Merge tag 'rcu.2022.01.09a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU updates from Paul McKenney:

 - Documentation updates, perhaps most notably Neil Brown's writeup of
   the reference-counting analogy to RCU.

 - Expedited grace-period cleanups.

 - Remove CONFIG_RCU_FAST_NO_HZ due to lack of valid users. I have asked
   around, posted a blog entry, and sent this series to LKML without
   result.

 - Miscellaneous fixes.

 - RCU callback offloading updates, perhaps most notably Frederic
   Weisbecker's updates allowing CPUs booted in the de-offloaded state
   to be offloaded at runtime.

 - nolibc fixes from Willy Tarreau and Anmar Faizi, but also including
   Mark Brown's addition of gettid().

 - RCU Tasks Trace fixes, including changes that increase the
   scalability of call_rcu_tasks_trace() for the BPF folks (Martin Lau
   and KP Singh).

 - Various fixes including those from Wander Lairson Costa and Li
   Zhijian.

 - Fixes plus addition of tests for the increased call_rcu_tasks_trace()
   scalability.

* tag 'rcu.2022.01.09a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (87 commits)
  rcu/nocb: Merge rcu_spawn_cpu_nocb_kthread() and rcu_spawn_one_nocb_kthread()
  rcu/nocb: Allow empty "rcu_nocbs" kernel parameter
  rcu/nocb: Create kthreads on all CPUs if "rcu_nocbs=" or "nohz_full=" are passed
  rcu/nocb: Optimize kthreads and rdp initialization
  rcu/nocb: Prepare nocb_cb_wait() to start with a non-offloaded rdp
  rcu/nocb: Remove rcu_node structure from nocb list when de-offloaded
  rcu-tasks: Use fewer callbacks queues if callback flood ends
  rcu-tasks: Use separate ->percpu_dequeue_lim for callback dequeueing
  rcu-tasks: Use more callback queues if contention encountered
  rcu-tasks: Avoid raw-spinlocked wakeups from call_rcu_tasks_generic()
  rcu-tasks: Count trylocks to estimate call_rcu_tasks() contention
  rcu-tasks: Add rcupdate.rcu_task_enqueue_lim to set initial queueing
  rcu-tasks: Make rcu_barrier_tasks*() handle multiple callback queues
  rcu-tasks: Use workqueues for multiple rcu_tasks_invoke_cbs() invocations
  rcu-tasks: Abstract invocations of callbacks
  rcu-tasks: Abstract checking of callback lists
  rcu-tasks: Add a ->percpu_enqueue_lim to the rcu_tasks structure
  rcu-tasks: Inspect stalled task's trc state in locked state
  rcu-tasks: Use spin_lock_rcu_node() and friends
  rcutorture: Combine n_max_cbs from all kthreads in a callback flood
  ...

1 files changed, 15 insertions, 16 deletions

diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 305cf6aeb408..486fc901bd08 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -157,7 +157,6 @@ struct rcu_data {
 	bool		core_needs_qs;	/* Core waits for quiescent state. */
 	bool		beenonline;	/* CPU online at least once. */
 	bool		gpwrap;		/* Possible ->gp_seq wrap. */
-	bool		exp_deferred_qs; /* This CPU awaiting a deferred QS? */
 	bool		cpu_started;	/* RCU watching this onlining CPU. */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
@@ -189,11 +188,6 @@ struct rcu_data {
 	bool rcu_urgent_qs;		/* GP old need light quiescent state. */
 	bool rcu_forced_tick;		/* Forced tick to provide QS. */
 	bool rcu_forced_tick_exp;	/*   ... provide QS to expedited GP. */
-#ifdef CONFIG_RCU_FAST_NO_HZ
-	unsigned long last_accelerate;	/* Last jiffy CBs were accelerated. */
-	unsigned long last_advance_all;	/* Last jiffy CBs were all advanced. */
-	int tick_nohz_enabled_snap;	/* Previously seen value from sysfs. */
-#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 
 	/* 4) rcu_barrier(), OOM callbacks, and expediting. */
 	struct rcu_head barrier_head;
@@ -227,8 +221,11 @@ struct rcu_data {
 	struct swait_queue_head nocb_gp_wq; /* For nocb kthreads to sleep on. */
 	bool nocb_cb_sleep;		/* Is the nocb CB thread asleep? */
 	struct task_struct *nocb_cb_kthread;
-	struct rcu_data *nocb_next_cb_rdp;
-					/* Next rcu_data in wakeup chain. */
+	struct list_head nocb_head_rdp; /*
+					 * Head of rcu_data list in wakeup chain,
+					 * if rdp_gp.
+					 */
+	struct list_head nocb_entry_rdp; /* rcu_data node in wakeup chain. */
 
 	/* The following fields are used by CB kthread, hence new cacheline. */
 	struct rcu_data *nocb_gp_rdp ____cacheline_internodealigned_in_smp;
@@ -419,8 +416,6 @@ static bool rcu_is_callbacks_kthread(void);
 static void rcu_cpu_kthread_setup(unsigned int cpu);
 static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp);
 static void __init rcu_spawn_boost_kthreads(void);
-static void rcu_cleanup_after_idle(void);
-static void rcu_prepare_for_idle(void);
 static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
 static void rcu_preempt_deferred_qs(struct task_struct *t);
@@ -447,12 +442,16 @@ static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp,
 static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp);
 #ifdef CONFIG_RCU_NOCB_CPU
 static void __init rcu_organize_nocb_kthreads(void);
-#define rcu_nocb_lock_irqsave(rdp, flags)				\
-do {									\
-	if (!rcu_segcblist_is_offloaded(&(rdp)->cblist))		\
-		local_irq_save(flags);					\
-	else								\
-		raw_spin_lock_irqsave(&(rdp)->nocb_lock, (flags));	\
+
+/*
+ * Disable IRQs before checking offloaded state so that local
+ * locking is safe against concurrent de-offloading.
+ */
+#define rcu_nocb_lock_irqsave(rdp, flags)			\
+do {								\
+	local_irq_save(flags);					\
+	if (rcu_segcblist_is_offloaded(&(rdp)->cblist))	\
+		raw_spin_lock(&(rdp)->nocb_lock);		\
 } while (0)
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
 #define rcu_nocb_lock_irqsave(rdp, flags) local_irq_save(flags)