This is a note to let you know that I've just added the patch titled
tracing/ftrace: disable preemption in syscall probe
to the 6.6-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
tracing-ftrace-disable-preemption-in-syscall-probe.patch
and it can be found in the queue-6.6 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 8126dcd7495734e2d89016b42bc2f4818e2c60a2
Author: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Date: Tue Oct 8 21:07:12 2024 -0400
tracing/ftrace: disable preemption in syscall probe
[ Upstream commit 13d750c2c03e9861e15268574ed2c239cca9c9d5 ]
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.
Cc: Michael Jeanson <mjeanson@xxxxxxxxxxxx>
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>
Link: https://lore.kernel.org/20241009010718.2050182-3-mathieu.desnoyers@xxxxxxxxxxxx
Acked-by: Masami Hiramatsu (Google) <mhiramat@xxxxxxxxxx>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Signed-off-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index c2f9cabf154d1..fa0d51cad57a8 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -244,6 +244,9 @@ 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)
@@ -374,11 +377,11 @@ 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;\
@@ -403,6 +406,29 @@ 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
@@ -418,6 +444,8 @@ 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 de753403cdafb..9508d9022940f 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;
