tracing: Add perf counter support for syscalls tracing

The perf counter support is automated for usual trace events. But we
have to define specific callbacks for this to handle syscalls trace
events

Make 'perf stat -e syscalls:sys_enter_blah' work with syscall style
tracepoints.

Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Jiaying Zhang <jiayingz@google.com>
Cc: Martin Bligh <mbligh@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>

include/linux/perf_counter.h

@@ -734,6 +734,8 @@ extern int sysctl_perf_counter_mlock;
 extern int sysctl_perf_counter_sample_rate;
 
 extern void perf_counter_init(void);
+extern void perf_tpcounter_event(int event_id, u64 addr, u64 count,
+				 void *record, int entry_size);
 
 #ifndef perf_misc_flags
 #define perf_misc_flags(regs)	(user_mode(regs) ? PERF_EVENT_MISC_USER : \

include/linux/syscalls.h

@@ -98,6 +98,53 @@ struct perf_counter_attr;
 #define __SC_TEST5(t5, a5, ...)	__SC_TEST(t5); __SC_TEST4(__VA_ARGS__)
 #define __SC_TEST6(t6, a6, ...)	__SC_TEST(t6); __SC_TEST5(__VA_ARGS__)
 
+#ifdef CONFIG_EVENT_PROFILE
+#define TRACE_SYS_ENTER_PROFILE(sname)					       \
+static int prof_sysenter_enable_##sname(struct ftrace_event_call *event_call)  \
+{									       \
+	int ret = 0;							       \
+	if (!atomic_inc_return(&event_enter_##sname.profile_count))	       \
+		ret = reg_prof_syscall_enter("sys"#sname);		       \
+	return ret;							       \
+}									       \
+									       \
+static void prof_sysenter_disable_##sname(struct ftrace_event_call *event_call)\
+{									       \
+	if (atomic_add_negative(-1, &event_enter_##sname.profile_count))       \
+		unreg_prof_syscall_enter("sys"#sname);			       \
+}
+
+#define TRACE_SYS_EXIT_PROFILE(sname)					       \
+static int prof_sysexit_enable_##sname(struct ftrace_event_call *event_call)   \
+{									       \
+	int ret = 0;							       \
+	if (!atomic_inc_return(&event_exit_##sname.profile_count))	       \
+		ret = reg_prof_syscall_exit("sys"#sname);		       \
+	return ret;							       \
+}									       \
+									       \
+static void prof_sysexit_disable_##sname(struct ftrace_event_call *event_call) \
+{                                                                              \
+	if (atomic_add_negative(-1, &event_exit_##sname.profile_count))	       \
+		unreg_prof_syscall_exit("sys"#sname);			       \
+}
+
+#define TRACE_SYS_ENTER_PROFILE_INIT(sname)				       \
+	.profile_count = ATOMIC_INIT(-1),				       \
+	.profile_enable = prof_sysenter_enable_##sname,			       \
+	.profile_disable = prof_sysenter_disable_##sname,
+
+#define TRACE_SYS_EXIT_PROFILE_INIT(sname)				       \
+	.profile_count = ATOMIC_INIT(-1),				       \
+	.profile_enable = prof_sysexit_enable_##sname,			       \
+	.profile_disable = prof_sysexit_disable_##sname,
+#else
+#define TRACE_SYS_ENTER_PROFILE(sname)
+#define TRACE_SYS_ENTER_PROFILE_INIT(sname)
+#define TRACE_SYS_EXIT_PROFILE(sname)
+#define TRACE_SYS_EXIT_PROFILE_INIT(sname)
+#endif
+
 #ifdef CONFIG_FTRACE_SYSCALLS
 #define __SC_STR_ADECL1(t, a)		#a
 #define __SC_STR_ADECL2(t, a, ...)	#a, __SC_STR_ADECL1(__VA_ARGS__)
@@ -113,7 +160,6 @@ struct perf_counter_attr;
 #define __SC_STR_TDECL5(t, a, ...)	#t, __SC_STR_TDECL4(__VA_ARGS__)
 #define __SC_STR_TDECL6(t, a, ...)	#t, __SC_STR_TDECL5(__VA_ARGS__)
 
-
 #define SYSCALL_TRACE_ENTER_EVENT(sname)				\
 	static struct ftrace_event_call event_enter_##sname;		\
 	struct trace_event enter_syscall_print_##sname = {		\
@@ -134,6 +180,7 @@ struct perf_counter_attr;
 		init_preds(&event_enter_##sname);			\
 		return 0;						\
 	}								\
+	TRACE_SYS_ENTER_PROFILE(sname);					\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
@@ -145,6 +192,7 @@ struct perf_counter_attr;
 		.regfunc		= reg_event_syscall_enter,	\
 		.unregfunc		= unreg_event_syscall_enter,	\
 		.data			= "sys"#sname,			\
+		TRACE_SYS_ENTER_PROFILE_INIT(sname)			\
 	}
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
@@ -167,6 +215,7 @@ struct perf_counter_attr;
 		init_preds(&event_exit_##sname);			\
 		return 0;						\
 	}								\
+	TRACE_SYS_EXIT_PROFILE(sname);					\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
@@ -178,6 +227,7 @@ struct perf_counter_attr;
 		.regfunc		= reg_event_syscall_exit,	\
 		.unregfunc		= unreg_event_syscall_exit,	\
 		.data			= "sys"#sname,			\
+		TRACE_SYS_EXIT_PROFILE_INIT(sname)			\
 	}
 
 #define SYSCALL_METADATA(sname, nb)				\

include/trace/syscall.h

@@ -57,6 +57,13 @@ extern int reg_event_syscall_exit(void *ptr);
 extern void unreg_event_syscall_exit(void *ptr);
 enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags);
 enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
+#endif
+#ifdef CONFIG_EVENT_PROFILE
+int reg_prof_syscall_enter(char *name);
+void unreg_prof_syscall_enter(char *name);
+int reg_prof_syscall_exit(char *name);
+void unreg_prof_syscall_exit(char *name);
+
 #endif
 
 #endif /* _TRACE_SYSCALL_H */

kernel/trace/trace_syscalls.c

@@ -1,6 +1,7 @@
 #include <trace/syscall.h>
 #include <linux/kernel.h>
 #include <linux/ftrace.h>
+#include <linux/perf_counter.h>
 #include <asm/syscall.h>
 
 #include "trace_output.h"
@@ -252,3 +253,123 @@ struct trace_event event_syscall_enter = {
 struct trace_event event_syscall_exit = {
 	.trace			= print_syscall_exit,
 };
+
+#ifdef CONFIG_EVENT_PROFILE
+static DECLARE_BITMAP(enabled_prof_enter_syscalls, FTRACE_SYSCALL_MAX);
+static DECLARE_BITMAP(enabled_prof_exit_syscalls, FTRACE_SYSCALL_MAX);
+static int sys_prof_refcount_enter;
+static int sys_prof_refcount_exit;
+
+static void prof_syscall_enter(struct pt_regs *regs, long id)
+{
+	struct syscall_metadata *sys_data;
+	int syscall_nr;
+
+	syscall_nr = syscall_get_nr(current, regs);
+	if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
+		return;
+
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	perf_tpcounter_event(sys_data->enter_id, 0, 1, NULL, 0);
+}
+
+int reg_prof_syscall_enter(char *name)
+{
+	int ret = 0;
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
+		return -ENOSYS;
+
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_prof_refcount_enter)
+		ret = register_trace_syscall_enter(prof_syscall_enter);
+	if (ret) {
+		pr_info("event trace: Could not activate"
+				"syscall entry trace point");
+	} else {
+		set_bit(num, enabled_prof_enter_syscalls);
+		sys_prof_refcount_enter++;
+	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
+
+void unreg_prof_syscall_enter(char *name)
+{
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
+		return;
+
+	mutex_lock(&syscall_trace_lock);
+	sys_prof_refcount_enter--;
+	clear_bit(num, enabled_prof_enter_syscalls);
+	if (!sys_prof_refcount_enter)
+		unregister_trace_syscall_enter(prof_syscall_enter);
+	mutex_unlock(&syscall_trace_lock);
+}
+
+static void prof_syscall_exit(struct pt_regs *regs, long ret)
+{
+	struct syscall_metadata *sys_data;
+	int syscall_nr;
+
+	syscall_nr = syscall_get_nr(current, regs);
+	if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
+		return;
+
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	perf_tpcounter_event(sys_data->exit_id, 0, 1, NULL, 0);
+}
+
+int reg_prof_syscall_exit(char *name)
+{
+	int ret = 0;
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
+		return -ENOSYS;
+
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_prof_refcount_exit)
+		ret = register_trace_syscall_exit(prof_syscall_exit);
+	if (ret) {
+		pr_info("event trace: Could not activate"
+				"syscall entry trace point");
+	} else {
+		set_bit(num, enabled_prof_exit_syscalls);
+		sys_prof_refcount_exit++;
+	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
+
+void unreg_prof_syscall_exit(char *name)
+{
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
+		return;
+
+	mutex_lock(&syscall_trace_lock);
+	sys_prof_refcount_exit--;
+	clear_bit(num, enabled_prof_exit_syscalls);
+	if (!sys_prof_refcount_exit)
+		unregister_trace_syscall_exit(prof_syscall_exit);
+	mutex_unlock(&syscall_trace_lock);
+}
+
+#endif
+
+