In preparation for allowing system call tracepoints to handle page
faults, introduce TRACE_EVENT_SYSCALL to declare the sys_enter/sys_exit
tracepoints.
Emit the static inlines register_trace_syscall_##name for events
declared with TRACE_EVENT_SYSCALL, allowing source-level validation
that only probes meant to handle system call entry/exit events are
registered to them.
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.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
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>
---
include/linux/tracepoint.h | 66 +++++++++++++++++++++++++--------
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 ++++++++++++++
kernel/entry/common.c | 4 +-
kernel/trace/trace_syscalls.c | 8 ++--
8 files changed, 98 insertions(+), 23 deletions(-)
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 6be396bb4297..2e4b4952bba2 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -248,10 +248,28 @@ 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 int \
+ unregister_trace_##name(void (*probe)(data_proto), void *data) \
+ { \
+ return tracepoint_probe_unregister(&__tracepoint_##name,\
+ (void *)probe, data); \
+ } \
+ static inline void \
+ check_trace_callback_type_##name(void (*cb)(data_proto)) \
+ { \
+ } \
+ static inline bool \
+ trace_##name##_enabled(void) \
+ { \
+ return static_key_false(&__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_key_false(&__tracepoint_##name.key)) \
@@ -263,8 +281,13 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
"RCU not watching for tracepoint"); \
} \
} \
- __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \
- PARAMS(cond)) \
+ static inline void trace_##name##_rcuidle(proto) \
+ { \
+ if (static_key_false(&__tracepoint_##name.key)) \
+ __DO_TRACE(name, \
+ TP_ARGS(args), \
+ TP_CONDITION(cond), 1); \
+ } \
static inline int \
register_trace_##name(void (*probe)(data_proto), void *data) \
{ \
@@ -277,21 +300,26 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
{ \
return tracepoint_probe_register_prio(&__tracepoint_##name, \
(void *)probe, data, prio); \
- } \
- static inline int \
- unregister_trace_##name(void (*probe)(data_proto), void *data) \
- { \
- return tracepoint_probe_unregister(&__tracepoint_##name,\
- (void *)probe, data); \
- } \
- static inline void \
- check_trace_callback_type_##name(void (*cb)(data_proto)) \
+ }
+
+#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_syscall_##name(proto) \
{ \
+ if (static_key_false(&__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"); \
+ } \
} \
- static inline bool \
- trace_##name##_enabled(void) \
+ static inline int \
+ register_trace_syscall_##name(void (*probe)(data_proto), void *data) \
{ \
- return static_key_false(&__tracepoint_##name.key); \
+ return tracepoint_probe_register(&__tracepoint_##name, \
+ (void *)probe, data); \
}
/*
@@ -439,6 +467,11 @@ 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...)
@@ -576,6 +609,9 @@ 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) \
\
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 90843cc38588..d08472421d0e 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -58,7 +58,7 @@ long syscall_trace_enter(struct pt_regs *regs, long syscall,
syscall = syscall_get_nr(current, regs);
if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
- trace_sys_enter(regs, syscall);
+ trace_syscall_sys_enter(regs, syscall);
/*
* Probes or BPF hooks in the tracepoint may have changed the
* system call number as well.
@@ -166,7 +166,7 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
audit_syscall_exit(regs);
if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
- trace_sys_exit(regs, syscall_get_return_value(current, regs));
+ trace_syscall_sys_exit(regs, syscall_get_return_value(current, regs));
step = report_single_step(work);
if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 9c581d6da843..067f8e2b930f 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -377,7 +377,7 @@ static int reg_event_syscall_enter(struct trace_event_file *file,
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!tr->sys_refcount_enter)
- ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
+ ret = register_trace_syscall_sys_enter(ftrace_syscall_enter, tr);
if (!ret) {
rcu_assign_pointer(tr->enter_syscall_files[num], file);
tr->sys_refcount_enter++;
@@ -415,7 +415,7 @@ static int reg_event_syscall_exit(struct trace_event_file *file,
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!tr->sys_refcount_exit)
- ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
+ ret = register_trace_syscall_sys_exit(ftrace_syscall_exit, tr);
if (!ret) {
rcu_assign_pointer(tr->exit_syscall_files[num], file);
tr->sys_refcount_exit++;
@@ -631,7 +631,7 @@ static int perf_sysenter_enable(struct trace_event_call *call)
mutex_lock(&syscall_trace_lock);
if (!sys_perf_refcount_enter)
- ret = register_trace_sys_enter(perf_syscall_enter, NULL);
+ ret = register_trace_syscall_sys_enter(perf_syscall_enter, NULL);
if (ret) {
pr_info("event trace: Could not activate syscall entry trace point");
} else {
@@ -728,7 +728,7 @@ static int perf_sysexit_enable(struct trace_event_call *call)
mutex_lock(&syscall_trace_lock);
if (!sys_perf_refcount_exit)
- ret = register_trace_sys_exit(perf_syscall_exit, NULL);
+ ret = register_trace_syscall_sys_exit(perf_syscall_exit, NULL);
if (ret) {
pr_info("event trace: Could not activate syscall exit trace point");
} else {
--
2.39.2Hi Mathieu,
kernel test robot noticed the following build errors:
[auto build test ERROR on peterz-queue/sched/core]
[also build test ERROR on linus/master v6.12-rc1 next-20241003]
[cannot apply to rostedt-trace/for-next rostedt-trace/for-next-urgent tip/core/entry]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Mathieu-Desnoyers/tracing-Declare-system-call-tracepoints-with-TRACE_EVENT_SYSCALL/20241001-032827
base: https://git.kernel.org/pub/scm/linux/kernel/git/peterz/queue.git sched/core
patch link: https://lore.kernel.org/r/20240930192357.1154417-2-mathieu.desnoyers%40efficios.com
patch subject: [PATCH resend 1/8] tracing: Declare system call tracepoints with TRACE_EVENT_SYSCALL
config: riscv-allnoconfig (https://download.01.org/0day-ci/archive/20241003/202410031716.sTBC2OLt-lkp@intel.com/config)
compiler: riscv64-linux-gcc (GCC) 14.1.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20241003/202410031716.sTBC2OLt-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202410031716.sTBC2OLt-lkp@intel.com/
All errors (new ones prefixed by >>):
In file included from include/trace/syscall.h:5,
from include/linux/syscalls.h:93,
from include/linux/entry-common.h:7,
from kernel/entry/common.c:4:
include/trace/events/syscalls.h:20:18: error: expected ')' before 'struct'
20 | TP_PROTO(struct pt_regs *regs, long id),
| ^~~~~~
include/linux/tracepoint.h:106:25: note: in definition of macro 'PARAMS'
106 | #define PARAMS(args...) args
| ^~~~
include/linux/tracepoint.h:614:9: note: in expansion of macro 'DECLARE_TRACE_SYSCALL'
614 | DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args))
| ^~~~~~~~~~~~~~~~~~~~~
include/linux/tracepoint.h:614:37: note: in expansion of macro 'PARAMS'
614 | DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args))
| ^~~~~~
include/trace/events/syscalls.h:18:1: note: in expansion of macro 'TRACE_EVENT_SYSCALL'
18 | TRACE_EVENT_SYSCALL(sys_enter,
| ^~~~~~~~~~~~~~~~~~~
include/trace/events/syscalls.h:20:9: note: in expansion of macro 'TP_PROTO'
20 | TP_PROTO(struct pt_regs *regs, long id),
| ^~~~~~~~
include/trace/events/syscalls.h:46:18: error: expected ')' before 'struct'
46 | TP_PROTO(struct pt_regs *regs, long ret),
| ^~~~~~
include/linux/tracepoint.h:106:25: note: in definition of macro 'PARAMS'
106 | #define PARAMS(args...) args
| ^~~~
include/linux/tracepoint.h:614:9: note: in expansion of macro 'DECLARE_TRACE_SYSCALL'
614 | DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args))
| ^~~~~~~~~~~~~~~~~~~~~
include/linux/tracepoint.h:614:37: note: in expansion of macro 'PARAMS'
614 | DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args))
| ^~~~~~
include/trace/events/syscalls.h:44:1: note: in expansion of macro 'TRACE_EVENT_SYSCALL'
44 | TRACE_EVENT_SYSCALL(sys_exit,
| ^~~~~~~~~~~~~~~~~~~
include/trace/events/syscalls.h:46:9: note: in expansion of macro 'TP_PROTO'
46 | TP_PROTO(struct pt_regs *regs, long ret),
| ^~~~~~~~
kernel/entry/common.c: In function 'syscall_trace_enter':
>> kernel/entry/common.c:61:17: error: implicit declaration of function 'trace_syscall_sys_enter' [-Wimplicit-function-declaration]
61 | trace_syscall_sys_enter(regs, syscall);
| ^~~~~~~~~~~~~~~~~~~~~~~
kernel/entry/common.c: In function 'syscall_exit_work':
>> kernel/entry/common.c:169:17: error: implicit declaration of function 'trace_syscall_sys_exit' [-Wimplicit-function-declaration]
169 | trace_syscall_sys_exit(regs, syscall_get_return_value(current, regs));
| ^~~~~~~~~~~~~~~~~~~~~~
vim +/trace_syscall_sys_enter +61 kernel/entry/common.c
27
28 long syscall_trace_enter(struct pt_regs *regs, long syscall,
29 unsigned long work)
30 {
31 long ret = 0;
32
33 /*
34 * Handle Syscall User Dispatch. This must comes first, since
35 * the ABI here can be something that doesn't make sense for
36 * other syscall_work features.
37 */
38 if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
39 if (syscall_user_dispatch(regs))
40 return -1L;
41 }
42
43 /* Handle ptrace */
44 if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
45 ret = ptrace_report_syscall_entry(regs);
46 if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
47 return -1L;
48 }
49
50 /* Do seccomp after ptrace, to catch any tracer changes. */
51 if (work & SYSCALL_WORK_SECCOMP) {
52 ret = __secure_computing(NULL);
53 if (ret == -1L)
54 return ret;
55 }
56
57 /* Either of the above might have changed the syscall number */
58 syscall = syscall_get_nr(current, regs);
59
60 if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
> 61 trace_syscall_sys_enter(regs, syscall);
62 /*
63 * Probes or BPF hooks in the tracepoint may have changed the
64 * system call number as well.
65 */
66 syscall = syscall_get_nr(current, regs);
67 }
68
69 syscall_enter_audit(regs, syscall);
70
71 return ret ? : syscall;
72 }
73
74 noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
75 {
76 enter_from_user_mode(regs);
77 instrumentation_begin();
78 local_irq_enable();
79 instrumentation_end();
80 }
81
82 /* Workaround to allow gradual conversion of architecture code */
83 void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
84
85 /**
86 * exit_to_user_mode_loop - do any pending work before leaving to user space
87 * @regs: Pointer to pt_regs on entry stack
88 * @ti_work: TIF work flags as read by the caller
89 */
90 __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
91 unsigned long ti_work)
92 {
93 /*
94 * Before returning to user space ensure that all pending work
95 * items have been completed.
96 */
97 while (ti_work & EXIT_TO_USER_MODE_WORK) {
98
99 local_irq_enable_exit_to_user(ti_work);
100
101 if (ti_work & _TIF_NEED_RESCHED)
102 schedule();
103
104 if (ti_work & _TIF_UPROBE)
105 uprobe_notify_resume(regs);
106
107 if (ti_work & _TIF_PATCH_PENDING)
108 klp_update_patch_state(current);
109
110 if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
111 arch_do_signal_or_restart(regs);
112
113 if (ti_work & _TIF_NOTIFY_RESUME)
114 resume_user_mode_work(regs);
115
116 /* Architecture specific TIF work */
117 arch_exit_to_user_mode_work(regs, ti_work);
118
119 /*
120 * Disable interrupts and reevaluate the work flags as they
121 * might have changed while interrupts and preemption was
122 * enabled above.
123 */
124 local_irq_disable_exit_to_user();
125
126 /* Check if any of the above work has queued a deferred wakeup */
127 tick_nohz_user_enter_prepare();
128
129 ti_work = read_thread_flags();
130 }
131
132 /* Return the latest work state for arch_exit_to_user_mode() */
133 return ti_work;
134 }
135
136 /*
137 * If SYSCALL_EMU is set, then the only reason to report is when
138 * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall
139 * instruction has been already reported in syscall_enter_from_user_mode().
140 */
141 static inline bool report_single_step(unsigned long work)
142 {
143 if (work & SYSCALL_WORK_SYSCALL_EMU)
144 return false;
145
146 return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
147 }
148
149 static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
150 {
151 bool step;
152
153 /*
154 * If the syscall was rolled back due to syscall user dispatching,
155 * then the tracers below are not invoked for the same reason as
156 * the entry side was not invoked in syscall_trace_enter(): The ABI
157 * of these syscalls is unknown.
158 */
159 if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
160 if (unlikely(current->syscall_dispatch.on_dispatch)) {
161 current->syscall_dispatch.on_dispatch = false;
162 return;
163 }
164 }
165
166 audit_syscall_exit(regs);
167
168 if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
> 169 trace_syscall_sys_exit(regs, syscall_get_return_value(current, regs));
170
171 step = report_single_step(work);
172 if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
173 ptrace_report_syscall_exit(regs, step);
174 }
175
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Hi Mathieu,
kernel test robot noticed the following build errors:
[auto build test ERROR on peterz-queue/sched/core]
[also build test ERROR on linus/master v6.12-rc1 next-20241003]
[cannot apply to rostedt-trace/for-next rostedt-trace/for-next-urgent tip/core/entry]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Mathieu-Desnoyers/tracing-Declare-system-call-tracepoints-with-TRACE_EVENT_SYSCALL/20241001-032827
base: https://git.kernel.org/pub/scm/linux/kernel/git/peterz/queue.git sched/core
patch link: https://lore.kernel.org/r/20240930192357.1154417-2-mathieu.desnoyers%40efficios.com
patch subject: [PATCH resend 1/8] tracing: Declare system call tracepoints with TRACE_EVENT_SYSCALL
config: powerpc-allnoconfig (https://download.01.org/0day-ci/archive/20241003/202410031750.cFIt2Rmx-lkp@intel.com/config)
compiler: powerpc-linux-gcc (GCC) 14.1.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20241003/202410031750.cFIt2Rmx-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202410031750.cFIt2Rmx-lkp@intel.com/
All errors (new ones prefixed by >>):
In file included from include/trace/syscall.h:5,
from include/linux/syscalls.h:93,
from arch/powerpc/kernel/ptrace/ptrace.c:19:
include/trace/events/syscalls.h:20:18: error: expected ')' before 'struct'
20 | TP_PROTO(struct pt_regs *regs, long id),
| ^~~~~~
include/linux/tracepoint.h:106:25: note: in definition of macro 'PARAMS'
106 | #define PARAMS(args...) args
| ^~~~
include/linux/tracepoint.h:614:9: note: in expansion of macro 'DECLARE_TRACE_SYSCALL'
614 | DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args))
| ^~~~~~~~~~~~~~~~~~~~~
include/linux/tracepoint.h:614:37: note: in expansion of macro 'PARAMS'
614 | DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args))
| ^~~~~~
include/trace/events/syscalls.h:18:1: note: in expansion of macro 'TRACE_EVENT_SYSCALL'
18 | TRACE_EVENT_SYSCALL(sys_enter,
| ^~~~~~~~~~~~~~~~~~~
include/trace/events/syscalls.h:20:9: note: in expansion of macro 'TP_PROTO'
20 | TP_PROTO(struct pt_regs *regs, long id),
| ^~~~~~~~
include/trace/events/syscalls.h:46:18: error: expected ')' before 'struct'
46 | TP_PROTO(struct pt_regs *regs, long ret),
| ^~~~~~
include/linux/tracepoint.h:106:25: note: in definition of macro 'PARAMS'
106 | #define PARAMS(args...) args
| ^~~~
include/linux/tracepoint.h:614:9: note: in expansion of macro 'DECLARE_TRACE_SYSCALL'
614 | DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args))
| ^~~~~~~~~~~~~~~~~~~~~
include/linux/tracepoint.h:614:37: note: in expansion of macro 'PARAMS'
614 | DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args))
| ^~~~~~
include/trace/events/syscalls.h:44:1: note: in expansion of macro 'TRACE_EVENT_SYSCALL'
44 | TRACE_EVENT_SYSCALL(sys_exit,
| ^~~~~~~~~~~~~~~~~~~
include/trace/events/syscalls.h:46:9: note: in expansion of macro 'TP_PROTO'
46 | TP_PROTO(struct pt_regs *regs, long ret),
| ^~~~~~~~
arch/powerpc/kernel/ptrace/ptrace.c: In function 'do_syscall_trace_enter':
>> arch/powerpc/kernel/ptrace/ptrace.c:298:17: error: implicit declaration of function 'trace_sys_enter'; did you mean 'ftrace_nmi_enter'? [-Wimplicit-function-declaration]
298 | trace_sys_enter(regs, regs->gpr[0]);
| ^~~~~~~~~~~~~~~
| ftrace_nmi_enter
arch/powerpc/kernel/ptrace/ptrace.c: In function 'do_syscall_trace_leave':
>> arch/powerpc/kernel/ptrace/ptrace.c:329:17: error: implicit declaration of function 'trace_sys_exit'; did you mean 'ftrace_nmi_exit'? [-Wimplicit-function-declaration]
329 | trace_sys_exit(regs, regs->result);
| ^~~~~~~~~~~~~~
| ftrace_nmi_exit
vim +298 arch/powerpc/kernel/ptrace/ptrace.c
2449acc5348b94 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 235
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 236 /**
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 237 * do_syscall_trace_enter() - Do syscall tracing on kernel entry.
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 238 * @regs: the pt_regs of the task to trace (current)
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 239 *
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 240 * Performs various types of tracing on syscall entry. This includes seccomp,
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 241 * ptrace, syscall tracepoints and audit.
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 242 *
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 243 * The pt_regs are potentially visible to userspace via ptrace, so their
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 244 * contents is ABI.
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 245 *
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 246 * One or more of the tracers may modify the contents of pt_regs, in particular
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 247 * to modify arguments or even the syscall number itself.
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 248 *
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 249 * It's also possible that a tracer can choose to reject the system call. In
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 250 * that case this function will return an illegal syscall number, and will put
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 251 * an appropriate return value in regs->r3.
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 252 *
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 253 * Return: the (possibly changed) syscall number.
^1da177e4c3f41 arch/ppc/kernel/ptrace.c Linus Torvalds 2005-04-16 254 */
4f72c4279eab1e arch/powerpc/kernel/ptrace.c Roland McGrath 2008-07-27 255 long do_syscall_trace_enter(struct pt_regs *regs)
ea9c102cb0a796 arch/ppc/kernel/ptrace.c David Woodhouse 2005-05-08 256 {
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 257 u32 flags;
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 258
985faa78687de6 arch/powerpc/kernel/ptrace/ptrace.c Mark Rutland 2021-11-29 259 flags = read_thread_flags() & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 260
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 261 if (flags) {
153474ba1a4aed arch/powerpc/kernel/ptrace/ptrace.c Eric W. Biederman 2022-01-27 262 int rc = ptrace_report_syscall_entry(regs);
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 263
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 264 if (unlikely(flags & _TIF_SYSCALL_EMU)) {
5521eb4bca2db7 arch/powerpc/kernel/ptrace.c Breno Leitao 2018-09-20 265 /*
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 266 * A nonzero return code from
153474ba1a4aed arch/powerpc/kernel/ptrace/ptrace.c Eric W. Biederman 2022-01-27 267 * ptrace_report_syscall_entry() tells us to prevent
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 268 * the syscall execution, but we are not going to
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 269 * execute it anyway.
a225f156740555 arch/powerpc/kernel/ptrace.c Elvira Khabirova 2018-12-07 270 *
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 271 * Returning -1 will skip the syscall execution. We want
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 272 * to avoid clobbering any registers, so we don't goto
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 273 * the skip label below.
5521eb4bca2db7 arch/powerpc/kernel/ptrace.c Breno Leitao 2018-09-20 274 */
5521eb4bca2db7 arch/powerpc/kernel/ptrace.c Breno Leitao 2018-09-20 275 return -1;
5521eb4bca2db7 arch/powerpc/kernel/ptrace.c Breno Leitao 2018-09-20 276 }
5521eb4bca2db7 arch/powerpc/kernel/ptrace.c Breno Leitao 2018-09-20 277
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 278 if (rc) {
4f72c4279eab1e arch/powerpc/kernel/ptrace.c Roland McGrath 2008-07-27 279 /*
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 280 * The tracer decided to abort the syscall. Note that
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 281 * the tracer may also just change regs->gpr[0] to an
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 282 * invalid syscall number, that is handled below on the
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 283 * exit path.
4f72c4279eab1e arch/powerpc/kernel/ptrace.c Roland McGrath 2008-07-27 284 */
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 285 goto skip;
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 286 }
8dbdec0bcb416d arch/powerpc/kernel/ptrace.c Dmitry V. Levin 2018-12-16 287 }
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 288
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 289 /* Run seccomp after ptrace; allow it to set gpr[3]. */
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 290 if (do_seccomp(regs))
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 291 return -1;
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 292
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 293 /* Avoid trace and audit when syscall is invalid. */
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 294 if (regs->gpr[0] >= NR_syscalls)
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 295 goto skip;
ea9c102cb0a796 arch/ppc/kernel/ptrace.c David Woodhouse 2005-05-08 296
02424d8966d803 arch/powerpc/kernel/ptrace.c Ian Munsie 2011-02-02 297 if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
02424d8966d803 arch/powerpc/kernel/ptrace.c Ian Munsie 2011-02-02 @298 trace_sys_enter(regs, regs->gpr[0]);
02424d8966d803 arch/powerpc/kernel/ptrace.c Ian Munsie 2011-02-02 299
cab175f9fa2973 arch/powerpc/kernel/ptrace.c Denis Kirjanov 2010-08-27 300 if (!is_32bit_task())
91397401bb5072 arch/powerpc/kernel/ptrace.c Eric Paris 2014-03-11 301 audit_syscall_entry(regs->gpr[0], regs->gpr[3], regs->gpr[4],
ea9c102cb0a796 arch/ppc/kernel/ptrace.c David Woodhouse 2005-05-08 302 regs->gpr[5], regs->gpr[6]);
cfcd1705b61ecc arch/powerpc/kernel/ptrace.c David Woodhouse 2007-01-14 303 else
91397401bb5072 arch/powerpc/kernel/ptrace.c Eric Paris 2014-03-11 304 audit_syscall_entry(regs->gpr[0],
cfcd1705b61ecc arch/powerpc/kernel/ptrace.c David Woodhouse 2007-01-14 305 regs->gpr[3] & 0xffffffff,
cfcd1705b61ecc arch/powerpc/kernel/ptrace.c David Woodhouse 2007-01-14 306 regs->gpr[4] & 0xffffffff,
cfcd1705b61ecc arch/powerpc/kernel/ptrace.c David Woodhouse 2007-01-14 307 regs->gpr[5] & 0xffffffff,
cfcd1705b61ecc arch/powerpc/kernel/ptrace.c David Woodhouse 2007-01-14 308 regs->gpr[6] & 0xffffffff);
4f72c4279eab1e arch/powerpc/kernel/ptrace.c Roland McGrath 2008-07-27 309
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 310 /* Return the possibly modified but valid syscall number */
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 311 return regs->gpr[0];
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 312
1addc57e111b92 arch/powerpc/kernel/ptrace.c Kees Cook 2016-06-02 313 skip:
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 314 /*
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 315 * If we are aborting explicitly, or if the syscall number is
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 316 * now invalid, set the return value to -ENOSYS.
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 317 */
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 318 regs->gpr[3] = -ENOSYS;
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 319 return -1;
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 320 }
d38374142b2560 arch/powerpc/kernel/ptrace.c Michael Ellerman 2015-07-23 321
ea9c102cb0a796 arch/ppc/kernel/ptrace.c David Woodhouse 2005-05-08 322 void do_syscall_trace_leave(struct pt_regs *regs)
ea9c102cb0a796 arch/ppc/kernel/ptrace.c David Woodhouse 2005-05-08 323 {
4f72c4279eab1e arch/powerpc/kernel/ptrace.c Roland McGrath 2008-07-27 324 int step;
4f72c4279eab1e arch/powerpc/kernel/ptrace.c Roland McGrath 2008-07-27 325
d7e7528bcd456f arch/powerpc/kernel/ptrace.c Eric Paris 2012-01-03 326 audit_syscall_exit(regs);
ea9c102cb0a796 arch/ppc/kernel/ptrace.c David Woodhouse 2005-05-08 327
02424d8966d803 arch/powerpc/kernel/ptrace.c Ian Munsie 2011-02-02 328 if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
02424d8966d803 arch/powerpc/kernel/ptrace.c Ian Munsie 2011-02-02 @329 trace_sys_exit(regs, regs->result);
02424d8966d803 arch/powerpc/kernel/ptrace.c Ian Munsie 2011-02-02 330
4f72c4279eab1e arch/powerpc/kernel/ptrace.c Roland McGrath 2008-07-27 331 step = test_thread_flag(TIF_SINGLESTEP);
4f72c4279eab1e arch/powerpc/kernel/ptrace.c Roland McGrath 2008-07-27 332 if (step || test_thread_flag(TIF_SYSCALL_TRACE))
153474ba1a4aed arch/powerpc/kernel/ptrace/ptrace.c Eric W. Biederman 2022-01-27 333 ptrace_report_syscall_exit(regs, step);
ea9c102cb0a796 arch/ppc/kernel/ptrace.c David Woodhouse 2005-05-08 334 }
002af9391bfbe8 arch/powerpc/kernel/ptrace.c Michael Ellerman 2018-10-12 335
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
© 2016 - 2024 Red Hat, Inc.