Merge tag 'rcu.next.v6.10' of https://github.com/urezki/linux

Pull RCU updates from Uladzislau Rezki:

 - Fix a lockdep complain for lazy-preemptible kernel, remove redundant
   BH disable for TINY_RCU, remove redundant READ_ONCE() in tree.c, fix
   false positives KCSAN splat and fix buffer overflow in the
   print_cpu_stall_info().

 - Misc updates related to bpf, tracing and update the MAINTAINERS file.

 - An improvement of a normal synchronize_rcu() call in terms of
   latency. It maintains a separate track for sync. users only. This
   approach bypasses per-cpu nocb-lists thus sync-users do not depend on
   nocb-list length and how fast regular callbacks are processed.

 - RCU tasks: switch tasks RCU grace periods to sleep at TASK_IDLE
   priority, fix some comments, add some diagnostic warning to the
   exit_tasks_rcu_start() and fix a buffer overflow in the
   show_rcu_tasks_trace_gp_kthread().

 - RCU torture: Increase memory to guest OS, fix a Tasks Rude RCU
   testing, some updates for TREE09, dump mode information to debug GP
   kthread state, remove redundant READ_ONCE(), fix some comments about
   RCU_TORTURE_PIPE_LEN and pipe_count, remove some redundant pointer
   initialization, fix a hung splat task by when the rcutorture tests
   start to exit, fix invalid context warning, add '--do-kvfree'
   parameter to torture test and use slow register unregister callbacks
   only for rcutype test.

* tag 'rcu.next.v6.10' of https://github.com/urezki/linux: (48 commits)
  rcutorture: Use rcu_gp_slow_register/unregister() only for rcutype test
  torture: Scale --do-kvfree test time
  rcutorture: Fix invalid context warning when enable srcu barrier testing
  rcutorture: Make stall-tasks directly exit when rcutorture tests end
  rcutorture: Removing redundant function pointer initialization
  rcutorture: Make rcutorture support print rcu-tasks gp state
  rcutorture: Use the gp_kthread_dbg operation specified by cur_ops
  rcutorture: Re-use value stored to ->rtort_pipe_count instead of re-reading
  rcutorture: Fix rcu_torture_one_read() pipe_count overflow comment
  rcutorture: Remove extraneous rcu_torture_pipe_update_one() READ_ONCE()
  rcu: Allocate WQ with WQ_MEM_RECLAIM bit set
  rcu: Support direct wake-up of synchronize_rcu() users
  rcu: Add a trace event for synchronize_rcu_normal()
  rcu: Reduce synchronize_rcu() latency
  rcu: Fix buffer overflow in print_cpu_stall_info()
  rcu: Mollify sparse with RCU guard
  rcu-tasks: Fix show_rcu_tasks_trace_gp_kthread buffer overflow
  rcu-tasks: Fix the comments for tasks_rcu_exit_srcu_stall_timer
  rcu-tasks: Replace exit_tasks_rcu_start() initialization with WARN_ON_ONCE()
  rcu: Remove redundant CONFIG_PROVE_RCU #if condition
  ...

3 files changed, 28 insertions, 14 deletions

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 17d7ed5f3ae6..dfd2399f2cde 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -401,15 +401,15 @@ static inline int debug_lockdep_rcu_enabled(void)
 		}							\
 	} while (0)
 
-#if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU)
+#ifndef CONFIG_PREEMPT_RCU
 static inline void rcu_preempt_sleep_check(void)
 {
 	RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map),
 			 "Illegal context switch in RCU read-side critical section");
 }
-#else /* #ifdef CONFIG_PROVE_RCU */
+#else // #ifndef CONFIG_PREEMPT_RCU
 static inline void rcu_preempt_sleep_check(void) { }
-#endif /* #else #ifdef CONFIG_PROVE_RCU */
+#endif // #else // #ifndef CONFIG_PREEMPT_RCU
 
 #define rcu_sleep_check()						\
 	do {								\
@@ -809,9 +809,9 @@ static inline void rcu_read_unlock(void)
 {
 	RCU_LOCKDEP_WARN(!rcu_is_watching(),
 			 "rcu_read_unlock() used illegally while idle");
+	rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */
 	__release(RCU);
 	__rcu_read_unlock();
-	rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */
 }
 
 /**
@@ -1090,6 +1090,18 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f)
 extern int rcu_expedited;
 extern int rcu_normal;
 
-DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock())
+DEFINE_LOCK_GUARD_0(rcu,
+	do {
+		rcu_read_lock();
+		/*
+		 * sparse doesn't call the cleanup function,
+		 * so just release immediately and don't track
+		 * the context. We don't need to anyway, since
+		 * the whole point of the guard is to not need
+		 * the explicit unlock.
+		 */
+		__release(RCU);
+	} while (0),
+	rcu_read_unlock())
 
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h
index d07f0848802e..303ab9bee155 100644
--- a/include/linux/rcupdate_wait.h
+++ b/include/linux/rcupdate_wait.h
@@ -19,18 +19,18 @@ struct rcu_synchronize {
 };
 void wakeme_after_rcu(struct rcu_head *head);
 
-void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
+void __wait_rcu_gp(bool checktiny, unsigned int state, int n, call_rcu_func_t *crcu_array,
 		   struct rcu_synchronize *rs_array);
 
-#define _wait_rcu_gp(checktiny, ...) \
-do {									\
-	call_rcu_func_t __crcu_array[] = { __VA_ARGS__ };		\
-	struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)];	\
-	__wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array),		\
-			__crcu_array, __rs_array);			\
+#define _wait_rcu_gp(checktiny, state, ...) \
+do {												\
+	call_rcu_func_t __crcu_array[] = { __VA_ARGS__ };					\
+	struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)];				\
+	__wait_rcu_gp(checktiny, state, ARRAY_SIZE(__crcu_array), __crcu_array, __rs_array);	\
 } while (0)
 
-#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
+#define wait_rcu_gp(...) _wait_rcu_gp(false, TASK_UNINTERRUPTIBLE, __VA_ARGS__)
+#define wait_rcu_gp_state(state, ...) _wait_rcu_gp(false, state, __VA_ARGS__)
 
 /**
  * synchronize_rcu_mult - Wait concurrently for multiple grace periods
@@ -54,7 +54,7 @@ do {									\
  * grace period.
  */
 #define synchronize_rcu_mult(...) \
-	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
+	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), TASK_UNINTERRUPTIBLE, __VA_ARGS__)
 
 static inline void cond_resched_rcu(void)
 {
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index 447133171d95..4d96bbdb45f0 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -64,8 +64,10 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp)
 {
 	int idx;
 
+	preempt_disable();  // Needed for PREEMPT_AUTO
 	idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1;
 	WRITE_ONCE(ssp->srcu_lock_nesting[idx], READ_ONCE(ssp->srcu_lock_nesting[idx]) + 1);
+	preempt_enable();
 	return idx;
 }