[for-next][PATCH 01/10] tracing: Declare system call tracepoints with TRACE_EVENT_SYSCALL

From: Steven Rostedt
Date: Thu Oct 10 2024 - 10:30:11 EST

Next message: Steven Rostedt: "[for-next][PATCH 04/10] tracing/bpf: disable preemption in syscall probe"
Previous message: Steven Rostedt: "[for-next][PATCH 02/10] tracing/ftrace: disable preemption in syscall probe"
In reply to: Steven Rostedt: "[for-next][PATCH 02/10] tracing/ftrace: disable preemption in syscall probe"
Next in thread: Steven Rostedt: "[for-next][PATCH 04/10] tracing/bpf: disable preemption in syscall probe"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

From: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>

In preparation for allowing system call tracepoints to handle page
faults, introduce TRACE_EVENT_SYSCALL to declare the sys_enter/sys_exit
tracepoints.

Move the common code between __DECLARE_TRACE and __DECLARE_TRACE_SYSCALL
into __DECLARE_TRACE_COMMON.

This change is not meant to alter the generated code, and only prepares
the following modifications.

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/20241009010718.2050182-2-mathieu.desnoyers@xxxxxxxxxxxx
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Signed-off-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
---
include/linux/tracepoint.h | 53 +++++++++++++++++++++++++--------
include/trace/bpf_probe.h | 3 ++
include/trace/define_trace.h | 5 ++++
include/trace/events/syscalls.h | 4 +--
include/trace/perf.h | 3 ++
include/trace/trace_events.h | 28 +++++++++++++++++
6 files changed, 81 insertions(+), 15 deletions(-)

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 3d33b9872cec..76e441b39a96 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -197,7 +197,7 @@ 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.
*/
-#define __DO_TRACE(name, args, cond) \
+#define __DO_TRACE(name, args, cond, syscall) \
do { \
int __maybe_unused __idx = 0; \
\
@@ -222,21 +222,10 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
* site if it is not watching, as it will need to be active when the
* tracepoint is enabled.
*/
-#define __DECLARE_TRACE(name, proto, args, cond, data_proto) \
+#define __DECLARE_TRACE_COMMON(name, proto, args, cond, data_proto) \
extern int __traceiter_##name(data_proto); \
DECLARE_STATIC_CALL(tp_func_##name, __traceiter_##name); \
extern struct tracepoint __tracepoint_##name; \
- static inline void trace_##name(proto) \
- { \
- if (static_branch_unlikely(&__tracepoint_##name.key)) \
- __DO_TRACE(name, \
- TP_ARGS(args), \
- TP_CONDITION(cond)); \
- if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \
- WARN_ONCE(!rcu_is_watching(), \
- "RCU not watching for tracepoint"); \
- } \
- } \
static inline int \
register_trace_##name(void (*probe)(data_proto), void *data) \
{ \
@@ -266,6 +255,34 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
return static_branch_unlikely(&__tracepoint_##name.key);\
}

+#define __DECLARE_TRACE(name, proto, args, cond, data_proto) \
+ __DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), cond, PARAMS(data_proto)) \
+ static inline void trace_##name(proto) \
+ { \
+ if (static_branch_unlikely(&__tracepoint_##name.key)) \
+ __DO_TRACE(name, \
+ TP_ARGS(args), \
+ TP_CONDITION(cond), 0); \
+ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \
+ WARN_ONCE(!rcu_is_watching(), \
+ "RCU not watching for tracepoint"); \
+ } \
+ }
+
+#define __DECLARE_TRACE_SYSCALL(name, proto, args, cond, data_proto) \
+ __DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), cond, PARAMS(data_proto)) \
+ static inline void trace_##name(proto) \
+ { \
+ if (static_branch_unlikely(&__tracepoint_##name.key)) \
+ __DO_TRACE(name, \
+ TP_ARGS(args), \
+ TP_CONDITION(cond), 1); \
+ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \
+ WARN_ONCE(!rcu_is_watching(), \
+ "RCU not watching for tracepoint"); \
+ } \
+ }
+
/*
* We have no guarantee that gcc and the linker won't up-align the tracepoint
* structures, so we create an array of pointers that will be used for iteration
@@ -348,6 +365,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
return false; \
}

+#define __DECLARE_TRACE_SYSCALL __DECLARE_TRACE
+
#define DEFINE_TRACE_FN(name, reg, unreg, proto, args)
#define DEFINE_TRACE(name, proto, args)
#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
@@ -409,6 +428,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
cpu_online(raw_smp_processor_id()) && (PARAMS(cond)), \
PARAMS(void *__data, proto))

+#define DECLARE_TRACE_SYSCALL(name, proto, args) \
+ __DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args), \
+ cpu_online(raw_smp_processor_id()), \
+ PARAMS(void *__data, proto))
+
#define TRACE_EVENT_FLAGS(event, flag)

#define TRACE_EVENT_PERF_PERM(event, expr...)
@@ -546,6 +570,9 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
struct, assign, print) \
DECLARE_TRACE_CONDITION(name, PARAMS(proto), \
PARAMS(args), PARAMS(cond))
+#define TRACE_EVENT_SYSCALL(name, proto, args, struct, assign, \
+ print, reg, unreg) \
+ DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args))

#define TRACE_EVENT_FLAGS(event, flag)

diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h
index a2ea11cc912e..c85bbce5aaa5 100644
--- a/include/trace/bpf_probe.h
+++ b/include/trace/bpf_probe.h
@@ -53,6 +53,9 @@ __bpf_trace_##call(void *__data, proto) \
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
__BPF_DECLARE_TRACE(call, PARAMS(proto), PARAMS(args))

+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
+
/*
* 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/include/trace/define_trace.h b/include/trace/define_trace.h
index 00723935dcc7..ff5fa17a6259 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -46,6 +46,10 @@
assign, print, reg, unreg) \
DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args))

+#undef TRACE_EVENT_SYSCALL
+#define TRACE_EVENT_SYSCALL(name, proto, args, struct, assign, print, reg, unreg) \
+ DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args))
+
#undef TRACE_EVENT_NOP
#define TRACE_EVENT_NOP(name, proto, args, struct, assign, print)

@@ -107,6 +111,7 @@
#undef TRACE_EVENT
#undef TRACE_EVENT_FN
#undef TRACE_EVENT_FN_COND
+#undef TRACE_EVENT_SYSCALL
#undef TRACE_EVENT_CONDITION
#undef TRACE_EVENT_NOP
#undef DEFINE_EVENT_NOP
diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index b6e0cbc2c71f..f31ff446b468 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -15,7 +15,7 @@

#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS

-TRACE_EVENT_FN(sys_enter,
+TRACE_EVENT_SYSCALL(sys_enter,

TP_PROTO(struct pt_regs *regs, long id),

@@ -41,7 +41,7 @@ TRACE_EVENT_FN(sys_enter,

TRACE_EVENT_FLAGS(sys_enter, TRACE_EVENT_FL_CAP_ANY)

-TRACE_EVENT_FN(sys_exit,
+TRACE_EVENT_SYSCALL(sys_exit,

TP_PROTO(struct pt_regs *regs, long ret),

diff --git a/include/trace/perf.h b/include/trace/perf.h
index 2c11181c82e0..ded997af481e 100644
--- a/include/trace/perf.h
+++ b/include/trace/perf.h
@@ -55,6 +55,9 @@ perf_trace_##call(void *__data, proto) \
head, __task); \
}

+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
+
/*
* 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/include/trace/trace_events.h b/include/trace/trace_events.h
index c2f9cabf154d..8bcbb9ee44de 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -45,6 +45,16 @@
PARAMS(print)); \
DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args));

+#undef TRACE_EVENT_SYSCALL
+#define TRACE_EVENT_SYSCALL(name, proto, args, tstruct, assign, print, reg, unreg) \
+ DECLARE_EVENT_SYSCALL_CLASS(name, \
+ PARAMS(proto), \
+ PARAMS(args), \
+ PARAMS(tstruct), \
+ PARAMS(assign), \
+ PARAMS(print)); \
+ DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args));
+
#include "stages/stage1_struct_define.h"

#undef DECLARE_EVENT_CLASS
@@ -57,6 +67,9 @@
\
static struct trace_event_class event_class_##name;

+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
+
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args) \
static struct trace_event_call __used \
@@ -117,6 +130,9 @@
tstruct; \
};

+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
+
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args)

@@ -208,6 +224,9 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \
.trace = trace_raw_output_##call, \
};

+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
+
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \
static notrace enum print_line_t \
@@ -265,6 +284,9 @@ static inline notrace int trace_event_get_offsets_##call( \
return __data_size; \
}

+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
+
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)

/*
@@ -409,6 +431,9 @@ trace_event_raw_event_##call(void *__data, proto) \
* 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) \
@@ -434,6 +459,9 @@ static struct trace_event_class __used __refdata event_class_##call = { \
_TRACE_PERF_INIT(call) \
};

+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
+
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
\
--
2.45.2

Next message: Steven Rostedt: "[for-next][PATCH 04/10] tracing/bpf: disable preemption in syscall probe"
Previous message: Steven Rostedt: "[for-next][PATCH 02/10] tracing/ftrace: disable preemption in syscall probe"
In reply to: Steven Rostedt: "[for-next][PATCH 02/10] tracing/ftrace: disable preemption in syscall probe"
Next in thread: Steven Rostedt: "[for-next][PATCH 04/10] tracing/bpf: disable preemption in syscall probe"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]