[PATCH 5/8] tracing: Allow system call tracepoints to handle page faults

[Mathieu Desnoyers]

Use Tasks Trace RCU to protect iteration of system call enter/exit
tracepoint probes to allow those probes to handle page faults.

In preparation for this change, all tracers registering to system call
enter/exit tracepoints should expect those to be called with preemption
enabled.

This allows tracers to fault-in userspace system call arguments such as
path strings within their probe callbacks.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Cc: Michael Jeanson <mjeanson@xxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Yonghong Song <yhs@xxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Andrii Nakryiko <andrii.nakryiko@xxxxxxxxx>
Cc: bpf@xxxxxxxxxxxxxxx
Cc: Joel Fernandes <joel@xxxxxxxxxxxxxxxxx>
---
 include/linux/tracepoint.h | 25 +++++++++++++++++--------
 init/Kconfig               |  1 +
 2 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index b2cfe6a9097c..005ede3b1afa 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -18,6 +18,7 @@
 #include <linux/types.h>
 #include <linux/cpumask.h>
 #include <linux/rcupdate.h>
+#include <linux/rcupdate_trace.h>
 #include <linux/tracepoint-defs.h>
 #include <linux/static_call.h>
 
@@ -90,6 +91,7 @@ int unregister_tracepoint_module_notifier(struct notifier_block *nb)
 #ifdef CONFIG_TRACEPOINTS
 static inline void tracepoint_synchronize_unregister(void)
 {
+	synchronize_rcu_tasks_trace();
 	synchronize_srcu(&tracepoint_srcu);
 	synchronize_rcu();
 }
@@ -192,7 +194,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * it_func[0] is never NULL because there is at least one element in the array
  * when the array itself is non NULL.
  */
-#define __DO_TRACE(name, args, cond, rcuidle)				\
+#define __DO_TRACE(name, args, cond, rcuidle, syscall)			\
 	do {								\
 		int __maybe_unused __idx = 0;				\
 									\
@@ -203,8 +205,12 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 			      "Bad RCU usage for tracepoint"))		\
 			return;						\
 									\
-		/* keep srcu and sched-rcu usage consistent */		\
-		preempt_disable_notrace();				\
+		if (syscall) {						\
+			rcu_read_lock_trace();				\
+		} else {						\
+			/* keep srcu and sched-rcu usage consistent */	\
+			preempt_disable_notrace();			\
+		}							\
 									\
 		/*							\
 		 * For rcuidle callers, use srcu since sched-rcu	\
@@ -222,7 +228,10 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 			srcu_read_unlock_notrace(&tracepoint_srcu, __idx);\
 		}							\
 									\
-		preempt_enable_notrace();				\
+		if (syscall)						\
+			rcu_read_unlock_trace();			\
+		else							\
+			preempt_enable_notrace();			\
 	} while (0)
 
 #ifndef MODULE
@@ -232,7 +241,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		if (static_key_false(&__tracepoint_##name.key))		\
 			__DO_TRACE(name,				\
 				TP_ARGS(args),				\
-				TP_CONDITION(cond), 1);			\
+				TP_CONDITION(cond), 1, 0);		\
 	}
 #else
 #define __DECLARE_TRACE_RCU(name, proto, args, cond)
@@ -276,7 +285,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		if (static_key_false(&__tracepoint_##name.key))		\
 			__DO_TRACE(name,				\
 				TP_ARGS(args),				\
-				TP_CONDITION(cond), 0);			\
+				TP_CONDITION(cond), 0, 0);		\
 		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
 			WARN_ONCE(!rcu_is_watching(),			\
 				  "RCU not watching for tracepoint");	\
@@ -287,7 +296,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		if (static_key_false(&__tracepoint_##name.key))		\
 			__DO_TRACE(name,				\
 				TP_ARGS(args),				\
-				TP_CONDITION(cond), 1);			\
+				TP_CONDITION(cond), 1, 0);		\
 	}								\
 	static inline int						\
 	register_trace_##name(void (*probe)(data_proto), void *data)	\
@@ -310,7 +319,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		if (static_key_false(&__tracepoint_##name.key))		\
 			__DO_TRACE(name,				\
 				TP_ARGS(args),				\
-				TP_CONDITION(cond), 0);			\
+				TP_CONDITION(cond), 0, 1);		\
 		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
 			WARN_ONCE(!rcu_is_watching(),			\
 				  "RCU not watching for tracepoint");	\
diff --git a/init/Kconfig b/init/Kconfig
index d8a971b804d3..c854b2887e7f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1937,6 +1937,7 @@ config BINDGEN_VERSION_TEXT
 #
 config TRACEPOINTS
 	bool
+	select TASKS_TRACE_RCU
 
 source "kernel/Kconfig.kexec"
 
-- 
2.39.2