
` (4 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Steven Rostedt @ 2013-12-23 21:38 UTC (permalink / raw)
To: linux-kernel; +Cc: Ingo Molnar, Frederic Weisbecker, Tom Zanussi, Andrew Morton
[-- Attachment #1: 0005-tracing-Add-enable_event-and-disable_event-event-tri.patch --]
[-- Type: text/plain, Size: 13076 bytes --]
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Add 'enable_event' and 'disable_event' event_command commands.
enable_event and disable_event event triggers are added by the user
via these commands in a similar way and using practically the same
syntax as the analagous 'enable_event' and 'disable_event' ftrace
function commands, but instead of writing to the set_ftrace_filter
file, the enable_event and disable_event triggers are written to the
per-event 'trigger' files:
echo 'enable_event:system:event' > .../othersys/otherevent/trigger
echo 'disable_event:system:event' > .../othersys/otherevent/trigger
The above commands will enable or disable the 'system:event' trace
events whenever the othersys:otherevent events are hit.
This also adds a 'count' version that limits the number of times the
command will be invoked:
echo 'enable_event:system:event:N' > .../othersys/otherevent/trigger
echo 'disable_event:system:event:N' > .../othersys/otherevent/trigger
Where N is the number of times the command will be invoked.
The above commands will will enable or disable the 'system:event'
trace events whenever the othersys:otherevent events are hit, but only
N times.
This also makes the find_event_file() helper function extern, since
it's useful to use from other places, such as the event triggers code,
so make it accessible.
Link: http://lkml.kernel.org/r/f825f3048c3f6b026ee37ae5825f9fc373451828.1382622043.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 1 +
kernel/trace/trace.h | 4 +
kernel/trace/trace_events.c | 2 +-
kernel/trace/trace_events_trigger.c | 359 ++++++++++++++++++++++++++++++++++++
4 files changed, 365 insertions(+), 1 deletion(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 65caee4..2f73c398 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -348,6 +348,7 @@ enum event_trigger_type {
ETT_TRACE_ONOFF = (1 << 0),
ETT_SNAPSHOT = (1 << 1),
ETT_STACKTRACE = (1 << 2),
+ ETT_EVENT_ENABLE = (1 << 3),
};
extern void destroy_preds(struct ftrace_event_file *file);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 50723e5..ccbd810 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1028,6 +1028,10 @@ extern void trace_event_enable_cmd_record(bool enable);
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
extern int event_trace_del_tracer(struct trace_array *tr);
+extern struct ftrace_event_file *find_event_file(struct trace_array *tr,
+ const char *system,
+ const char *event);
+
static inline void *event_file_data(struct file *filp)
{
return ACCESS_ONCE(file_inode(filp)->i_private);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 442775c..9a974bd 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1868,7 +1868,7 @@ struct event_probe_data {
bool enable;
};
-static struct ftrace_event_file *
+struct ftrace_event_file *
find_event_file(struct trace_array *tr, const char *system, const char *event)
{
struct ftrace_event_file *file;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index a3bd1da..45e48b1 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -864,6 +864,364 @@ static __init void unregister_trigger_traceon_traceoff_cmds(void)
unregister_event_command(&trigger_traceoff_cmd);
}
+/* Avoid typos */
+#define ENABLE_EVENT_STR "enable_event"
+#define DISABLE_EVENT_STR "disable_event"
+
+struct enable_trigger_data {
+ struct ftrace_event_file *file;
+ bool enable;
+};
+
+static void
+event_enable_trigger(struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ if (enable_data->enable)
+ clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &enable_data->file->flags);
+ else
+ set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &enable_data->file->flags);
+}
+
+static void
+event_enable_count_trigger(struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ if (!data->count)
+ return;
+
+ /* Skip if the event is in a state we want to switch to */
+ if (enable_data->enable == !(enable_data->file->flags & FTRACE_EVENT_FL_SOFT_DISABLED))
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ event_enable_trigger(data);
+}
+
+static int
+event_enable_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ seq_printf(m, "%s:%s:%s",
+ enable_data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
+ enable_data->file->event_call->class->system,
+ enable_data->file->event_call->name);
+
+ if (data->count == -1)
+ seq_puts(m, ":unlimited");
+ else
+ seq_printf(m, ":count=%ld", data->count);
+
+ if (data->filter_str)
+ seq_printf(m, " if %s\n", data->filter_str);
+ else
+ seq_puts(m, "\n");
+
+ return 0;
+}
+
+static void
+event_enable_trigger_free(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ if (WARN_ON_ONCE(data->ref <= 0))
+ return;
+
+ data->ref--;
+ if (!data->ref) {
+ /* Remove the SOFT_MODE flag */
+ trace_event_enable_disable(enable_data->file, 0, 1);
+ module_put(enable_data->file->event_call->mod);
+ trigger_data_free(data);
+ kfree(enable_data);
+ }
+}
+
+static struct event_trigger_ops event_enable_trigger_ops = {
+ .func = event_enable_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_enable_count_trigger_ops = {
+ .func = event_enable_count_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_disable_trigger_ops = {
+ .func = event_enable_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_disable_count_trigger_ops = {
+ .func = event_enable_count_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static int
+event_enable_trigger_func(struct event_command *cmd_ops,
+ struct ftrace_event_file *file,
+ char *glob, char *cmd, char *param)
+{
+ struct ftrace_event_file *event_enable_file;
+ struct enable_trigger_data *enable_data;
+ struct event_trigger_data *trigger_data;
+ struct event_trigger_ops *trigger_ops;
+ struct trace_array *tr = file->tr;
+ const char *system;
+ const char *event;
+ char *trigger;
+ char *number;
+ bool enable;
+ int ret;
+
+ if (!param)
+ return -EINVAL;
+
+ /* separate the trigger from the filter (s:e:n [if filter]) */
+ trigger = strsep(¶m, " \t");
+ if (!trigger)
+ return -EINVAL;
+
+ system = strsep(&trigger, ":");
+ if (!trigger)
+ return -EINVAL;
+
+ event = strsep(&trigger, ":");
+
+ ret = -EINVAL;
+ event_enable_file = find_event_file(tr, system, event);
+ if (!event_enable_file)
+ goto out;
+
+ enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
+
+ trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+
+ ret = -ENOMEM;
+ trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+ if (!trigger_data)
+ goto out;
+
+ enable_data = kzalloc(sizeof(*enable_data), GFP_KERNEL);
+ if (!enable_data) {
+ kfree(trigger_data);
+ goto out;
+ }
+
+ trigger_data->count = -1;
+ trigger_data->ops = trigger_ops;
+ trigger_data->cmd_ops = cmd_ops;
+ INIT_LIST_HEAD(&trigger_data->list);
+ RCU_INIT_POINTER(trigger_data->filter, NULL);
+
+ enable_data->enable = enable;
+ enable_data->file = event_enable_file;
+ trigger_data->private_data = enable_data;
+
+ if (glob[0] == '!') {
+ cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+ kfree(trigger_data);
+ kfree(enable_data);
+ ret = 0;
+ goto out;
+ }
+
+ if (trigger) {
+ number = strsep(&trigger, ":");
+
+ ret = -EINVAL;
+ if (!strlen(number))
+ goto out_free;
+
+ /*
+ * We use the callback data field (which is a pointer)
+ * as our counter.
+ */
+ ret = kstrtoul(number, 0, &trigger_data->count);
+ if (ret)
+ goto out_free;
+ }
+
+ if (!param) /* if param is non-empty, it's supposed to be a filter */
+ goto out_reg;
+
+ if (!cmd_ops->set_filter)
+ goto out_reg;
+
+ ret = cmd_ops->set_filter(param, trigger_data, file);
+ if (ret < 0)
+ goto out_free;
+
+ out_reg:
+ /* Don't let event modules unload while probe registered */
+ ret = try_module_get(event_enable_file->event_call->mod);
+ if (!ret) {
+ ret = -EBUSY;
+ goto out_free;
+ }
+
+ ret = trace_event_enable_disable(event_enable_file, 1, 1);
+ if (ret < 0)
+ goto out_put;
+ ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
+ /*
+ * The above returns on success the # of functions enabled,
+ * but if it didn't find any functions it returns zero.
+ * Consider no functions a failure too.
+ */
+ if (!ret) {
+ ret = -ENOENT;
+ goto out_disable;
+ } else if (ret < 0)
+ goto out_disable;
+ /* Just return zero, not the number of enabled functions */
+ ret = 0;
+ out:
+ return ret;
+
+ out_disable:
+ trace_event_enable_disable(event_enable_file, 0, 1);
+ out_put:
+ module_put(event_enable_file->event_call->mod);
+ out_free:
+ kfree(trigger_data);
+ kfree(enable_data);
+ goto out;
+}
+
+static int event_enable_register_trigger(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+ struct enable_trigger_data *test_enable_data;
+ struct event_trigger_data *test;
+ int ret = 0;
+
+ list_for_each_entry_rcu(test, &file->triggers, list) {
+ test_enable_data = test->private_data;
+ if (test_enable_data &&
+ (test_enable_data->file == enable_data->file)) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+
+ if (data->ops->init) {
+ ret = data->ops->init(data->ops, data);
+ if (ret < 0)
+ goto out;
+ }
+
+ list_add_rcu(&data->list, &file->triggers);
+ ret++;
+
+ if (trace_event_trigger_enable_disable(file, 1) < 0) {
+ list_del_rcu(&data->list);
+ ret--;
+ }
+out:
+ return ret;
+}
+
+static void event_enable_unregister_trigger(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *test,
+ struct ftrace_event_file *file)
+{
+ struct enable_trigger_data *test_enable_data = test->private_data;
+ struct enable_trigger_data *enable_data;
+ struct event_trigger_data *data;
+ bool unregistered = false;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ enable_data = data->private_data;
+ if (enable_data &&
+ (enable_data->file == test_enable_data->file)) {
+ unregistered = true;
+ list_del_rcu(&data->list);
+ trace_event_trigger_enable_disable(file, 0);
+ break;
+ }
+ }
+
+ if (unregistered && data->ops->free)
+ data->ops->free(data->ops, data);
+}
+
+static struct event_trigger_ops *
+event_enable_get_trigger_ops(char *cmd, char *param)
+{
+ struct event_trigger_ops *ops;
+ bool enable;
+
+ enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
+
+ if (enable)
+ ops = param ? &event_enable_count_trigger_ops :
+ &event_enable_trigger_ops;
+ else
+ ops = param ? &event_disable_count_trigger_ops :
+ &event_disable_trigger_ops;
+
+ return ops;
+}
+
+static struct event_command trigger_enable_cmd = {
+ .name = ENABLE_EVENT_STR,
+ .trigger_type = ETT_EVENT_ENABLE,
+ .func = event_enable_trigger_func,
+ .reg = event_enable_register_trigger,
+ .unreg = event_enable_unregister_trigger,
+ .get_trigger_ops = event_enable_get_trigger_ops,
+};
+
+static struct event_command trigger_disable_cmd = {
+ .name = DISABLE_EVENT_STR,
+ .trigger_type = ETT_EVENT_ENABLE,
+ .func = event_enable_trigger_func,
+ .reg = event_enable_register_trigger,
+ .unreg = event_enable_unregister_trigger,
+ .get_trigger_ops = event_enable_get_trigger_ops,
+};
+
+static __init void unregister_trigger_enable_disable_cmds(void)
+{
+ unregister_event_command(&trigger_enable_cmd);
+ unregister_event_command(&trigger_disable_cmd);
+}
+
+static __init int register_trigger_enable_disable_cmds(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_enable_cmd);
+ if (WARN_ON(ret < 0))
+ return ret;
+ ret = register_event_command(&trigger_disable_cmd);
+ if (WARN_ON(ret < 0))
+ unregister_trigger_enable_disable_cmds();
+
+ return ret;
+}
+
static __init int register_trigger_traceon_traceoff_cmds(void)
{
int ret;
@@ -883,6 +1241,7 @@ __init int register_trigger_cmds(void)
register_trigger_traceon_traceoff_cmds();
register_trigger_snapshot_cmd();
register_trigger_stacktrace_cmd();
+ register_trigger_enable_disable_cmds();
return 0;
}
--
1.8.4.3
^ permalink raw reply related [flat|nested] 11+ messages in thread* [for-next][PATCH 06/10] tracing: Move ftrace_event_file() out of DYNAMIC_FTRACE ifdef
2013-12-23 21:38 [for-next][PATCH 00/10] tracing: Addition of trace event trigeers Steven Rostedt
` (4 preceding siblings ...)
2013-12-23 21:38 ` [for-next][PATCH 05/10] tracing: Add enable_event and disable_event event trigger commands Steven Rostedt
@ 2013-12-23 21:38 ` Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 07/10] tracing: Add and use generic set_trigger_filter() implementation Steven Rostedt
` (3 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Steven Rostedt @ 2013-12-23 21:38 UTC (permalink / raw)
To: linux-kernel; +Cc: Ingo Molnar, Frederic Weisbecker, Tom Zanussi, Andrew Morton
[-- Attachment #1: 0006-tracing-Move-ftrace_event_file-out-of-DYNAMIC_FTRACE.patch --]
[-- Type: text/plain, Size: 1492 bytes --]
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Now that event triggers use ftrace_event_file(), it needs to be outside
the #ifdef CONFIG_DYNAMIC_FTRACE, as it can now be used when that is
not defined.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
kernel/trace/trace_events.c | 26 +++++++++++++-------------
1 file changed, 13 insertions(+), 13 deletions(-)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 9a974bd..e71ffd4 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1855,19 +1855,6 @@ __trace_add_event_dirs(struct trace_array *tr)
}
}
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-/* Avoid typos */
-#define ENABLE_EVENT_STR "enable_event"
-#define DISABLE_EVENT_STR "disable_event"
-
-struct event_probe_data {
- struct ftrace_event_file *file;
- unsigned long count;
- int ref;
- bool enable;
-};
-
struct ftrace_event_file *
find_event_file(struct trace_array *tr, const char *system, const char *event)
{
@@ -1891,6 +1878,19 @@ find_event_file(struct trace_array *tr, const char *system, const char *event)
return NULL;
}
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+/* Avoid typos */
+#define ENABLE_EVENT_STR "enable_event"
+#define DISABLE_EVENT_STR "disable_event"
+
+struct event_probe_data {
+ struct ftrace_event_file *file;
+ unsigned long count;
+ int ref;
+ bool enable;
+};
+
static void
event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data)
{
--
1.8.4.3
^ permalink raw reply related [flat|nested] 11+ messages in thread* [for-next][PATCH 07/10] tracing: Add and use generic set_trigger_filter() implementation
2013-12-23 21:38 [for-next][PATCH 00/10] tracing: Addition of trace event trigeers Steven Rostedt
` (5 preceding siblings ...)
2013-12-23 21:38 ` [for-next][PATCH 06/10] tracing: Move ftrace_event_file() out of DYNAMIC_FTRACE ifdef Steven Rostedt
@ 2013-12-23 21:38 ` Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 08/10] tracing: Add documentation for trace event triggers Steven Rostedt
` (2 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Steven Rostedt @ 2013-12-23 21:38 UTC (permalink / raw)
To: linux-kernel; +Cc: Ingo Molnar, Frederic Weisbecker, Tom Zanussi, Andrew Morton
[-- Attachment #1: 0007-tracing-Add-and-use-generic-set_trigger_filter-imple.patch --]
[-- Type: text/plain, Size: 24190 bytes --]
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Add a generic event_command.set_trigger_filter() op implementation and
have the current set of trigger commands use it - this essentially
gives them all support for filters.
Syntactically, filters are supported by adding 'if <filter>' just
after the command, in which case only events matching the filter will
invoke the trigger. For example, to add a filter to an
enable/disable_event command:
echo 'enable_event:system:event if common_pid == 999' > \
.../othersys/otherevent/trigger
The above command will only enable the system:event event if the
common_pid field in the othersys:otherevent event is 999.
As another example, to add a filter to a stacktrace command:
echo 'stacktrace if common_pid == 999' > \
.../somesys/someevent/trigger
The above command will only trigger a stacktrace if the common_pid
field in the event is 999.
The filter syntax is the same as that described in the 'Event
filtering' section of Documentation/trace/events.txt.
Because triggers can now use filters, the trigger-invoking logic needs
to be moved in those cases - e.g. for ftrace_raw_event_calls, if a
trigger has a filter associated with it, the trigger invocation now
needs to happen after the { assign; } part of the call, in order for
the trigger condition to be tested.
There's still a SOFT_DISABLED-only check at the top of e.g. the
ftrace_raw_events function, so when an event is soft disabled but not
because of the presence of a trigger, the original SOFT_DISABLED
behavior remains unchanged.
There's also a bit of trickiness in that some triggers need to avoid
being invoked while an event is currently in the process of being
logged, since the trigger may itself log data into the trace buffer.
Thus we make sure the current event is committed before invoking those
triggers. To do that, we split the trigger invocation in two - the
first part (event_triggers_call()) checks the filter using the current
trace record; if a command has the post_trigger flag set, it sets a
bit for itself in the return value, otherwise it directly invoks the
trigger. Once all commands have been either invoked or set their
return flag, event_triggers_call() returns. The current record is
then either committed or discarded; if any commands have deferred
their triggers, those commands are finally invoked following the close
of the current event by event_triggers_post_call().
To simplify the above and make it more efficient, the TRIGGER_COND bit
is introduced, which is set only if a soft-disabled trigger needs to
use the log record for filter testing or needs to wait until the
current log record is closed.
The syscall event invocation code is also changed in analogous ways.
Because event triggers need to be able to create and free filters,
this also adds a couple external wrappers for the existing
create_filter and free_filter functions, which are too generic to be
made extern functions themselves.
Link: http://lkml.kernel.org/r/7164930759d8719ef460357f143d995406e4eead.1382622043.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 9 +-
include/trace/ftrace.h | 48 +++++++---
kernel/trace/trace.h | 5 ++
kernel/trace/trace_events_filter.c | 12 +++
kernel/trace/trace_events_trigger.c | 170 +++++++++++++++++++++++++++++++++++-
kernel/trace/trace_syscalls.c | 46 +++++++---
6 files changed, 263 insertions(+), 27 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 2f73c398..03d2db2 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -1,3 +1,4 @@
+
#ifndef _LINUX_FTRACE_EVENT_H
#define _LINUX_FTRACE_EVENT_H
@@ -265,6 +266,7 @@ enum {
FTRACE_EVENT_FL_SOFT_MODE_BIT,
FTRACE_EVENT_FL_SOFT_DISABLED_BIT,
FTRACE_EVENT_FL_TRIGGER_MODE_BIT,
+ FTRACE_EVENT_FL_TRIGGER_COND_BIT,
};
/*
@@ -277,6 +279,7 @@ enum {
* SOFT_DISABLED - When set, do not trace the event (even though its
* tracepoint may be enabled)
* TRIGGER_MODE - When set, invoke the triggers associated with the event
+ * TRIGGER_COND - When set, one or more triggers has an associated filter
*/
enum {
FTRACE_EVENT_FL_ENABLED = (1 << FTRACE_EVENT_FL_ENABLED_BIT),
@@ -286,6 +289,7 @@ enum {
FTRACE_EVENT_FL_SOFT_MODE = (1 << FTRACE_EVENT_FL_SOFT_MODE_BIT),
FTRACE_EVENT_FL_SOFT_DISABLED = (1 << FTRACE_EVENT_FL_SOFT_DISABLED_BIT),
FTRACE_EVENT_FL_TRIGGER_MODE = (1 << FTRACE_EVENT_FL_TRIGGER_MODE_BIT),
+ FTRACE_EVENT_FL_TRIGGER_COND = (1 << FTRACE_EVENT_FL_TRIGGER_COND_BIT),
};
struct ftrace_event_file {
@@ -361,7 +365,10 @@ extern int filter_check_discard(struct ftrace_event_file *file, void *rec,
extern int call_filter_check_discard(struct ftrace_event_call *call, void *rec,
struct ring_buffer *buffer,
struct ring_buffer_event *event);
-extern void event_triggers_call(struct ftrace_event_file *file);
+extern enum event_trigger_type event_triggers_call(struct ftrace_event_file *file,
+ void *rec);
+extern void event_triggers_post_call(struct ftrace_event_file *file,
+ enum event_trigger_type tt);
enum {
FILTER_OTHER = 0,
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 0a48bff..0962968 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -418,6 +418,8 @@ static inline notrace int ftrace_get_offsets_##call( \
* struct ftrace_event_file *ftrace_file = __data;
* struct ftrace_event_call *event_call = ftrace_file->event_call;
* struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
+ * unsigned long eflags = ftrace_file->flags;
+ * enum event_trigger_type __tt = ETT_NONE;
* struct ring_buffer_event *event;
* struct ftrace_raw_<call> *entry; <-- defined in stage 1
* struct ring_buffer *buffer;
@@ -425,9 +427,12 @@ static inline notrace int ftrace_get_offsets_##call( \
* int __data_size;
* int pc;
*
- * if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT,
- * &ftrace_file->flags))
- * return;
+ * if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND)) {
+ * if (eflags & FTRACE_EVENT_FL_TRIGGER_MODE)
+ * event_triggers_call(ftrace_file, NULL);
+ * if (eflags & FTRACE_EVENT_FL_SOFT_DISABLED)
+ * return;
+ * }
*
* local_save_flags(irq_flags);
* pc = preempt_count();
@@ -445,8 +450,17 @@ static inline notrace int ftrace_get_offsets_##call( \
* { <assign>; } <-- Here we assign the entries by the __field and
* __array macros.
*
- * if (!filter_check_discard(ftrace_file, entry, buffer, event))
+ * if (eflags & FTRACE_EVENT_FL_TRIGGER_COND)
+ * __tt = event_triggers_call(ftrace_file, entry);
+ *
+ * if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT,
+ * &ftrace_file->flags))
+ * ring_buffer_discard_commit(buffer, event);
+ * else if (!filter_check_discard(ftrace_file, entry, buffer, event))
* trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ *
+ * if (__tt)
+ * event_triggers_post_call(ftrace_file, __tt);
* }
*
* static struct trace_event ftrace_event_type_<call> = {
@@ -532,6 +546,8 @@ ftrace_raw_event_##call(void *__data, proto) \
struct ftrace_event_file *ftrace_file = __data; \
struct ftrace_event_call *event_call = ftrace_file->event_call; \
struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
+ unsigned long eflags = ftrace_file->flags; \
+ enum event_trigger_type __tt = ETT_NONE; \
struct ring_buffer_event *event; \
struct ftrace_raw_##call *entry; \
struct ring_buffer *buffer; \
@@ -539,13 +555,12 @@ ftrace_raw_event_##call(void *__data, proto) \
int __data_size; \
int pc; \
\
- if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, \
- &ftrace_file->flags)) \
- event_triggers_call(ftrace_file); \
- \
- if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, \
- &ftrace_file->flags)) \
- return; \
+ if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND)) { \
+ if (eflags & FTRACE_EVENT_FL_TRIGGER_MODE) \
+ event_triggers_call(ftrace_file, NULL); \
+ if (eflags & FTRACE_EVENT_FL_SOFT_DISABLED) \
+ return; \
+ } \
\
local_save_flags(irq_flags); \
pc = preempt_count(); \
@@ -564,8 +579,17 @@ ftrace_raw_event_##call(void *__data, proto) \
\
{ assign; } \
\
- if (!filter_check_discard(ftrace_file, entry, buffer, event)) \
+ if (eflags & FTRACE_EVENT_FL_TRIGGER_COND) \
+ __tt = event_triggers_call(ftrace_file, entry); \
+ \
+ if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, \
+ &ftrace_file->flags)) \
+ ring_buffer_discard_commit(buffer, event); \
+ else if (!filter_check_discard(ftrace_file, entry, buffer, event)) \
trace_buffer_unlock_commit(buffer, event, irq_flags, pc); \
+ \
+ if (__tt) \
+ event_triggers_post_call(ftrace_file, __tt); \
}
/*
* The ftrace_test_probe is compiled out, it is only here as a build time check
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index ccbd810..433bfc5 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1,3 +1,4 @@
+
#ifndef _LINUX_KERNEL_TRACE_H
#define _LINUX_KERNEL_TRACE_H
@@ -1020,6 +1021,10 @@ extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
extern void print_subsystem_event_filter(struct event_subsystem *system,
struct trace_seq *s);
extern int filter_assign_type(const char *type);
+extern int create_event_filter(struct ftrace_event_call *call,
+ char *filter_str, bool set_str,
+ struct event_filter **filterp);
+extern void free_event_filter(struct event_filter *filter);
struct ftrace_event_field *
trace_find_event_field(struct ftrace_event_call *call, char *name);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 2468f56..8a86319 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -799,6 +799,11 @@ static void __free_filter(struct event_filter *filter)
kfree(filter);
}
+void free_event_filter(struct event_filter *filter)
+{
+ __free_filter(filter);
+}
+
void destroy_call_preds(struct ftrace_event_call *call)
{
__free_filter(call->filter);
@@ -1938,6 +1943,13 @@ static int create_filter(struct ftrace_event_call *call,
return err;
}
+int create_event_filter(struct ftrace_event_call *call,
+ char *filter_str, bool set_str,
+ struct event_filter **filterp)
+{
+ return create_filter(call, filter_str, set_str, filterp);
+}
+
/**
* create_system_filter - create a filter for an event_subsystem
* @system: event_subsystem to create a filter for
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 45e48b1..f5b3f78 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -31,6 +31,9 @@ static DEFINE_MUTEX(trigger_cmd_mutex);
static void
trigger_data_free(struct event_trigger_data *data)
{
+ if (data->cmd_ops->set_filter)
+ data->cmd_ops->set_filter(NULL, data, NULL);
+
synchronize_sched(); /* make sure current triggers exit before free */
kfree(data);
}
@@ -38,27 +41,78 @@ trigger_data_free(struct event_trigger_data *data)
/**
* event_triggers_call - Call triggers associated with a trace event
* @file: The ftrace_event_file associated with the event
+ * @rec: The trace entry for the event, NULL for unconditional invocation
*
* For each trigger associated with an event, invoke the trigger
- * function registered with the associated trigger command.
+ * function registered with the associated trigger command. If rec is
+ * non-NULL, it means that the trigger requires further processing and
+ * shouldn't be unconditionally invoked. If rec is non-NULL and the
+ * trigger has a filter associated with it, rec will checked against
+ * the filter and if the record matches the trigger will be invoked.
+ * If the trigger is a 'post_trigger', meaning it shouldn't be invoked
+ * in any case until the current event is written, the trigger
+ * function isn't invoked but the bit associated with the deferred
+ * trigger is set in the return value.
+ *
+ * Returns an enum event_trigger_type value containing a set bit for
+ * any trigger that should be deferred, ETT_NONE if nothing to defer.
*
* Called from tracepoint handlers (with rcu_read_lock_sched() held).
*
* Return: an enum event_trigger_type value containing a set bit for
* any trigger that should be deferred, ETT_NONE if nothing to defer.
*/
-void event_triggers_call(struct ftrace_event_file *file)
+enum event_trigger_type
+event_triggers_call(struct ftrace_event_file *file, void *rec)
{
struct event_trigger_data *data;
+ enum event_trigger_type tt = ETT_NONE;
if (list_empty(&file->triggers))
- return;
+ return tt;
- list_for_each_entry_rcu(data, &file->triggers, list)
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (!rec) {
+ data->ops->func(data);
+ continue;
+ }
+ if (data->filter && !filter_match_preds(data->filter, rec))
+ continue;
+ if (data->cmd_ops->post_trigger) {
+ tt |= data->cmd_ops->trigger_type;
+ continue;
+ }
data->ops->func(data);
+ }
+ return tt;
}
EXPORT_SYMBOL_GPL(event_triggers_call);
+/**
+ * event_triggers_post_call - Call 'post_triggers' for a trace event
+ * @file: The ftrace_event_file associated with the event
+ * @tt: enum event_trigger_type containing a set bit for each trigger to invoke
+ *
+ * For each trigger associated with an event, invoke the trigger
+ * function registered with the associated trigger command, if the
+ * corresponding bit is set in the tt enum passed into this function.
+ * See @event_triggers_call for details on how those bits are set.
+ *
+ * Called from tracepoint handlers (with rcu_read_lock_sched() held).
+ */
+void
+event_triggers_post_call(struct ftrace_event_file *file,
+ enum event_trigger_type tt)
+{
+ struct event_trigger_data *data;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->cmd_ops->trigger_type & tt)
+ data->ops->func(data);
+ }
+}
+EXPORT_SYMBOL_GPL(event_triggers_post_call);
+
static void *trigger_next(struct seq_file *m, void *t, loff_t *pos)
{
struct ftrace_event_file *event_file = event_file_data(m->private);
@@ -403,6 +457,34 @@ clear_event_triggers(struct trace_array *tr)
}
/**
+ * update_cond_flag - Set or reset the TRIGGER_COND bit
+ * @file: The ftrace_event_file associated with the event
+ *
+ * If an event has triggers and any of those triggers has a filter or
+ * a post_trigger, trigger invocation needs to be deferred until after
+ * the current event has logged its data, and the event should have
+ * its TRIGGER_COND bit set, otherwise the TRIGGER_COND bit should be
+ * cleared.
+ */
+static void update_cond_flag(struct ftrace_event_file *file)
+{
+ struct event_trigger_data *data;
+ bool set_cond = false;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->filter || data->cmd_ops->post_trigger) {
+ set_cond = true;
+ break;
+ }
+ }
+
+ if (set_cond)
+ set_bit(FTRACE_EVENT_FL_TRIGGER_COND_BIT, &file->flags);
+ else
+ clear_bit(FTRACE_EVENT_FL_TRIGGER_COND_BIT, &file->flags);
+}
+
+/**
* register_trigger - Generic event_command @reg implementation
* @glob: The raw string used to register the trigger
* @ops: The trigger ops associated with the trigger
@@ -443,6 +525,7 @@ static int register_trigger(char *glob, struct event_trigger_ops *ops,
list_del_rcu(&data->list);
ret--;
}
+ update_cond_flag(file);
out:
return ret;
}
@@ -470,6 +553,7 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
unregistered = true;
list_del_rcu(&data->list);
+ update_cond_flag(file);
trace_event_trigger_enable_disable(file, 0);
break;
}
@@ -572,10 +656,78 @@ event_trigger_callback(struct event_command *cmd_ops,
return ret;
out_free:
+ if (cmd_ops->set_filter)
+ cmd_ops->set_filter(NULL, trigger_data, NULL);
kfree(trigger_data);
goto out;
}
+/**
+ * set_trigger_filter - Generic event_command @set_filter implementation
+ * @filter_str: The filter string for the trigger, NULL to remove filter
+ * @trigger_data: Trigger-specific data
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event command filter parsing and filter
+ * instantiation.
+ *
+ * Usually used directly as the @set_filter method in event command
+ * implementations.
+ *
+ * Also used to remove a filter (if filter_str = NULL).
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int set_trigger_filter(char *filter_str,
+ struct event_trigger_data *trigger_data,
+ struct ftrace_event_file *file)
+{
+ struct event_trigger_data *data = trigger_data;
+ struct event_filter *filter = NULL, *tmp;
+ int ret = -EINVAL;
+ char *s;
+
+ if (!filter_str) /* clear the current filter */
+ goto assign;
+
+ s = strsep(&filter_str, " \t");
+
+ if (!strlen(s) || strcmp(s, "if") != 0)
+ goto out;
+
+ if (!filter_str)
+ goto out;
+
+ /* The filter is for the 'trigger' event, not the triggered event */
+ ret = create_event_filter(file->event_call, filter_str, false, &filter);
+ if (ret)
+ goto out;
+ assign:
+ tmp = data->filter;
+
+ rcu_assign_pointer(data->filter, filter);
+
+ if (tmp) {
+ /* Make sure the call is done with the filter */
+ synchronize_sched();
+ free_event_filter(tmp);
+ }
+
+ kfree(data->filter_str);
+ data->filter_str = NULL;
+
+ if (filter_str) {
+ data->filter_str = kstrdup(filter_str, GFP_KERNEL);
+ if (!data->filter_str) {
+ free_event_filter(data->filter);
+ data->filter = NULL;
+ ret = -ENOMEM;
+ }
+ }
+ out:
+ return ret;
+}
+
static void
traceon_trigger(struct event_trigger_data *data)
{
@@ -685,6 +837,7 @@ static struct event_command trigger_traceon_cmd = {
.reg = register_trigger,
.unreg = unregister_trigger,
.get_trigger_ops = onoff_get_trigger_ops,
+ .set_filter = set_trigger_filter,
};
static struct event_command trigger_traceoff_cmd = {
@@ -694,6 +847,7 @@ static struct event_command trigger_traceoff_cmd = {
.reg = register_trigger,
.unreg = unregister_trigger,
.get_trigger_ops = onoff_get_trigger_ops,
+ .set_filter = set_trigger_filter,
};
#ifdef CONFIG_TRACER_SNAPSHOT
@@ -765,6 +919,7 @@ static struct event_command trigger_snapshot_cmd = {
.reg = register_snapshot_trigger,
.unreg = unregister_trigger,
.get_trigger_ops = snapshot_get_trigger_ops,
+ .set_filter = set_trigger_filter,
};
static __init int register_trigger_snapshot_cmd(void)
@@ -843,6 +998,7 @@ static struct event_command trigger_stacktrace_cmd = {
.reg = register_trigger,
.unreg = unregister_trigger,
.get_trigger_ops = stacktrace_get_trigger_ops,
+ .set_filter = set_trigger_filter,
};
static __init int register_trigger_stacktrace_cmd(void)
@@ -1100,6 +1256,8 @@ event_enable_trigger_func(struct event_command *cmd_ops,
out_put:
module_put(event_enable_file->event_call->mod);
out_free:
+ if (cmd_ops->set_filter)
+ cmd_ops->set_filter(NULL, trigger_data, NULL);
kfree(trigger_data);
kfree(enable_data);
goto out;
@@ -1137,6 +1295,7 @@ static int event_enable_register_trigger(char *glob,
list_del_rcu(&data->list);
ret--;
}
+ update_cond_flag(file);
out:
return ret;
}
@@ -1157,6 +1316,7 @@ static void event_enable_unregister_trigger(char *glob,
(enable_data->file == test_enable_data->file)) {
unregistered = true;
list_del_rcu(&data->list);
+ update_cond_flag(file);
trace_event_trigger_enable_disable(file, 0);
break;
}
@@ -1191,6 +1351,7 @@ static struct event_command trigger_enable_cmd = {
.reg = event_enable_register_trigger,
.unreg = event_enable_unregister_trigger,
.get_trigger_ops = event_enable_get_trigger_ops,
+ .set_filter = set_trigger_filter,
};
static struct event_command trigger_disable_cmd = {
@@ -1200,6 +1361,7 @@ static struct event_command trigger_disable_cmd = {
.reg = event_enable_register_trigger,
.unreg = event_enable_unregister_trigger,
.get_trigger_ops = event_enable_get_trigger_ops,
+ .set_filter = set_trigger_filter,
};
static __init void unregister_trigger_enable_disable_cmds(void)
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 936ec39..fdd955f 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -306,8 +306,10 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
struct syscall_trace_enter *entry;
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
+ enum event_trigger_type __tt = ETT_NONE;
struct ring_buffer *buffer;
unsigned long irq_flags;
+ unsigned long eflags;
int pc;
int syscall_nr;
int size;
@@ -321,10 +323,14 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
if (!ftrace_file)
return;
- if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &ftrace_file->flags))
- event_triggers_call(ftrace_file);
- if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
- return;
+ eflags = ftrace_file->flags;
+
+ if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND)) {
+ if (eflags & FTRACE_EVENT_FL_TRIGGER_MODE)
+ event_triggers_call(ftrace_file, NULL);
+ if (eflags & FTRACE_EVENT_FL_SOFT_DISABLED)
+ return;
+ }
sys_data = syscall_nr_to_meta(syscall_nr);
if (!sys_data)
@@ -345,9 +351,16 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
entry->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
- if (!filter_check_discard(ftrace_file, entry, buffer, event))
+ if (eflags & FTRACE_EVENT_FL_TRIGGER_COND)
+ __tt = event_triggers_call(ftrace_file, entry);
+
+ if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+ ring_buffer_discard_commit(buffer, event);
+ else if (!filter_check_discard(ftrace_file, entry, buffer, event))
trace_current_buffer_unlock_commit(buffer, event,
irq_flags, pc);
+ if (__tt)
+ event_triggers_post_call(ftrace_file, __tt);
}
static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -357,8 +370,10 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
struct syscall_trace_exit *entry;
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
+ enum event_trigger_type __tt = ETT_NONE;
struct ring_buffer *buffer;
unsigned long irq_flags;
+ unsigned long eflags;
int pc;
int syscall_nr;
@@ -371,10 +386,14 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
if (!ftrace_file)
return;
- if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &ftrace_file->flags))
- event_triggers_call(ftrace_file);
- if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
- return;
+ eflags = ftrace_file->flags;
+
+ if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND)) {
+ if (eflags & FTRACE_EVENT_FL_TRIGGER_MODE)
+ event_triggers_call(ftrace_file, NULL);
+ if (eflags & FTRACE_EVENT_FL_SOFT_DISABLED)
+ return;
+ }
sys_data = syscall_nr_to_meta(syscall_nr);
if (!sys_data)
@@ -394,9 +413,16 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
entry->nr = syscall_nr;
entry->ret = syscall_get_return_value(current, regs);
- if (!filter_check_discard(ftrace_file, entry, buffer, event))
+ if (eflags & FTRACE_EVENT_FL_TRIGGER_COND)
+ __tt = event_triggers_call(ftrace_file, entry);
+
+ if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+ ring_buffer_discard_commit(buffer, event);
+ else if (!filter_check_discard(ftrace_file, entry, buffer, event))
trace_current_buffer_unlock_commit(buffer, event,
irq_flags, pc);
+ if (__tt)
+ event_triggers_post_call(ftrace_file, __tt);
}
static int reg_event_syscall_enter(struct ftrace_event_file *file,
--
1.8.4.3
^ permalink raw reply related [flat|nested] 11+ messages in thread* [for-next][PATCH 08/10] tracing: Add documentation for trace event triggers
2013-12-23 21:38 [for-next][PATCH 00/10] tracing: Addition of trace event trigeers Steven Rostedt
` (6 preceding siblings ...)
2013-12-23 21:38 ` [for-next][PATCH 07/10] tracing: Add and use generic set_trigger_filter() implementation Steven Rostedt
@ 2013-12-23 21:38 ` Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 09/10] tracing: Add generic tracing_lseek() function Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 10/10] tracing: Fix rcu handling of event_trigger_data filter field Steven Rostedt
9 siblings, 0 replies; 11+ messages in thread
From: Steven Rostedt @ 2013-12-23 21:38 UTC (permalink / raw)
To: linux-kernel; +Cc: Ingo Molnar, Frederic Weisbecker, Tom Zanussi, Andrew Morton
[-- Attachment #1: 0008-tracing-Add-documentation-for-trace-event-triggers.patch --]
[-- Type: text/plain, Size: 8700 bytes --]
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Provide a basic overview of trace event triggers and document the
available trigger commands, along with a few simple examples.
Link: http://lkml.kernel.org/r/2595dd9196d7b553049611f2a3f849ca75d650a2.1382622043.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
Documentation/trace/events.txt | 207 +++++++++++++++++++++++++++++++++++++++++
1 file changed, 207 insertions(+)
diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt
index 37732a2..c94435d 100644
--- a/Documentation/trace/events.txt
+++ b/Documentation/trace/events.txt
@@ -287,3 +287,210 @@ their old filters):
prev_pid == 0
# cat sched_wakeup/filter
common_pid == 0
+
+6. Event triggers
+=================
+
+Trace events can be made to conditionally invoke trigger 'commands'
+which can take various forms and are described in detail below;
+examples would be enabling or disabling other trace events or invoking
+a stack trace whenever the trace event is hit. Whenever a trace event
+with attached triggers is invoked, the set of trigger commands
+associated with that event is invoked. Any given trigger can
+additionally have an event filter of the same form as described in
+section 5 (Event filtering) associated with it - the command will only
+be invoked if the event being invoked passes the associated filter.
+If no filter is associated with the trigger, it always passes.
+
+Triggers are added to and removed from a particular event by writing
+trigger expressions to the 'trigger' file for the given event.
+
+A given event can have any number of triggers associated with it,
+subject to any restrictions that individual commands may have in that
+regard.
+
+Event triggers are implemented on top of "soft" mode, which means that
+whenever a trace event has one or more triggers associated with it,
+the event is activated even if it isn't actually enabled, but is
+disabled in a "soft" mode. That is, the tracepoint will be called,
+but just will not be traced, unless of course it's actually enabled.
+This scheme allows triggers to be invoked even for events that aren't
+enabled, and also allows the current event filter implementation to be
+used for conditionally invoking triggers.
+
+The syntax for event triggers is roughly based on the syntax for
+set_ftrace_filter 'ftrace filter commands' (see the 'Filter commands'
+section of Documentation/trace/ftrace.txt), but there are major
+differences and the implementation isn't currently tied to it in any
+way, so beware about making generalizations between the two.
+
+6.1 Expression syntax
+---------------------
+
+Triggers are added by echoing the command to the 'trigger' file:
+
+ # echo 'command[:count] [if filter]' > trigger
+
+Triggers are removed by echoing the same command but starting with '!'
+to the 'trigger' file:
+
+ # echo '!command[:count] [if filter]' > trigger
+
+The [if filter] part isn't used in matching commands when removing, so
+leaving that off in a '!' command will accomplish the same thing as
+having it in.
+
+The filter syntax is the same as that described in the 'Event
+filtering' section above.
+
+For ease of use, writing to the trigger file using '>' currently just
+adds or removes a single trigger and there's no explicit '>>' support
+('>' actually behaves like '>>') or truncation support to remove all
+triggers (you have to use '!' for each one added.)
+
+6.2 Supported trigger commands
+------------------------------
+
+The following commands are supported:
+
+- enable_event/disable_event
+
+ These commands can enable or disable another trace event whenever
+ the triggering event is hit. When these commands are registered,
+ the other trace event is activated, but disabled in a "soft" mode.
+ That is, the tracepoint will be called, but just will not be traced.
+ The event tracepoint stays in this mode as long as there's a trigger
+ in effect that can trigger it.
+
+ For example, the following trigger causes kmalloc events to be
+ traced when a read system call is entered, and the :1 at the end
+ specifies that this enablement happens only once:
+
+ # echo 'enable_event:kmem:kmalloc:1' > \
+ /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger
+
+ The following trigger causes kmalloc events to stop being traced
+ when a read system call exits. This disablement happens on every
+ read system call exit:
+
+ # echo 'disable_event:kmem:kmalloc' > \
+ /sys/kernel/debug/tracing/events/syscalls/sys_exit_read/trigger
+
+ The format is:
+
+ enable_event:<system>:<event>[:count]
+ disable_event:<system>:<event>[:count]
+
+ To remove the above commands:
+
+ # echo '!enable_event:kmem:kmalloc:1' > \
+ /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger
+
+ # echo '!disable_event:kmem:kmalloc' > \
+ /sys/kernel/debug/tracing/events/syscalls/sys_exit_read/trigger
+
+ Note that there can be any number of enable/disable_event triggers
+ per triggering event, but there can only be one trigger per
+ triggered event. e.g. sys_enter_read can have triggers enabling both
+ kmem:kmalloc and sched:sched_switch, but can't have two kmem:kmalloc
+ versions such as kmem:kmalloc and kmem:kmalloc:1 or 'kmem:kmalloc if
+ bytes_req == 256' and 'kmem:kmalloc if bytes_alloc == 256' (they
+ could be combined into a single filter on kmem:kmalloc though).
+
+- stacktrace
+
+ This command dumps a stacktrace in the trace buffer whenever the
+ triggering event occurs.
+
+ For example, the following trigger dumps a stacktrace every time the
+ kmalloc tracepoint is hit:
+
+ # echo 'stacktrace' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ The following trigger dumps a stacktrace the first 5 times a kmalloc
+ request happens with a size >= 64K
+
+ # echo 'stacktrace:5 if bytes_req >= 65536' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ The format is:
+
+ stacktrace[:count]
+
+ To remove the above commands:
+
+ # echo '!stacktrace' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ # echo '!stacktrace:5 if bytes_req >= 65536' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ The latter can also be removed more simply by the following (without
+ the filter):
+
+ # echo '!stacktrace:5' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ Note that there can be only one stacktrace trigger per triggering
+ event.
+
+- snapshot
+
+ This command causes a snapshot to be triggered whenever the
+ triggering event occurs.
+
+ The following command creates a snapshot every time a block request
+ queue is unplugged with a depth > 1. If you were tracing a set of
+ events or functions at the time, the snapshot trace buffer would
+ capture those events when the trigger event occured:
+
+ # echo 'snapshot if nr_rq > 1' > \
+ /sys/kernel/debug/tracing/events/block/block_unplug/trigger
+
+ To only snapshot once:
+
+ # echo 'snapshot:1 if nr_rq > 1' > \
+ /sys/kernel/debug/tracing/events/block/block_unplug/trigger
+
+ To remove the above commands:
+
+ # echo '!snapshot if nr_rq > 1' > \
+ /sys/kernel/debug/tracing/events/block/block_unplug/trigger
+
+ # echo '!snapshot:1 if nr_rq > 1' > \
+ /sys/kernel/debug/tracing/events/block/block_unplug/trigger
+
+ Note that there can be only one snapshot trigger per triggering
+ event.
+
+- traceon/traceoff
+
+ These commands turn tracing on and off when the specified events are
+ hit. The parameter determines how many times the tracing system is
+ turned on and off. If unspecified, there is no limit.
+
+ The following command turns tracing off the first time a block
+ request queue is unplugged with a depth > 1. If you were tracing a
+ set of events or functions at the time, you could then examine the
+ trace buffer to see the sequence of events that led up to the
+ trigger event:
+
+ # echo 'traceoff:1 if nr_rq > 1' > \
+ /sys/kernel/debug/tracing/events/block/block_unplug/trigger
+
+ To always disable tracing when nr_rq > 1 :
+
+ # echo 'traceoff if nr_rq > 1' > \
+ /sys/kernel/debug/tracing/events/block/block_unplug/trigger
+
+ To remove the above commands:
+
+ # echo '!traceoff:1 if nr_rq > 1' > \
+ /sys/kernel/debug/tracing/events/block/block_unplug/trigger
+
+ # echo '!traceoff if nr_rq > 1' > \
+ /sys/kernel/debug/tracing/events/block/block_unplug/trigger
+
+ Note that there can be only one traceon or traceoff trigger per
+ triggering event.
--
1.8.4.3
^ permalink raw reply related [flat|nested] 11+ messages in thread* [for-next][PATCH 09/10] tracing: Add generic tracing_lseek() function
2013-12-23 21:38 [for-next][PATCH 00/10] tracing: Addition of trace event trigeers Steven Rostedt
` (7 preceding siblings ...)
2013-12-23 21:38 ` [for-next][PATCH 08/10] tracing: Add documentation for trace event triggers Steven Rostedt
@ 2013-12-23 21:38 ` Steven Rostedt
2013-12-23 21:38 ` [for-next][PATCH 10/10] tracing: Fix rcu handling of event_trigger_data filter field Steven Rostedt
9 siblings, 0 replies; 11+ messages in thread
From: Steven Rostedt @ 2013-12-23 21:38 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Frederic Weisbecker, Tom Zanussi, Andrew Morton,
kbuild test robot
[-- Attachment #1: 0009-tracing-Add-generic-tracing_lseek-function.patch --]
[-- Type: text/plain, Size: 6484 bytes --]
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Trace event triggers added a lseek that uses the ftrace_filter_lseek()
function. Unfortunately, when function tracing is not configured in
that function is not defined and the kernel fails to build.
This is the second time that function was added to a file ops and
it broke the build due to requiring special config dependencies.
Make a generic tracing_lseek() that all the tracing utilities may
use.
Also, modify the old ftrace_filter_lseek() to return 0 instead of
1 on WRONLY. Not sure why it was a 1 as that does not make sense.
This also changes the old tracing_seek() to modify the file pos
pointer on WRONLY as well.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace.h | 2 --
kernel/trace/ftrace.c | 25 ++++++-------------------
kernel/trace/trace.c | 14 +++++++++-----
kernel/trace/trace.h | 2 ++
kernel/trace/trace_events_trigger.c | 2 +-
kernel/trace/trace_stack.c | 2 +-
6 files changed, 19 insertions(+), 28 deletions(-)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 31ea4b4..f4233b1 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -570,8 +570,6 @@ static inline int
ftrace_regex_release(struct inode *inode, struct file *file) { return -ENODEV; }
#endif /* CONFIG_DYNAMIC_FTRACE */
-loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence);
-
/* totally disable ftrace - can not re-enable after this */
void ftrace_kill(void);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0e9f9ea..531ffa6 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1082,19 +1082,6 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
-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
@@ -2739,7 +2726,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash)
* routine, you can use ftrace_filter_write() for the write
* routine if @flag has FTRACE_ITER_FILTER set, or
* ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set.
- * ftrace_filter_lseek() should be used as the lseek routine, and
+ * tracing_lseek() should be used as the lseek routine, and
* release must call ftrace_regex_release().
*/
int
@@ -3767,7 +3754,7 @@ static const struct file_operations ftrace_filter_fops = {
.open = ftrace_filter_open,
.read = seq_read,
.write = ftrace_filter_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_regex_release,
};
@@ -3775,7 +3762,7 @@ static const struct file_operations ftrace_notrace_fops = {
.open = ftrace_notrace_open,
.read = seq_read,
.write = ftrace_notrace_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_regex_release,
};
@@ -4038,7 +4025,7 @@ static const struct file_operations ftrace_graph_fops = {
.open = ftrace_graph_open,
.read = seq_read,
.write = ftrace_graph_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_graph_release,
};
@@ -4046,7 +4033,7 @@ static const struct file_operations ftrace_graph_notrace_fops = {
.open = ftrace_graph_notrace_open,
.read = seq_read,
.write = ftrace_graph_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_graph_release,
};
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -4719,7 +4706,7 @@ static const struct file_operations ftrace_pid_fops = {
.open = ftrace_pid_open,
.write = ftrace_pid_write,
.read = seq_read,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_pid_release,
};
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 59bf5b5..e32a2f4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3183,19 +3183,23 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
return count;
}
-static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
+loff_t tracing_lseek(struct file *file, loff_t offset, int whence)
{
+ int ret;
+
if (file->f_mode & FMODE_READ)
- return seq_lseek(file, offset, origin);
+ ret = seq_lseek(file, offset, whence);
else
- return 0;
+ file->f_pos = ret = 0;
+
+ return ret;
}
static const struct file_operations tracing_fops = {
.open = tracing_open,
.read = seq_read,
.write = tracing_write_stub,
- .llseek = tracing_seek,
+ .llseek = tracing_lseek,
.release = tracing_release,
};
@@ -4940,7 +4944,7 @@ static const struct file_operations snapshot_fops = {
.open = tracing_snapshot_open,
.read = seq_read,
.write = tracing_snapshot_write,
- .llseek = tracing_seek,
+ .llseek = tracing_lseek,
.release = tracing_snapshot_release,
};
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 433bfc5..0380cab 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -588,6 +588,8 @@ void tracing_start_sched_switch_record(void);
int register_tracer(struct tracer *type);
int is_tracing_stopped(void);
+loff_t tracing_lseek(struct file *file, loff_t offset, int whence);
+
extern cpumask_var_t __read_mostly tracing_buffer_mask;
#define for_each_tracing_cpu(cpu) \
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index f5b3f78..12ac8a5 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -281,7 +281,7 @@ const struct file_operations event_trigger_fops = {
.open = event_trigger_open,
.read = seq_read,
.write = event_trigger_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = event_trigger_release,
};
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index b20428c..e6be585 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -382,7 +382,7 @@ static const struct file_operations stack_trace_filter_fops = {
.open = stack_trace_filter_open,
.read = seq_read,
.write = ftrace_filter_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_regex_release,
};
--
1.8.4.3
^ permalink raw reply related [flat|nested] 11+ messages in thread* [for-next][PATCH 10/10] tracing: Fix rcu handling of event_trigger_data filter field
2013-12-23 21:38 [for-next][PATCH 00/10] tracing: Addition of trace event trigeers Steven Rostedt
` (8 preceding siblings ...)
2013-12-23 21:38 ` [for-next][PATCH 09/10] tracing: Add generic tracing_lseek() function Steven Rostedt
@ 2013-12-23 21:38 ` Steven Rostedt
9 siblings, 0 replies; 11+ messages in thread
From: Steven Rostedt @ 2013-12-23 21:38 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Frederic Weisbecker, Tom Zanussi, Andrew Morton,
kbuild test robot
[-- Attachment #1: 0010-tracing-Fix-rcu-handling-of-event_trigger_data-filte.patch --]
[-- Type: text/plain, Size: 2288 bytes --]
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
The filter field of the event_trigger_data structure is protected under
RCU sched locks. It was not annotated as such, and after doing so,
sparse pointed out several locations that required fix ups.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
kernel/trace/trace.h | 2 +-
kernel/trace/trace_events_trigger.c | 8 +++++---
2 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 0380cab..02b592f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1057,7 +1057,7 @@ struct event_trigger_data {
int ref;
struct event_trigger_ops *ops;
struct event_command *cmd_ops;
- struct event_filter *filter;
+ struct event_filter __rcu *filter;
char *filter_str;
void *private_data;
struct list_head list;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 12ac8a5..f6dd115 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -67,6 +67,7 @@ event_triggers_call(struct ftrace_event_file *file, void *rec)
{
struct event_trigger_data *data;
enum event_trigger_type tt = ETT_NONE;
+ struct event_filter *filter;
if (list_empty(&file->triggers))
return tt;
@@ -76,7 +77,8 @@ event_triggers_call(struct ftrace_event_file *file, void *rec)
data->ops->func(data);
continue;
}
- if (data->filter && !filter_match_preds(data->filter, rec))
+ filter = rcu_dereference(data->filter);
+ if (filter && !filter_match_preds(filter, rec))
continue;
if (data->cmd_ops->post_trigger) {
tt |= data->cmd_ops->trigger_type;
@@ -703,7 +705,7 @@ static int set_trigger_filter(char *filter_str,
if (ret)
goto out;
assign:
- tmp = data->filter;
+ tmp = rcu_access_pointer(data->filter);
rcu_assign_pointer(data->filter, filter);
@@ -719,7 +721,7 @@ static int set_trigger_filter(char *filter_str,
if (filter_str) {
data->filter_str = kstrdup(filter_str, GFP_KERNEL);
if (!data->filter_str) {
- free_event_filter(data->filter);
+ free_event_filter(rcu_access_pointer(data->filter));
data->filter = NULL;
ret = -ENOMEM;
}
--
1.8.4.3
^ permalink raw reply related [flat|nested] 11+ messages in thread