[PATCH 01/10] tracing: Add support for SOFT_DISABLE to syscall events

From: Tom Zanussi
Date: Sat Sep 07 2013 - 11:29:42 EST


The original SOFT_DISABLE patches didn't add support for soft disable
of syscall events; this adds it and paves the way for future patches
allowing triggers to be added to syscall events, since triggers are
built on top of SOFT_DISABLE.

Add an array of ftrace_event_file pointers indexed by syscall number
to the trace array and remove the existing enabled bitmaps, which as a
result are now redundant. The ftrace_event_file structs in turn
contain the soft disable flags we need for per-syscall soft disable
accounting; later patches add additional 'trigger' flags and
per-syscall triggers and filters.

Signed-off-by: Tom Zanussi <tom.zanussi@xxxxxxxxxxxxxxx>
---
kernel/trace/trace.h | 4 ++--
kernel/trace/trace_syscalls.c | 36 ++++++++++++++++++++++++++++++------
2 files changed, 32 insertions(+), 8 deletions(-)

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 502fed7..aea32f7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -192,8 +192,8 @@ struct trace_array {
#ifdef CONFIG_FTRACE_SYSCALLS
int sys_refcount_enter;
int sys_refcount_exit;
- DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
- DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+ struct ftrace_event_file *enter_syscall_files[NR_syscalls];
+ struct ftrace_event_file *exit_syscall_files[NR_syscalls];
#endif
int stop_count;
int clock_id;
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 559329d..2f7d172 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -302,6 +302,7 @@ static int __init syscall_exit_define_fields(struct ftrace_event_call *call)
static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
{
struct trace_array *tr = data;
+ struct ftrace_event_file *ftrace_file;
struct syscall_trace_enter *entry;
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
@@ -314,7 +315,13 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0)
return;
- if (!test_bit(syscall_nr, tr->enabled_enter_syscalls))
+
+ /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
+ ftrace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]);
+ if (!ftrace_file)
+ return;
+
+ if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
return;

sys_data = syscall_nr_to_meta(syscall_nr);
@@ -345,6 +352,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
{
struct trace_array *tr = data;
+ struct ftrace_event_file *ftrace_file;
struct syscall_trace_exit *entry;
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
@@ -356,7 +364,13 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0)
return;
- if (!test_bit(syscall_nr, tr->enabled_exit_syscalls))
+
+ /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
+ ftrace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]);
+ if (!ftrace_file)
+ return;
+
+ if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
return;

sys_data = syscall_nr_to_meta(syscall_nr);
@@ -397,7 +411,7 @@ static int reg_event_syscall_enter(struct ftrace_event_file *file,
if (!tr->sys_refcount_enter)
ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
if (!ret) {
- set_bit(num, tr->enabled_enter_syscalls);
+ rcu_assign_pointer(tr->enter_syscall_files[num], file);
tr->sys_refcount_enter++;
}
mutex_unlock(&syscall_trace_lock);
@@ -415,10 +429,15 @@ static void unreg_event_syscall_enter(struct ftrace_event_file *file,
return;
mutex_lock(&syscall_trace_lock);
tr->sys_refcount_enter--;
- clear_bit(num, tr->enabled_enter_syscalls);
+ rcu_assign_pointer(tr->enter_syscall_files[num], NULL);
if (!tr->sys_refcount_enter)
unregister_trace_sys_enter(ftrace_syscall_enter, tr);
mutex_unlock(&syscall_trace_lock);
+ /*
+ * Callers expect the event to be completely disabled on
+ * return, so wait for current handlers to finish.
+ */
+ synchronize_sched();
}

static int reg_event_syscall_exit(struct ftrace_event_file *file,
@@ -435,7 +454,7 @@ static int reg_event_syscall_exit(struct ftrace_event_file *file,
if (!tr->sys_refcount_exit)
ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
if (!ret) {
- set_bit(num, tr->enabled_exit_syscalls);
+ rcu_assign_pointer(tr->exit_syscall_files[num], file);
tr->sys_refcount_exit++;
}
mutex_unlock(&syscall_trace_lock);
@@ -453,10 +472,15 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file,
return;
mutex_lock(&syscall_trace_lock);
tr->sys_refcount_exit--;
- clear_bit(num, tr->enabled_exit_syscalls);
+ rcu_assign_pointer(tr->exit_syscall_files[num], NULL);
if (!tr->sys_refcount_exit)
unregister_trace_sys_exit(ftrace_syscall_exit, tr);
mutex_unlock(&syscall_trace_lock);
+ /*
+ * Callers expect the event to be completely disabled on
+ * return, so wait for current handlers to finish.
+ */
+ synchronize_sched();
}

static int __init init_syscall_trace(struct ftrace_event_call *call)
--
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/