[RFC PATCH 3/6] tracing: bpf-trace: add support for sleepable tracepoints

[Michael Jeanson]

In preparation for converting system call enter/exit instrumentation
into sleepable tracepoints, make sure that bpf can handle registering to
such tracepoints by explicitly disabling preemption within the bpf
tracepoint probes to respect the current expectations within bpf tracing
code.

This change does not yet allow bpf to take page faults per se within its
probe, but allows its existing probes to connect to sleepable
tracepoints.

Co-developed-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Signed-off-by: Michael Jeanson <mjeanson@xxxxxxxxxxxx>
Cc: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
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: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Cc: bpf@xxxxxxxxxxxxxxx
---
 include/trace/bpf_probe.h | 23 +++++++++++++++++++++--
 kernel/trace/bpf_trace.c  |  5 ++++-
 2 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h
index 1ce3be63add1..d688cb9b32fe 100644
--- a/include/trace/bpf_probe.h
+++ b/include/trace/bpf_probe.h
@@ -55,15 +55,34 @@
 /* tracepoints with more than 12 arguments will hit build error */
 #define CAST_TO_U64(...) CONCATENATE(__CAST, COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__)
 
-#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, tp_flags)	\
 static notrace void							\
 __bpf_trace_##call(void *__data, proto)					\
 {									\
 	struct bpf_prog *prog = __data;					\
+									\
+	if ((tp_flags) & TRACEPOINT_MAYSLEEP)				\
+		preempt_disable_notrace();				\
+									\
 	CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(prog, CAST_TO_U64(args));	\
+									\
+	if ((tp_flags) & TRACEPOINT_MAYSLEEP)				\
+		preempt_enable_notrace();				\
 }
 
+#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),	0)
+
+#undef DECLARE_EVENT_CLASS_MAYSLEEP
+#define DECLARE_EVENT_CLASS_MAYSLEEP(call, proto, args, tstruct,	\
+		assign, print)						\
+	_DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args),		\
+		PARAMS(tstruct), PARAMS(assign), PARAMS(print),		\
+		TRACEPOINT_MAYSLEEP)
+
 /*
  * This part is compiled out, it is only here as a build time check
  * to make sure that if the tracepoint handling changes, the
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index a8d4f253ed77..54f8b320fe2f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1947,7 +1947,10 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *
 	if (prog->aux->max_tp_access > btp->writable_size)
 		return -EINVAL;
 
-	return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog);
+	if (tp->flags & TRACEPOINT_MAYSLEEP)
+		return tracepoint_probe_register_maysleep(tp, (void *)btp->bpf_func, prog);
+	else
+		return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog);
 }
 
 int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
-- 
2.25.1