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
  ...

5 files changed, 70 insertions, 45 deletions

diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h
index 3db96c4f45fd..659d13a7ddaa 100644
--- a/include/linux/rcu_segcblist.h
+++ b/include/linux/rcu_segcblist.h
@@ -69,7 +69,7 @@ struct rcu_cblist {
  *
  *
  *  ----------------------------------------------------------------------------
- *  |                         SEGCBLIST_SOFTIRQ_ONLY                           |
+ *  |                              SEGCBLIST_RCU_CORE                          |
  *  |                                                                          |
  *  |  Callbacks processed by rcu_core() from softirqs or local                |
  *  |  rcuc kthread, without holding nocb_lock.                                |
@@ -77,7 +77,7 @@ struct rcu_cblist {
  *                                         |
  *                                         v
  *  ----------------------------------------------------------------------------
- *  |                        SEGCBLIST_OFFLOADED                               |
+ *  |       SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED       |
  *  |                                                                          |
  *  | Callbacks processed by rcu_core() from softirqs or local                 |
  *  | rcuc kthread, while holding nocb_lock. Waking up CB and GP kthreads,     |
@@ -89,7 +89,9 @@ struct rcu_cblist {
  *                        |                                 |
  *                        v                                 v
  *  ---------------------------------------  ----------------------------------|
- *  |        SEGCBLIST_OFFLOADED |        |  |     SEGCBLIST_OFFLOADED |       |
+ *  |        SEGCBLIST_RCU_CORE   |       |  |     SEGCBLIST_RCU_CORE   |      |
+ *  |        SEGCBLIST_LOCKING    |       |  |     SEGCBLIST_LOCKING    |      |
+ *  |        SEGCBLIST_OFFLOADED  |       |  |     SEGCBLIST_OFFLOADED  |      |
  *  |        SEGCBLIST_KTHREAD_CB         |  |     SEGCBLIST_KTHREAD_GP        |
  *  |                                     |  |                                 |
  *  |                                     |  |                                 |
@@ -104,9 +106,10 @@ struct rcu_cblist {
  *                                         |
  *                                         v
  *  |--------------------------------------------------------------------------|
- *  |                           SEGCBLIST_OFFLOADED |                          |
- *  |                           SEGCBLIST_KTHREAD_CB |                         |
- *  |                           SEGCBLIST_KTHREAD_GP                           |
+ *  |                           SEGCBLIST_LOCKING    |                         |
+ *  |                           SEGCBLIST_OFFLOADED  |                         |
+ *  |                           SEGCBLIST_KTHREAD_GP |                         |
+ *  |                           SEGCBLIST_KTHREAD_CB                           |
  *  |                                                                          |
  *  |   Kthreads handle callbacks holding nocb_lock, local rcu_core() stops    |
  *  |   handling callbacks. Enable bypass queueing.                            |
@@ -120,7 +123,8 @@ struct rcu_cblist {
  *
  *
  *  |--------------------------------------------------------------------------|
- *  |                           SEGCBLIST_OFFLOADED |                          |
+ *  |                           SEGCBLIST_LOCKING    |                         |
+ *  |                           SEGCBLIST_OFFLOADED  |                         |
  *  |                           SEGCBLIST_KTHREAD_CB |                         |
  *  |                           SEGCBLIST_KTHREAD_GP                           |
  *  |                                                                          |
@@ -130,6 +134,22 @@ struct rcu_cblist {
  *                                      |
  *                                      v
  *  |--------------------------------------------------------------------------|
+ *  |                           SEGCBLIST_RCU_CORE   |                         |
+ *  |                           SEGCBLIST_LOCKING    |                         |
+ *  |                           SEGCBLIST_OFFLOADED  |                         |
+ *  |                           SEGCBLIST_KTHREAD_CB |                         |
+ *  |                           SEGCBLIST_KTHREAD_GP                           |
+ *  |                                                                          |
+ *  |   CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core()    |
+ *  |   handles callbacks concurrently. Bypass enqueue is enabled.             |
+ *  |   Invoke RCU core so we make sure not to preempt it in the middle with   |
+ *  |   leaving some urgent work unattended within a jiffy.                    |
+ *  ----------------------------------------------------------------------------
+ *                                      |
+ *                                      v
+ *  |--------------------------------------------------------------------------|
+ *  |                           SEGCBLIST_RCU_CORE   |                         |
+ *  |                           SEGCBLIST_LOCKING    |                         |
  *  |                           SEGCBLIST_KTHREAD_CB |                         |
  *  |                           SEGCBLIST_KTHREAD_GP                           |
  *  |                                                                          |
@@ -143,7 +163,9 @@ struct rcu_cblist {
  *                     |                                 |
  *                     v                                 v
  *  ---------------------------------------------------------------------------|
- *  |                                                                          |
+ *  |                                     |                                    |
+ *  |        SEGCBLIST_RCU_CORE |         |       SEGCBLIST_RCU_CORE |         |
+ *  |        SEGCBLIST_LOCKING  |         |       SEGCBLIST_LOCKING  |         |
  *  |        SEGCBLIST_KTHREAD_CB         |       SEGCBLIST_KTHREAD_GP         |
  *  |                                     |                                    |
  *  | GP kthread woke up and              |   CB kthread woke up and           |
@@ -159,7 +181,7 @@ struct rcu_cblist {
  *                                      |
  *                                      v
  *  ----------------------------------------------------------------------------
- *  |                                   0                                      |
+ *  |                SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING                    |
  *  |                                                                          |
  *  | Callbacks processed by rcu_core() from softirqs or local                 |
  *  | rcuc kthread, while holding nocb_lock. Forbid nocb_timer to be armed.    |
@@ -168,17 +190,18 @@ struct rcu_cblist {
  *                                      |
  *                                      v
  *  ----------------------------------------------------------------------------
- *  |                         SEGCBLIST_SOFTIRQ_ONLY                           |
+ *  |                         SEGCBLIST_RCU_CORE                               |
  *  |                                                                          |
  *  |  Callbacks processed by rcu_core() from softirqs or local                |
  *  |  rcuc kthread, without holding nocb_lock.                                |
  *  ----------------------------------------------------------------------------
  */
 #define SEGCBLIST_ENABLED	BIT(0)
-#define SEGCBLIST_SOFTIRQ_ONLY	BIT(1)
-#define SEGCBLIST_KTHREAD_CB	BIT(2)
-#define SEGCBLIST_KTHREAD_GP	BIT(3)
-#define SEGCBLIST_OFFLOADED	BIT(4)
+#define SEGCBLIST_RCU_CORE	BIT(1)
+#define SEGCBLIST_LOCKING	BIT(2)
+#define SEGCBLIST_KTHREAD_CB	BIT(3)
+#define SEGCBLIST_KTHREAD_GP	BIT(4)
+#define SEGCBLIST_OFFLOADED	BIT(5)
 
 struct rcu_segcblist {
 	struct rcu_head *head;
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 5e0beb5c5659..88b42eb46406 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -364,6 +364,12 @@ static inline void rcu_preempt_sleep_check(void) { }
 #define rcu_check_sparse(p, space)
 #endif /* #else #ifdef __CHECKER__ */
 
+#define __unrcu_pointer(p, local)					\
+({									\
+	typeof(*p) *local = (typeof(*p) *__force)(p);			\
+	rcu_check_sparse(p, __rcu);					\
+	((typeof(*p) __force __kernel *)(local)); 			\
+})
 /**
  * unrcu_pointer - mark a pointer as not being RCU protected
  * @p: pointer needing to lose its __rcu property
@@ -371,39 +377,35 @@ static inline void rcu_preempt_sleep_check(void) { }
  * Converts @p from an __rcu pointer to a __kernel pointer.
  * This allows an __rcu pointer to be used with xchg() and friends.
  */
-#define unrcu_pointer(p)						\
-({									\
-	typeof(*p) *_________p1 = (typeof(*p) *__force)(p);		\
-	rcu_check_sparse(p, __rcu);					\
-	((typeof(*p) __force __kernel *)(_________p1)); 		\
-})
+#define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu))
 
-#define __rcu_access_pointer(p, space) \
+#define __rcu_access_pointer(p, local, space) \
 ({ \
-	typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \
+	typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \
 	rcu_check_sparse(p, space); \
-	((typeof(*p) __force __kernel *)(_________p1)); \
+	((typeof(*p) __force __kernel *)(local)); \
 })
-#define __rcu_dereference_check(p, c, space) \
+#define __rcu_dereference_check(p, local, c, space) \
 ({ \
 	/* Dependency order vs. p above. */ \
-	typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \
+	typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \
 	RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \
 	rcu_check_sparse(p, space); \
-	((typeof(*p) __force __kernel *)(________p1)); \
+	((typeof(*p) __force __kernel *)(local)); \
 })
-#define __rcu_dereference_protected(p, c, space) \
+#define __rcu_dereference_protected(p, local, c, space) \
 ({ \
 	RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \
 	rcu_check_sparse(p, space); \
 	((typeof(*p) __force __kernel *)(p)); \
 })
-#define rcu_dereference_raw(p) \
+#define __rcu_dereference_raw(p, local) \
 ({ \
 	/* Dependency order vs. p above. */ \
-	typeof(p) ________p1 = READ_ONCE(p); \
-	((typeof(*p) __force __kernel *)(________p1)); \
+	typeof(p) local = READ_ONCE(p); \
+	((typeof(*p) __force __kernel *)(local)); \
 })
+#define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu))
 
 /**
  * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
@@ -490,7 +492,7 @@ do {									      \
  * when tearing down multi-linked structures after a grace period
  * has elapsed.
  */
-#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu)
+#define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu)
 
 /**
  * rcu_dereference_check() - rcu_dereference with debug checking
@@ -526,7 +528,8 @@ do {									      \
  * annotated as __rcu.
  */
 #define rcu_dereference_check(p, c) \
-	__rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu)
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || rcu_read_lock_held(), __rcu)
 
 /**
  * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking
@@ -541,7 +544,8 @@ do {									      \
  * rcu_read_lock() but also rcu_read_lock_bh() into account.
  */
 #define rcu_dereference_bh_check(p, c) \
-	__rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu)
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || rcu_read_lock_bh_held(), __rcu)
 
 /**
  * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking
@@ -556,7 +560,8 @@ do {									      \
  * only rcu_read_lock() but also rcu_read_lock_sched() into account.
  */
 #define rcu_dereference_sched_check(p, c) \
-	__rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || rcu_read_lock_sched_held(), \
 				__rcu)
 
 /*
@@ -566,7 +571,8 @@ do {									      \
  * The no-tracing version of rcu_dereference_raw() must not call
  * rcu_read_lock_held().
  */
-#define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu)
+#define rcu_dereference_raw_check(p) \
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu)
 
 /**
  * rcu_dereference_protected() - fetch RCU pointer when updates prevented
@@ -585,7 +591,7 @@ do {									      \
  * but very ugly failures.
  */
 #define rcu_dereference_protected(p, c) \
-	__rcu_dereference_protected((p), (c), __rcu)
+	__rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu)
 
 
 /**
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 9be015305f9f..858f4d429946 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -85,7 +85,7 @@ static inline void rcu_irq_enter_irqson(void) { }
 static inline void rcu_irq_exit(void) { }
 static inline void rcu_irq_exit_check_preempt(void) { }
 #define rcu_is_idle_cpu(cpu) \
-	(is_idle_task(current) && !in_nmi() && !in_irq() && !in_serving_softirq())
+	(is_idle_task(current) && !in_nmi() && !in_hardirq() && !in_serving_softirq())
 static inline void exit_rcu(void) { }
 static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index e6011a9975af..01226e4d960a 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -117,7 +117,8 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp)
  * lockdep_is_held() calls.
  */
 #define srcu_dereference_check(p, ssp, c) \
-	__rcu_dereference_check((p), (c) || srcu_read_lock_held(ssp), __rcu)
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || srcu_read_lock_held(ssp), __rcu)
 
 /**
  * srcu_dereference - fetch SRCU-protected pointer for later dereferencing
diff --git a/include/linux/torture.h b/include/linux/torture.h
index 24f58e50a94b..63fa4196e51c 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -38,13 +38,8 @@ do {										\
 		pr_alert("%s" TORTURE_FLAG " %s\n", torture_type, s);		\
 	}									\
 } while (0)
-#define VERBOSE_TOROUT_ERRSTRING(s) \
-do {										\
-	if (verbose) {								\
-		verbose_torout_sleep();						\
-		pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s);	\
-	}									\
-} while (0)
+#define TOROUT_ERRSTRING(s) \
+	pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s)
 void verbose_torout_sleep(void);
 
 #define torture_init_error(firsterr)						\