diff mbox series

[v4,2/8] tracing/ftrace: disable preemption in syscall probe

Message ID 20241009010718.2050182-3-mathieu.desnoyers@efficios.com (mailing list archive)
State Queued
Headers show
Series tracing: Allow system call tracepoints to handle page faults | expand

Commit Message

Mathieu Desnoyers Oct. 9, 2024, 1:07 a.m. UTC 
In preparation for allowing system call enter/exit instrumentation to
handle page faults, make sure that ftrace can handle this change by
explicitly disabling preemption within the ftrace system call tracepoint
probes to respect the current expectations within ftrace ring buffer
code.

This change does not yet allow ftrace to take page faults per se within
its probe, but allows its existing probes to adapt to the upcoming
change.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Michael Jeanson <mjeanson@efficios.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
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>
---
Changes since v3:
- Do not use guard() for single line function, based on
  feedback from Steven.
---
 include/trace/trace_events.h  | 39 ++++++++++++++++++++++++++++-------
 kernel/trace/trace_syscalls.c | 12 +++++++++++
 2 files changed, 44 insertions(+), 7 deletions(-)
diff mbox series

Patch

diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 8bcbb9ee44de..63071aa5923d 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -263,6 +263,9 @@  static struct trace_event_fields trace_event_fields_##call[] = {	\
 	tstruct								\
 	{} };
 
+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
+
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)
 
@@ -396,11 +399,11 @@  static inline notrace int trace_event_get_offsets_##call(		\
 
 #include "stages/stage6_event_callback.h"
 
-#undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
-									\
+
+#undef __DECLARE_EVENT_CLASS
+#define __DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
 static notrace void							\
-trace_event_raw_event_##call(void *__data, proto)			\
+do_trace_event_raw_event_##call(void *__data, proto)			\
 {									\
 	struct trace_event_file *trace_file = __data;			\
 	struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\
@@ -425,15 +428,35 @@  trace_event_raw_event_##call(void *__data, proto)			\
 									\
 	trace_event_buffer_commit(&fbuffer);				\
 }
+
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \
+		      PARAMS(assign), PARAMS(print))			\
+static notrace void							\
+trace_event_raw_event_##call(void *__data, proto)			\
+{									\
+	do_trace_event_raw_event_##call(__data, args);			\
+}
+
+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS(call, proto, args, tstruct, assign, print) \
+__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \
+		      PARAMS(assign), PARAMS(print))			\
+static notrace void							\
+trace_event_raw_event_##call(void *__data, proto)			\
+{									\
+	preempt_disable_notrace();					\
+	do_trace_event_raw_event_##call(__data, args);			\
+	preempt_enable_notrace();					\
+}
+
 /*
  * The ftrace_test_probe is compiled out, it is only here as a build time check
  * to make sure that if the tracepoint handling changes, the ftrace probe will
  * fail to compile unless it too is updated.
  */
 
-#undef DECLARE_EVENT_SYSCALL_CLASS
-#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
-
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, call, proto, args)			\
 static inline void ftrace_test_probe_##call(void)			\
@@ -443,6 +466,8 @@  static inline void ftrace_test_probe_##call(void)			\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+#undef __DECLARE_EVENT_CLASS
+
 #include "stages/stage7_class_define.h"
 
 #undef DECLARE_EVENT_CLASS
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 785733245ead..f9b21bac9d45 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -299,6 +299,12 @@  static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	int syscall_nr;
 	int size;
 
+	/*
+	 * Syscall probe called with preemption enabled, but the ring
+	 * buffer and per-cpu data require preemption to be disabled.
+	 */
+	guard(preempt_notrace)();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
@@ -338,6 +344,12 @@  static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	struct trace_event_buffer fbuffer;
 	int syscall_nr;
 
+	/*
+	 * Syscall probe called with preemption enabled, but the ring
+	 * buffer and per-cpu data require preemption to be disabled.
+	 */
+	guard(preempt_notrace)();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;