tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast

The current use of guard(preempt_notrace)() within __DECLARE_TRACE()
to protect invocation of __DO_TRACE_CALL() means that BPF programs
attached to tracepoints are non-preemptible.  This is unhelpful in
real-time systems, whose users apparently wish to use BPF while also
achieving low latencies.  (Who knew?)

One option would be to use preemptible RCU, but this introduces
many opportunities for infinite recursion, which many consider to
be counterproductive, especially given the relatively small stacks
provided by the Linux kernel.  These opportunities could be shut down
by sufficiently energetic duplication of code, but this sort of thing
is considered impolite in some circles.

Therefore, use the shiny new SRCU-fast API, which provides somewhat faster
readers than those of preemptible RCU, at least on Paul E. McKenney's
laptop, where task_struct access is more expensive than access to per-CPU
variables.  And SRCU-fast provides way faster readers than does SRCU,
courtesy of being able to avoid the read-side use of smp_mb().  Also,
it is quite straightforward to create srcu_read_{,un}lock_fast_notrace()
functions.

Link: https://lore.kernel.org/all/20250613152218.1924093-1-bigeasy@linutronix.de/
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Alexei Starovoitov <ast@kernel.org>
Link: https://patch.msgid.link/20260126231256.499701982@kernel.org
Co-developed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 8a56f3278b1b95896274849644ef3b2bbaecd557..22ca1c8b54f32b65a34d3324dc72f397cc54ecd6 100644 (file)
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -108,14 +108,15 @@ void for_each_tracepoint_in_module(struct module *mod,
  * An alternative is to use the following for batch reclaim associated
  * with a given tracepoint:
  *
- * - tracepoint_is_faultable() == false: call_rcu()
+ * - tracepoint_is_faultable() == false: call_srcu()
  * - tracepoint_is_faultable() == true:  call_rcu_tasks_trace()
  */
 #ifdef CONFIG_TRACEPOINTS
+extern struct srcu_struct tracepoint_srcu;
 static inline void tracepoint_synchronize_unregister(void)
 {
        synchronize_rcu_tasks_trace();
-       synchronize_rcu();
+       synchronize_srcu(&tracepoint_srcu);
 }
 static inline bool tracepoint_is_faultable(struct tracepoint *tp)
 {
@@ -275,13 +276,13 @@ 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)           \
+#define __DECLARE_TRACE(name, proto, args, cond, data_proto)                   \
        __DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto)) \
        static inline void __do_trace_##name(proto)                     \
        {                                                               \
                TRACEPOINT_CHECK(name)                                  \
                if (cond) {                                             \
-                       guard(preempt_notrace)();                       \
+                       guard(srcu_fast_notrace)(&tracepoint_srcu);     \
                        __DO_TRACE_CALL(name, TP_ARGS(args));           \
                }                                                       \
        }                                                               \

diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 4f22136fd4656c755473d28a0689b5a939e95839..fbc07d353be6b68fd9a2908422c192bdb937a8ef 100644 (file)
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -436,6 +436,7 @@ __DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \
 static notrace void                                                    \
 trace_event_raw_event_##call(void *__data, proto)                      \
 {                                                                      \
+       guard(preempt_notrace)();                                       \
        do_trace_event_raw_event_##call(__data, args);                  \
 }
 
@@ -447,9 +448,8 @@ static notrace void                                                 \
 trace_event_raw_event_##call(void *__data, proto)                      \
 {                                                                      \
        might_fault();                                                  \
-       preempt_disable_notrace();                                      \
+       guard(preempt_notrace)();                                       \
        do_trace_event_raw_event_##call(__data, args);                  \
-       preempt_enable_notrace();                                       \
 }
 
 /*

diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 62719d2941c9005f793b96dab469e9fa899a8126..fd2ee879815cc9ba1092d8d1953be68e5bb907cf 100644 (file)
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -34,9 +34,13 @@ enum tp_transition_sync {
 
 struct tp_transition_snapshot {
        unsigned long rcu;
+       unsigned long srcu_gp;
        bool ongoing;
 };
 
+DEFINE_SRCU_FAST(tracepoint_srcu);
+EXPORT_SYMBOL_GPL(tracepoint_srcu);
+
 /* Protected by tracepoints_mutex */
 static struct tp_transition_snapshot tp_transition_snapshot[_NR_TP_TRANSITION_SYNC];
 
@@ -46,6 +50,7 @@ static void tp_rcu_get_state(enum tp_transition_sync sync)
 
        /* Keep the latest get_state snapshot. */
        snapshot->rcu = get_state_synchronize_rcu();
+       snapshot->srcu_gp = start_poll_synchronize_srcu(&tracepoint_srcu);
        snapshot->ongoing = true;
 }
 
@@ -56,6 +61,8 @@ static void tp_rcu_cond_sync(enum tp_transition_sync sync)
        if (!snapshot->ongoing)
                return;
        cond_synchronize_rcu(snapshot->rcu);
+       if (!poll_state_synchronize_srcu(&tracepoint_srcu, snapshot->srcu_gp))
+               synchronize_srcu(&tracepoint_srcu);
        snapshot->ongoing = false;
 }
 
@@ -112,10 +119,13 @@ static inline void release_probes(struct tracepoint *tp, struct tracepoint_func
                struct tp_probes *tp_probes = container_of(old,
                        struct tp_probes, probes[0]);
 
-               if (tracepoint_is_faultable(tp))
-                       call_rcu_tasks_trace(&tp_probes->rcu, rcu_free_old_probes);
-               else
-                       call_rcu(&tp_probes->rcu, rcu_free_old_probes);
+               if (tracepoint_is_faultable(tp)) {
+                       call_rcu_tasks_trace(&tp_probes->rcu,
+                                            rcu_free_old_probes);
+               } else {
+                       call_srcu(&tracepoint_srcu, &tp_probes->rcu,
+                                 rcu_free_old_probes);
+               }
        }
 }