From 17a1a107d0e96c1b7eef875de46f1d953c557f88 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 23 Sep 2025 09:04:58 -0400 Subject: [PATCH] tracing: Replace syscall RCU pointer assignment with READ/WRITE_ONCE() The syscall events are pseudo events that hook to the raw syscalls. The ftrace_syscall_enter/exit() callback is called by the raw_syscall enter/exit tracepoints respectively whenever any of the syscall events are enabled. The trace_array has an array of syscall "files" that correspond to the system calls based on their __NR_SYSCALL number. The array is read and if there's a pointer to a trace_event_file then it is considered enabled and if it is NULL that syscall event is considered disabled. Currently it uses an rcu_dereference_sched() to get this pointer and a rcu_assign_ptr() or RCU_INIT_POINTER() to write to it. This is unnecessary as the file pointer will not go away outside the synchronization of the tracepoint logic itself. And this code adds no extra RCU synchronization that uses this. Replace these functions with a simple READ_ONCE() and WRITE_ONCE() which is all they need. This will also allow this code to not depend on preemption being disabled as system call tracepoints are now allowed to fault. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Cc: Namhyung Kim Cc: Takaya Saeki Cc: Tom Zanussi Cc: Thomas Gleixner Cc: Ian Rogers Cc: Douglas Raillard Link: https://lore.kernel.org/20250923130713.594320290@kernel.org Reviewed-by: Paul E. McKenney Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.h | 4 ++-- kernel/trace/trace_syscalls.c | 14 ++++++-------- 2 files changed, 8 insertions(+), 10 deletions(-) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5f4bed5842f92..85eabb454bee9 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -380,8 +380,8 @@ struct trace_array { #ifdef CONFIG_FTRACE_SYSCALLS int sys_refcount_enter; int sys_refcount_exit; - struct trace_event_file __rcu *enter_syscall_files[NR_syscalls]; - struct trace_event_file __rcu *exit_syscall_files[NR_syscalls]; + struct trace_event_file *enter_syscall_files[NR_syscalls]; + struct trace_event_file *exit_syscall_files[NR_syscalls]; #endif int stop_count; int clock_id; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 46aab0ab9350a..3a0b65f891300 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -310,8 +310,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; - /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */ - trace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]); + trace_file = READ_ONCE(tr->enter_syscall_files[syscall_nr]); if (!trace_file) return; @@ -356,8 +355,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; - /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */ - trace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]); + trace_file = READ_ONCE(tr->exit_syscall_files[syscall_nr]); if (!trace_file) return; @@ -393,7 +391,7 @@ static int reg_event_syscall_enter(struct trace_event_file *file, if (!tr->sys_refcount_enter) ret = register_trace_sys_enter(ftrace_syscall_enter, tr); if (!ret) { - rcu_assign_pointer(tr->enter_syscall_files[num], file); + WRITE_ONCE(tr->enter_syscall_files[num], file); tr->sys_refcount_enter++; } mutex_unlock(&syscall_trace_lock); @@ -411,7 +409,7 @@ static void unreg_event_syscall_enter(struct trace_event_file *file, return; mutex_lock(&syscall_trace_lock); tr->sys_refcount_enter--; - RCU_INIT_POINTER(tr->enter_syscall_files[num], NULL); + WRITE_ONCE(tr->enter_syscall_files[num], NULL); if (!tr->sys_refcount_enter) unregister_trace_sys_enter(ftrace_syscall_enter, tr); mutex_unlock(&syscall_trace_lock); @@ -431,7 +429,7 @@ static int reg_event_syscall_exit(struct trace_event_file *file, if (!tr->sys_refcount_exit) ret = register_trace_sys_exit(ftrace_syscall_exit, tr); if (!ret) { - rcu_assign_pointer(tr->exit_syscall_files[num], file); + WRITE_ONCE(tr->exit_syscall_files[num], file); tr->sys_refcount_exit++; } mutex_unlock(&syscall_trace_lock); @@ -449,7 +447,7 @@ static void unreg_event_syscall_exit(struct trace_event_file *file, return; mutex_lock(&syscall_trace_lock); tr->sys_refcount_exit--; - RCU_INIT_POINTER(tr->exit_syscall_files[num], NULL); + WRITE_ONCE(tr->exit_syscall_files[num], NULL); if (!tr->sys_refcount_exit) unregister_trace_sys_exit(ftrace_syscall_exit, tr); mutex_unlock(&syscall_trace_lock); -- 2.47.3