rseq: Expose lightweight statistics in debugfs

Analyzing the call frequency without actually using tracing is helpful for
analysis of this infrastructure. The overhead is minimal as it just
increments a per CPU counter associated to each operation.

The debugfs readout provides a racy sum of all counters.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20251027084307.027916598@linutronix.de

1 files changed, 49 insertions, 0 deletions

diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h
index 5be507a127eb..ff9080b89be3 100644
--- a/include/linux/rseq_entry.h
+++ b/include/linux/rseq_entry.h
@@ -2,6 +2,37 @@
 #ifndef _LINUX_RSEQ_ENTRY_H
 #define _LINUX_RSEQ_ENTRY_H
 
+/* Must be outside the CONFIG_RSEQ guard to resolve the stubs */
+#ifdef CONFIG_RSEQ_STATS
+#include <linux/percpu.h>
+
+struct rseq_stats {
+	unsigned long	exit;
+	unsigned long	signal;
+	unsigned long	slowpath;
+	unsigned long	ids;
+	unsigned long	cs;
+	unsigned long	clear;
+	unsigned long	fixup;
+};
+
+DECLARE_PER_CPU(struct rseq_stats, rseq_stats);
+
+/*
+ * Slow path has interrupts and preemption enabled, but the fast path
+ * runs with interrupts disabled so there is no point in having the
+ * preemption checks implied in __this_cpu_inc() for every operation.
+ */
+#ifdef RSEQ_BUILD_SLOW_PATH
+#define rseq_stat_inc(which)	this_cpu_inc((which))
+#else
+#define rseq_stat_inc(which)	raw_cpu_inc((which))
+#endif
+
+#else /* CONFIG_RSEQ_STATS */
+#define rseq_stat_inc(x)	do { } while (0)
+#endif /* !CONFIG_RSEQ_STATS */
+
 #ifdef CONFIG_RSEQ
 #include <linux/rseq.h>
 
@@ -39,8 +70,26 @@ static __always_inline void rseq_note_user_irq_entry(void)
 		current->rseq.event.user_irq = true;
 }
 
+static __always_inline void rseq_exit_to_user_mode(void)
+{
+	struct rseq_event *ev = &current->rseq.event;
+
+	rseq_stat_inc(rseq_stats.exit);
+
+	if (IS_ENABLED(CONFIG_DEBUG_RSEQ))
+		WARN_ON_ONCE(ev->sched_switch);
+
+	/*
+	 * Ensure that event (especially user_irq) is cleared when the
+	 * interrupt did not result in a schedule and therefore the
+	 * rseq processing did not clear it.
+	 */
+	ev->events = 0;
+}
+
 #else /* CONFIG_RSEQ */
 static inline void rseq_note_user_irq_entry(void) { }
+static inline void rseq_exit_to_user_mode(void) { }
 #endif /* !CONFIG_RSEQ */
 
 #endif /* _LINUX_RSEQ_ENTRY_H */