[PATCH AUTOSEL 6.1 02/15] tracing/ftrace: disable preemption in syscall probe

[PATCH AUTOSEL 6.1 02/15] tracing/ftrace: disable preemption in syscall probe

[Sasha Levin]

From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

[ 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@efficios.com>
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>
Link: https://lore.kernel.org/20241009010718.2050182-3-mathieu.desnoyers@efficios.com
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/trace/trace_events.h  | 36 +++++++++++++++++++++++++++++++----
 kernel/trace/trace_syscalls.c | 12 ++++++++++++
 2 files changed, 44 insertions(+), 4 deletions(-)

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 942ddbdace4a4..e39c5ca76eabb 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;
-- 
2.43.0

[PATCH AUTOSEL 6.1 03/15] tracing: Use atomic64_inc_return() in trace_clock_counter()

[Sasha Levin]

From: Uros Bizjak <ubizjak@gmail.com>

[ Upstream commit eb887c4567d1b0e7684c026fe7df44afa96589e6 ]

Use atomic64_inc_return(&ref) instead of atomic64_add_return(1, &ref)
to use optimized implementation and ease register pressure around
the primitive for targets that implement optimized variant.

Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20241007085651.48544-1-ubizjak@gmail.com
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/trace/trace_clock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 4702efb00ff21..4cb2ebc439be6 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -154,5 +154,5 @@ static atomic64_t trace_counter;
  */
 u64 notrace trace_clock_counter(void)
 {
-	return atomic64_add_return(1, &trace_counter);
+	return atomic64_inc_return(&trace_counter);
 }
-- 
2.43.0

[PATCH AUTOSEL 6.1 04/15] tools/rtla: fix collision with glibc sched_attr/sched_set_attr

[Sasha Levin]

From: Jan Stancek <jstancek@redhat.com>

[ Upstream commit 0eecee340672c4b512f6f4a8c6add26df05d130c ]

glibc commit 21571ca0d703 ("Linux: Add the sched_setattr
and sched_getattr functions") now also provides 'struct sched_attr'
and sched_setattr() which collide with the ones from rtla.

  In file included from src/trace.c:11:
  src/utils.h:49:8: error: redefinition of ‘struct sched_attr’
     49 | struct sched_attr {
        |        ^~~~~~~~~~
  In file included from /usr/include/bits/sched.h:60,
                   from /usr/include/sched.h:43,
                   from /usr/include/tracefs/tracefs.h:10,
                   from src/trace.c:4:
  /usr/include/linux/sched/types.h:98:8: note: originally defined here
     98 | struct sched_attr {
        |        ^~~~~~~~~~

Define 'struct sched_attr' conditionally, similar to what strace did:
  https://lore.kernel.org/all/20240930222913.3981407-1-raj.khem@gmail.com/
and rename rtla's version of sched_setattr() to avoid collision.

Link: https://lore.kernel.org/8088f66a7a57c1b209cd8ae0ae7c336a7f8c930d.1728572865.git.jstancek@redhat.com
Signed-off-by: Jan Stancek <jstancek@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/tracing/rtla/src/utils.c | 4 ++--
 tools/tracing/rtla/src/utils.h | 2 ++
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
index 8c8d63c7196cf..02194773ef12d 100644
--- a/tools/tracing/rtla/src/utils.c
+++ b/tools/tracing/rtla/src/utils.c
@@ -238,7 +238,7 @@ long parse_ns_duration(char *val)
 
 #define SCHED_DEADLINE		6
 
-static inline int sched_setattr(pid_t pid, const struct sched_attr *attr,
+static inline int syscall_sched_setattr(pid_t pid, const struct sched_attr *attr,
 				unsigned int flags) {
 	return syscall(__NR_sched_setattr, pid, attr, flags);
 }
@@ -248,7 +248,7 @@ int __set_sched_attr(int pid, struct sched_attr *attr)
 	int flags = 0;
 	int retval;
 
-	retval = sched_setattr(pid, attr, flags);
+	retval = syscall_sched_setattr(pid, attr, flags);
 	if (retval < 0) {
 		err_msg("Failed to set sched attributes to the pid %d: %s\n",
 			pid, strerror(errno));
diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h
index 92da41aaf4c4c..e445ccf15e701 100644
--- a/tools/tracing/rtla/src/utils.h
+++ b/tools/tracing/rtla/src/utils.h
@@ -44,6 +44,7 @@ update_sum(unsigned long long *a, unsigned long long *b)
 	*a += *b;
 }
 
+#ifndef SCHED_ATTR_SIZE_VER0
 struct sched_attr {
 	uint32_t size;
 	uint32_t sched_policy;
@@ -54,6 +55,7 @@ struct sched_attr {
 	uint64_t sched_deadline;
 	uint64_t sched_period;
 };
+#endif /* SCHED_ATTR_SIZE_VER0 */
 
 int parse_prio(char *arg, struct sched_attr *sched_param);
 int set_comm_sched_attr(const char *comm_prefix, struct sched_attr *attr);
-- 
2.43.0

[PATCH AUTOSEL 6.1 15/15] verification/dot2: Improve dot parser robustness

[Sasha Levin]

From: Gabriele Monaco <gmonaco@redhat.com>

[ Upstream commit 571f8b3f866a6d990a50fe5c89fe0ea78784d70b ]

This patch makes the dot parser used by dot2c and dot2k slightly more
robust, namely:
* allows parsing files with the gv extension (GraphViz)
* correctly parses edges with any indentation
    * used to work only with a single character (e.g. '\t')
Additionally it fixes a couple of warnings reported by pylint such as
wrong indentation and comparison to False instead of `not ...`

Link: https://lore.kernel.org/20241017064238.41394-2-gmonaco@redhat.com
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/verification/dot2/automata.py | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/verification/dot2/automata.py b/tools/verification/dot2/automata.py
index baffeb960ff0b..bdeb98baa8b06 100644
--- a/tools/verification/dot2/automata.py
+++ b/tools/verification/dot2/automata.py
@@ -29,11 +29,11 @@ class Automata:
 
     def __get_model_name(self):
         basename = ntpath.basename(self.__dot_path)
-        if basename.endswith(".dot") == False:
+        if not basename.endswith(".dot") and not basename.endswith(".gv"):
             print("not a dot file")
             raise Exception("not a dot file: %s" % self.__dot_path)
 
-        model_name = basename[0:-4]
+        model_name = ntpath.splitext(basename)[0]
         if model_name.__len__() == 0:
             raise Exception("not a dot file: %s" % self.__dot_path)
 
@@ -68,9 +68,9 @@ class Automata:
     def __get_cursor_begin_events(self):
         cursor = 0
         while self.__dot_lines[cursor].split()[0] != "{node":
-           cursor += 1
+            cursor += 1
         while self.__dot_lines[cursor].split()[0] == "{node":
-           cursor += 1
+            cursor += 1
         # skip initial state transition
         cursor += 1
         return cursor
@@ -94,11 +94,11 @@ class Automata:
                 initial_state = state[7:]
             else:
                 states.append(state)
-                if self.__dot_lines[cursor].__contains__("doublecircle") == True:
+                if "doublecircle" in self.__dot_lines[cursor]:
                     final_states.append(state)
                     has_final_states = True
 
-                if self.__dot_lines[cursor].__contains__("ellipse") == True:
+                if "ellipse" in self.__dot_lines[cursor]:
                     final_states.append(state)
                     has_final_states = True
 
@@ -110,7 +110,7 @@ class Automata:
         # Insert the initial state at the bein og the states
         states.insert(0, initial_state)
 
-        if has_final_states == False:
+        if not has_final_states:
             final_states.append(initial_state)
 
         return states, initial_state, final_states
@@ -120,7 +120,7 @@ class Automata:
         cursor = self.__get_cursor_begin_events()
 
         events = []
-        while self.__dot_lines[cursor][1] == '"':
+        while self.__dot_lines[cursor].lstrip()[0] == '"':
             # transitions have the format:
             # "all_fired" -> "both_fired" [ label = "disable_irq" ];
             #  ------------ event is here ------------^^^^^
@@ -161,7 +161,7 @@ class Automata:
         # and we are back! Let's fill the matrix
         cursor = self.__get_cursor_begin_events()
 
-        while self.__dot_lines[cursor][1] == '"':
+        while self.__dot_lines[cursor].lstrip()[0] == '"':
             if self.__dot_lines[cursor].split()[1] == "->":
                 line = self.__dot_lines[cursor].split()
                 origin_state = line[0].replace('"','').replace(',','_')
-- 
2.43.0