[PATCH v2 4/7] 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 | 18 +++++++++++++-----
 init/Kconfig               |  1 +
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 1a78c9bbece8..a09a97480f5a 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/rcupdate.h>
+#include <linux/rcupdate_trace.h>
 #include <linux/tracepoint-defs.h>
 #include <linux/static_call.h>
 
@@ -107,6 +108,7 @@ void for_each_tracepoint_in_module(struct module *mod,
 #ifdef CONFIG_TRACEPOINTS
 static inline void tracepoint_synchronize_unregister(void)
 {
+	synchronize_rcu_tasks_trace();
 	synchronize_rcu();
 }
 #else
@@ -197,18 +199,24 @@ 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)					\
+#define __DO_TRACE(name, args, cond, syscall)				\
 	do {								\
 		int __maybe_unused __idx = 0;				\
 									\
 		if (!(cond))						\
 			return;						\
 									\
-		preempt_disable_notrace();				\
+		if (syscall)						\
+			rcu_read_lock_trace();				\
+		else							\
+			preempt_disable_notrace();			\
 									\
 		__DO_TRACE_CALL(name, TP_ARGS(args));			\
 									\
-		preempt_enable_notrace();				\
+		if (syscall)						\
+			rcu_read_unlock_trace();			\
+		else							\
+			preempt_enable_notrace();			\
 	} while (0)
 
 /*
@@ -238,7 +246,7 @@ 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));			\
+				TP_CONDITION(cond), 0);			\
 		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
 			WARN_ONCE(!rcu_is_watching(),			\
 				  "RCU not watching for tracepoint");	\
@@ -276,7 +284,7 @@ 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), 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 fbd0cb06a50a..eedd0064fb36 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1984,6 +1984,7 @@ config BINDGEN_VERSION_TEXT
 #
 config TRACEPOINTS
 	bool
+	select TASKS_TRACE_RCU
 
 source "kernel/Kconfig.kexec"
 
-- 
2.39.2