tracing: Allow system call tracepoints to handle page faults

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.

Cc: Michael Jeanson <mjeanson@efficios.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Cc: bpf@vger.kernel.org
Cc: Joel Fernandes <joel@joelfernandes.org>
Link: https://lore.kernel.org/20241009010718.2050182-6-mathieu.desnoyers@efficios.com
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 76e441b..0dc67fa 100644 (file)
--- 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
@@ -196,6 +198,12 @@ 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.
+ *
+ * With @syscall=0, the tracepoint callback array dereference is
+ * protected by disabling preemption.
+ * With @syscall=1, the tracepoint callback array dereference is
+ * protected by Tasks Trace RCU, which allows probes to handle page
+ * faults.
  */
 #define __DO_TRACE(name, args, cond, syscall)                          \
        do {                                                            \
@@ -204,11 +212,17 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
                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)
 
 /*

diff --git a/init/Kconfig b/init/Kconfig
index 530a382..4ac3d1b 100644 (file)
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1985,6 +1985,7 @@ config BINDGEN_VERSION_TEXT
 #
 config TRACEPOINTS
        bool
+       select TASKS_TRACE_RCU
 
 source "kernel/Kconfig.kexec"