Merge branches 'doc.2021.11.30c', 'exp.2021.12.07a', 'fastnohz.2021.11.30c', 'fixes.2021.11.30c', 'nocb.2021.12.09a', 'nolibc.2021.11.30c', 'tasks.2021.12.09a', 'torture.2021.12.07a' and 'torturescript.2021.11.30c' into HEAD

doc.2021.11.30c: Documentation updates. exp.2021.12.07a: Expedited-grace-period fixes. fastnohz.2021.11.30c: Remove CONFIG_RCU_FAST_NO_HZ. fixes.2021.11.30c: Miscellaneous fixes. nocb.2021.12.09a: No-CB CPU updates. nolibc.2021.11.30c: Tiny in-kernel library updates. tasks.2021.12.09a: RCU-tasks updates, including update-side scalability. torture.2021.12.07a: Torture-test in-kernel module updates. torturescript.2021.11.30c: Torture-test scripting updates.
2026-01-06 12:30:45 -08:00 · 2021-12-09 11:38:09 -08:00
parent 5861dad198 81f6d49cce bc849e9192 1f8da406a9 10d4703154 b0fe9dec66 fd796e4139 53b541fbdb 90b21bcfb2
commit f80fe66c38
51 changed files with 1088 additions and 718 deletions
--- a/Documentation/RCU/stallwarn.rst
+++ b/Documentation/RCU/stallwarn.rst
@@ -254,17 +254,6 @@ period (in this case 2603), the grace-period sequence number (7075), and
 an estimate of the total number of RCU callbacks queued across all CPUs
 (625 in this case).

-In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed
-for each CPU::
-
-	0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 dyntick_enabled: 1
-
-The "last_accelerate:" prints the low-order 16 bits (in hex) of the
-jiffies counter when this CPU last invoked rcu_try_advance_all_cbs()
-from rcu_needs_cpu() or last invoked rcu_accelerate_cbs() from
-rcu_prepare_for_idle(). "dyntick_enabled: 1" indicates that dyntick-idle
-processing is enabled.
-
 If the grace period ends just as the stall warning starts printing,
 there will be a spurious stall-warning message, which will include
 the following::
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4343,19 +4343,30 @@
 				Disable the Correctable Errors Collector,
 				see CONFIG_RAS_CEC help text.

-	rcu_nocbs=	[KNL]
-			The argument is a cpu list, as described above.
+	rcu_nocbs[=cpu-list]
+			[KNL] The optional argument is a cpu list,
+			as described above.

-			In kernels built with CONFIG_RCU_NOCB_CPU=y, set
-			the specified list of CPUs to be no-callback CPUs.
-			Invocation of these CPUs' RCU callbacks will be
-			offloaded to "rcuox/N" kthreads created for that
-			purpose, where "x" is "p" for RCU-preempt, and
-			"s" for RCU-sched, and "N" is the CPU number.
-			This reduces OS jitter on the offloaded CPUs,
-			which can be useful for HPC and real-time
-			workloads.  It can also improve energy efficiency
-			for asymmetric multiprocessors.
+			In kernels built with CONFIG_RCU_NOCB_CPU=y,
+			enable the no-callback CPU mode, which prevents
+			such CPUs' callbacks from being invoked in
+			softirq context.  Invocation of such CPUs' RCU
+			callbacks will instead be offloaded to "rcuox/N"
+			kthreads created for that purpose, where "x" is
+			"p" for RCU-preempt, "s" for RCU-sched, and "g"
+			for the kthreads that mediate grace periods; and
+			"N" is the CPU number. This reduces OS jitter on
+			the offloaded CPUs, which can be useful for HPC
+			and real-time workloads.  It can also improve
+			energy efficiency for asymmetric multiprocessors.
+
+			If a cpulist is passed as an argument, the specified
+			list of	CPUs is set to no-callback mode from boot.
+
+			Otherwise, if the '=' sign and the cpulist
+			arguments are omitted, no CPU will be set to
+			no-callback mode from boot but the mode may be
+			toggled at runtime via cpusets.

 	rcu_nocb_poll	[KNL]
 			Rather than requiring that offloaded CPUs
@@ -4489,10 +4500,6 @@
 			on rcutree.qhimark at boot time and to zero to
 			disable more aggressive help enlistment.

-	rcutree.rcu_idle_gp_delay= [KNL]
-			Set wakeup interval for idle CPUs that have
-			RCU callbacks (RCU_FAST_NO_HZ=y).
-
 	rcutree.rcu_kick_kthreads= [KNL]
 			Cause the grace-period kthread to get an extra
 			wake_up() if it sleeps three times longer than
@@ -4603,8 +4610,12 @@
 			in seconds.

 	rcutorture.fwd_progress= [KNL]
-			Enable RCU grace-period forward-progress testing
+			Specifies the number of kthreads to be used
+			for  RCU grace-period forward-progress testing
 			for the types of RCU supporting this notion.
+			Defaults to 1 kthread, values less than zero or
+			greater than the number of CPUs cause the number
+			of CPUs to be used.

 	rcutorture.fwd_progress_div= [KNL]
 			Specify the fraction of a CPU-stall-warning
@@ -4805,6 +4816,29 @@
 			period to instead use normal non-expedited
 			grace-period processing.

+	rcupdate.rcu_task_collapse_lim= [KNL]
+			Set the maximum number of callbacks present
+			at the beginning of a grace period that allows
+			the RCU Tasks flavors to collapse back to using
+			a single callback queue.  This switching only
+			occurs when rcupdate.rcu_task_enqueue_lim is
+			set to the default value of -1.
+
+	rcupdate.rcu_task_contend_lim= [KNL]
+			Set the minimum number of callback-queuing-time
+			lock-contention events per jiffy required to
+			cause the RCU Tasks flavors to switch to per-CPU
+			callback queuing.  This switching only occurs
+			when rcupdate.rcu_task_enqueue_lim is set to
+			the default value of -1.
+
+	rcupdate.rcu_task_enqueue_lim= [KNL]
+			Set the number of callback queues to use for the
+			RCU Tasks family of RCU flavors.  The default
+			of -1 allows this to be automatically (and
+			dynamically) adjusted.	This parameter is intended
+			for use in testing.
+
 	rcupdate.rcu_task_ipi_delay= [KNL]
 			Set time in jiffies during which RCU tasks will
 			avoid sending IPIs, starting with the beginning
--- a/Documentation/timers/no_hz.rst
+++ b/Documentation/timers/no_hz.rst
@@ -184,16 +184,12 @@ There are situations in which idle CPUs cannot be permitted to
 enter either dyntick-idle mode or adaptive-tick mode, the most
 common being when that CPU has RCU callbacks pending.

-The CONFIG_RCU_FAST_NO_HZ=y Kconfig option may be used to cause such CPUs
-to enter dyntick-idle mode or adaptive-tick mode anyway.  In this case,
-a timer will awaken these CPUs every four jiffies in order to ensure
-that the RCU callbacks are processed in a timely fashion.
-
-Another approach is to offload RCU callback processing to "rcuo" kthreads
+Avoid this by offloading RCU callback processing to "rcuo" kthreads
 using the CONFIG_RCU_NOCB_CPU=y Kconfig option.  The specific CPUs to
 offload may be selected using The "rcu_nocbs=" kernel boot parameter,
 which takes a comma-separated list of CPUs and CPU ranges, for example,
-"1,3-5" selects CPUs 1, 3, 4, and 5.
+"1,3-5" selects CPUs 1, 3, 4, and 5.  Note that CPUs specified by
+the "nohz_full" kernel boot parameter are also offloaded.

 The offloaded CPUs will never queue RCU callbacks, and therefore RCU
 never prevents offloaded CPUs from entering either dyntick-idle mode
--- 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;
--- 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)


 /**
--- 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)
 {
--- 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
--- 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)						\
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -1047,7 +1047,7 @@ static int __init lock_torture_init(void)
 				       sizeof(writer_tasks[0]),
 				       GFP_KERNEL);
 		if (writer_tasks == NULL) {
-			VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
+			TOROUT_ERRSTRING("writer_tasks: Out of memory");
 			firsterr = -ENOMEM;
 			goto unwind;
 		}
@@ -1058,7 +1058,7 @@ static int __init lock_torture_init(void)
 				       sizeof(reader_tasks[0]),
 				       GFP_KERNEL);
 		if (reader_tasks == NULL) {
-			VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
+			TOROUT_ERRSTRING("reader_tasks: Out of memory");
 			kfree(writer_tasks);
 			writer_tasks = NULL;
 			firsterr = -ENOMEM;
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -112,7 +112,7 @@ config RCU_STALL_COMMON
 	  making these warnings mandatory for the tree variants.

 config RCU_NEED_SEGCBLIST
-	def_bool ( TREE_RCU || TREE_SRCU )
+	def_bool ( TREE_RCU || TREE_SRCU || TASKS_RCU_GENERIC )

 config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
@@ -169,24 +169,6 @@ config RCU_FANOUT_LEAF

 	  Take the default if unsure.

-config RCU_FAST_NO_HZ
-	bool "Accelerate last non-dyntick-idle CPU's grace periods"
-	depends on NO_HZ_COMMON && SMP && RCU_EXPERT
-	default n
-	help
-	  This option permits CPUs to enter dynticks-idle state even if
-	  they have RCU callbacks queued, and prevents RCU from waking
-	  these CPUs up more than roughly once every four jiffies (by
-	  default, you can adjust this using the rcutree.rcu_idle_gp_delay
-	  parameter), thus improving energy efficiency.  On the other
-	  hand, this option increases the duration of RCU grace periods,
-	  for example, slowing down synchronize_rcu().
-
-	  Say Y if energy efficiency is critically important, and you
-	  	don't care about increased grace-period durations.
-
-	  Say N if you are unsure.
-
 config RCU_BOOST
 	bool "Enable RCU priority boosting"
 	depends on (RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT) || PREEMPT_RT
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -261,16 +261,14 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
 }

 /*
- * Mark the specified rcu_segcblist structure as offloaded.
+ * Mark the specified rcu_segcblist structure as offloaded (or not)
 */
 void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload)
 {
-	if (offload) {
-		rcu_segcblist_clear_flags(rsclp, SEGCBLIST_SOFTIRQ_ONLY);
-		rcu_segcblist_set_flags(rsclp, SEGCBLIST_OFFLOADED);
-	} else {
+	if (offload)
+		rcu_segcblist_set_flags(rsclp, SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED);
+	else
 		rcu_segcblist_clear_flags(rsclp, SEGCBLIST_OFFLOADED);
-	}
 }

 /*
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -80,11 +80,14 @@ static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp)
 	return rcu_segcblist_test_flags(rsclp, SEGCBLIST_ENABLED);
 }

-/* Is the specified rcu_segcblist offloaded, or is SEGCBLIST_SOFTIRQ_ONLY set? */
+/*
+ * Is the specified rcu_segcblist NOCB offloaded (or in the middle of the
+ * [de]offloading process)?
+ */
 static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp)
 {
 	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
-	    !rcu_segcblist_test_flags(rsclp, SEGCBLIST_SOFTIRQ_ONLY))
+	    rcu_segcblist_test_flags(rsclp, SEGCBLIST_LOCKING))
 		return true;

 	return false;
@@ -92,9 +95,8 @@ static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp)

 static inline bool rcu_segcblist_completely_offloaded(struct rcu_segcblist *rsclp)
 {
-	int flags = SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | SEGCBLIST_OFFLOADED;
-
-	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) && (rsclp->flags & flags) == flags)
+	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
+	    !rcu_segcblist_test_flags(rsclp, SEGCBLIST_RCU_CORE))
 		return true;

 	return false;
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -50,8 +50,8 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
 	pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s)
 #define VERBOSE_SCALEOUT_STRING(s) \
 	do { if (verbose) pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s); } while (0)
-#define VERBOSE_SCALEOUT_ERRSTRING(s) \
-	do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! %s\n", scale_type, s); } while (0)
+#define SCALEOUT_ERRSTRING(s) \
+	pr_alert("%s" SCALE_FLAG "!!! %s\n", scale_type, s)

 /*
 * The intended use cases for the nreaders and nwriters module parameters
@@ -514,11 +514,11 @@ rcu_scale_cleanup(void)
 	 * during the mid-boot phase, so have to wait till the end.
 	 */
 	if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp)
-		VERBOSE_SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
+		SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
 	if (rcu_gp_is_normal() && gp_exp)
-		VERBOSE_SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
+		SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
 	if (gp_exp && gp_async)
-		VERBOSE_SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!");
+		SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!");

 	if (torture_cleanup_begin())
 		return;
@@ -845,7 +845,7 @@ rcu_scale_init(void)
 	reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
 			       GFP_KERNEL);
 	if (reader_tasks == NULL) {
-		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+		SCALEOUT_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
@@ -865,7 +865,7 @@ rcu_scale_init(void)
 		kcalloc(nrealwriters, sizeof(*writer_n_durations),
 			GFP_KERNEL);
 	if (!writer_tasks || !writer_durations || !writer_n_durations) {
-		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+		SCALEOUT_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
--- a/kernel/rcu/refscale.c
+++ b/kernel/rcu/refscale.c
@@ -44,7 +44,10 @@
 	pr_alert("%s" SCALE_FLAG s, scale_type, ## x)

 #define VERBOSE_SCALEOUT(s, x...) \
-	do { if (verbose) pr_alert("%s" SCALE_FLAG s, scale_type, ## x); } while (0)
+	do { \
+		if (verbose) \
+			pr_alert("%s" SCALE_FLAG s "\n", scale_type, ## x); \
+	} while (0)

 static atomic_t verbose_batch_ctr;

@@ -54,12 +57,11 @@ do {											\
 	    (verbose_batched <= 0 ||							\
 	     !(atomic_inc_return(&verbose_batch_ctr) % verbose_batched))) {		\
 		schedule_timeout_uninterruptible(1);					\
-		pr_alert("%s" SCALE_FLAG s, scale_type, ## x);				\
+		pr_alert("%s" SCALE_FLAG s "\n", scale_type, ## x);			\
 	}										\
 } while (0)

-#define VERBOSE_SCALEOUT_ERRSTRING(s, x...) \
-	do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! " s, scale_type, ## x); } while (0)
+#define SCALEOUT_ERRSTRING(s, x...) pr_alert("%s" SCALE_FLAG "!!! " s "\n", scale_type, ## x)

 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Joel Fernandes (Google) <joel@joelfernandes.org>");
@@ -604,7 +606,7 @@ static u64 process_durations(int n)
 	char *buf;
 	u64 sum = 0;

-	buf = kmalloc(128 + nreaders * 32, GFP_KERNEL);
+	buf = kmalloc(800 + 64, GFP_KERNEL);
 	if (!buf)
 		return 0;
 	buf[0] = 0;
@@ -617,13 +619,15 @@ static u64 process_durations(int n)

 		if (i % 5 == 0)
 			strcat(buf, "\n");
+		if (strlen(buf) >= 800) {
+			pr_alert("%s", buf);
+			buf[0] = 0;
+		}
 		strcat(buf, buf1);

 		sum += rt->last_duration_ns;
 	}
-	strcat(buf, "\n");
-
-	SCALEOUT("%s\n", buf);
+	pr_alert("%s\n", buf);

 	kfree(buf);
 	return sum;
@@ -637,7 +641,6 @@ static u64 process_durations(int n)
 // point all the timestamps are printed.
 static int main_func(void *arg)
 {
-	bool errexit = false;
 	int exp, r;
 	char buf1[64];
 	char *buf;
@@ -648,10 +651,10 @@ static int main_func(void *arg)

 	VERBOSE_SCALEOUT("main_func task started");
 	result_avg = kzalloc(nruns * sizeof(*result_avg), GFP_KERNEL);
-	buf = kzalloc(64 + nruns * 32, GFP_KERNEL);
+	buf = kzalloc(800 + 64, GFP_KERNEL);
 	if (!result_avg || !buf) {
-		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
-		errexit = true;
+		SCALEOUT_ERRSTRING("out of memory");
+		goto oom_exit;
 	}
 	if (holdoff)
 		schedule_timeout_interruptible(holdoff * HZ);
@@ -663,8 +666,6 @@ static int main_func(void *arg)

 	// Start exp readers up per experiment
 	for (exp = 0; exp < nruns && !torture_must_stop(); exp++) {
-		if (errexit)
-			break;
 		if (torture_must_stop())
 			goto end;

@@ -698,26 +699,23 @@ static int main_func(void *arg)
 	// Print the average of all experiments
 	SCALEOUT("END OF TEST. Calculating average duration per loop (nanoseconds)...\n");

-	if (!errexit) {
-		buf[0] = 0;
-		strcat(buf, "\n");
-		strcat(buf, "Runs\tTime(ns)\n");
-	}
-
+	pr_alert("Runs\tTime(ns)\n");
 	for (exp = 0; exp < nruns; exp++) {
 		u64 avg;
 		u32 rem;

-		if (errexit)
-			break;
 		avg = div_u64_rem(result_avg[exp], 1000, &rem);
 		sprintf(buf1, "%d\t%llu.%03u\n", exp + 1, avg, rem);
 		strcat(buf, buf1);
+		if (strlen(buf) >= 800) {
+			pr_alert("%s", buf);
+			buf[0] = 0;
+		}
 	}

-	if (!errexit)
-		SCALEOUT("%s", buf);
+	pr_alert("%s", buf);

+oom_exit:
 	// This will shutdown everything including us.
 	if (shutdown) {
 		shutdown_start = 1;
@@ -841,12 +839,12 @@ ref_scale_init(void)
 	reader_tasks = kcalloc(nreaders, sizeof(reader_tasks[0]),
 			       GFP_KERNEL);
 	if (!reader_tasks) {
-		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+		SCALEOUT_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}

-	VERBOSE_SCALEOUT("Starting %d reader threads\n", nreaders);
+	VERBOSE_SCALEOUT("Starting %d reader threads", nreaders);

 	for (i = 0; i < nreaders; i++) {
 		firsterr = torture_create_kthread(ref_scale_reader, (void *)i,
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -99,7 +99,7 @@ void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
 	int newval = READ_ONCE(ssp->srcu_lock_nesting[idx]) - 1;

 	WRITE_ONCE(ssp->srcu_lock_nesting[idx], newval);
-	if (!newval && READ_ONCE(ssp->srcu_gp_waiting))
+	if (!newval && READ_ONCE(ssp->srcu_gp_waiting) && in_task())
 		swake_up_one(&ssp->srcu_wq);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -79,7 +79,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
 	.dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
 	.dynticks = ATOMIC_INIT(1),
 #ifdef CONFIG_RCU_NOCB_CPU
-	.cblist.flags = SEGCBLIST_SOFTIRQ_ONLY,
+	.cblist.flags = SEGCBLIST_RCU_CORE,
 #endif
 };
 static struct rcu_state rcu_state = {
@@ -624,7 +624,6 @@ static noinstr void rcu_eqs_enter(bool user)
 	instrumentation_begin();
 	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
-	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);

 	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
@@ -768,9 +767,6 @@ noinstr void rcu_nmi_exit(void)
 	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */

-	if (!in_nmi())
-		rcu_prepare_for_idle();
-
 	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
 	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
 	instrumentation_end();
@@ -872,7 +868,6 @@ static void noinstr rcu_eqs_exit(bool user)
 	// instrumentation for the noinstr rcu_dynticks_eqs_exit()
 	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));

-	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	WRITE_ONCE(rdp->dynticks_nesting, 1);
@@ -1014,12 +1009,6 @@ noinstr void rcu_nmi_enter(void)
 		rcu_dynticks_eqs_exit();
 		// ... but is watching here.

-		if (!in_nmi()) {
-			instrumentation_begin();
-			rcu_cleanup_after_idle();
-			instrumentation_end();
-		}
-
 		instrumentation_begin();
 		// instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
 		instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
@@ -1086,6 +1075,24 @@ void rcu_irq_enter_irqson(void)
 	local_irq_restore(flags);
 }

+/*
+ * Check to see if any future non-offloaded RCU-related work will need
+ * to be done by the current CPU, even if none need be done immediately,
+ * returning 1 if so.  This function is part of the RCU implementation;
+ * it is -not- an exported member of the RCU API.  This is used by
+ * the idle-entry code to figure out whether it is safe to disable the
+ * scheduler-clock interrupt.
+ *
+ * Just check whether or not this CPU has non-offloaded RCU callbacks
+ * queued.
+ */
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
+{
+	*nextevt = KTIME_MAX;
+	return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) &&
+		!rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data));
+}
+
 /*
 * If any sort of urgency was applied to the current CPU (for example,
 * the scheduler-clock interrupt was enabled on a nohz_full CPU) in order
@@ -1467,7 +1474,7 @@ static void rcu_gp_kthread_wake(void)
 {
 	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);

-	if ((current == t && !in_irq() && !in_serving_softirq()) ||
+	if ((current == t && !in_hardirq() && !in_serving_softirq()) ||
 	    !READ_ONCE(rcu_state.gp_flags) || !t)
 		return;
 	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
@@ -1590,10 +1597,11 @@ static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
 						  struct rcu_data *rdp)
 {
 	rcu_lockdep_assert_cblist_protected(rdp);
-	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) ||
-	    !raw_spin_trylock_rcu_node(rnp))
+	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) || !raw_spin_trylock_rcu_node(rnp))
 		return;
-	WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
+	// The grace period cannot end while we hold the rcu_node lock.
+	if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))
+		WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
 	raw_spin_unlock_rcu_node(rnp);
 }

@@ -2277,7 +2285,7 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 	unsigned long flags;
 	unsigned long mask;
 	bool needwake = false;
-	const bool offloaded = rcu_rdp_is_offloaded(rdp);
+	bool needacc = false;
 	struct rcu_node *rnp;

 	WARN_ON_ONCE(rdp->cpu != smp_processor_id());
@@ -2304,15 +2312,30 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 		/*
 		 * This GP can't end until cpu checks in, so all of our
 		 * callbacks can be processed during the next GP.
+		 *
+		 * NOCB kthreads have their own way to deal with that...
 		 */
-		if (!offloaded)
+		if (!rcu_rdp_is_offloaded(rdp)) {
 			needwake = rcu_accelerate_cbs(rnp, rdp);
+		} else if (!rcu_segcblist_completely_offloaded(&rdp->cblist)) {
+			/*
+			 * ...but NOCB kthreads may miss or delay callbacks acceleration
+			 * if in the middle of a (de-)offloading process.
+			 */
+			needacc = true;
+		}

 		rcu_disable_urgency_upon_qs(rdp);
 		rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
 		/* ^^^ Released rnp->lock */
 		if (needwake)
 			rcu_gp_kthread_wake();
+
+		if (needacc) {
+			rcu_nocb_lock_irqsave(rdp, flags);
+			rcu_accelerate_cbs_unlocked(rnp, rdp);
+			rcu_nocb_unlock_irqrestore(rdp, flags);
+		}
 	}
 }

@@ -2444,7 +2467,6 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	int div;
 	bool __maybe_unused empty;
 	unsigned long flags;
-	const bool offloaded = rcu_rdp_is_offloaded(rdp);
 	struct rcu_head *rhp;
 	struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
 	long bl, count = 0;
@@ -2462,18 +2484,17 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	}

 	/*
-	 * Extract the list of ready callbacks, disabling to prevent
+	 * Extract the list of ready callbacks, disabling IRQs to prevent
 	 * races with call_rcu() from interrupt handlers.  Leave the
 	 * callback counts, as rcu_barrier() needs to be conservative.
 	 */
-	local_irq_save(flags);
-	rcu_nocb_lock(rdp);
+	rcu_nocb_lock_irqsave(rdp, flags);
 	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
 	pending = rcu_segcblist_n_cbs(&rdp->cblist);
 	div = READ_ONCE(rcu_divisor);
 	div = div < 0 ? 7 : div > sizeof(long) * 8 - 2 ? sizeof(long) * 8 - 2 : div;
 	bl = max(rdp->blimit, pending >> div);
-	if (unlikely(bl > 100)) {
+	if (in_serving_softirq() && unlikely(bl > 100)) {
 		long rrn = READ_ONCE(rcu_resched_ns);

 		rrn = rrn < NSEC_PER_MSEC ? NSEC_PER_MSEC : rrn > NSEC_PER_SEC ? NSEC_PER_SEC : rrn;
@@ -2482,7 +2503,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	trace_rcu_batch_start(rcu_state.name,
 			      rcu_segcblist_n_cbs(&rdp->cblist), bl);
 	rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
-	if (offloaded)
+	if (rcu_rdp_is_offloaded(rdp))
 		rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);

 	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbDequeued"));
@@ -2510,18 +2531,21 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		/*
 		 * Stop only if limit reached and CPU has something to do.
 		 */
-		if (count >= bl && !offloaded &&
-		    (need_resched() ||
-		     (!is_idle_task(current) && !rcu_is_callbacks_kthread())))
-			break;
-		if (unlikely(tlimit)) {
-			/* only call local_clock() every 32 callbacks */
-			if (likely((count & 31) || local_clock() < tlimit))
-				continue;
-			/* Exceeded the time limit, so leave. */
-			break;
-		}
-		if (!in_serving_softirq()) {
+		if (in_serving_softirq()) {
+			if (count >= bl && (need_resched() || !is_idle_task(current)))
+				break;
+			/*
+			 * Make sure we don't spend too much time here and deprive other
+			 * softirq vectors of CPU cycles.
+			 */
+			if (unlikely(tlimit)) {
+				/* only call local_clock() every 32 callbacks */
+				if (likely((count & 31) || local_clock() < tlimit))
+					continue;
+				/* Exceeded the time limit, so leave. */
+				break;
+			}
+		} else {
 			local_bh_enable();
 			lockdep_assert_irqs_enabled();
 			cond_resched_tasks_rcu_qs();
@@ -2530,8 +2554,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		}
 	}

-	local_irq_save(flags);
-	rcu_nocb_lock(rdp);
+	rcu_nocb_lock_irqsave(rdp, flags);
 	rdp->n_cbs_invoked += count;
 	trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
 			    is_idle_task(current), rcu_is_callbacks_kthread());
@@ -2565,9 +2588,6 @@ static void rcu_do_batch(struct rcu_data *rdp)

 	rcu_nocb_unlock_irqrestore(rdp, flags);

-	/* Re-invoke RCU core processing if there are callbacks remaining. */
-	if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist))
-		invoke_rcu_core();
 	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
 }

@@ -2706,6 +2726,23 @@ static __latent_entropy void rcu_core(void)
 	unsigned long flags;
 	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
+	/*
+	 * On RT rcu_core() can be preempted when IRQs aren't disabled.
+	 * Therefore this function can race with concurrent NOCB (de-)offloading
+	 * on this CPU and the below condition must be considered volatile.
+	 * However if we race with:
+	 *
+	 * _ Offloading:   In the worst case we accelerate or process callbacks
+	 *                 concurrently with NOCB kthreads. We are guaranteed to
+	 *                 call rcu_nocb_lock() if that happens.
+	 *
+	 * _ Deoffloading: In the worst case we miss callbacks acceleration or
+	 *                 processing. This is fine because the early stage
+	 *                 of deoffloading invokes rcu_core() after setting
+	 *                 SEGCBLIST_RCU_CORE. So we guarantee that we'll process
+	 *                 what could have been dismissed without the need to wait
+	 *                 for the next rcu_pending() check in the next jiffy.
+	 */
 	const bool do_batch = !rcu_segcblist_completely_offloaded(&rdp->cblist);

 	if (cpu_is_offline(smp_processor_id()))
@@ -2714,7 +2751,7 @@ static __latent_entropy void rcu_core(void)
 	WARN_ON_ONCE(!rdp->beenonline);

 	/* Report any deferred quiescent states if preemption enabled. */
-	if (!(preempt_count() & PREEMPT_MASK)) {
+	if (IS_ENABLED(CONFIG_PREEMPT_COUNT) && (!(preempt_count() & PREEMPT_MASK))) {
 		rcu_preempt_deferred_qs(current);
 	} else if (rcu_preempt_need_deferred_qs(current)) {
 		set_tsk_need_resched(current);
@@ -2737,8 +2774,12 @@ static __latent_entropy void rcu_core(void)

 	/* If there are callbacks ready, invoke them. */
 	if (do_batch && rcu_segcblist_ready_cbs(&rdp->cblist) &&
-	    likely(READ_ONCE(rcu_scheduler_fully_active)))
+	    likely(READ_ONCE(rcu_scheduler_fully_active))) {
 		rcu_do_batch(rdp);
+		/* Re-invoke RCU core processing if there are callbacks remaining. */
+		if (rcu_segcblist_ready_cbs(&rdp->cblist))
+			invoke_rcu_core();
+	}

 	/* Do any needed deferred wakeups of rcuo kthreads. */
 	do_nocb_deferred_wakeup(rdp);
@@ -2982,7 +3023,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 	head->func = func;
 	head->next = NULL;
 	local_irq_save(flags);
-	kasan_record_aux_stack(head);
+	kasan_record_aux_stack_noalloc(head);
 	rdp = this_cpu_ptr(&rcu_data);

 	/* Add the callback to our list. */
@@ -3547,7 +3588,7 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		return;
 	}

-	kasan_record_aux_stack(ptr);
+	kasan_record_aux_stack_noalloc(ptr);
 	success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head);
 	if (!success) {
 		run_page_cache_worker(krcp);
--- 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)
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -255,7 +255,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_node *rnp,
 */
 static void rcu_report_exp_rdp(struct rcu_data *rdp)
 {
-	WRITE_ONCE(rdp->exp_deferred_qs, false);
+	WRITE_ONCE(rdp->cpu_no_qs.b.exp, false);
 	rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true);
 }

@@ -387,6 +387,7 @@ retry_ipi:
 			continue;
 		}
 		if (get_cpu() == cpu) {
+			mask_ofl_test |= mask;
 			put_cpu();
 			continue;
 		}
@@ -506,7 +507,10 @@ static void synchronize_rcu_expedited_wait(void)
 				if (rdp->rcu_forced_tick_exp)
 					continue;
 				rdp->rcu_forced_tick_exp = true;
-				tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+				preempt_disable();
+				if (cpu_online(cpu))
+					tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+				preempt_enable();
 			}
 		}
 		j = READ_ONCE(jiffies_till_first_fqs);
@@ -655,7 +659,7 @@ static void rcu_exp_handler(void *unused)
 		    rcu_dynticks_curr_cpu_in_eqs()) {
 			rcu_report_exp_rdp(rdp);
 		} else {
-			rdp->exp_deferred_qs = true;
+			WRITE_ONCE(rdp->cpu_no_qs.b.exp, true);
 			set_tsk_need_resched(t);
 			set_preempt_need_resched();
 		}
@@ -677,7 +681,7 @@ static void rcu_exp_handler(void *unused)
 	if (depth > 0) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmask & rdp->grpmask) {
-			rdp->exp_deferred_qs = true;
+			WRITE_ONCE(rdp->cpu_no_qs.b.exp, true);
 			t->rcu_read_unlock_special.b.exp_hint = true;
 		}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -759,7 +763,7 @@ static void sync_sched_exp_online_cleanup(int cpu)
 	my_cpu = get_cpu();
 	/* Quiescent state either not needed or already requested, leave. */
 	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
-	    rdp->cpu_no_qs.b.exp) {
+	    READ_ONCE(rdp->cpu_no_qs.b.exp)) {
 		put_cpu();
 		return;
 	}
--- a/Show More
+++ b/Show More