Merge branches 'doc.2022.08.31b', 'fixes.2022.08.31b', 'kvfree.2022.08.31b',...

Merge branches 'doc.2022.08.31b', 'fixes.2022.08.31b', 'kvfree.2022.08.31b', 'nocb.2022.09.01a', 'poll.2022.08.31b', 'poll-srcu.2022.08.31b' and 'tasks.2022.08.31b' into HEAD

doc.2022.08.31b: Documentation updates
fixes.2022.08.31b: Miscellaneous fixes
kvfree.2022.08.31b: kvfree_rcu() updates
nocb.2022.09.01a: NOCB CPU updates
poll.2022.08.31b: Full-oldstate RCU polling grace-period API
poll-srcu.2022.08.31b: Polled SRCU grace-period updates
tasks.2022.08.31b: Tasks RCU updates

include/linux/rcupdate.h

@@ -42,7 +42,31 @@ 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);
+
+struct rcu_gp_oldstate;
 unsigned long get_completed_synchronize_rcu(void);
+void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
+
+// Maximum number of unsigned long values corresponding to
+// not-yet-completed RCU grace periods.
+#define NUM_ACTIVE_RCU_POLL_OLDSTATE 2
+
+/**
+ * same_state_synchronize_rcu - Are two old-state values identical?
+ * @oldstate1: First old-state value.
+ * @oldstate2: Second old-state value.
+ *
+ * The two old-state values must have been obtained from either
+ * get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or
+ * get_completed_synchronize_rcu().  Returns @true if the two values are
+ * identical and @false otherwise.  This allows structures whose lifetimes
+ * are tracked by old-state values to push these values to a list header,
+ * allowing those structures to be slightly smaller.
+ */
+static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2)
+{
+	return oldstate1 == oldstate2;
+}
 
 #ifdef CONFIG_PREEMPT_RCU
 
@@ -496,13 +520,21 @@ do {									      \
  * against NULL.  Although rcu_access_pointer() may also be used in cases
  * where update-side locks prevent the value of the pointer from changing,
  * you should instead use rcu_dereference_protected() for this use case.
+ * Within an RCU read-side critical section, there is little reason to
+ * use rcu_access_pointer().
+ *
+ * It is usually best to test the rcu_access_pointer() return value
+ * directly in order to avoid accidental dereferences being introduced
+ * by later inattentive changes.  In other words, assigning the
+ * rcu_access_pointer() return value to a local variable results in an
+ * accident waiting to happen.
  *
  * It is also permissible to use rcu_access_pointer() when read-side
- * access to the pointer was removed at least one grace period ago, as
- * is the case in the context of the RCU callback that is freeing up
- * the data, or after a synchronize_rcu() returns.  This can be useful
- * when tearing down multi-linked structures after a grace period
- * has elapsed.
+ * access to the pointer was removed at least one grace period ago, as is
+ * the case in the context of the RCU callback that is freeing up the data,
+ * or after a synchronize_rcu() returns.  This can be useful when tearing
+ * down multi-linked structures after a grace period has elapsed.  However,
+ * rcu_dereference_protected() is normally preferred for this use case.
  */
 #define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu)
 

include/linux/rcutiny.h

@@ -14,25 +14,75 @@
 
 #include <asm/param.h> /* for HZ */
 
+struct rcu_gp_oldstate {
+	unsigned long rgos_norm;
+};
+
+// Maximum number of rcu_gp_oldstate values corresponding to
+// not-yet-completed RCU grace periods.
+#define NUM_ACTIVE_RCU_POLL_FULL_OLDSTATE 2
+
+/*
+ * Are the two oldstate values the same?  See the Tree RCU version for
+ * docbook header.
+ */
+static inline bool same_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp1,
+						   struct rcu_gp_oldstate *rgosp2)
+{
+	return rgosp1->rgos_norm == rgosp2->rgos_norm;
+}
+
 unsigned long get_state_synchronize_rcu(void);
+
+static inline void get_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	rgosp->rgos_norm = get_state_synchronize_rcu();
+}
+
 unsigned long start_poll_synchronize_rcu(void);
+
+static inline void start_poll_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	rgosp->rgos_norm = start_poll_synchronize_rcu();
+}
+
 bool poll_state_synchronize_rcu(unsigned long oldstate);
 
+static inline bool poll_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	return poll_state_synchronize_rcu(rgosp->rgos_norm);
+}
+
 static inline void cond_synchronize_rcu(unsigned long oldstate)
 {
 	might_sleep();
 }
 
+static inline void cond_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	cond_synchronize_rcu(rgosp->rgos_norm);
+}
+
 static inline unsigned long start_poll_synchronize_rcu_expedited(void)
 {
 	return start_poll_synchronize_rcu();
 }
 
+static inline void start_poll_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp)
+{
+	rgosp->rgos_norm = start_poll_synchronize_rcu_expedited();
+}
+
 static inline void cond_synchronize_rcu_expedited(unsigned long oldstate)
 {
 	cond_synchronize_rcu(oldstate);
 }
 
+static inline void cond_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp)
+{
+	cond_synchronize_rcu_expedited(rgosp->rgos_norm);
+}
+
 extern void rcu_barrier(void);
 
 static inline void synchronize_rcu_expedited(void)

include/linux/rcutree.h

@@ -40,12 +40,52 @@ 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);
+
+struct rcu_gp_oldstate {
+	unsigned long rgos_norm;
+	unsigned long rgos_exp;
+};
+
+// Maximum number of rcu_gp_oldstate values corresponding to
+// not-yet-completed RCU grace periods.
+#define NUM_ACTIVE_RCU_POLL_FULL_OLDSTATE 4
+
+/**
+ * same_state_synchronize_rcu_full - Are two old-state values identical?
+ * @rgosp1: First old-state value.
+ * @rgosp2: Second old-state value.
+ *
+ * The two old-state values must have been obtained from either
+ * get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(),
+ * or get_completed_synchronize_rcu_full().  Returns @true if the two
+ * values are identical and @false otherwise.  This allows structures
+ * whose lifetimes are tracked by old-state values to push these values
+ * to a list header, allowing those structures to be slightly smaller.
+ *
+ * Note that equality is judged on a bitwise basis, so that an
+ * @rcu_gp_oldstate structure with an already-completed state in one field
+ * will compare not-equal to a structure with an already-completed state
+ * in the other field.  After all, the @rcu_gp_oldstate structure is opaque
+ * so how did such a situation come to pass in the first place?
+ */
+static inline bool same_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp1,
+						   struct rcu_gp_oldstate *rgosp2)
+{
+	return rgosp1->rgos_norm == rgosp2->rgos_norm && rgosp1->rgos_exp == rgosp2->rgos_exp;
+}
+
 unsigned long start_poll_synchronize_rcu_expedited(void);
+void start_poll_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp);
 void cond_synchronize_rcu_expedited(unsigned long oldstate);
+void cond_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp);
 unsigned long get_state_synchronize_rcu(void);
+void get_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
 unsigned long start_poll_synchronize_rcu(void);
+void start_poll_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
 bool poll_state_synchronize_rcu(unsigned long oldstate);
+bool poll_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
 void cond_synchronize_rcu(unsigned long oldstate);
+void cond_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
 
 bool rcu_is_idle_cpu(int cpu);
 

include/linux/srcutiny.h

@@ -15,10 +15,10 @@
 
 struct srcu_struct {
 	short srcu_lock_nesting[2];	/* srcu_read_lock() nesting depth. */
-	unsigned short srcu_idx;	/* Current reader array element in bit 0x2. */
-	unsigned short srcu_idx_max;	/* Furthest future srcu_idx request. */
 	u8 srcu_gp_running;		/* GP workqueue running? */
 	u8 srcu_gp_waiting;		/* GP waiting for readers? */
+	unsigned long srcu_idx;		/* Current reader array element in bit 0x2. */
+	unsigned long srcu_idx_max;	/* Furthest future srcu_idx request. */
 	struct swait_queue_head srcu_wq;
 					/* Last srcu_read_unlock() wakes GP. */
 	struct rcu_head *srcu_cb_head;	/* Pending callbacks: Head. */
@@ -82,10 +82,12 @@ static inline void srcu_torture_stats_print(struct srcu_struct *ssp,
 	int idx;
 
 	idx = ((data_race(READ_ONCE(ssp->srcu_idx)) + 1) & 0x2) >> 1;
-	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n",
+	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd) gp: %lu->%lu\n",
 		 tt, tf, idx,
 		 data_race(READ_ONCE(ssp->srcu_lock_nesting[!idx])),
-		 data_race(READ_ONCE(ssp->srcu_lock_nesting[idx])));
+		 data_race(READ_ONCE(ssp->srcu_lock_nesting[idx])),
+		 data_race(READ_ONCE(ssp->srcu_idx)),
+		 data_race(READ_ONCE(ssp->srcu_idx_max)));
 }
 
 #endif

kernel/rcu/srcutiny.c

@@ -117,7 +117,7 @@ void srcu_drive_gp(struct work_struct *wp)
 	struct srcu_struct *ssp;
 
 	ssp = container_of(wp, struct srcu_struct, srcu_work);
-	if (ssp->srcu_gp_running || USHORT_CMP_GE(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
+	if (ssp->srcu_gp_running || ULONG_CMP_GE(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
 		return; /* Already running or nothing to do. */
 
 	/* Remove recently arrived callbacks and wait for readers. */
@@ -150,17 +150,17 @@ void srcu_drive_gp(struct work_struct *wp)
 	 * straighten that out.
 	 */
 	WRITE_ONCE(ssp->srcu_gp_running, false);
-	if (USHORT_CMP_LT(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
+	if (ULONG_CMP_LT(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
 		schedule_work(&ssp->srcu_work);
 }
 EXPORT_SYMBOL_GPL(srcu_drive_gp);
 
 static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 {
-	unsigned short cookie;
+	unsigned long cookie;
 
 	cookie = get_state_synchronize_srcu(ssp);
-	if (USHORT_CMP_GE(READ_ONCE(ssp->srcu_idx_max), cookie))
+	if (ULONG_CMP_GE(READ_ONCE(ssp->srcu_idx_max), cookie))
 		return;
 	WRITE_ONCE(ssp->srcu_idx_max, cookie);
 	if (!READ_ONCE(ssp->srcu_gp_running)) {
@@ -215,7 +215,7 @@ unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp)
 	barrier();
 	ret = (READ_ONCE(ssp->srcu_idx) + 3) & ~0x1;
 	barrier();
-	return ret & USHRT_MAX;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_srcu);
 
@@ -240,10 +240,10 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu);
  */
 bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie)
 {
-	bool ret = USHORT_CMP_GE(READ_ONCE(ssp->srcu_idx), cookie);
+	unsigned long cur_s = READ_ONCE(ssp->srcu_idx);
 
 	barrier();
-	return ret;
+	return ULONG_CMP_GE(cur_s, cookie) || ULONG_CMP_LT(cur_s, cookie - 3);
 }
 EXPORT_SYMBOL_GPL(poll_state_synchronize_srcu);
 

kernel/rcu/tasks.h

@@ -560,7 +560,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp)
 {
 	/* Complain if the scheduler has not started.  */
-	RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
+	WARN_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
 			 "synchronize_rcu_tasks called too soon");
 
 	// If the grace-period kthread is running, use it.
@@ -1500,6 +1500,7 @@ static void rcu_tasks_trace_pregp_step(struct list_head *hop)
 		if (rcu_tasks_trace_pertask_prep(t, true))
 			trc_add_holdout(t, hop);
 		rcu_read_unlock();
+		cond_resched_tasks_rcu_qs();
 	}
 
 	// Only after all running tasks have been accounted for is it
@@ -1520,6 +1521,7 @@ static void rcu_tasks_trace_pregp_step(struct list_head *hop)
 			raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
 		}
 		raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+		cond_resched_tasks_rcu_qs();
 	}
 
 	// Re-enable CPU hotplug now that the holdout list is populated.
@@ -1619,6 +1621,7 @@ static void check_all_holdout_tasks_trace(struct list_head *hop,
 			trc_del_holdout(t);
 		else if (needreport)
 			show_stalled_task_trace(t, firstreport);
+		cond_resched_tasks_rcu_qs();
 	}
 
 	// Re-enable CPU hotplug now that the holdout list scan has completed.

kernel/rcu/tiny.c

@@ -158,6 +158,10 @@ void synchronize_rcu(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
+static void tiny_rcu_leak_callback(struct rcu_head *rhp)
+{
+}
+
 /*
  * Post an RCU callback to be invoked after the end of an RCU grace
  * period.  But since we have but one CPU, that would be after any
@@ -165,9 +169,20 @@ EXPORT_SYMBOL_GPL(synchronize_rcu);
  */
 void call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
+	static atomic_t doublefrees;
 	unsigned long flags;
 
-	debug_rcu_head_queue(head);
+	if (debug_rcu_head_queue(head)) {
+		if (atomic_inc_return(&doublefrees) < 4) {
+			pr_err("%s(): Double-freed CB %p->%pS()!!!  ", __func__, head, head->func);
+			mem_dump_obj(head);
+		}
+
+		if (!__is_kvfree_rcu_offset((unsigned long)head->func))
+			WRITE_ONCE(head->func, tiny_rcu_leak_callback);
+		return;
+	}
+
 	head->func = func;
 	head->next = NULL;
 
@@ -183,6 +198,16 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func)
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
+/*
+ * Store a grace-period-counter "cookie".  For more information,
+ * see the Tree RCU header comment.
+ */
+void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	rgosp->rgos_norm = RCU_GET_STATE_COMPLETED;
+}
+EXPORT_SYMBOL_GPL(get_completed_synchronize_rcu_full);
+
 /*
  * Return a grace-period-counter "cookie".  For more information,
  * see the Tree RCU header comment.

kernel/rcu/tree_exp.h

@@ -828,11 +828,13 @@ static void rcu_exp_handler(void *unused)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
+	bool preempt_bh_enabled = !(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK));
 
 	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
 	    __this_cpu_read(rcu_data.cpu_no_qs.b.exp))
 		return;
-	if (rcu_is_cpu_rrupt_from_idle()) {
+	if (rcu_is_cpu_rrupt_from_idle() ||
+	    (IS_ENABLED(CONFIG_PREEMPT_COUNT) && preempt_bh_enabled)) {
 		rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
 		return;
 	}
@@ -906,6 +908,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
 void synchronize_rcu_expedited(void)
 {
 	bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT);
+	unsigned long flags;
 	struct rcu_exp_work rew;
 	struct rcu_node *rnp;
 	unsigned long s;
@@ -924,8 +927,11 @@ void synchronize_rcu_expedited(void)
 		// them, which allows reuse of ->gp_seq_polled_exp_snap.
 		rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_exp_snap);
 		rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_exp_snap);
-		if (rcu_init_invoked())
-			cond_resched();
+
+		local_irq_save(flags);
+		WARN_ON_ONCE(num_online_cpus() > 1);
+		rcu_state.expedited_sequence += (1 << RCU_SEQ_CTR_SHIFT);
+		local_irq_restore(flags);
 		return;  // Context allows vacuous grace periods.
 	}
 
@@ -1027,6 +1033,24 @@ unsigned long start_poll_synchronize_rcu_expedited(void)
 }
 EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_expedited);
 
+/**
+ * start_poll_synchronize_rcu_expedited_full - Take a full snapshot and start expedited grace period
+ * @rgosp: Place to put snapshot of grace-period state
+ *
+ * Places the normal and expedited grace-period states in rgosp.  This
+ * state value can be passed to a later call to cond_synchronize_rcu_full()
+ * or poll_state_synchronize_rcu_full() to determine whether or not a
+ * grace period (whether normal or expedited) has elapsed in the meantime.
+ * If the needed expedited grace period is not already slated to start,
+ * initiates that grace period.
+ */
+void start_poll_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp)
+{
+	get_state_synchronize_rcu_full(rgosp);
+	(void)start_poll_synchronize_rcu_expedited();
+}
+EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_expedited_full);
+
 /**
  * cond_synchronize_rcu_expedited - Conditionally wait for an expedited RCU grace period
  *
@@ -1053,3 +1077,30 @@ void cond_synchronize_rcu_expedited(unsigned long oldstate)
 		synchronize_rcu_expedited();
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_rcu_expedited);
+
+/**
+ * cond_synchronize_rcu_expedited_full - Conditionally wait for an expedited RCU grace period
+ * @rgosp: value from get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(), or start_poll_synchronize_rcu_expedited_full()
+ *
+ * If a full RCU grace period has elapsed since the call to
+ * get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(),
+ * or start_poll_synchronize_rcu_expedited_full() from which @rgosp was
+ * obtained, just return.  Otherwise, invoke synchronize_rcu_expedited()
+ * to wait for a full grace period.
+ *
+ * Yes, this function does not take counter wrap into account.
+ * But counter wrap is harmless.  If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!),
+ * so waiting for a couple of additional grace periods should be just fine.
+ *
+ * This function provides the same memory-ordering guarantees that
+ * would be provided by a synchronize_rcu() that was invoked at the call
+ * to the function that provided @rgosp and that returned at the end of
+ * this function.
+ */
+void cond_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp)
+{
+	if (!poll_state_synchronize_rcu_full(rgosp))
+		synchronize_rcu_expedited();
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_rcu_expedited_full);

kernel/rcu/tree_nocb.h

@@ -1111,7 +1111,7 @@ int rcu_nocb_cpu_deoffload(int cpu)
 			if (!ret)
 				cpumask_clear_cpu(cpu, rcu_nocb_mask);
 		} else {
-			pr_info("NOCB: Can't CB-deoffload an offline CPU\n");
+			pr_info("NOCB: Cannot CB-deoffload offline CPU %d\n", rdp->cpu);
 			ret = -EINVAL;
 		}
 	}
@@ -1196,7 +1196,7 @@ int rcu_nocb_cpu_offload(int cpu)
 			if (!ret)
 				cpumask_set_cpu(cpu, rcu_nocb_mask);
 		} else {
-			pr_info("NOCB: Can't CB-offload an offline CPU\n");
+			pr_info("NOCB: Cannot CB-offload offline CPU %d\n", rdp->cpu);
 			ret = -EINVAL;
 		}
 	}
@@ -1452,8 +1452,8 @@ static void show_rcu_nocb_gp_state(struct rcu_data *rdp)
 		(long)rdp->nocb_gp_seq,
 		rnp->grplo, rnp->grphi, READ_ONCE(rdp->nocb_gp_loops),
 		rdp->nocb_gp_kthread ? task_state_to_char(rdp->nocb_gp_kthread) : '.',
-		rdp->nocb_cb_kthread ? (int)task_cpu(rdp->nocb_gp_kthread) : -1,
-		show_rcu_should_be_on_cpu(rdp->nocb_cb_kthread));
+		rdp->nocb_gp_kthread ? (int)task_cpu(rdp->nocb_gp_kthread) : -1,
+		show_rcu_should_be_on_cpu(rdp->nocb_gp_kthread));
 }
 
 /* Dump out nocb kthread state for the specified rcu_data structure. */
@@ -1497,7 +1497,7 @@ static void show_rcu_nocb_state(struct rcu_data *rdp)
 		".B"[!!rcu_cblist_n_cbs(&rdp->nocb_bypass)],
 		rcu_segcblist_n_cbs(&rdp->cblist),
 		rdp->nocb_cb_kthread ? task_state_to_char(rdp->nocb_cb_kthread) : '.',
-		rdp->nocb_cb_kthread ? (int)task_cpu(rdp->nocb_gp_kthread) : -1,
+		rdp->nocb_cb_kthread ? (int)task_cpu(rdp->nocb_cb_kthread) : -1,
 		show_rcu_should_be_on_cpu(rdp->nocb_cb_kthread));
 
 	/* It is OK for GP kthreads to have GP state. */

kernel/rcu/tree_plugin.h

@@ -641,7 +641,8 @@ static void rcu_read_unlock_special(struct task_struct *t)
 
 		expboost = (t->rcu_blocked_node && READ_ONCE(t->rcu_blocked_node->exp_tasks)) ||
 			   (rdp->grpmask & READ_ONCE(rnp->expmask)) ||
-			   IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ||
+			   (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) &&
+			   ((rdp->grpmask & READ_ONCE(rnp->qsmask)) || t->rcu_blocked_node)) ||
 			   (IS_ENABLED(CONFIG_RCU_BOOST) && irqs_were_disabled &&
 			    t->rcu_blocked_node);
 		// Need to defer quiescent state until everything is enabled.
@@ -718,9 +719,6 @@ static void rcu_flavor_sched_clock_irq(int user)
 	struct task_struct *t = current;
 
 	lockdep_assert_irqs_disabled();
-	if (user || rcu_is_cpu_rrupt_from_idle()) {
-		rcu_note_voluntary_context_switch(current);
-	}
 	if (rcu_preempt_depth() > 0 ||
 	    (preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) {
 		/* No QS, force context switch if deferred. */
@@ -824,6 +822,7 @@ void rcu_read_unlock_strict(void)
 	if (irqs_disabled() || preempt_count() || !rcu_state.gp_kthread)
 		return;
 	rdp = this_cpu_ptr(&rcu_data);
+	rdp->cpu_no_qs.b.norm = false;
 	rcu_report_qs_rdp(rdp);
 	udelay(rcu_unlock_delay);
 }
@@ -869,7 +868,7 @@ void rcu_all_qs(void)
 
 	if (!raw_cpu_read(rcu_data.rcu_urgent_qs))
 		return;
-	preempt_disable();
+	preempt_disable();  // For CONFIG_PREEMPT_COUNT=y kernels
 	/* Load rcu_urgent_qs before other flags. */
 	if (!smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) {
 		preempt_enable();
@@ -931,10 +930,13 @@ static notrace bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 	return false;
 }
 
-// Except that we do need to respond to a request by an expedited grace
-// period for a quiescent state from this CPU.  Note that requests from
-// tasks are handled when removing the task from the blocked-tasks list
-// below.
+// Except that we do need to respond to a request by an expedited
+// grace period for a quiescent state from this CPU.  Note that in
+// non-preemptible kernels, there can be no context switches within RCU
+// read-side critical sections, which in turn means that the leaf rcu_node
+// structure's blocked-tasks list is always empty.  is therefore no need to
+// actually check it.  Instead, a quiescent state from this CPU suffices,
+// and this function is only called from such a quiescent state.
 notrace void rcu_preempt_deferred_qs(struct task_struct *t)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
@@ -972,7 +974,6 @@ static void rcu_flavor_sched_clock_irq(int user)
 		 * neither access nor modify, at least not while the
 		 * corresponding CPU is online.
 		 */
-
 		rcu_qs();
 	}
 }
@@ -1238,8 +1239,11 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 		    cpu != outgoingcpu)
 			cpumask_set_cpu(cpu, cm);
 	cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU));
-	if (cpumask_empty(cm))
+	if (cpumask_empty(cm)) {
 		cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU));
+		if (outgoingcpu >= 0)
+			cpumask_clear_cpu(outgoingcpu, cm);
+	}
 	set_cpus_allowed_ptr(t, cm);
 	mutex_unlock(&rnp->boost_kthread_mutex);
 	free_cpumask_var(cm);

kernel/rcu/tree_stall.h

@@ -368,7 +368,7 @@ static void rcu_dump_cpu_stacks(void)
 			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
 				if (cpu_is_offline(cpu))
 					pr_err("Offline CPU %d blocking current GP.\n", cpu);
-				else if (!trigger_single_cpu_backtrace(cpu))
+				else
 					dump_cpu_task(cpu);
 			}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -511,7 +511,6 @@ static void rcu_check_gp_kthread_starvation(void)
 					pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
 				} else  {
 					pr_err("Stack dump where RCU GP kthread last ran:\n");
-					if (!trigger_single_cpu_backtrace(cpu))
 					dump_cpu_task(cpu);
 				}
 			}

kernel/sched/core.c

@@ -73,6 +73,7 @@
 
 #include <uapi/linux/sched/types.h>
 
+#include <asm/irq_regs.h>
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
 
@@ -11183,6 +11184,19 @@ struct cgroup_subsys cpu_cgrp_subsys = {
 
 void dump_cpu_task(int cpu)
 {
+	if (cpu == smp_processor_id() && in_hardirq()) {
+		struct pt_regs *regs;
+
+		regs = get_irq_regs();
+		if (regs) {
+			show_regs(regs);
+			return;
+		}
+	}
+
+	if (trigger_single_cpu_backtrace(cpu))
+		return;
+
 	pr_info("Task dump for CPU %d:\n", cpu);
 	sched_show_task(cpu_curr(cpu));
 }

kernel/smp.c

@@ -370,7 +370,6 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
 	if (cpu >= 0) {
 		if (static_branch_unlikely(&csdlock_debug_extended))
 			csd_lock_print_extended(csd, cpu);
-		if (!trigger_single_cpu_backtrace(cpu))
 		dump_cpu_task(cpu);
 		if (!cpu_cur_csd) {
 			pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu);