[PATCH v3 7/9] tracing: add and use generic set_trigger_filter() implementation

From: Tom Zanussi
Date: Fri Jul 19 2013 - 11:10:10 EST

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 - for ftrace_raw_event_calls, trigger invocation now needs
to happen after the { assign; } part of the call.

Also, because triggers need to be invoked even for soft-disabled
events, the SOFT_DISABLED check and return needs to be moved from the
top of the call to a point following the trigger check, which means
that soft-disabled events actually get discarded instead of simply
skipped. There's still a SOFT_DISABLED-only check at the top of the
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().

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.

Signed-off-by: Tom Zanussi <tom.zanussi@xxxxxxxxxxxxxxx>
---
include/linux/ftrace_event.h | 6 ++-
include/trace/ftrace.h | 45 ++++++++++++-----
kernel/trace/trace.h | 4 ++
kernel/trace/trace_events_filter.c | 13 +++++
kernel/trace/trace_events_trigger.c | 97 +++++++++++++++++++++++++++++++++++--
kernel/trace/trace_syscalls.c | 36 ++++++++++----
6 files changed, 174 insertions(+), 27 deletions(-)

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 57ca386..f0c6e80 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -328,7 +328,11 @@ extern int filter_current_check_discard(struct ring_buffer *buffer,
struct ftrace_event_call *call,
void *rec,
struct ring_buffer_event *event);
-extern void event_triggers_call(struct ftrace_event_file *file);
+extern enum trigger_mode event_triggers_call(struct ftrace_event_file *file,
+ void *rec);
+extern void event_triggers_post_call(struct ftrace_event_file *file,
+ enum trigger_mode tm);
+

enum {
FILTER_OTHER = 0,
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 63dfb0a..311f38e 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -412,13 +412,15 @@ static inline notrace int ftrace_get_offsets_##call( \
* struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
* struct ring_buffer_event *event;
* struct ftrace_raw_<call> *entry; <-- defined in stage 1
+ * enum trigger_mode __tm = TM_NONE;
* struct ring_buffer *buffer;
* unsigned long irq_flags;
* int __data_size;
* int pc;
*
- * if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT,
- * &ftrace_file->flags))
+ * if ((ftrace_file->flags & (FTRACE_EVENT_FL_SOFT_DISABLED |
+ * FTRACE_EVENT_FL_TRIGGER_MODE)) ==
+ * FTRACE_EVENT_FL_SOFT_DISABLED)
* return;
*
* local_save_flags(irq_flags);
@@ -437,9 +439,19 @@ static inline notrace int ftrace_get_offsets_##call( \
* { <assign>; } <-- Here we assign the entries by the __field and
* __array macros.
*
- * if (!filter_current_check_discard(buffer, event_call, entry, event))
- * trace_nowake_buffer_unlock_commit(buffer,
- * event, irq_flags, pc);
+ * if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT,
+ * &ftrace_file->flags))
+ * __tm = 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_current_check_discard(buffer, event_call,
+ * entry, event))
+ * trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ *
+ * if (__tm)
+ * event_triggers_post_call(ftrace_file, __tm);
* }
*
* static struct trace_event ftrace_event_type_<call> = {
@@ -521,17 +533,15 @@ ftrace_raw_event_##call(void *__data, proto) \
struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
struct ring_buffer_event *event; \
struct ftrace_raw_##call *entry; \
+ enum trigger_mode __tm = TM_NONE; \
struct ring_buffer *buffer; \
unsigned long irq_flags; \
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)) \
+ if ((ftrace_file->flags & (FTRACE_EVENT_FL_SOFT_DISABLED | \
+ FTRACE_EVENT_FL_TRIGGER_MODE)) == \
+ FTRACE_EVENT_FL_SOFT_DISABLED) \
return; \
\
local_save_flags(irq_flags); \
@@ -551,8 +561,19 @@ ftrace_raw_event_##call(void *__data, proto) \
\
{ assign; } \
\
- if (!filter_current_check_discard(buffer, event_call, entry, event)) \
+ if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, \
+ &ftrace_file->flags)) \
+ __tm = 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_current_check_discard(buffer, event_call, \
+ entry, event)) \
trace_buffer_unlock_commit(buffer, event, irq_flags, pc); \
+ \
+ if (__tm) \
+ event_triggers_post_call(ftrace_file, __tm); \
}
/*
* 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 c06d2d2..8597592 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -996,6 +996,10 @@ 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 0d883dc..6cf2cef 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -783,6 +783,11 @@ static void __free_filter(struct event_filter *filter)
kfree(filter);
}

+void free_event_filter(struct event_filter *filter)
+{
+ __free_filter(filter);
+}
+
/*
* Called when destroying the ftrace_event_call.
* The call is being freed, so we do not need to worry about
@@ -1808,6 +1813,14 @@ 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 2300fc8..b0ca093 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -35,6 +35,7 @@ struct event_trigger_data {
bool enable;
struct event_trigger_ops *ops;
enum trigger_mode mode;
+ bool post_trigger;
struct event_filter *filter;
char *filter_str;
struct list_head list;
@@ -44,20 +45,45 @@ struct trigger_iterator {
struct ftrace_event_file *file;
};

-void event_triggers_call(struct ftrace_event_file *file)
+enum trigger_mode
+event_triggers_call(struct ftrace_event_file *file, void *rec)
{
struct event_trigger_data *data;
+ enum trigger_mode tm = TM_NONE;

if (list_empty(&file->triggers))
- return;
+ return tm;

preempt_disable_notrace();
- list_for_each_entry_rcu(data, &file->triggers, list)
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->filter && !filter_match_preds(data->filter, rec))
+ continue;
+ if (data->post_trigger) {
+ tm |= data->mode;
+ continue;
+ }
data->ops->func((void **)&data);
+ }
preempt_enable_notrace();
+
+ return tm;
}
EXPORT_SYMBOL_GPL(event_triggers_call);

+void
+event_triggers_post_call(struct ftrace_event_file *file, enum trigger_mode tm)
+{
+ struct event_trigger_data *data;
+
+ preempt_disable_notrace();
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->mode & tm)
+ data->ops->func((void **)&data);
+ }
+ preempt_enable_notrace();
+}
+EXPORT_SYMBOL_GPL(event_triggers_post_call);
+
static void *trigger_next(struct seq_file *m, void *t, loff_t *pos)
{
struct trigger_iterator *iter = m->private;
@@ -400,6 +426,52 @@ event_trigger_free(struct event_trigger_ops *ops, void **_data)
kfree(data);
}

+static int set_trigger_filter(char *filter_str, void *trigger_data,
+ void *cmd_data)
+{
+ struct trigger_iterator *iter = cmd_data;
+ struct event_trigger_data *data = trigger_data;
+ struct event_filter *filter, *tmp;
+ int ret = -EINVAL;
+ char *s;
+
+ 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(iter->file->event_call,
+ filter_str, false, &filter);
+ if (ret)
+ goto out;
+
+ 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 = kstrdup(filter_str, GFP_KERNEL);
+ if (!data->filter_str) {
+ free_event_filter(data->filter);
+ data->filter = NULL;
+ ret = -ENOMEM;
+ }
+
+ out:
+ return ret;
+}
+
static int
event_trigger_callback(struct event_command *cmd_ops, void *cmd_data,
char *glob, char *cmd, char *param, int enabled)
@@ -623,6 +695,7 @@ 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 = {
@@ -632,6 +705,7 @@ 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,
};

static void
@@ -713,6 +787,7 @@ 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,
};

/*
@@ -764,6 +839,17 @@ stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
data->filter_str);
}

+static int stacktrace_register_trigger(char *glob,
+ struct event_trigger_ops *ops,
+ void *trigger_data, void *cmd_data)
+{
+ struct event_trigger_data *data = trigger_data;
+
+ data->post_trigger = true;
+
+ return register_trigger(glob, ops, trigger_data, cmd_data);
+}
+
static struct event_trigger_ops stacktrace_trigger_ops = {
.func = stacktrace_trigger,
.print = stacktrace_trigger_print,
@@ -788,9 +874,10 @@ static struct event_command trigger_stacktrace_cmd = {
.name = "stacktrace",
.trigger_mode = TM_STACKTRACE,
.func = event_trigger_callback,
- .reg = register_trigger,
+ .reg = stacktrace_register_trigger,
.unreg = unregister_trigger,
.get_trigger_ops = stacktrace_get_trigger_ops,
+ .set_filter = set_trigger_filter,
};

static __init void unregister_trigger_traceon_traceoff_cmds(void)
@@ -1119,6 +1206,7 @@ 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 = {
@@ -1128,6 +1216,7 @@ 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 a79f85b..609190b 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -306,6 +306,7 @@ 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 trigger_mode __tm = TM_NONE;
struct ring_buffer *buffer;
unsigned long irq_flags;
int pc;
@@ -319,9 +320,9 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
return;

ftrace_file = rcu_dereference_raw(tr->enter_syscall_files[syscall_nr]);
- 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))
+ if ((ftrace_file->flags &
+ (FTRACE_EVENT_FL_SOFT_DISABLED | FTRACE_EVENT_FL_TRIGGER_MODE)) ==
+ FTRACE_EVENT_FL_SOFT_DISABLED)
return;

sys_data = syscall_nr_to_meta(syscall_nr);
@@ -343,10 +344,17 @@ 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_current_check_discard(buffer, sys_data->enter_event,
- entry, event))
+ if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &ftrace_file->flags))
+ __tm = 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_current_check_discard(buffer, sys_data->enter_event,
+ entry, event))
trace_current_buffer_unlock_commit(buffer, event,
irq_flags, pc);
+ if (__tm)
+ event_triggers_post_call(ftrace_file, __tm);
}

static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -356,6 +364,7 @@ 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 trigger_mode __tm = TM_NONE;
struct ring_buffer *buffer;
unsigned long irq_flags;
int pc;
@@ -368,9 +377,9 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
return;

ftrace_file = rcu_dereference_raw(tr->exit_syscall_files[syscall_nr]);
- 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))
+ if ((ftrace_file->flags &
+ (FTRACE_EVENT_FL_SOFT_DISABLED | FTRACE_EVENT_FL_TRIGGER_MODE)) ==
+ FTRACE_EVENT_FL_SOFT_DISABLED)
return;

sys_data = syscall_nr_to_meta(syscall_nr);
@@ -391,10 +400,17 @@ 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_current_check_discard(buffer, sys_data->exit_event,
- entry, event))
+ if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &ftrace_file->flags))
+ __tm = 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_current_check_discard(buffer, sys_data->exit_event,
+ entry, event))
trace_current_buffer_unlock_commit(buffer, event,
irq_flags, pc);
+ if (__tm)
+ event_triggers_post_call(ftrace_file, __tm);
}

static int reg_event_syscall_enter(struct ftrace_event_file *file,
--
1.7.11.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/