[PATCH RFC 01/13] rcu-tasks: Add per-task trampoline nesting count

@@ -5,6 +5,7 @@
 #include <linux/context_tracking.h>
 #include <linux/hrtimer_rearm.h>
 #include <linux/kmsan.h>
+#include <linux/rcupdate.h>
 #include <linux/rseq_entry.h>
 #include <linux/static_call_types.h>
 #include <linux/syscalls.h>

@@ -214,6 +215,7 @@ static __always_inline void __exit_to_user_mode_validate(void)
 {
 	/* Ensure that kernel state is sane for a return to userspace */
 	kmap_assert_nomap();
+	rcu_tasks_trampoline_assert_none();
 	lockdep_assert_irqs_disabled();
 	lockdep_sys_exit();
 }

@@ -180,6 +180,37 @@ static inline void rcu_nocb_flush_deferred_wakeup(void) { }
 #ifdef CONFIG_TASKS_RCU_GENERIC
 
 # ifdef CONFIG_TASKS_RCU
+
+/*
+ * Trampoline nesting: dynamically allocated text (ftrace trampolines, BPF
+ * trampoline images, kprobe optinsn slots) that relies on Tasks RCU for its
+ * lifetime brackets itself with an increment/decrement of
+ * current->rcu_tramp_nesting.  While the count is non-zero the task is inside,
+ * or was called from, such text and an involuntary context switch must not be
+ * treated as a Tasks RCU quiescent state.
+ *
+ * Only current writes the count and only current (or an interrupt on the same
+ * CPU) reads it, so plain accesses suffice.
+ */
+static __always_inline void rcu_tasks_trampoline_enter(void)
+{
+	current->rcu_tramp_nesting++;
+	barrier();
+}
+
+static __always_inline void rcu_tasks_trampoline_exit(void)
+{
+	barrier();
+	current->rcu_tramp_nesting--;
+}
+
+/* A task must never reach userspace with a trampoline on its stack. */
+static __always_inline void rcu_tasks_trampoline_assert_none(void)
+{
+	if (IS_ENABLED(CONFIG_PROVE_RCU))
+		WARN_ON_ONCE(current->rcu_tramp_nesting);
+}
+
 # define rcu_tasks_classic_qs(t, preempt)				\
 	do {								\
 		if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout))	\

@@ -192,6 +223,9 @@ void rcu_tasks_torture_stats_print(char *tt, char *tf);
 # define rcu_tasks_classic_qs(t, preempt) do { } while (0)
 # define call_rcu_tasks call_rcu
 # define synchronize_rcu_tasks synchronize_rcu
+static inline void rcu_tasks_trampoline_enter(void) { }
+static inline void rcu_tasks_trampoline_exit(void) { }
+static inline void rcu_tasks_trampoline_assert_none(void) { }
 # endif
 
 #define rcu_tasks_qs(t, preempt) rcu_tasks_classic_qs((t), (preempt))

@@ -208,6 +242,9 @@ void exit_tasks_rcu_finish(void);
 #define rcu_tasks_classic_qs(t, preempt) do { } while (0)
 #define rcu_tasks_qs(t, preempt) do { } while (0)
 #define rcu_note_voluntary_context_switch(t) do { } while (0)
+static inline void rcu_tasks_trampoline_enter(void) { }
+static inline void rcu_tasks_trampoline_exit(void) { }
+static inline void rcu_tasks_trampoline_assert_none(void) { }
 #define call_rcu_tasks call_rcu
 #define synchronize_rcu_tasks synchronize_rcu
 static inline void exit_tasks_rcu_start(void) { }

@@ -956,6 +956,7 @@ struct task_struct {
 	unsigned long			rcu_tasks_nvcsw;
 	u8				rcu_tasks_holdout;
 	u8				rcu_tasks_idx;
+	int				rcu_tramp_nesting;
 	int				rcu_tasks_idle_cpu;
 	struct list_head		rcu_tasks_holdout_list;
 	int				rcu_tasks_exit_cpu;

@@ -1869,6 +1869,7 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 #ifdef CONFIG_TASKS_RCU
 	p->rcu_tasks_holdout = false;
+	p->rcu_tramp_nesting = 0;
 	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
 	p->rcu_tasks_idle_cpu = -1;
 	INIT_LIST_HEAD(&p->rcu_tasks_exit_list);

@@ -1113,10 +1113,11 @@ static void check_holdout_task(struct task_struct *t,
 		*firstreport = false;
 	}
 	cpu = task_cpu(t);
-	pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
+	pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d tramp_nesting: %d idle_cpu: %d/%d\n",
 		 t, ".I"[is_idle_task(t)],
 		 "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
 		 t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
+		 data_race(t->rcu_tramp_nesting),
 		 data_race(t->rcu_tasks_idle_cpu), cpu);
 	sched_show_task(t);
 }