In preparation for converting system call enter/exit instrumentation
into sleepable tracepoints, make sure that perf can handle registering
to such tracepoints by explicitly disabling preemption within the perf
tracepoint probes to respect the current expectations within perf ring
buffer code.
This change does not yet allow perf 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/perf.h | 26 ++++++++++++++++++++++----
1 file changed, 22 insertions(+), 4 deletions(-)
diff --git a/include/trace/perf.h b/include/trace/perf.h
index dbc6c74defc3..e1d866c3a076 100644
--- a/include/trace/perf.h
+++ b/include/trace/perf.h
@@ -27,8 +27,8 @@
#undef __perf_task
#define __perf_task(t) (__task = (t))
-#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 \
perf_trace_##call(void *__data, proto) \
{ \
@@ -43,13 +43,16 @@ perf_trace_##call(void *__data, proto) \
int __data_size; \
int rctx; \
\
+ if ((tp_flags) & TRACEPOINT_MAYSLEEP) \
+ preempt_disable_notrace(); \
+ \
__data_size = trace_event_get_offsets_##call(&__data_offsets, args); \
\
head = this_cpu_ptr(event_call->perf_events); \
if (!bpf_prog_array_valid(event_call) && \
__builtin_constant_p(!__task) && !__task && \
hlist_empty(head)) \
- return; \
+ goto end; \
\
__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
sizeof(u64)); \
@@ -57,7 +60,7 @@ perf_trace_##call(void *__data, proto) \
\
entry = perf_trace_buf_alloc(__entry_size, &__regs, &rctx); \
if (!entry) \
- return; \
+ goto end; \
\
perf_fetch_caller_regs(__regs); \
\
@@ -68,8 +71,23 @@ perf_trace_##call(void *__data, proto) \
perf_trace_run_bpf_submit(entry, __entry_size, rctx, \
event_call, __count, __regs, \
head, __task); \
+end: \
+ 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
--
2.25.1
