tracing/ftrace: syscall tracing infrastructure, basics

Provide basic callbacks to do syscall tracing.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <1236401580-5758-2-git-send-email-fweisbec@gmail.com>
[ simplified it to a trace_printk() for now. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>

5 files changed, 147 insertions, 0 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e1583f2639b0..c146c1021a29 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -503,4 +503,25 @@ static inline void trace_hw_branch_oops(void) {}
 
 #endif /* CONFIG_HW_BRANCH_TRACER */
 
+/*
+ * A syscall entry in the ftrace syscalls array.
+ *
+ * @syscall_nr: syscall number
+ */
+struct syscall_trace_entry {
+        int             syscall_nr;
+};
+
+#ifdef CONFIG_FTRACE_SYSCALLS
+extern void start_ftrace_syscalls(void);
+extern void stop_ftrace_syscalls(void);
+extern void ftrace_syscall_enter(struct pt_regs *regs);
+extern void ftrace_syscall_exit(struct pt_regs *regs);
+#else
+static inline void start_ftrace_syscalls(void) { }
+static inline void stop_ftrace_syscalls(void) { }
+static inline void ftrace_syscall_enter(struct pt_regs *regs) { }
+static inline void ftrace_syscall_exit(struct pt_regs *regs) { }
+#endif
+
 #endif /* _LINUX_FTRACE_H */
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 8e4a2a61cd75..95a0ad191f19 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -34,6 +34,9 @@ config HAVE_FTRACE_MCOUNT_RECORD
 config HAVE_HW_BRANCH_TRACER
         bool
 
+config HAVE_FTRACE_SYSCALLS
+        bool
+
 config TRACER_MAX_TRACE
         bool
 
@@ -175,6 +178,13 @@ config EVENT_TRACER
           allowing the user to pick and choose which trace point they
           want to trace.
 
+config FTRACE_SYSCALLS
+        bool "Trace syscalls"
+        depends on HAVE_FTRACE_SYSCALLS
+        select TRACING
+        help
+          Basic tracer to catch the syscall entry and exit events.
+
 config BOOT_TRACER
         bool "Trace boot initcalls"
         select TRACING
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index c7a2943796eb..c3feea01c3e0 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -43,5 +43,6 @@ obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o
 obj-$(CONFIG_EVENT_TRACER) += trace_events.o
 obj-$(CONFIG_EVENT_TRACER) += events.o
 obj-$(CONFIG_EVENT_TRACER) += trace_export.o
+obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c5e1d8865fe4..3d49daae47dc 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -30,6 +30,8 @@ enum trace_type {
         TRACE_GRAPH_ENT,
         TRACE_USER_STACK,
         TRACE_HW_BRANCHES,
+        TRACE_SYSCALL_ENTER,
+        TRACE_SYSCALL_EXIT,
         TRACE_KMEM_ALLOC,
         TRACE_KMEM_FREE,
         TRACE_POWER,
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
new file mode 100644
index 000000000000..66cf97449af3
--- /dev/null
+++ b/kernel/trace/trace_syscalls.c
@@ -0,0 +1,113 @@
+#include <linux/ftrace.h>
+#include <linux/kernel.h>
+
+#include <asm/syscall.h>
+
+#include "trace_output.h"
+#include "trace.h"
+
+static atomic_t refcount;
+
+void start_ftrace_syscalls(void)
+{
+        unsigned long flags;
+        struct task_struct *g, *t;
+
+        if (atomic_inc_return(&refcount) != 1)
+                goto out;
+
+        read_lock_irqsave(&tasklist_lock, flags);
+
+        do_each_thread(g, t) {
+                set_tsk_thread_flag(t, TIF_SYSCALL_FTRACE);
+        } while_each_thread(g, t);
+
+        read_unlock_irqrestore(&tasklist_lock, flags);
+out:
+        atomic_dec(&refcount);
+}
+
+void stop_ftrace_syscalls(void)
+{
+        unsigned long flags;
+        struct task_struct *g, *t;
+
+        if (atomic_dec_return(&refcount))
+                goto out;
+
+        read_lock_irqsave(&tasklist_lock, flags);
+
+        do_each_thread(g, t) {
+                clear_tsk_thread_flag(t, TIF_SYSCALL_FTRACE);
+        } while_each_thread(g, t);
+
+        read_unlock_irqrestore(&tasklist_lock, flags);
+out:
+        atomic_inc(&refcount);
+}
+
+void ftrace_syscall_enter(struct pt_regs *regs)
+{
+        int syscall_nr;
+
+        syscall_nr = syscall_get_nr(current, regs);
+
+        trace_printk("syscall %d enter\n", syscall_nr);
+}
+
+void ftrace_syscall_exit(struct pt_regs *regs)
+{
+        int syscall_nr;
+
+        syscall_nr = syscall_get_nr(current, regs);
+
+        trace_printk("syscall %d exit\n", syscall_nr);
+}
+
+static int init_syscall_tracer(struct trace_array *tr)
+{
+        start_ftrace_syscalls();
+
+        return 0;
+}
+
+static void reset_syscall_tracer(struct trace_array *tr)
+{
+        stop_ftrace_syscalls();
+}
+
+static struct trace_event syscall_enter_event = {
+        .type           = TRACE_SYSCALL_ENTER,
+};
+
+static struct trace_event syscall_exit_event = {
+        .type           = TRACE_SYSCALL_EXIT,
+};
+
+static struct tracer syscall_tracer __read_mostly = {
+        .name           = "syscall",
+        .init           = init_syscall_tracer,
+        .reset          = reset_syscall_tracer
+};
+
+__init int register_ftrace_syscalls(void)
+{
+        int ret;
+
+        ret = register_ftrace_event(&syscall_enter_event);
+        if (!ret) {
+                printk(KERN_WARNING "event %d failed to register\n",
+                       syscall_enter_event.type);
+                WARN_ON_ONCE(1);
+        }
+
+        ret = register_ftrace_event(&syscall_exit_event);
+        if (!ret) {
+                printk(KERN_WARNING "event %d failed to register\n",
+                       syscall_exit_event.type);
+                WARN_ON_ONCE(1);
+        }
+
+        return register_tracer(&syscall_tracer);
+}
+device_initcall(register_ftrace_syscalls);