Merge branches 'doc.2022.06.21a', 'fixes.2022.07.19a', 'nocb.2022.07.19a', 'poll.2022.07.21a', 'rcu-tasks.2022.06.21a' and 'torture.2022.06.21a' into HEAD

doc.2022.06.21a: Documentation updates.
fixes.2022.07.19a: Miscellaneous fixes.
nocb.2022.07.19a: Callback-offload updates.
poll.2022.07.21a: Polled grace-period updates.
rcu-tasks.2022.06.21a: Tasks RCU updates.
torture.2022.06.21a: Torture-test updates.

Author: paulmckrcu

Documentation/admin-guide/kernel-parameters.txt

@@ -3659,6 +3659,9 @@
 			just as if they had also been called out in the
 			rcu_nocbs= boot parameter.
 
+			Note that this argument takes precedence over
+			the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
+
 	noiotrap	[SH] Disables trapped I/O port accesses.
 
 	noirqdebug	[X86-32] Disables the code which attempts to detect and
@@ -4557,6 +4560,9 @@
 			no-callback mode from boot but the mode may be
 			toggled at runtime via cpusets.
 
+			Note that this argument takes precedence over
+			the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
+
 	rcu_nocb_poll	[KNL]
 			Rather than requiring that offloaded CPUs
 			(specified by rcu_nocbs= above) explicitly
@@ -5799,6 +5805,24 @@
 			expediting.  Set to zero to disable automatic
 			expediting.
 
+	srcutree.srcu_max_nodelay [KNL]
+			Specifies the number of no-delay instances
+			per jiffy for which the SRCU grace period
+			worker thread will be rescheduled with zero
+			delay. Beyond this limit, worker thread will
+			be rescheduled with a sleep delay of one jiffy.
+
+	srcutree.srcu_max_nodelay_phase [KNL]
+			Specifies the per-grace-period phase, number of
+			non-sleeping polls of readers. Beyond this limit,
+			grace period worker thread will be rescheduled
+			with a sleep delay of one jiffy, between each
+			rescan of the readers, for a grace period phase.
+
+	srcutree.srcu_retry_check_delay [KNL]
+			Specifies number of microseconds of non-sleeping
+			delay between each non-sleeping poll of readers.
+
 	srcutree.small_contention_lim [KNL]
 			Specifies the number of update-side contention
 			events per jiffy will be tolerated before

include/linux/rcupdate.h

@@ -41,6 +41,7 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func);
 void rcu_barrier_tasks(void);
 void rcu_barrier_tasks_rude(void);
 void synchronize_rcu(void);
+unsigned long get_completed_synchronize_rcu(void);
 
 #ifdef CONFIG_PREEMPT_RCU
 
@@ -169,13 +170,24 @@ void synchronize_rcu_tasks(void);
 # endif
 
 # ifdef CONFIG_TASKS_TRACE_RCU
-# define rcu_tasks_trace_qs(t)						\
-	do {								\
-		if (!likely(READ_ONCE((t)->trc_reader_checked)) &&	\
-		    !unlikely(READ_ONCE((t)->trc_reader_nesting))) {	\
-			smp_store_release(&(t)->trc_reader_checked, true); \
-			smp_mb(); /* Readers partitioned by store. */	\
-		}							\
+// Bits for ->trc_reader_special.b.need_qs field.
+#define TRC_NEED_QS		0x1  // Task needs a quiescent state.
+#define TRC_NEED_QS_CHECKED	0x2  // Task has been checked for needing quiescent state.
+
+u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new);
+void rcu_tasks_trace_qs_blkd(struct task_struct *t);
+
+# define rcu_tasks_trace_qs(t)							\
+	do {									\
+		int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting);	\
+										\
+		if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) &&	\
+		    likely(!___rttq_nesting)) {					\
+			rcu_trc_cmpxchg_need_qs((t), 0,	TRC_NEED_QS_CHECKED);	\
+		} else if (___rttq_nesting && ___rttq_nesting != INT_MIN &&	\
+			   !READ_ONCE((t)->trc_reader_special.b.blocked)) {	\
+			rcu_tasks_trace_qs_blkd(t);				\
+		}								\
 	} while (0)
 # else
 # define rcu_tasks_trace_qs(t) do { } while (0)
@@ -184,7 +196,7 @@ void synchronize_rcu_tasks(void);
 #define rcu_tasks_qs(t, preempt)					\
 do {									\
 	rcu_tasks_classic_qs((t), (preempt));				\
-	rcu_tasks_trace_qs((t));					\
+	rcu_tasks_trace_qs(t);						\
 } while (0)
 
 # ifdef CONFIG_TASKS_RUDE_RCU

include/linux/rcupdate_trace.h

@@ -75,7 +75,7 @@ static inline void rcu_read_unlock_trace(void)
 	nesting = READ_ONCE(t->trc_reader_nesting) - 1;
 	barrier(); // Critical section before disabling.
 	// Disable IPI-based setting of .need_qs.
-	WRITE_ONCE(t->trc_reader_nesting, INT_MIN);
+	WRITE_ONCE(t->trc_reader_nesting, INT_MIN + nesting);
 	if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) {
 		WRITE_ONCE(t->trc_reader_nesting, nesting);
 		return;  // We assume shallow reader nesting.

include/linux/rcutiny.h

@@ -23,6 +23,16 @@ static inline void cond_synchronize_rcu(unsigned long oldstate)
 	might_sleep();
 }
 
+static inline unsigned long start_poll_synchronize_rcu_expedited(void)
+{
+	return start_poll_synchronize_rcu();
+}
+
+static inline void cond_synchronize_rcu_expedited(unsigned long oldstate)
+{
+	cond_synchronize_rcu(oldstate);
+}
+
 extern void rcu_barrier(void);
 
 static inline void synchronize_rcu_expedited(void)
@@ -38,7 +48,7 @@ static inline void synchronize_rcu_expedited(void)
  */
 extern void kvfree(const void *addr);
 
-static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+static inline void __kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
 	if (head) {
 		call_rcu(head, func);
@@ -51,6 +61,15 @@ static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 	kvfree((void *) func);
 }
 
+#ifdef CONFIG_KASAN_GENERIC
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
+#else
+static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+{
+	__kvfree_call_rcu(head, func);
+}
+#endif
+
 void rcu_qs(void);
 
 static inline void rcu_softirq_qs(void)

include/linux/rcutree.h

@@ -40,6 +40,8 @@ bool rcu_eqs_special_set(int cpu);
 void rcu_momentary_dyntick_idle(void);
 void kfree_rcu_scheduler_running(void);
 bool rcu_gp_might_be_stalled(void);
+unsigned long start_poll_synchronize_rcu_expedited(void);
+void cond_synchronize_rcu_expedited(unsigned long oldstate);
 unsigned long get_state_synchronize_rcu(void);
 unsigned long start_poll_synchronize_rcu(void);
 bool poll_state_synchronize_rcu(unsigned long oldstate);

include/linux/sched.h

@@ -843,8 +843,9 @@ struct task_struct {
 	int				trc_reader_nesting;
 	int				trc_ipi_to_cpu;
 	union rcu_special		trc_reader_special;
-	bool				trc_reader_checked;
 	struct list_head		trc_holdout_list;
+	struct list_head		trc_blkd_node;
+	int				trc_blkd_cpu;
 #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 
 	struct sched_info		sched_info;
@@ -2223,6 +2224,7 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 extern bool sched_task_on_rq(struct task_struct *p);
 extern unsigned long get_wchan(struct task_struct *p);
+extern struct task_struct *cpu_curr_snapshot(int cpu);
 
 /*
  * In order to reduce various lock holder preemption latencies provide an

init/init_task.c

@@ -157,6 +157,7 @@ struct task_struct init_task
 	.trc_reader_nesting = 0,
 	.trc_reader_special.s = 0,
 	.trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list),
+	.trc_blkd_node = LIST_HEAD_INIT(init_task.trc_blkd_node),
 #endif
 #ifdef CONFIG_CPUSETS
 	.mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,

kernel/fork.c

@@ -1814,6 +1814,7 @@ static inline void rcu_copy_process(struct task_struct *p)
 	p->trc_reader_nesting = 0;
 	p->trc_reader_special.s = 0;
 	INIT_LIST_HEAD(&p->trc_holdout_list);
+	INIT_LIST_HEAD(&p->trc_blkd_node);
 #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 }
 

kernel/rcu/Kconfig

@@ -262,6 +262,35 @@ config RCU_NOCB_CPU
 	  Say Y here if you need reduced OS jitter, despite added overhead.
 	  Say N here if you are unsure.
 
+config RCU_NOCB_CPU_DEFAULT_ALL
+	bool "Offload RCU callback processing from all CPUs by default"
+	depends on RCU_NOCB_CPU
+	default n
+	help
+	  Use this option to offload callback processing from all CPUs
+	  by default, in the absence of the rcu_nocbs or nohz_full boot
+	  parameter. This also avoids the need to use any boot parameters
+	  to achieve the effect of offloading all CPUs on boot.
+
+	  Say Y here if you want offload all CPUs by default on boot.
+	  Say N here if you are unsure.
+
+config RCU_NOCB_CPU_CB_BOOST
+	bool "Offload RCU callback from real-time kthread"
+	depends on RCU_NOCB_CPU && RCU_BOOST
+	default y if PREEMPT_RT
+	help
+	  Use this option to invoke offloaded callbacks as SCHED_FIFO
+	  to avoid starvation by heavy SCHED_OTHER background load.
+	  Of course, running as SCHED_FIFO during callback floods will
+	  cause the rcuo[ps] kthreads to monopolize the CPU for hundreds
+	  of milliseconds or more.  Therefore, when enabling this option,
+	  it is your responsibility to ensure that latency-sensitive
+	  tasks either run with higher priority or run on some other CPU.
+
+	  Say Y here if you want to set RT priority for offloading kthreads.
+	  Say N here if you are building a !PREEMPT_RT kernel and are unsure.
+
 config TASKS_TRACE_RCU_READ_MB
 	bool "Tasks Trace RCU readers use memory barriers in user and idle"
 	depends on RCU_EXPERT && TASKS_TRACE_RCU

kernel/rcu/Kconfig.debug

@@ -121,7 +121,7 @@ config RCU_EQS_DEBUG
 
 config RCU_STRICT_GRACE_PERIOD
 	bool "Provide debug RCU implementation with short grace periods"
-	depends on DEBUG_KERNEL && RCU_EXPERT && NR_CPUS <= 4
+	depends on DEBUG_KERNEL && RCU_EXPERT && NR_CPUS <= 4 && !TINY_RCU
 	default n
 	select PREEMPT_COUNT if PREEMPT=n
 	help