Skip to contentSkip to conversation

tracing: Updates for v6.20

PATCH In review Steven Rostedt 3 participants 8 messages Jan 30

Subsystems (5)
BPF Tracing BPF tracing BPF LSM +1 more subsystems
lore
Share & tools
lore
#0 lore raw

cover tracing: Updates for v6.20

git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
trace/for-next

Head SHA1: a46023d5616ed3ed781e56ca93400eb9490e3646

Paul E. McKenney (1):
srcu: Fix warning to permit SRCU-fast readers in NMI handlers

Steven Rostedt (3):
tracing: perf: Have perf tracepoint callbacks always disable preemption
bpf: Have __bpf_trace_run() use rcu_read_lock_dont_migrate()
tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast

----

 include/linux/tracepoint.h   |  9 +++++----
 include/trace/perf.h         |  4 ++--
 include/trace/trace_events.h |  4 ++--
 kernel/rcu/srcutree.c        |  3 ++-
 kernel/trace/bpf_trace.c     |  5 ++---
 kernel/tracepoint.c          | 18 ++++++++++++++----
 6 files changed, 27 insertions(+), 16 deletions(-)
#1 lore raw

PATCH 1/4 tracing: perf: Have perf tracepoint callbacks always disable preemption

From: Steven Rostedt <[email protected]>

In preparation to convert protection of tracepoints from being protected by a preempt disabled section to being protected by SRCU, have all the perf callbacks disable preemption as perf expects preemption to be disabled when processing tracepoints.

While at it, convert the perf system call callback preempt_disable() to a guard(preempt).

Cc Masami Hiramatsu <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Mathieu Desnoyers <[email protected]>
Cc Andrew Morton <[email protected]>
Cc "Paul E. McKenney" <[email protected]>
Cc Sebastian Andrzej Siewior <[email protected]>
Cc Alexei Starovoitov <[email protected]>
---
 include/trace/perf.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
include/trace/perf.h +2 -2
index a1754b73a8f5..348ad1d9b556 100644
@@ -71,6 +71,7 @@ perf_trace_##call(void *__data, proto)					\
 	u64 __count __attribute__((unused));				\
 	struct task_struct *__task __attribute__((unused));		\
 									\
+	guard(preempt_notrace)();					\
 	do_perf_trace_##call(__data, args);				\
 }
 
@@ -85,9 +86,8 @@ perf_trace_##call(void *__data, proto)					\
 	struct task_struct *__task __attribute__((unused));		\
 									\
 	might_fault();							\
-	preempt_disable_notrace();					\
+	guard(preempt_notrace)();					\
 	do_perf_trace_##call(__data, args);				\
-	preempt_enable_notrace();					\
 }
 
 /*
Signature · 1 line
2.51.0
#2 lore raw

PATCH 2/4 bpf: Have __bpf_trace_run() use rcu_read_lock_dont_migrate()

In reply to Steven Rostedt

From: Steven Rostedt <[email protected]>

In order to switch the protection of tracepoint callbacks from preempt_disable() to srcu_read_lock_fast() the BPF callback from tracepoints needs to have migration prevention as the BPF programs expect to stay on the same CPU as they execute. Put together the RCU protection with migration prevention and use rcu_read_lock_dont_migrate() in __bpf_trace_run(). This will allow tracepoints callbacks to be preemptible.

Cc Masami Hiramatsu <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Mathieu Desnoyers <[email protected]>
Cc Andrew Morton <[email protected]>
Cc "Paul E. McKenney" <[email protected]>
Cc Sebastian Andrzej Siewior <[email protected]>
Cc Alexei Starovoitov <[email protected]>
---
 kernel/trace/bpf_trace.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
kernel/trace/bpf_trace.c +2 -3
index fe28d86f7c35..abbf0177ad20 100644
@@ -2062,7 +2062,7 @@ void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args)
 	struct bpf_run_ctx *old_run_ctx;
 	struct bpf_trace_run_ctx run_ctx;
 
-	cant_sleep();
+	rcu_read_lock_dont_migrate();
 	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
 		bpf_prog_inc_misses_counter(prog);
 		goto out;
@@ -2071,13 +2071,12 @@ void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args)
 	run_ctx.bpf_cookie = link->cookie;
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 
-	rcu_read_lock();
 	(void) bpf_prog_run(prog, args);
-	rcu_read_unlock();
 
 	bpf_reset_run_ctx(old_run_ctx);
 out:
 	this_cpu_dec(*(prog->active));
+	rcu_read_unlock_migrate();
 }
 
 #define UNPACK(...)			__VA_ARGS__
Signature · 1 line
2.51.0
#3 lore raw

PATCH 3/4 srcu: Fix warning to permit SRCU-fast readers in NMI handlers

In reply to Steven Rostedt

From: "Paul E. McKenney" <[email protected]>

SRCU-fast is designed to be used in NMI handlers, even going so far as to use atomic operations for architectures supporting NMIs but not providing NMI-safe per-CPU atomic operations. However, the WARN_ON_ONCE() in __srcu_check_read_flavor() complains if SRCU-fast is used in an NMI handler. This commit therefore modifies that WARN_ON_ONCE() to avoid such complaints.

---
 kernel/rcu/srcutree.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/rcu/srcutree.c +2 -1
index ea3f128de06f..c4a0a93e8da4 100644
@@ -789,7 +789,8 @@ void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor)
 	struct srcu_data *sdp;
 
 	/* NMI-unsafe use in NMI is a bad sign, as is multi-bit read_flavor values. */
-	WARN_ON_ONCE((read_flavor != SRCU_READ_FLAVOR_NMI) && in_nmi());
+	WARN_ON_ONCE(read_flavor != SRCU_READ_FLAVOR_NMI &&
+		     read_flavor != SRCU_READ_FLAVOR_FAST && in_nmi());
 	WARN_ON_ONCE(read_flavor & (read_flavor - 1));
 
 	sdp = raw_cpu_ptr(ssp->sda);
Signature · 1 line
2.51.0
#4 lore raw

Re: [for-next][PATCH 3/4] srcu: Fix warning to permit SRCU-fast readers in NMI handlers

Quoted 9 lines · Steven Rostedt

From: "Paul E. McKenney" <[email protected]>

SRCU-fast is designed to be used in NMI handlers, even going so far as to use atomic operations for architectures supporting NMIs but not providing NMI-safe per-CPU atomic operations. However, the WARN_ON_ONCE() in __srcu_check_read_flavor() complains if SRCU-fast is used in an NMI handler. This commit therefore modifies that WARN_ON_ONCE() to avoid such complaints.

Quoted 10 lines

Thank you, Steven! I will drop this in the RCU PR since you already plan to carry it via tracing.

Regards,
Boqun

Quoted 22 lines
---
 kernel/rcu/srcutree.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/rcu/srcutree.c +2 -1
index ea3f128de06f..c4a0a93e8da4 100644
@@ -789,7 +789,8 @@ void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor)
 	struct srcu_data *sdp;
 
 	/* NMI-unsafe use in NMI is a bad sign, as is multi-bit read_flavor values. */
-	WARN_ON_ONCE((read_flavor != SRCU_READ_FLAVOR_NMI) && in_nmi());
+	WARN_ON_ONCE(read_flavor != SRCU_READ_FLAVOR_NMI &&
+		     read_flavor != SRCU_READ_FLAVOR_FAST && in_nmi());
 	WARN_ON_ONCE(read_flavor & (read_flavor - 1));
 
 	sdp = raw_cpu_ptr(ssp->sda);
Signature · 1 line
2.51.0
maintainer
#5 lore raw

Re: [for-next][PATCH 3/4] srcu: Fix warning to permit SRCU-fast readers in NMI handlers

Quoted 21 lines · Boqun Feng
Quoted 9 lines · Steven Rostedt

From: "Paul E. McKenney" <[email protected]>

SRCU-fast is designed to be used in NMI handlers, even going so far as to use atomic operations for architectures supporting NMIs but not providing NMI-safe per-CPU atomic operations. However, the WARN_ON_ONCE() in __srcu_check_read_flavor() complains if SRCU-fast is used in an NMI handler. This commit therefore modifies that WARN_ON_ONCE() to avoid such complaints.

Quoted 10 lines
Quoted 2 lines

Thank you, Steven! I will drop this in the RCU PR since you already plan to carry it via tracing.

Thank you both!

Thanx, Paul

Quoted 25 lines

Regards,
Boqun

Quoted 22 lines
---
 kernel/rcu/srcutree.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/rcu/srcutree.c +2 -1
index ea3f128de06f..c4a0a93e8da4 100644
@@ -789,7 +789,8 @@ void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor)
 	struct srcu_data *sdp;
 
 	/* NMI-unsafe use in NMI is a bad sign, as is multi-bit read_flavor values. */
-	WARN_ON_ONCE((read_flavor != SRCU_READ_FLAVOR_NMI) && in_nmi());
+	WARN_ON_ONCE(read_flavor != SRCU_READ_FLAVOR_NMI &&
+		     read_flavor != SRCU_READ_FLAVOR_FAST && in_nmi());
 	WARN_ON_ONCE(read_flavor & (read_flavor - 1));
 
 	sdp = raw_cpu_ptr(ssp->sda);
Signature · 1 line
2.51.0
#6 lore raw

Re: [for-next][PATCH 3/4] srcu: Fix warning to permit SRCU-fast readers in NMI handlers

In reply to Boqun Feng
Quoted 2 lines · On Fri, 30 Jan 2026 07:51:16 -0800 Boqun Feng <[email protected]> wrote:

Thank you, Steven! I will drop this in the RCU PR since you already plan to carry it via tracing.

Thanks. It was a needed dependency for the last patch.

-- Steve

#7 lore raw

PATCH 4/4 tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast

In reply to Steven Rostedt

From: Steven Rostedt <[email protected]>

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.

Cc Masami Hiramatsu <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Mathieu Desnoyers <[email protected]>
Cc Andrew Morton <[email protected]>
Cc Sebastian Andrzej Siewior <[email protected]>
Cc Alexei Starovoitov <[email protected]>
---
 include/linux/tracepoint.h   |  9 +++++----
 include/trace/trace_events.h |  4 ++--
 kernel/tracepoint.c          | 18 ++++++++++++++----
 3 files changed, 21 insertions(+), 10 deletions(-)
include/linux/tracepoint.h +5 -4
index 8a56f3278b1b..22ca1c8b54f3 100644
@@ -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));		\
 		}							\
 	}								\
include/trace/trace_events.h +2 -2
index 4f22136fd465..fbc07d353be6 100644
@@ -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();					\
 }
 
 /*
kernel/tracepoint.c +14 -4
index 62719d2941c9..fd2ee879815c 100644
@@ -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);
+		}
 	}
 }
 
Signature · 1 line
2.51.0